chtmp223 commited on
Commit
dbb0dfe
·
verified ·
1 Parent(s): ff259c3

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +4 -0
  2. all_results.json +8 -0
  3. config.json +30 -0
  4. generation_config.json +7 -0
  5. log.out +0 -0
  6. model-00001-of-00007.safetensors +3 -0
  7. model-00002-of-00007.safetensors +3 -0
  8. model-00003-of-00007.safetensors +3 -0
  9. model-00004-of-00007.safetensors +3 -0
  10. model-00005-of-00007.safetensors +3 -0
  11. model-00006-of-00007.safetensors +3 -0
  12. model-00007-of-00007.safetensors +3 -0
  13. model.safetensors.index.json +298 -0
  14. special_tokens_map.json +16 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +2062 -0
  17. train_results.json +8 -0
  18. trainer_state.json +0 -0
  19. training_args.bin +3 -0
  20. wandb/debug-cli.ctpham_umass_edu.log +0 -0
  21. wandb/debug-internal.log +0 -0
  22. wandb/debug.log +32 -0
  23. wandb/run-20241225_001558-sxxraa4n/files/conda-environment.yaml +232 -0
  24. wandb/run-20241225_001558-sxxraa4n/files/config.yaml +705 -0
  25. wandb/run-20241225_001558-sxxraa4n/files/output.log +9 -0
  26. wandb/run-20241225_001558-sxxraa4n/files/requirements.txt +242 -0
  27. wandb/run-20241225_001558-sxxraa4n/files/wandb-metadata.json +705 -0
  28. wandb/run-20241225_001558-sxxraa4n/files/wandb-summary.json +1 -0
  29. wandb/run-20241225_001558-sxxraa4n/logs/debug-internal.log +0 -0
  30. wandb/run-20241225_001558-sxxraa4n/logs/debug.log +31 -0
  31. wandb/run-20241225_001558-sxxraa4n/run-sxxraa4n.wandb +3 -0
  32. wandb/run-20241225_152744-sac86tlv/files/conda-environment.yaml +232 -0
  33. wandb/run-20241225_152744-sac86tlv/files/config.yaml +705 -0
  34. wandb/run-20241225_152744-sac86tlv/files/output.log +0 -0
  35. wandb/run-20241225_152744-sac86tlv/files/requirements.txt +242 -0
  36. wandb/run-20241225_152744-sac86tlv/files/wandb-metadata.json +705 -0
  37. wandb/run-20241225_152744-sac86tlv/files/wandb-summary.json +1 -0
  38. wandb/run-20241225_152744-sac86tlv/logs/debug-internal.log +0 -0
  39. wandb/run-20241225_152744-sac86tlv/logs/debug.log +31 -0
  40. wandb/run-20241225_152744-sac86tlv/run-sac86tlv.wandb +3 -0
  41. wandb/run-20241226_145403-c7ovtvny/files/conda-environment.yaml +232 -0
  42. wandb/run-20241226_145403-c7ovtvny/files/config.yaml +705 -0
  43. wandb/run-20241226_145403-c7ovtvny/files/output.log +0 -0
  44. wandb/run-20241226_145403-c7ovtvny/files/requirements.txt +242 -0
  45. wandb/run-20241226_145403-c7ovtvny/files/wandb-metadata.json +705 -0
  46. wandb/run-20241226_145403-c7ovtvny/files/wandb-summary.json +1 -0
  47. wandb/run-20241226_145403-c7ovtvny/logs/debug-internal.log +0 -0
  48. wandb/run-20241226_145403-c7ovtvny/logs/debug.log +31 -0
  49. wandb/run-20241226_145403-c7ovtvny/run-c7ovtvny.wandb +3 -0
  50. wandb/run-20241226_224836-fta6xses/files/conda-environment.yaml +232 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ wandb/run-20241225_001558-sxxraa4n/run-sxxraa4n.wandb filter=lfs diff=lfs merge=lfs -text
37
+ wandb/run-20241225_152744-sac86tlv/run-sac86tlv.wandb filter=lfs diff=lfs merge=lfs -text
38
+ wandb/run-20241226_145403-c7ovtvny/run-c7ovtvny.wandb filter=lfs diff=lfs merge=lfs -text
39
+ wandb/run-20241226_224836-fta6xses/run-fta6xses.wandb filter=lfs diff=lfs merge=lfs -text
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.13208570653647952,
3
+ "num_input_tokens_seen": 7732199424,
4
+ "train_loss": 0.059379862848258066,
5
+ "train_runtime": 15793.1588,
6
+ "train_samples_per_second": 0.467,
7
+ "train_steps_per_second": 0.233
8
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 524288,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 32,
19
+ "num_key_value_heads": 8,
20
+ "pad_token_id": 0,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 128000000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.44.2",
28
+ "use_cache": true,
29
+ "vocab_size": 128256
30
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": 128009,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.44.2"
7
+ }
log.out ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c26dc16ca4103321217d048b95c093a962f9ac89050c3a8dd174346e207b3e7
3
+ size 4886466168
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4809e517ef7c60c0f63a0c81f1adcf297ffcf154e63b2a6db6d726dda1c5308c
3
+ size 4832007448
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e660ec0d0db2990b9b6ceae9215fbe5c95c1f8340fec45431712f87d49a9bb87
3
+ size 4999813112
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6a3bbc5a9053dbc89101e717c9e0a761bde1c3d70e098e721f5b3616924ed33
3
+ size 4999813128
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf1a00576deac5ab4ea67235bca5a8f00e16426c8d1b8664925073d5603d77af
3
+ size 4832007496
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08282142ed7be238fc32e6843b2b02b98620c7addda0a6541f36f5632788d1c0
3
+ size 4999813120
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c47188f45c65ffd7a396325f96621c61ef98c383daa96752fbe7c7975917c9ad
3
+ size 2571158184
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 32121044992
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00007-of-00007.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
296
+ "model.norm.weight": "model-00007-of-00007.safetensors"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ }
16
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2062 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "tokenizer_class": "PreTrainedTokenizerFast"
2062
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 0.13208570653647952,
3
+ "num_input_tokens_seen": 7732199424,
4
+ "train_loss": 0.059379862848258066,
5
+ "train_runtime": 15793.1588,
6
+ "train_samples_per_second": 0.467,
7
+ "train_steps_per_second": 0.233
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6940cd967bdcf38d3c718ee07e93eda4a57d949efbc9b707df65a82dd8cc581e
3
+ size 5560
wandb/debug-cli.ctpham_umass_edu.log ADDED
File without changes
wandb/debug-internal.log ADDED
The diff for this file is too large to render. See raw diff
 
wandb/debug.log ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-12-26 22:48:36,725 INFO MainThread:839109 [wandb_setup.py:_flush():76] Current SDK version is 0.17.3
2
+ 2024-12-26 22:48:36,725 INFO MainThread:839109 [wandb_setup.py:_flush():76] Configure stats pid to 839109
3
+ 2024-12-26 22:48:36,725 INFO MainThread:839109 [wandb_setup.py:_flush():76] Loading settings from /home/ctpham_umass_edu/.config/wandb/settings
4
+ 2024-12-26 22:48:36,725 INFO MainThread:839109 [wandb_setup.py:_flush():76] Loading settings from /work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/wandb/settings
5
+ 2024-12-26 22:48:36,725 INFO MainThread:839109 [wandb_setup.py:_flush():76] Loading settings from environment variables: {'root_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'project': 'prolong', 'api_key': '***REDACTED***', 'mode': 'online'}
6
+ 2024-12-26 22:48:36,725 INFO MainThread:839109 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
7
+ 2024-12-26 22:48:36,725 INFO MainThread:839109 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'prolong-final/finetune.py', 'program_abspath': '/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py', 'program': '/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py'}
8
+ 2024-12-26 22:48:36,725 INFO MainThread:839109 [wandb_setup.py:_flush():76] Applying login settings: {}
9
+ 2024-12-26 22:48:36,726 INFO MainThread:839109 [wandb_init.py:_log_setup():520] Logging user logs to /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/wandb/run-20241226_224836-fta6xses/logs/debug.log
10
+ 2024-12-26 22:48:36,726 INFO MainThread:839109 [wandb_init.py:_log_setup():521] Logging internal logs to /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/wandb/run-20241226_224836-fta6xses/logs/debug-internal.log
11
+ 2024-12-26 22:48:36,726 INFO MainThread:839109 [wandb_init.py:init():560] calling init triggers
12
+ 2024-12-26 22:48:36,726 INFO MainThread:839109 [wandb_init.py:init():567] wandb.init called with sweep_config: {}
13
+ config: {}
14
+ 2024-12-26 22:48:36,726 INFO MainThread:839109 [wandb_init.py:init():610] starting backend
15
+ 2024-12-26 22:48:36,726 INFO MainThread:839109 [wandb_init.py:init():614] setting up manager
16
+ 2024-12-26 22:48:36,729 INFO MainThread:839109 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
17
+ 2024-12-26 22:48:36,732 INFO MainThread:839109 [wandb_init.py:init():622] backend started and connected
18
+ 2024-12-26 22:48:36,740 INFO MainThread:839109 [wandb_init.py:init():711] updated telemetry
19
+ 2024-12-26 22:48:36,765 INFO MainThread:839109 [wandb_init.py:init():744] communicating run to backend with 90.0 second timeout
20
+ 2024-12-26 22:48:37,011 INFO MainThread:839109 [wandb_run.py:_on_init():2402] communicating current version
21
+ 2024-12-26 22:48:37,074 INFO MainThread:839109 [wandb_run.py:_on_init():2411] got version response upgrade_message: "wandb version 0.19.1 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
22
+
23
+ 2024-12-26 22:48:37,074 INFO MainThread:839109 [wandb_init.py:init():795] starting run threads in backend
24
+ 2024-12-26 22:48:44,772 INFO MainThread:839109 [wandb_run.py:_console_start():2380] atexit reg
25
+ 2024-12-26 22:48:44,773 INFO MainThread:839109 [wandb_run.py:_redirect():2235] redirect: wrap_raw
26
+ 2024-12-26 22:48:44,773 INFO MainThread:839109 [wandb_run.py:_redirect():2300] Wrapping output streams.
27
+ 2024-12-26 22:48:44,773 INFO MainThread:839109 [wandb_run.py:_redirect():2325] Redirects installed.
28
+ 2024-12-26 22:48:44,775 INFO MainThread:839109 [wandb_init.py:init():838] run started, returning control to user process
29
+ 2024-12-26 22:48:44,777 INFO MainThread:839109 [wandb_run.py:_config_callback():1382] config_cb None None {'vocab_size': 128256, 'max_position_embeddings': 524288, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'pretraining_tp': 1, 'use_cache': True, 'rope_theta': 128000000.0, 'rope_scaling': None, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['LlamaForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 128000, 'pad_token_id': 0, 'eos_token_id': 128009, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': '/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/', 'transformers_version': '4.44.2', 'model_type': 'llama', 'output_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'overwrite_output_dir': False, 'do_train': True, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 1e-06, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.95, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.05, 'warmup_steps': 0, 'log_level': 'info', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/runs/Dec26_22-45-54_gpu021', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1.0, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 200, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 1, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'disable_tqdm': True, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': True, 'fsdp': ['auto_wrap', 'offload'], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': False, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'eval_use_gather_object': False, 'min_lr_ratio': 0.1, 'cuda_empty_cache': True, 'streaming_dataset': True, 'seq_parallel_size': 8}
30
+ 2024-12-26 22:48:44,780 INFO MainThread:839109 [wandb_config.py:__setitem__():151] config set model/num_parameters = 1003782656 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x78858f51ed40>>
31
+ 2024-12-26 22:48:44,780 INFO MainThread:839109 [wandb_run.py:_config_callback():1382] config_cb model/num_parameters 1003782656 None
32
+ 2024-12-27 03:13:36,487 WARNING MsgRouterThr:839109 [router.py:message_loop():77] message_loop has been closed
wandb/run-20241225_001558-sxxraa4n/files/conda-environment.yaml ADDED
@@ -0,0 +1,232 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ name: /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final
2
+ channels:
3
+ - conda-forge
4
+ dependencies:
5
+ - _libgcc_mutex=0.1=conda_forge
6
+ - _openmp_mutex=4.5=2_gnu
7
+ - bzip2=1.0.8=h4bc722e_7
8
+ - ca-certificates=2024.12.14=hbcca054_0
9
+ - ld_impl_linux-64=2.43=h712a8e2_2
10
+ - libffi=3.4.2=h7f98852_5
11
+ - libgcc=14.2.0=h77fa898_1
12
+ - libgcc-ng=14.2.0=h69a702a_1
13
+ - libgomp=14.2.0=h77fa898_1
14
+ - liblzma=5.6.3=hb9d3cd8_1
15
+ - liblzma-devel=5.6.3=hb9d3cd8_1
16
+ - libnsl=2.0.1=hd590300_0
17
+ - libsqlite=3.47.2=hee588c1_0
18
+ - libuuid=2.38.1=h0b41bf4_0
19
+ - libzlib=1.3.1=hb9d3cd8_2
20
+ - ncurses=6.5=he02047a_1
21
+ - openssl=3.4.0=hb9d3cd8_0
22
+ - pip=24.3.1=pyh8b19718_2
23
+ - python=3.10.0=h543edf9_3_cpython
24
+ - readline=8.2=h8228510_1
25
+ - setuptools=75.6.0=pyhff2d567_1
26
+ - sqlite=3.47.2=h9eae976_0
27
+ - tk=8.6.13=noxft_h4845f30_101
28
+ - wheel=0.45.1=pyhd8ed1ab_1
29
+ - xz=5.6.3=hbcc6ac9_1
30
+ - xz-gpl-tools=5.6.3=hbcc6ac9_1
31
+ - xz-tools=5.6.3=hb9d3cd8_1
32
+ - pip:
33
+ - accelerate==0.32.1
34
+ - aiohappyeyeballs==2.4.3
35
+ - aiohttp==3.11.2
36
+ - aioprometheus==23.12.0
37
+ - aiosignal==1.3.1
38
+ - annotated-types==0.7.0
39
+ - anthropic==0.39.0
40
+ - anyio==4.6.2.post1
41
+ - argcomplete==3.5.1
42
+ - arrow==1.3.0
43
+ - async-timeout==5.0.1
44
+ - attrs==24.2.0
45
+ - azure-core==1.32.0
46
+ - azure-identity==1.19.0
47
+ - azure-storage-blob==12.24.0
48
+ - azure-storage-file-datalake==12.18.0
49
+ - backoff==2.2.1
50
+ - bcrypt==4.2.0
51
+ - blobfile==3.0.0
52
+ - boto3==1.35.63
53
+ - botocore==1.35.63
54
+ - brotli==1.1.0
55
+ - cachetools==5.5.0
56
+ - certifi==2024.8.30
57
+ - cffi==1.17.1
58
+ - charset-normalizer==3.4.0
59
+ - circuitbreaker==2.0.0
60
+ - click==8.1.7
61
+ - cloudpickle==3.1.0
62
+ - compressed-tensors==0.8.0
63
+ - contourpy==1.3.1
64
+ - cramjam==2.9.0
65
+ - cryptography==43.0.3
66
+ - cycler==0.12.1
67
+ - datasets==2.20.0
68
+ - debugpy==1.8.11
69
+ - dill==0.3.8
70
+ - diskcache==5.6.3
71
+ - distro==1.9.0
72
+ - docker-pycreds==0.4.0
73
+ - docstring-parser==0.16
74
+ - einops==0.8.0
75
+ - fastapi==0.115.5
76
+ - filelock==3.16.1
77
+ - flash-attn==2.6.1
78
+ - fonttools==4.55.0
79
+ - frozenlist==1.5.0
80
+ - fsspec==2024.5.0
81
+ - gguf==0.10.0
82
+ - gitdb==4.0.11
83
+ - gitpython==3.1.43
84
+ - google-api-core==2.23.0
85
+ - google-auth==2.36.0
86
+ - google-cloud-aiplatform==1.71.1
87
+ - google-cloud-bigquery==3.27.0
88
+ - google-cloud-core==2.4.1
89
+ - google-cloud-resource-manager==1.13.1
90
+ - google-cloud-storage==2.10.0
91
+ - google-crc32c==1.6.0
92
+ - google-resumable-media==2.7.2
93
+ - googleapis-common-protos==1.66.0
94
+ - gql==3.5.0
95
+ - graphql-core==3.2.5
96
+ - grpc-google-iam-v1==0.13.1
97
+ - grpcio==1.68.0
98
+ - grpcio-status==1.62.3
99
+ - h11==0.14.0
100
+ - httpcore==1.0.7
101
+ - httptools==0.6.4
102
+ - httpx==0.27.2
103
+ - huggingface-hub==0.26.2
104
+ - idna==3.10
105
+ - importlib-metadata==8.5.0
106
+ - interegular==0.3.3
107
+ - ipython==8.18.0
108
+ - isodate==0.7.2
109
+ - jedi==0.19.2
110
+ - jinja2==3.1.4
111
+ - jiter==0.7.1
112
+ - jmespath==1.0.1
113
+ - jsonschema==4.23.0
114
+ - jsonschema-specifications==2024.10.1
115
+ - kiwisolver==1.4.7
116
+ - lark==1.2.2
117
+ - llvmlite==0.43.0
118
+ - lm-format-enforcer==0.10.9
119
+ - lxml==5.3.0
120
+ - markdown-it-py==3.0.0
121
+ - markupsafe==3.0.2
122
+ - matplotlib==3.9.2
123
+ - mdurl==0.1.2
124
+ - mosaicml-cli==0.5.34
125
+ - mosaicml-streaming==0.8.1
126
+ - mpmath==1.3.0
127
+ - msal==1.31.1
128
+ - msal-extensions==1.2.0
129
+ - msgpack==1.1.0
130
+ - msgspec==0.18.6
131
+ - multidict==6.1.0
132
+ - multiprocess==0.70.16
133
+ - networkx==3.4.2
134
+ - ninja==1.11.1.1
135
+ - numba==0.60.0
136
+ - numpy==1.26.3
137
+ - nvidia-cublas-cu12==12.1.3.1
138
+ - nvidia-cuda-cupti-cu12==12.1.105
139
+ - nvidia-cuda-nvrtc-cu12==12.1.105
140
+ - nvidia-cuda-runtime-cu12==12.1.105
141
+ - nvidia-cudnn-cu12==9.1.0.70
142
+ - nvidia-cufft-cu12==11.0.2.54
143
+ - nvidia-curand-cu12==10.3.2.106
144
+ - nvidia-cusolver-cu12==11.4.5.107
145
+ - nvidia-cusparse-cu12==12.1.0.106
146
+ - nvidia-ml-py==12.560.30
147
+ - nvidia-nccl-cu12==2.20.5
148
+ - nvidia-nvjitlink-cu12==12.4.127
149
+ - nvidia-nvtx-cu12==12.1.105
150
+ - oci==2.138.1
151
+ - openai==1.54.5
152
+ - opencv-python-headless==4.10.0.84
153
+ - orjson==3.10.11
154
+ - outlines==0.0.46
155
+ - packaging==24.1
156
+ - pandas==2.2.1
157
+ - paramiko==3.5.0
158
+ - partial-json-parser==0.2.1.1.post4
159
+ - pillow==10.4.0
160
+ - portalocker==2.10.1
161
+ - prometheus-client==0.21.0
162
+ - prometheus-fastapi-instrumentator==7.0.0
163
+ - prompt-toolkit==3.0.36
164
+ - propcache==0.2.0
165
+ - proto-plus==1.25.0
166
+ - protobuf==4.25.3
167
+ - py-cpuinfo==9.0.0
168
+ - pyairports==2.1.1
169
+ - pyarrow==18.0.0
170
+ - pyarrow-hotfix==0.6
171
+ - pyasn1==0.6.1
172
+ - pyasn1-modules==0.4.1
173
+ - pycountry==24.6.1
174
+ - pycparser==2.22
175
+ - pycryptodomex==3.21.0
176
+ - pydantic==2.9.2
177
+ - pydantic-core==2.23.4
178
+ - pyjwt==2.10.0
179
+ - pynacl==1.5.0
180
+ - pyopenssl==24.2.1
181
+ - pyparsing==3.2.0
182
+ - python-dateutil==2.9.0
183
+ - python-dotenv==1.0.1
184
+ - python-snappy==0.7.3
185
+ - pytz==2024.2
186
+ - pyyaml==6.0.2
187
+ - quantile-python==1.1
188
+ - questionary==2.0.1
189
+ - ray==2.39.0
190
+ - referencing==0.35.1
191
+ - regex==2023.12.25
192
+ - requests==2.32.3
193
+ - rich==13.9.4
194
+ - rotary-emb==0.5.2
195
+ - rpds-py==0.21.0
196
+ - rsa==4.9
197
+ - ruamel-yaml==0.18.6
198
+ - ruamel-yaml-clib==0.2.12
199
+ - s3transfer==0.10.3
200
+ - safetensors==0.4.5
201
+ - sentencepiece==0.1.99
202
+ - sentry-sdk==2.18.0
203
+ - setproctitle==1.3.4
204
+ - shapely==2.0.6
205
+ - smmap==5.0.1
206
+ - sniffio==1.3.1
207
+ - starlette==0.41.3
208
+ - sympy==1.13.1
209
+ - tiktoken==0.7.0
210
+ - tokenizers==0.19.1
211
+ - torch==2.4.1
212
+ - torchvision==0.19.1
213
+ - tqdm==4.66.4
214
+ - transformers==4.44.2
215
+ - triton==3.0.0
216
+ - types-python-dateutil==2.9.0.20241003
217
+ - tzdata==2024.2
218
+ - urllib3==2.2.3
219
+ - uvicorn==0.32.0
220
+ - uvloop==0.21.0
221
+ - validators==0.34.0
222
+ - vertexai==1.71.1
223
+ - wandb==0.17.3
224
+ - watchfiles==0.24.0
225
+ - websockets==11.0.3
226
+ - xformers==0.0.28.post1
227
+ - xxhash==3.5.0
228
+ - yarl==1.17.2
229
+ - zipp==3.21.0
230
+ - zstandard==0.22.0
231
+ - zstd==1.5.5.1
232
+ prefix: /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final
wandb/run-20241225_001558-sxxraa4n/files/config.yaml ADDED
@@ -0,0 +1,705 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wandb_version: 1
2
+
3
+ _wandb:
4
+ desc: null
5
+ value:
6
+ python_version: 3.10.0
7
+ cli_version: 0.17.3
8
+ framework: huggingface
9
+ huggingface_version: 4.44.2
10
+ is_jupyter_run: false
11
+ is_kaggle_kernel: false
12
+ start_time: 1735085758
13
+ t:
14
+ 1:
15
+ - 1
16
+ - 11
17
+ - 41
18
+ - 49
19
+ - 51
20
+ - 55
21
+ - 71
22
+ - 105
23
+ 2:
24
+ - 1
25
+ - 11
26
+ - 41
27
+ - 49
28
+ - 51
29
+ - 55
30
+ - 71
31
+ - 105
32
+ 3:
33
+ - 7
34
+ - 13
35
+ - 19
36
+ - 23
37
+ - 66
38
+ 4: 3.10.0
39
+ 5: 0.17.3
40
+ 6: 4.44.2
41
+ 8:
42
+ - 5
43
+ 9:
44
+ 1: transformers_trainer
45
+ 13: linux-x86_64
46
+ m:
47
+ - 1: train/global_step
48
+ 6:
49
+ - 3
50
+ - 1: train/loss
51
+ 5: 1
52
+ 6:
53
+ - 1
54
+ - 1: train/grad_norm
55
+ 5: 1
56
+ 6:
57
+ - 1
58
+ - 1: train/learning_rate
59
+ 5: 1
60
+ 6:
61
+ - 1
62
+ - 1: train/epoch
63
+ 5: 1
64
+ 6:
65
+ - 1
66
+ - 1: train/num_input_tokens_seen
67
+ 5: 1
68
+ 6:
69
+ - 1
70
+ vocab_size:
71
+ desc: null
72
+ value: 128256
73
+ max_position_embeddings:
74
+ desc: null
75
+ value: 524288
76
+ hidden_size:
77
+ desc: null
78
+ value: 4096
79
+ intermediate_size:
80
+ desc: null
81
+ value: 14336
82
+ num_hidden_layers:
83
+ desc: null
84
+ value: 32
85
+ num_attention_heads:
86
+ desc: null
87
+ value: 32
88
+ num_key_value_heads:
89
+ desc: null
90
+ value: 8
91
+ hidden_act:
92
+ desc: null
93
+ value: silu
94
+ initializer_range:
95
+ desc: null
96
+ value: 0.02
97
+ rms_norm_eps:
98
+ desc: null
99
+ value: 1.0e-05
100
+ pretraining_tp:
101
+ desc: null
102
+ value: 1
103
+ use_cache:
104
+ desc: null
105
+ value: true
106
+ rope_theta:
107
+ desc: null
108
+ value: 128000000.0
109
+ rope_scaling:
110
+ desc: null
111
+ value: null
112
+ attention_bias:
113
+ desc: null
114
+ value: false
115
+ attention_dropout:
116
+ desc: null
117
+ value: 0.0
118
+ mlp_bias:
119
+ desc: null
120
+ value: false
121
+ return_dict:
122
+ desc: null
123
+ value: true
124
+ output_hidden_states:
125
+ desc: null
126
+ value: false
127
+ output_attentions:
128
+ desc: null
129
+ value: false
130
+ torchscript:
131
+ desc: null
132
+ value: false
133
+ torch_dtype:
134
+ desc: null
135
+ value: float32
136
+ use_bfloat16:
137
+ desc: null
138
+ value: false
139
+ tf_legacy_loss:
140
+ desc: null
141
+ value: false
142
+ pruned_heads:
143
+ desc: null
144
+ value: {}
145
+ tie_word_embeddings:
146
+ desc: null
147
+ value: false
148
+ chunk_size_feed_forward:
149
+ desc: null
150
+ value: 0
151
+ is_encoder_decoder:
152
+ desc: null
153
+ value: false
154
+ is_decoder:
155
+ desc: null
156
+ value: false
157
+ cross_attention_hidden_size:
158
+ desc: null
159
+ value: null
160
+ add_cross_attention:
161
+ desc: null
162
+ value: false
163
+ tie_encoder_decoder:
164
+ desc: null
165
+ value: false
166
+ max_length:
167
+ desc: null
168
+ value: 20
169
+ min_length:
170
+ desc: null
171
+ value: 0
172
+ do_sample:
173
+ desc: null
174
+ value: false
175
+ early_stopping:
176
+ desc: null
177
+ value: false
178
+ num_beams:
179
+ desc: null
180
+ value: 1
181
+ num_beam_groups:
182
+ desc: null
183
+ value: 1
184
+ diversity_penalty:
185
+ desc: null
186
+ value: 0.0
187
+ temperature:
188
+ desc: null
189
+ value: 1.0
190
+ top_k:
191
+ desc: null
192
+ value: 50
193
+ top_p:
194
+ desc: null
195
+ value: 1.0
196
+ typical_p:
197
+ desc: null
198
+ value: 1.0
199
+ repetition_penalty:
200
+ desc: null
201
+ value: 1.0
202
+ length_penalty:
203
+ desc: null
204
+ value: 1.0
205
+ no_repeat_ngram_size:
206
+ desc: null
207
+ value: 0
208
+ encoder_no_repeat_ngram_size:
209
+ desc: null
210
+ value: 0
211
+ bad_words_ids:
212
+ desc: null
213
+ value: null
214
+ num_return_sequences:
215
+ desc: null
216
+ value: 1
217
+ output_scores:
218
+ desc: null
219
+ value: false
220
+ return_dict_in_generate:
221
+ desc: null
222
+ value: false
223
+ forced_bos_token_id:
224
+ desc: null
225
+ value: null
226
+ forced_eos_token_id:
227
+ desc: null
228
+ value: null
229
+ remove_invalid_values:
230
+ desc: null
231
+ value: false
232
+ exponential_decay_length_penalty:
233
+ desc: null
234
+ value: null
235
+ suppress_tokens:
236
+ desc: null
237
+ value: null
238
+ begin_suppress_tokens:
239
+ desc: null
240
+ value: null
241
+ architectures:
242
+ desc: null
243
+ value:
244
+ - LlamaForCausalLM
245
+ finetuning_task:
246
+ desc: null
247
+ value: null
248
+ id2label:
249
+ desc: null
250
+ value:
251
+ '0': LABEL_0
252
+ '1': LABEL_1
253
+ label2id:
254
+ desc: null
255
+ value:
256
+ LABEL_0: 0
257
+ LABEL_1: 1
258
+ tokenizer_class:
259
+ desc: null
260
+ value: null
261
+ prefix:
262
+ desc: null
263
+ value: null
264
+ bos_token_id:
265
+ desc: null
266
+ value: 128000
267
+ pad_token_id:
268
+ desc: null
269
+ value: 0
270
+ eos_token_id:
271
+ desc: null
272
+ value: 128009
273
+ sep_token_id:
274
+ desc: null
275
+ value: null
276
+ decoder_start_token_id:
277
+ desc: null
278
+ value: null
279
+ task_specific_params:
280
+ desc: null
281
+ value: null
282
+ problem_type:
283
+ desc: null
284
+ value: null
285
+ _name_or_path:
286
+ desc: null
287
+ value: /scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/
288
+ transformers_version:
289
+ desc: null
290
+ value: 4.44.2
291
+ model_type:
292
+ desc: null
293
+ value: llama
294
+ output_dir:
295
+ desc: null
296
+ value: /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_
297
+ overwrite_output_dir:
298
+ desc: null
299
+ value: false
300
+ do_train:
301
+ desc: null
302
+ value: true
303
+ do_eval:
304
+ desc: null
305
+ value: false
306
+ do_predict:
307
+ desc: null
308
+ value: false
309
+ eval_strategy:
310
+ desc: null
311
+ value: 'no'
312
+ prediction_loss_only:
313
+ desc: null
314
+ value: false
315
+ per_device_train_batch_size:
316
+ desc: null
317
+ value: 1
318
+ per_device_eval_batch_size:
319
+ desc: null
320
+ value: 8
321
+ per_gpu_train_batch_size:
322
+ desc: null
323
+ value: null
324
+ per_gpu_eval_batch_size:
325
+ desc: null
326
+ value: null
327
+ gradient_accumulation_steps:
328
+ desc: null
329
+ value: 2
330
+ eval_accumulation_steps:
331
+ desc: null
332
+ value: null
333
+ eval_delay:
334
+ desc: null
335
+ value: 0
336
+ torch_empty_cache_steps:
337
+ desc: null
338
+ value: null
339
+ learning_rate:
340
+ desc: null
341
+ value: 1.0e-06
342
+ weight_decay:
343
+ desc: null
344
+ value: 0.1
345
+ adam_beta1:
346
+ desc: null
347
+ value: 0.9
348
+ adam_beta2:
349
+ desc: null
350
+ value: 0.95
351
+ adam_epsilon:
352
+ desc: null
353
+ value: 1.0e-08
354
+ max_grad_norm:
355
+ desc: null
356
+ value: 1.0
357
+ num_train_epochs:
358
+ desc: null
359
+ value: 1.0
360
+ max_steps:
361
+ desc: null
362
+ value: -1
363
+ lr_scheduler_type:
364
+ desc: null
365
+ value: cosine
366
+ lr_scheduler_kwargs:
367
+ desc: null
368
+ value: {}
369
+ warmup_ratio:
370
+ desc: null
371
+ value: 0.05
372
+ warmup_steps:
373
+ desc: null
374
+ value: 0
375
+ log_level:
376
+ desc: null
377
+ value: info
378
+ log_level_replica:
379
+ desc: null
380
+ value: warning
381
+ log_on_each_node:
382
+ desc: null
383
+ value: true
384
+ logging_dir:
385
+ desc: null
386
+ value: /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/runs/Dec25_00-13-47_gpu021
387
+ logging_strategy:
388
+ desc: null
389
+ value: steps
390
+ logging_first_step:
391
+ desc: null
392
+ value: false
393
+ logging_steps:
394
+ desc: null
395
+ value: 1.0
396
+ logging_nan_inf_filter:
397
+ desc: null
398
+ value: true
399
+ save_strategy:
400
+ desc: null
401
+ value: steps
402
+ save_steps:
403
+ desc: null
404
+ value: 200
405
+ save_total_limit:
406
+ desc: null
407
+ value: null
408
+ save_safetensors:
409
+ desc: null
410
+ value: true
411
+ save_on_each_node:
412
+ desc: null
413
+ value: false
414
+ save_only_model:
415
+ desc: null
416
+ value: false
417
+ restore_callback_states_from_checkpoint:
418
+ desc: null
419
+ value: false
420
+ no_cuda:
421
+ desc: null
422
+ value: false
423
+ use_cpu:
424
+ desc: null
425
+ value: false
426
+ use_mps_device:
427
+ desc: null
428
+ value: false
429
+ seed:
430
+ desc: null
431
+ value: 42
432
+ data_seed:
433
+ desc: null
434
+ value: null
435
+ jit_mode_eval:
436
+ desc: null
437
+ value: false
438
+ use_ipex:
439
+ desc: null
440
+ value: false
441
+ bf16:
442
+ desc: null
443
+ value: true
444
+ fp16:
445
+ desc: null
446
+ value: false
447
+ fp16_opt_level:
448
+ desc: null
449
+ value: O1
450
+ half_precision_backend:
451
+ desc: null
452
+ value: auto
453
+ bf16_full_eval:
454
+ desc: null
455
+ value: false
456
+ fp16_full_eval:
457
+ desc: null
458
+ value: false
459
+ tf32:
460
+ desc: null
461
+ value: null
462
+ local_rank:
463
+ desc: null
464
+ value: 0
465
+ ddp_backend:
466
+ desc: null
467
+ value: null
468
+ tpu_num_cores:
469
+ desc: null
470
+ value: null
471
+ tpu_metrics_debug:
472
+ desc: null
473
+ value: false
474
+ debug:
475
+ desc: null
476
+ value: []
477
+ dataloader_drop_last:
478
+ desc: null
479
+ value: false
480
+ eval_steps:
481
+ desc: null
482
+ value: null
483
+ dataloader_num_workers:
484
+ desc: null
485
+ value: 1
486
+ dataloader_prefetch_factor:
487
+ desc: null
488
+ value: null
489
+ past_index:
490
+ desc: null
491
+ value: -1
492
+ run_name:
493
+ desc: null
494
+ value: balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_
495
+ disable_tqdm:
496
+ desc: null
497
+ value: true
498
+ remove_unused_columns:
499
+ desc: null
500
+ value: false
501
+ label_names:
502
+ desc: null
503
+ value: null
504
+ load_best_model_at_end:
505
+ desc: null
506
+ value: false
507
+ metric_for_best_model:
508
+ desc: null
509
+ value: null
510
+ greater_is_better:
511
+ desc: null
512
+ value: null
513
+ ignore_data_skip:
514
+ desc: null
515
+ value: false
516
+ fsdp:
517
+ desc: null
518
+ value:
519
+ - auto_wrap
520
+ - offload
521
+ fsdp_min_num_params:
522
+ desc: null
523
+ value: 0
524
+ fsdp_config:
525
+ desc: null
526
+ value:
527
+ min_num_params: 0
528
+ xla: false
529
+ xla_fsdp_v2: false
530
+ xla_fsdp_grad_ckpt: false
531
+ fsdp_transformer_layer_cls_to_wrap:
532
+ desc: null
533
+ value: null
534
+ accelerator_config:
535
+ desc: null
536
+ value:
537
+ split_batches: false
538
+ dispatch_batches: null
539
+ even_batches: true
540
+ use_seedable_sampler: true
541
+ non_blocking: false
542
+ gradient_accumulation_kwargs: null
543
+ deepspeed:
544
+ desc: null
545
+ value: null
546
+ label_smoothing_factor:
547
+ desc: null
548
+ value: 0.0
549
+ optim:
550
+ desc: null
551
+ value: adamw_torch
552
+ optim_args:
553
+ desc: null
554
+ value: null
555
+ adafactor:
556
+ desc: null
557
+ value: false
558
+ group_by_length:
559
+ desc: null
560
+ value: false
561
+ length_column_name:
562
+ desc: null
563
+ value: length
564
+ report_to:
565
+ desc: null
566
+ value:
567
+ - wandb
568
+ ddp_find_unused_parameters:
569
+ desc: null
570
+ value: false
571
+ ddp_bucket_cap_mb:
572
+ desc: null
573
+ value: null
574
+ ddp_broadcast_buffers:
575
+ desc: null
576
+ value: null
577
+ dataloader_pin_memory:
578
+ desc: null
579
+ value: true
580
+ dataloader_persistent_workers:
581
+ desc: null
582
+ value: false
583
+ skip_memory_metrics:
584
+ desc: null
585
+ value: true
586
+ use_legacy_prediction_loop:
587
+ desc: null
588
+ value: false
589
+ push_to_hub:
590
+ desc: null
591
+ value: false
592
+ resume_from_checkpoint:
593
+ desc: null
594
+ value: null
595
+ hub_model_id:
596
+ desc: null
597
+ value: null
598
+ hub_strategy:
599
+ desc: null
600
+ value: every_save
601
+ hub_token:
602
+ desc: null
603
+ value: <HUB_TOKEN>
604
+ hub_private_repo:
605
+ desc: null
606
+ value: false
607
+ hub_always_push:
608
+ desc: null
609
+ value: false
610
+ gradient_checkpointing:
611
+ desc: null
612
+ value: true
613
+ gradient_checkpointing_kwargs:
614
+ desc: null
615
+ value: null
616
+ include_inputs_for_metrics:
617
+ desc: null
618
+ value: false
619
+ eval_do_concat_batches:
620
+ desc: null
621
+ value: true
622
+ fp16_backend:
623
+ desc: null
624
+ value: auto
625
+ evaluation_strategy:
626
+ desc: null
627
+ value: null
628
+ push_to_hub_model_id:
629
+ desc: null
630
+ value: null
631
+ push_to_hub_organization:
632
+ desc: null
633
+ value: null
634
+ push_to_hub_token:
635
+ desc: null
636
+ value: <PUSH_TO_HUB_TOKEN>
637
+ mp_parameters:
638
+ desc: null
639
+ value: ''
640
+ auto_find_batch_size:
641
+ desc: null
642
+ value: false
643
+ full_determinism:
644
+ desc: null
645
+ value: false
646
+ torchdynamo:
647
+ desc: null
648
+ value: null
649
+ ray_scope:
650
+ desc: null
651
+ value: last
652
+ ddp_timeout:
653
+ desc: null
654
+ value: 1800
655
+ torch_compile:
656
+ desc: null
657
+ value: false
658
+ torch_compile_backend:
659
+ desc: null
660
+ value: null
661
+ torch_compile_mode:
662
+ desc: null
663
+ value: null
664
+ dispatch_batches:
665
+ desc: null
666
+ value: null
667
+ split_batches:
668
+ desc: null
669
+ value: null
670
+ include_tokens_per_second:
671
+ desc: null
672
+ value: false
673
+ include_num_input_tokens_seen:
674
+ desc: null
675
+ value: false
676
+ neftune_noise_alpha:
677
+ desc: null
678
+ value: null
679
+ optim_target_modules:
680
+ desc: null
681
+ value: null
682
+ batch_eval_metrics:
683
+ desc: null
684
+ value: false
685
+ eval_on_start:
686
+ desc: null
687
+ value: false
688
+ eval_use_gather_object:
689
+ desc: null
690
+ value: false
691
+ min_lr_ratio:
692
+ desc: null
693
+ value: 0.1
694
+ cuda_empty_cache:
695
+ desc: null
696
+ value: true
697
+ streaming_dataset:
698
+ desc: null
699
+ value: true
700
+ seq_parallel_size:
701
+ desc: null
702
+ value: 8
703
+ model/num_parameters:
704
+ desc: null
705
+ value: 1003782656
wandb/run-20241225_001558-sxxraa4n/files/output.log ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final/lib/python3.10/site-packages/torch/utils/checkpoint.py:1399: FutureWarning: `torch.cpu.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cpu', args...)` instead.
2
+ with device_autocast_ctx, torch.cpu.amp.autocast(**cpu_autocast_kwargs), recompute_context: # type: ignore[attr-defined]
3
+ [INFO|trainer.py:175] 2024-12-25 00:16:55,348 >> {'loss': 1.4339, 'grad_norm': 39.49641418457031, 'learning_rate': 5.405405405405406e-09, 'epoch': 0.00027122321670735016, 'num_input_tokens_seen': 2097152, 'completed': '0.03% (1 / 3_687)', 'remaining time': '48:49:02', 'throughput': '2749.09', 'gpu_mem_free': '5581MB'}
4
+ [INFO|trainer.py:175] 2024-12-25 00:17:30,230 >> {'loss': 1.4592, 'grad_norm': 34.68007278442383, 'learning_rate': 1.0810810810810811e-08, 'epoch': 0.0005424464334147003, 'num_input_tokens_seen': 4194304, 'completed': '0.05% (2 / 3_687)', 'remaining time': '42:15:16', 'throughput': '7515.28', 'gpu_mem_free': '5581MB'}
5
+ [INFO|trainer.py:175] 2024-12-25 00:18:05,807 >> {'loss': 1.5967, 'grad_norm': 39.95429992675781, 'learning_rate': 1.6216216216216218e-08, 'epoch': 0.0008136696501220504, 'num_input_tokens_seen': 6291456, 'completed': '0.08% (3 / 3_687)', 'remaining time': '40:17:52', 'throughput': '7368.26', 'gpu_mem_free': '5581MB'}
6
+ [INFO|trainer.py:175] 2024-12-25 00:18:36,833 >> {'loss': 1.2915, 'grad_norm': 31.149150848388672, 'learning_rate': 2.1621621621621623e-08, 'epoch': 0.0010848928668294006, 'num_input_tokens_seen': 8388608, 'completed': '0.11% (4 / 3_687)', 'remaining time': '38:09:01', 'throughput': '8449.32', 'gpu_mem_free': '5581MB'}
7
+ [INFO|trainer.py:175] 2024-12-25 00:19:08,749 >> {'loss': 1.8907, 'grad_norm': 42.642982482910156, 'learning_rate': 2.7027027027027028e-08, 'epoch': 0.0013561160835367507, 'num_input_tokens_seen': 10485760, 'completed': '0.14% (5 / 3_687)', 'remaining time': '37:02:26', 'throughput': '8213.40', 'gpu_mem_free': '5581MB'}
8
+ [INFO|trainer.py:175] 2024-12-25 00:19:38,678 >> {'loss': 1.5168, 'grad_norm': 41.49152755737305, 'learning_rate': 3.2432432432432436e-08, 'epoch': 0.0016273393002441008, 'num_input_tokens_seen': 12582912, 'completed': '0.16% (6 / 3_687)', 'remaining time': '35:57:33', 'throughput': '8759.08', 'gpu_mem_free': '5581MB'}
9
+ [INFO|trainer.py:175] 2024-12-25 00:20:10,870 >> {'loss': 1.4075, 'grad_norm': 35.22410202026367, 'learning_rate': 3.783783783783784e-08, 'epoch': 0.001898562516951451, 'num_input_tokens_seen': 14680064, 'completed': '0.19% (7 / 3_687)', 'remaining time': '35:30:53', 'throughput': '8142.93', 'gpu_mem_free': '5581MB'}
wandb/run-20241225_001558-sxxraa4n/files/requirements.txt ADDED
@@ -0,0 +1,242 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Brotli==1.1.0
2
+ GitPython==3.1.43
3
+ Jinja2==3.1.4
4
+ MarkupSafe==3.0.2
5
+ PyJWT==2.10.0
6
+ PyNaCl==1.5.0
7
+ PyYAML==6.0.2
8
+ Pygments==2.18.0
9
+ accelerate==0.32.1
10
+ aiohappyeyeballs==2.4.3
11
+ aiohttp==3.11.2
12
+ aioprometheus==23.12.0
13
+ aiosignal==1.3.1
14
+ annotated-types==0.7.0
15
+ anthropic==0.39.0
16
+ anyio==4.6.2.post1
17
+ argcomplete==3.5.1
18
+ arrow==1.3.0
19
+ asttokens==2.4.1
20
+ async-timeout==5.0.1
21
+ attrs==24.2.0
22
+ autocommand==2.2.2
23
+ azure-core==1.32.0
24
+ azure-identity==1.19.0
25
+ azure-storage-blob==12.24.0
26
+ azure-storage-file-datalake==12.18.0
27
+ backoff==2.2.1
28
+ backports.tarfile==1.2.0
29
+ bcrypt==4.2.0
30
+ blobfile==3.0.0
31
+ boto3==1.35.63
32
+ botocore==1.35.63
33
+ cachetools==5.5.0
34
+ certifi==2024.8.30
35
+ cffi==1.17.1
36
+ charset-normalizer==3.4.0
37
+ circuitbreaker==2.0.0
38
+ click==8.1.7
39
+ cloudpickle==3.1.0
40
+ comm==0.2.2
41
+ compressed-tensors==0.8.0
42
+ contourpy==1.3.1
43
+ cramjam==2.9.0
44
+ cryptography==43.0.3
45
+ cycler==0.12.1
46
+ datasets==2.20.0
47
+ debugpy==1.8.11
48
+ decorator==5.1.1
49
+ dill==0.3.8
50
+ diskcache==5.6.3
51
+ distro==1.9.0
52
+ docker-pycreds==0.4.0
53
+ docstring_parser==0.16
54
+ einops==0.8.0
55
+ exceptiongroup==1.2.2
56
+ executing==2.1.0
57
+ fastapi==0.115.5
58
+ filelock==3.16.1
59
+ flash-attn==2.6.1
60
+ fonttools==4.55.0
61
+ frozenlist==1.5.0
62
+ fsspec==2024.5.0
63
+ gguf==0.10.0
64
+ gitdb==4.0.11
65
+ google-api-core==2.23.0
66
+ google-auth==2.36.0
67
+ google-cloud-aiplatform==1.71.1
68
+ google-cloud-bigquery==3.27.0
69
+ google-cloud-core==2.4.1
70
+ google-cloud-resource-manager==1.13.1
71
+ google-cloud-storage==2.10.0
72
+ google-crc32c==1.6.0
73
+ google-resumable-media==2.7.2
74
+ googleapis-common-protos==1.66.0
75
+ gql==3.5.0
76
+ graphql-core==3.2.5
77
+ grpc-google-iam-v1==0.13.1
78
+ grpcio-status==1.62.3
79
+ grpcio==1.68.0
80
+ h11==0.14.0
81
+ httpcore==1.0.7
82
+ httptools==0.6.4
83
+ httpx==0.27.2
84
+ huggingface-hub==0.26.2
85
+ idna==3.10
86
+ importlib_metadata==8.0.0
87
+ importlib_metadata==8.5.0
88
+ inflect==7.3.1
89
+ interegular==0.3.3
90
+ ipykernel==6.29.5
91
+ ipython==8.18.0
92
+ isodate==0.7.2
93
+ jaraco.collections==5.1.0
94
+ jaraco.context==5.3.0
95
+ jaraco.functools==4.0.1
96
+ jaraco.text==3.12.1
97
+ jedi==0.19.2
98
+ jiter==0.7.1
99
+ jmespath==1.0.1
100
+ jsonschema-specifications==2024.10.1
101
+ jsonschema==4.23.0
102
+ jupyter_client==8.6.3
103
+ jupyter_core==5.7.2
104
+ kiwisolver==1.4.7
105
+ lark==1.2.2
106
+ llvmlite==0.43.0
107
+ lm-format-enforcer==0.10.9
108
+ lxml==5.3.0
109
+ markdown-it-py==3.0.0
110
+ matplotlib-inline==0.1.7
111
+ matplotlib==3.9.2
112
+ mdurl==0.1.2
113
+ more-itertools==10.3.0
114
+ mosaicml-cli==0.5.34
115
+ mosaicml-streaming==0.8.1
116
+ mpmath==1.3.0
117
+ msal-extensions==1.2.0
118
+ msal==1.31.1
119
+ msgpack==1.1.0
120
+ msgspec==0.18.6
121
+ multidict==6.1.0
122
+ multiprocess==0.70.16
123
+ nest-asyncio==1.6.0
124
+ networkx==3.4.2
125
+ ninja==1.11.1.1
126
+ numba==0.60.0
127
+ numpy==1.26.3
128
+ nvidia-cublas-cu12==12.1.3.1
129
+ nvidia-cuda-cupti-cu12==12.1.105
130
+ nvidia-cuda-nvrtc-cu12==12.1.105
131
+ nvidia-cuda-runtime-cu12==12.1.105
132
+ nvidia-cudnn-cu12==9.1.0.70
133
+ nvidia-cufft-cu12==11.0.2.54
134
+ nvidia-curand-cu12==10.3.2.106
135
+ nvidia-cusolver-cu12==11.4.5.107
136
+ nvidia-cusparse-cu12==12.1.0.106
137
+ nvidia-ml-py==12.560.30
138
+ nvidia-nccl-cu12==2.20.5
139
+ nvidia-nvjitlink-cu12==12.4.127
140
+ nvidia-nvtx-cu12==12.1.105
141
+ oci==2.138.1
142
+ openai==1.54.5
143
+ opencv-python-headless==4.10.0.84
144
+ orjson==3.10.11
145
+ outlines==0.0.46
146
+ packaging==24.1
147
+ packaging==24.2
148
+ pandas==2.2.1
149
+ paramiko==3.5.0
150
+ parso==0.8.4
151
+ partial-json-parser==0.2.1.1.post4
152
+ pexpect==4.9.0
153
+ pillow==10.4.0
154
+ pip==24.3.1
155
+ platformdirs==4.2.2
156
+ platformdirs==4.3.6
157
+ portalocker==2.10.1
158
+ prometheus-fastapi-instrumentator==7.0.0
159
+ prometheus_client==0.21.0
160
+ prompt-toolkit==3.0.36
161
+ propcache==0.2.0
162
+ proto-plus==1.25.0
163
+ protobuf==4.25.3
164
+ psutil==6.1.0
165
+ ptyprocess==0.7.0
166
+ pure_eval==0.2.3
167
+ py-cpuinfo==9.0.0
168
+ pyOpenSSL==24.2.1
169
+ pyairports==2.1.1
170
+ pyarrow-hotfix==0.6
171
+ pyarrow==18.0.0
172
+ pyasn1==0.6.1
173
+ pyasn1_modules==0.4.1
174
+ pycountry==24.6.1
175
+ pycparser==2.22
176
+ pycryptodomex==3.21.0
177
+ pydantic==2.9.2
178
+ pydantic_core==2.23.4
179
+ pyparsing==3.2.0
180
+ python-dateutil==2.9.0
181
+ python-dotenv==1.0.1
182
+ python-snappy==0.7.3
183
+ pytz==2024.2
184
+ pyzmq==26.2.0
185
+ quantile-python==1.1
186
+ questionary==2.0.1
187
+ ray==2.39.0
188
+ referencing==0.35.1
189
+ regex==2023.12.25
190
+ requests==2.32.3
191
+ rich==13.9.4
192
+ rotary-emb==0.5.2
193
+ rpds-py==0.21.0
194
+ rsa==4.9
195
+ ruamel.yaml.clib==0.2.12
196
+ ruamel.yaml==0.18.6
197
+ s3transfer==0.10.3
198
+ safetensors==0.4.5
199
+ sentencepiece==0.1.99
200
+ sentry-sdk==2.18.0
201
+ setproctitle==1.3.4
202
+ setuptools==75.6.0
203
+ shapely==2.0.6
204
+ six==1.16.0
205
+ smmap==5.0.1
206
+ sniffio==1.3.1
207
+ stack-data==0.6.3
208
+ starlette==0.41.3
209
+ sympy==1.13.1
210
+ tiktoken==0.7.0
211
+ tokenizers==0.19.1
212
+ tomli==2.0.1
213
+ torch==2.4.1
214
+ torchvision==0.19.1
215
+ tornado==6.4.1
216
+ tqdm==4.66.4
217
+ traitlets==5.14.3
218
+ transformers==4.44.2
219
+ triton==3.0.0
220
+ typeguard==4.3.0
221
+ types-python-dateutil==2.9.0.20241003
222
+ typing_extensions==4.12.2
223
+ typing_extensions==4.12.2
224
+ tzdata==2024.2
225
+ urllib3==2.2.3
226
+ uvicorn==0.32.0
227
+ uvloop==0.21.0
228
+ validators==0.34.0
229
+ vertexai==1.71.1
230
+ wandb==0.17.3
231
+ watchfiles==0.24.0
232
+ wcwidth==0.2.13
233
+ websockets==11.0.3
234
+ wheel==0.43.0
235
+ wheel==0.45.1
236
+ xformers==0.0.28.post1
237
+ xxhash==3.5.0
238
+ yarl==1.17.2
239
+ zipp==3.19.2
240
+ zipp==3.21.0
241
+ zstandard==0.22.0
242
+ zstd==1.5.5.1
wandb/run-20241225_001558-sxxraa4n/files/wandb-metadata.json ADDED
@@ -0,0 +1,705 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-6.8.0-48-generic-x86_64-with-glibc2.39",
3
+ "python": "3.10.0",
4
+ "heartbeatAt": "2024-12-25T00:15:59.115811",
5
+ "startedAt": "2024-12-25T00:15:58.550714",
6
+ "docker": null,
7
+ "cuda": null,
8
+ "args": [
9
+ "--model_family",
10
+ "llama",
11
+ "--apply_instruct_masks",
12
+ "--token_scaled_loss",
13
+ "--seq_parallel_size",
14
+ "8",
15
+ "--report_to",
16
+ "wandb",
17
+ "--do_train",
18
+ "--model_name_or_path",
19
+ "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
20
+ "--config_name",
21
+ "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
22
+ "--tokenizer_name",
23
+ "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
24
+ "--run_name",
25
+ "balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_",
26
+ "--output_dir",
27
+ "/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_",
28
+ "--config_overrides_json",
29
+ "",
30
+ "--gradient_accumulation_steps",
31
+ "2",
32
+ "--per_device_train_batch_size",
33
+ "1",
34
+ "--bf16",
35
+ "--learning_rate",
36
+ "1e-6",
37
+ "--min_lr_ratio",
38
+ "0.1",
39
+ "--lr_scheduler_type",
40
+ "cosine",
41
+ "--max_grad_norm",
42
+ "1.0",
43
+ "--adam_beta1",
44
+ "0.9",
45
+ "--adam_beta2",
46
+ "0.95",
47
+ "--weight_decay",
48
+ "0.1",
49
+ "--warmup_ratio",
50
+ "0.05",
51
+ "--optim",
52
+ "adamw_torch",
53
+ "--logging_steps",
54
+ "1",
55
+ "--log_level",
56
+ "info",
57
+ "--save_steps",
58
+ "200",
59
+ "--dataloader_num_workers",
60
+ "1",
61
+ "--disable_tqdm",
62
+ "true",
63
+ "--use_fast_tokenizer",
64
+ "false",
65
+ "--remove_unused_columns",
66
+ "false",
67
+ "--ddp_find_unused_parameters",
68
+ "false",
69
+ "--fsdp",
70
+ "auto_wrap offload",
71
+ "--gradient_checkpointing",
72
+ "--tokenized_mds_train",
73
+ "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/data/ft/bookclaim_balanced_pack_complete",
74
+ "--cuda_empty_cache",
75
+ "--num_train_epochs",
76
+ "1"
77
+ ],
78
+ "state": "running",
79
+ "program": "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py",
80
+ "codePathLocal": "finetune.py",
81
+ "codePath": "prolong-final/finetune.py",
82
+ "git": {
83
+ "remote": "https://github.com/chtmp223/BookGen-dev.git",
84
+ "commit": "6da087f2362deca9028ab5004e1b057d7fcf3f63"
85
+ },
86
+ "email": "[email protected]",
87
+ "root": "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev",
88
+ "host": "gpu021",
89
+ "username": "ctpham_umass_edu",
90
+ "executable": "/scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final/bin/python3.10",
91
+ "cpu_count": 112,
92
+ "cpu_count_logical": 112,
93
+ "cpu_freq": {
94
+ "current": 916.1786517857144,
95
+ "min": 800.0,
96
+ "max": 3800.0
97
+ },
98
+ "cpu_freq_per_core": [
99
+ {
100
+ "current": 779.024,
101
+ "min": 800.0,
102
+ "max": 3800.0
103
+ },
104
+ {
105
+ "current": 800.0,
106
+ "min": 800.0,
107
+ "max": 3800.0
108
+ },
109
+ {
110
+ "current": 800.0,
111
+ "min": 800.0,
112
+ "max": 3800.0
113
+ },
114
+ {
115
+ "current": 800.0,
116
+ "min": 800.0,
117
+ "max": 3800.0
118
+ },
119
+ {
120
+ "current": 800.0,
121
+ "min": 800.0,
122
+ "max": 3800.0
123
+ },
124
+ {
125
+ "current": 800.0,
126
+ "min": 800.0,
127
+ "max": 3800.0
128
+ },
129
+ {
130
+ "current": 915.357,
131
+ "min": 800.0,
132
+ "max": 3800.0
133
+ },
134
+ {
135
+ "current": 800.0,
136
+ "min": 800.0,
137
+ "max": 3800.0
138
+ },
139
+ {
140
+ "current": 3000.0,
141
+ "min": 800.0,
142
+ "max": 3800.0
143
+ },
144
+ {
145
+ "current": 800.0,
146
+ "min": 800.0,
147
+ "max": 3800.0
148
+ },
149
+ {
150
+ "current": 2182.285,
151
+ "min": 800.0,
152
+ "max": 3800.0
153
+ },
154
+ {
155
+ "current": 800.0,
156
+ "min": 800.0,
157
+ "max": 3800.0
158
+ },
159
+ {
160
+ "current": 2400.0,
161
+ "min": 800.0,
162
+ "max": 3800.0
163
+ },
164
+ {
165
+ "current": 800.0,
166
+ "min": 800.0,
167
+ "max": 3800.0
168
+ },
169
+ {
170
+ "current": 2018.045,
171
+ "min": 800.0,
172
+ "max": 3800.0
173
+ },
174
+ {
175
+ "current": 800.0,
176
+ "min": 800.0,
177
+ "max": 3800.0
178
+ },
179
+ {
180
+ "current": 1743.52,
181
+ "min": 800.0,
182
+ "max": 3800.0
183
+ },
184
+ {
185
+ "current": 785.265,
186
+ "min": 800.0,
187
+ "max": 3800.0
188
+ },
189
+ {
190
+ "current": 1300.0,
191
+ "min": 800.0,
192
+ "max": 3800.0
193
+ },
194
+ {
195
+ "current": 800.0,
196
+ "min": 800.0,
197
+ "max": 3800.0
198
+ },
199
+ {
200
+ "current": 1998.947,
201
+ "min": 800.0,
202
+ "max": 3800.0
203
+ },
204
+ {
205
+ "current": 800.0,
206
+ "min": 800.0,
207
+ "max": 3800.0
208
+ },
209
+ {
210
+ "current": 800.0,
211
+ "min": 800.0,
212
+ "max": 3800.0
213
+ },
214
+ {
215
+ "current": 782.919,
216
+ "min": 800.0,
217
+ "max": 3800.0
218
+ },
219
+ {
220
+ "current": 800.0,
221
+ "min": 800.0,
222
+ "max": 3800.0
223
+ },
224
+ {
225
+ "current": 800.0,
226
+ "min": 800.0,
227
+ "max": 3800.0
228
+ },
229
+ {
230
+ "current": 800.0,
231
+ "min": 800.0,
232
+ "max": 3800.0
233
+ },
234
+ {
235
+ "current": 800.0,
236
+ "min": 800.0,
237
+ "max": 3800.0
238
+ },
239
+ {
240
+ "current": 800.0,
241
+ "min": 800.0,
242
+ "max": 3800.0
243
+ },
244
+ {
245
+ "current": 800.0,
246
+ "min": 800.0,
247
+ "max": 3800.0
248
+ },
249
+ {
250
+ "current": 800.0,
251
+ "min": 800.0,
252
+ "max": 3800.0
253
+ },
254
+ {
255
+ "current": 800.0,
256
+ "min": 800.0,
257
+ "max": 3800.0
258
+ },
259
+ {
260
+ "current": 800.0,
261
+ "min": 800.0,
262
+ "max": 3800.0
263
+ },
264
+ {
265
+ "current": 800.0,
266
+ "min": 800.0,
267
+ "max": 3800.0
268
+ },
269
+ {
270
+ "current": 800.0,
271
+ "min": 800.0,
272
+ "max": 3800.0
273
+ },
274
+ {
275
+ "current": 784.049,
276
+ "min": 800.0,
277
+ "max": 3800.0
278
+ },
279
+ {
280
+ "current": 800.0,
281
+ "min": 800.0,
282
+ "max": 3800.0
283
+ },
284
+ {
285
+ "current": 800.0,
286
+ "min": 800.0,
287
+ "max": 3800.0
288
+ },
289
+ {
290
+ "current": 800.0,
291
+ "min": 800.0,
292
+ "max": 3800.0
293
+ },
294
+ {
295
+ "current": 800.0,
296
+ "min": 800.0,
297
+ "max": 3800.0
298
+ },
299
+ {
300
+ "current": 800.0,
301
+ "min": 800.0,
302
+ "max": 3800.0
303
+ },
304
+ {
305
+ "current": 800.0,
306
+ "min": 800.0,
307
+ "max": 3800.0
308
+ },
309
+ {
310
+ "current": 800.0,
311
+ "min": 800.0,
312
+ "max": 3800.0
313
+ },
314
+ {
315
+ "current": 800.0,
316
+ "min": 800.0,
317
+ "max": 3800.0
318
+ },
319
+ {
320
+ "current": 800.0,
321
+ "min": 800.0,
322
+ "max": 3800.0
323
+ },
324
+ {
325
+ "current": 800.0,
326
+ "min": 800.0,
327
+ "max": 3800.0
328
+ },
329
+ {
330
+ "current": 800.0,
331
+ "min": 800.0,
332
+ "max": 3800.0
333
+ },
334
+ {
335
+ "current": 800.0,
336
+ "min": 800.0,
337
+ "max": 3800.0
338
+ },
339
+ {
340
+ "current": 789.099,
341
+ "min": 800.0,
342
+ "max": 3800.0
343
+ },
344
+ {
345
+ "current": 800.0,
346
+ "min": 800.0,
347
+ "max": 3800.0
348
+ },
349
+ {
350
+ "current": 800.0,
351
+ "min": 800.0,
352
+ "max": 3800.0
353
+ },
354
+ {
355
+ "current": 800.0,
356
+ "min": 800.0,
357
+ "max": 3800.0
358
+ },
359
+ {
360
+ "current": 800.0,
361
+ "min": 800.0,
362
+ "max": 3800.0
363
+ },
364
+ {
365
+ "current": 800.0,
366
+ "min": 800.0,
367
+ "max": 3800.0
368
+ },
369
+ {
370
+ "current": 800.0,
371
+ "min": 800.0,
372
+ "max": 3800.0
373
+ },
374
+ {
375
+ "current": 800.0,
376
+ "min": 800.0,
377
+ "max": 3800.0
378
+ },
379
+ {
380
+ "current": 800.0,
381
+ "min": 800.0,
382
+ "max": 3800.0
383
+ },
384
+ {
385
+ "current": 800.0,
386
+ "min": 800.0,
387
+ "max": 3800.0
388
+ },
389
+ {
390
+ "current": 1700.017,
391
+ "min": 800.0,
392
+ "max": 3800.0
393
+ },
394
+ {
395
+ "current": 800.0,
396
+ "min": 800.0,
397
+ "max": 3800.0
398
+ },
399
+ {
400
+ "current": 800.0,
401
+ "min": 800.0,
402
+ "max": 3800.0
403
+ },
404
+ {
405
+ "current": 800.0,
406
+ "min": 800.0,
407
+ "max": 3800.0
408
+ },
409
+ {
410
+ "current": 2400.0,
411
+ "min": 800.0,
412
+ "max": 3800.0
413
+ },
414
+ {
415
+ "current": 800.0,
416
+ "min": 800.0,
417
+ "max": 3800.0
418
+ },
419
+ {
420
+ "current": 800.0,
421
+ "min": 800.0,
422
+ "max": 3800.0
423
+ },
424
+ {
425
+ "current": 800.0,
426
+ "min": 800.0,
427
+ "max": 3800.0
428
+ },
429
+ {
430
+ "current": 800.0,
431
+ "min": 800.0,
432
+ "max": 3800.0
433
+ },
434
+ {
435
+ "current": 800.0,
436
+ "min": 800.0,
437
+ "max": 3800.0
438
+ },
439
+ {
440
+ "current": 800.0,
441
+ "min": 800.0,
442
+ "max": 3800.0
443
+ },
444
+ {
445
+ "current": 800.0,
446
+ "min": 800.0,
447
+ "max": 3800.0
448
+ },
449
+ {
450
+ "current": 800.0,
451
+ "min": 800.0,
452
+ "max": 3800.0
453
+ },
454
+ {
455
+ "current": 800.0,
456
+ "min": 800.0,
457
+ "max": 3800.0
458
+ },
459
+ {
460
+ "current": 800.0,
461
+ "min": 800.0,
462
+ "max": 3800.0
463
+ },
464
+ {
465
+ "current": 800.0,
466
+ "min": 800.0,
467
+ "max": 3800.0
468
+ },
469
+ {
470
+ "current": 800.0,
471
+ "min": 800.0,
472
+ "max": 3800.0
473
+ },
474
+ {
475
+ "current": 782.252,
476
+ "min": 800.0,
477
+ "max": 3800.0
478
+ },
479
+ {
480
+ "current": 800.0,
481
+ "min": 800.0,
482
+ "max": 3800.0
483
+ },
484
+ {
485
+ "current": 782.368,
486
+ "min": 800.0,
487
+ "max": 3800.0
488
+ },
489
+ {
490
+ "current": 800.0,
491
+ "min": 800.0,
492
+ "max": 3800.0
493
+ },
494
+ {
495
+ "current": 800.0,
496
+ "min": 800.0,
497
+ "max": 3800.0
498
+ },
499
+ {
500
+ "current": 800.0,
501
+ "min": 800.0,
502
+ "max": 3800.0
503
+ },
504
+ {
505
+ "current": 783.608,
506
+ "min": 800.0,
507
+ "max": 3800.0
508
+ },
509
+ {
510
+ "current": 800.0,
511
+ "min": 800.0,
512
+ "max": 3800.0
513
+ },
514
+ {
515
+ "current": 800.0,
516
+ "min": 800.0,
517
+ "max": 3800.0
518
+ },
519
+ {
520
+ "current": 800.0,
521
+ "min": 800.0,
522
+ "max": 3800.0
523
+ },
524
+ {
525
+ "current": 800.0,
526
+ "min": 800.0,
527
+ "max": 3800.0
528
+ },
529
+ {
530
+ "current": 800.0,
531
+ "min": 800.0,
532
+ "max": 3800.0
533
+ },
534
+ {
535
+ "current": 800.0,
536
+ "min": 800.0,
537
+ "max": 3800.0
538
+ },
539
+ {
540
+ "current": 800.0,
541
+ "min": 800.0,
542
+ "max": 3800.0
543
+ },
544
+ {
545
+ "current": 800.0,
546
+ "min": 800.0,
547
+ "max": 3800.0
548
+ },
549
+ {
550
+ "current": 800.0,
551
+ "min": 800.0,
552
+ "max": 3800.0
553
+ },
554
+ {
555
+ "current": 800.0,
556
+ "min": 800.0,
557
+ "max": 3800.0
558
+ },
559
+ {
560
+ "current": 800.0,
561
+ "min": 800.0,
562
+ "max": 3800.0
563
+ },
564
+ {
565
+ "current": 800.0,
566
+ "min": 800.0,
567
+ "max": 3800.0
568
+ },
569
+ {
570
+ "current": 800.0,
571
+ "min": 800.0,
572
+ "max": 3800.0
573
+ },
574
+ {
575
+ "current": 800.0,
576
+ "min": 800.0,
577
+ "max": 3800.0
578
+ },
579
+ {
580
+ "current": 800.0,
581
+ "min": 800.0,
582
+ "max": 3800.0
583
+ },
584
+ {
585
+ "current": 800.0,
586
+ "min": 800.0,
587
+ "max": 3800.0
588
+ },
589
+ {
590
+ "current": 800.0,
591
+ "min": 800.0,
592
+ "max": 3800.0
593
+ },
594
+ {
595
+ "current": 800.0,
596
+ "min": 800.0,
597
+ "max": 3800.0
598
+ },
599
+ {
600
+ "current": 1700.0,
601
+ "min": 800.0,
602
+ "max": 3800.0
603
+ },
604
+ {
605
+ "current": 800.0,
606
+ "min": 800.0,
607
+ "max": 3800.0
608
+ },
609
+ {
610
+ "current": 800.0,
611
+ "min": 800.0,
612
+ "max": 3800.0
613
+ },
614
+ {
615
+ "current": 800.0,
616
+ "min": 800.0,
617
+ "max": 3800.0
618
+ },
619
+ {
620
+ "current": 800.0,
621
+ "min": 800.0,
622
+ "max": 3800.0
623
+ },
624
+ {
625
+ "current": 800.0,
626
+ "min": 800.0,
627
+ "max": 3800.0
628
+ },
629
+ {
630
+ "current": 2400.0,
631
+ "min": 800.0,
632
+ "max": 3800.0
633
+ },
634
+ {
635
+ "current": 800.0,
636
+ "min": 800.0,
637
+ "max": 3800.0
638
+ },
639
+ {
640
+ "current": 800.0,
641
+ "min": 800.0,
642
+ "max": 3800.0
643
+ },
644
+ {
645
+ "current": 800.0,
646
+ "min": 800.0,
647
+ "max": 3800.0
648
+ },
649
+ {
650
+ "current": 800.0,
651
+ "min": 800.0,
652
+ "max": 3800.0
653
+ },
654
+ {
655
+ "current": 800.0,
656
+ "min": 800.0,
657
+ "max": 3800.0
658
+ }
659
+ ],
660
+ "disk": {
661
+ "/": {
662
+ "total": 438.487850189209,
663
+ "used": 16.227672576904297
664
+ }
665
+ },
666
+ "gpu": "NVIDIA A100-SXM4-80GB",
667
+ "gpu_count": 8,
668
+ "gpu_devices": [
669
+ {
670
+ "name": "NVIDIA A100-SXM4-80GB",
671
+ "memory_total": 85899345920
672
+ },
673
+ {
674
+ "name": "NVIDIA A100-SXM4-80GB",
675
+ "memory_total": 85899345920
676
+ },
677
+ {
678
+ "name": "NVIDIA A100-SXM4-80GB",
679
+ "memory_total": 85899345920
680
+ },
681
+ {
682
+ "name": "NVIDIA A100-SXM4-80GB",
683
+ "memory_total": 85899345920
684
+ },
685
+ {
686
+ "name": "NVIDIA A100-SXM4-80GB",
687
+ "memory_total": 85899345920
688
+ },
689
+ {
690
+ "name": "NVIDIA A100-SXM4-80GB",
691
+ "memory_total": 85899345920
692
+ },
693
+ {
694
+ "name": "NVIDIA A100-SXM4-80GB",
695
+ "memory_total": 85899345920
696
+ },
697
+ {
698
+ "name": "NVIDIA A100-SXM4-80GB",
699
+ "memory_total": 85899345920
700
+ }
701
+ ],
702
+ "memory": {
703
+ "total": 2015.3287200927734
704
+ }
705
+ }
wandb/run-20241225_001558-sxxraa4n/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train/loss": 0.5641, "train/grad_norm": 21.8282413482666, "train/learning_rate": 9.249723507271425e-07, "train/epoch": 0.22728505560075943, "train/num_input_tokens_seen": 1757413376, "train/global_step": 838, "_timestamp": 1735112616.697628, "_runtime": 26858.12992310524, "_step": 837}
wandb/run-20241225_001558-sxxraa4n/logs/debug-internal.log ADDED
The diff for this file is too large to render. See raw diff
 
wandb/run-20241225_001558-sxxraa4n/logs/debug.log ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-12-25 00:15:58,558 INFO MainThread:677532 [wandb_setup.py:_flush():76] Current SDK version is 0.17.3
2
+ 2024-12-25 00:15:58,558 INFO MainThread:677532 [wandb_setup.py:_flush():76] Configure stats pid to 677532
3
+ 2024-12-25 00:15:58,558 INFO MainThread:677532 [wandb_setup.py:_flush():76] Loading settings from /home/ctpham_umass_edu/.config/wandb/settings
4
+ 2024-12-25 00:15:58,558 INFO MainThread:677532 [wandb_setup.py:_flush():76] Loading settings from /work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/wandb/settings
5
+ 2024-12-25 00:15:58,558 INFO MainThread:677532 [wandb_setup.py:_flush():76] Loading settings from environment variables: {'root_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'project': 'prolong', 'api_key': '***REDACTED***', 'mode': 'online'}
6
+ 2024-12-25 00:15:58,558 INFO MainThread:677532 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
7
+ 2024-12-25 00:15:58,559 INFO MainThread:677532 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'prolong-final/finetune.py', 'program_abspath': '/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py', 'program': '/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py'}
8
+ 2024-12-25 00:15:58,559 INFO MainThread:677532 [wandb_setup.py:_flush():76] Applying login settings: {}
9
+ 2024-12-25 00:15:58,559 INFO MainThread:677532 [wandb_init.py:_log_setup():520] Logging user logs to /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/wandb/run-20241225_001558-sxxraa4n/logs/debug.log
10
+ 2024-12-25 00:15:58,559 INFO MainThread:677532 [wandb_init.py:_log_setup():521] Logging internal logs to /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/wandb/run-20241225_001558-sxxraa4n/logs/debug-internal.log
11
+ 2024-12-25 00:15:58,559 INFO MainThread:677532 [wandb_init.py:init():560] calling init triggers
12
+ 2024-12-25 00:15:58,559 INFO MainThread:677532 [wandb_init.py:init():567] wandb.init called with sweep_config: {}
13
+ config: {}
14
+ 2024-12-25 00:15:58,559 INFO MainThread:677532 [wandb_init.py:init():610] starting backend
15
+ 2024-12-25 00:15:58,559 INFO MainThread:677532 [wandb_init.py:init():614] setting up manager
16
+ 2024-12-25 00:15:58,562 INFO MainThread:677532 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
17
+ 2024-12-25 00:15:58,565 INFO MainThread:677532 [wandb_init.py:init():622] backend started and connected
18
+ 2024-12-25 00:15:58,571 INFO MainThread:677532 [wandb_init.py:init():711] updated telemetry
19
+ 2024-12-25 00:15:58,639 INFO MainThread:677532 [wandb_init.py:init():744] communicating run to backend with 90.0 second timeout
20
+ 2024-12-25 00:15:58,891 INFO MainThread:677532 [wandb_run.py:_on_init():2402] communicating current version
21
+ 2024-12-25 00:15:58,954 INFO MainThread:677532 [wandb_run.py:_on_init():2411] got version response upgrade_message: "wandb version 0.19.1 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
22
+
23
+ 2024-12-25 00:15:58,954 INFO MainThread:677532 [wandb_init.py:init():795] starting run threads in backend
24
+ 2024-12-25 00:16:07,232 INFO MainThread:677532 [wandb_run.py:_console_start():2380] atexit reg
25
+ 2024-12-25 00:16:07,233 INFO MainThread:677532 [wandb_run.py:_redirect():2235] redirect: wrap_raw
26
+ 2024-12-25 00:16:07,233 INFO MainThread:677532 [wandb_run.py:_redirect():2300] Wrapping output streams.
27
+ 2024-12-25 00:16:07,233 INFO MainThread:677532 [wandb_run.py:_redirect():2325] Redirects installed.
28
+ 2024-12-25 00:16:07,236 INFO MainThread:677532 [wandb_init.py:init():838] run started, returning control to user process
29
+ 2024-12-25 00:16:07,238 INFO MainThread:677532 [wandb_run.py:_config_callback():1382] config_cb None None {'vocab_size': 128256, 'max_position_embeddings': 524288, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'pretraining_tp': 1, 'use_cache': True, 'rope_theta': 128000000.0, 'rope_scaling': None, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['LlamaForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 128000, 'pad_token_id': 0, 'eos_token_id': 128009, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': '/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/', 'transformers_version': '4.44.2', 'model_type': 'llama', 'output_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'overwrite_output_dir': False, 'do_train': True, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 1e-06, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.95, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.05, 'warmup_steps': 0, 'log_level': 'info', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/runs/Dec25_00-13-47_gpu021', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1.0, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 200, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 1, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'disable_tqdm': True, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': ['auto_wrap', 'offload'], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': False, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'eval_use_gather_object': False, 'min_lr_ratio': 0.1, 'cuda_empty_cache': True, 'streaming_dataset': True, 'seq_parallel_size': 8}
30
+ 2024-12-25 00:16:07,240 INFO MainThread:677532 [wandb_config.py:__setitem__():151] config set model/num_parameters = 1003782656 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7882a024de40>>
31
+ 2024-12-25 00:16:07,240 INFO MainThread:677532 [wandb_run.py:_config_callback():1382] config_cb model/num_parameters 1003782656 None
wandb/run-20241225_001558-sxxraa4n/run-sxxraa4n.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b91b6f51d0a2d417083666b9c5a963db2a195e76381710e6b850746eb7235072
3
+ size 5051393
wandb/run-20241225_152744-sac86tlv/files/conda-environment.yaml ADDED
@@ -0,0 +1,232 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ name: /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final
2
+ channels:
3
+ - conda-forge
4
+ dependencies:
5
+ - _libgcc_mutex=0.1=conda_forge
6
+ - _openmp_mutex=4.5=2_gnu
7
+ - bzip2=1.0.8=h4bc722e_7
8
+ - ca-certificates=2024.12.14=hbcca054_0
9
+ - ld_impl_linux-64=2.43=h712a8e2_2
10
+ - libffi=3.4.2=h7f98852_5
11
+ - libgcc=14.2.0=h77fa898_1
12
+ - libgcc-ng=14.2.0=h69a702a_1
13
+ - libgomp=14.2.0=h77fa898_1
14
+ - liblzma=5.6.3=hb9d3cd8_1
15
+ - liblzma-devel=5.6.3=hb9d3cd8_1
16
+ - libnsl=2.0.1=hd590300_0
17
+ - libsqlite=3.47.2=hee588c1_0
18
+ - libuuid=2.38.1=h0b41bf4_0
19
+ - libzlib=1.3.1=hb9d3cd8_2
20
+ - ncurses=6.5=he02047a_1
21
+ - openssl=3.4.0=hb9d3cd8_0
22
+ - pip=24.3.1=pyh8b19718_2
23
+ - python=3.10.0=h543edf9_3_cpython
24
+ - readline=8.2=h8228510_1
25
+ - setuptools=75.6.0=pyhff2d567_1
26
+ - sqlite=3.47.2=h9eae976_0
27
+ - tk=8.6.13=noxft_h4845f30_101
28
+ - wheel=0.45.1=pyhd8ed1ab_1
29
+ - xz=5.6.3=hbcc6ac9_1
30
+ - xz-gpl-tools=5.6.3=hbcc6ac9_1
31
+ - xz-tools=5.6.3=hb9d3cd8_1
32
+ - pip:
33
+ - accelerate==0.32.1
34
+ - aiohappyeyeballs==2.4.3
35
+ - aiohttp==3.11.2
36
+ - aioprometheus==23.12.0
37
+ - aiosignal==1.3.1
38
+ - annotated-types==0.7.0
39
+ - anthropic==0.39.0
40
+ - anyio==4.6.2.post1
41
+ - argcomplete==3.5.1
42
+ - arrow==1.3.0
43
+ - async-timeout==5.0.1
44
+ - attrs==24.2.0
45
+ - azure-core==1.32.0
46
+ - azure-identity==1.19.0
47
+ - azure-storage-blob==12.24.0
48
+ - azure-storage-file-datalake==12.18.0
49
+ - backoff==2.2.1
50
+ - bcrypt==4.2.0
51
+ - blobfile==3.0.0
52
+ - boto3==1.35.63
53
+ - botocore==1.35.63
54
+ - brotli==1.1.0
55
+ - cachetools==5.5.0
56
+ - certifi==2024.8.30
57
+ - cffi==1.17.1
58
+ - charset-normalizer==3.4.0
59
+ - circuitbreaker==2.0.0
60
+ - click==8.1.7
61
+ - cloudpickle==3.1.0
62
+ - compressed-tensors==0.8.0
63
+ - contourpy==1.3.1
64
+ - cramjam==2.9.0
65
+ - cryptography==43.0.3
66
+ - cycler==0.12.1
67
+ - datasets==2.20.0
68
+ - debugpy==1.8.11
69
+ - dill==0.3.8
70
+ - diskcache==5.6.3
71
+ - distro==1.9.0
72
+ - docker-pycreds==0.4.0
73
+ - docstring-parser==0.16
74
+ - einops==0.8.0
75
+ - fastapi==0.115.5
76
+ - filelock==3.16.1
77
+ - flash-attn==2.6.1
78
+ - fonttools==4.55.0
79
+ - frozenlist==1.5.0
80
+ - fsspec==2024.5.0
81
+ - gguf==0.10.0
82
+ - gitdb==4.0.11
83
+ - gitpython==3.1.43
84
+ - google-api-core==2.23.0
85
+ - google-auth==2.36.0
86
+ - google-cloud-aiplatform==1.71.1
87
+ - google-cloud-bigquery==3.27.0
88
+ - google-cloud-core==2.4.1
89
+ - google-cloud-resource-manager==1.13.1
90
+ - google-cloud-storage==2.10.0
91
+ - google-crc32c==1.6.0
92
+ - google-resumable-media==2.7.2
93
+ - googleapis-common-protos==1.66.0
94
+ - gql==3.5.0
95
+ - graphql-core==3.2.5
96
+ - grpc-google-iam-v1==0.13.1
97
+ - grpcio==1.68.0
98
+ - grpcio-status==1.62.3
99
+ - h11==0.14.0
100
+ - httpcore==1.0.7
101
+ - httptools==0.6.4
102
+ - httpx==0.27.2
103
+ - huggingface-hub==0.26.2
104
+ - idna==3.10
105
+ - importlib-metadata==8.5.0
106
+ - interegular==0.3.3
107
+ - ipython==8.18.0
108
+ - isodate==0.7.2
109
+ - jedi==0.19.2
110
+ - jinja2==3.1.4
111
+ - jiter==0.7.1
112
+ - jmespath==1.0.1
113
+ - jsonschema==4.23.0
114
+ - jsonschema-specifications==2024.10.1
115
+ - kiwisolver==1.4.7
116
+ - lark==1.2.2
117
+ - llvmlite==0.43.0
118
+ - lm-format-enforcer==0.10.9
119
+ - lxml==5.3.0
120
+ - markdown-it-py==3.0.0
121
+ - markupsafe==3.0.2
122
+ - matplotlib==3.9.2
123
+ - mdurl==0.1.2
124
+ - mosaicml-cli==0.5.34
125
+ - mosaicml-streaming==0.8.1
126
+ - mpmath==1.3.0
127
+ - msal==1.31.1
128
+ - msal-extensions==1.2.0
129
+ - msgpack==1.1.0
130
+ - msgspec==0.18.6
131
+ - multidict==6.1.0
132
+ - multiprocess==0.70.16
133
+ - networkx==3.4.2
134
+ - ninja==1.11.1.1
135
+ - numba==0.60.0
136
+ - numpy==1.26.3
137
+ - nvidia-cublas-cu12==12.1.3.1
138
+ - nvidia-cuda-cupti-cu12==12.1.105
139
+ - nvidia-cuda-nvrtc-cu12==12.1.105
140
+ - nvidia-cuda-runtime-cu12==12.1.105
141
+ - nvidia-cudnn-cu12==9.1.0.70
142
+ - nvidia-cufft-cu12==11.0.2.54
143
+ - nvidia-curand-cu12==10.3.2.106
144
+ - nvidia-cusolver-cu12==11.4.5.107
145
+ - nvidia-cusparse-cu12==12.1.0.106
146
+ - nvidia-ml-py==12.560.30
147
+ - nvidia-nccl-cu12==2.20.5
148
+ - nvidia-nvjitlink-cu12==12.4.127
149
+ - nvidia-nvtx-cu12==12.1.105
150
+ - oci==2.138.1
151
+ - openai==1.54.5
152
+ - opencv-python-headless==4.10.0.84
153
+ - orjson==3.10.11
154
+ - outlines==0.0.46
155
+ - packaging==24.1
156
+ - pandas==2.2.1
157
+ - paramiko==3.5.0
158
+ - partial-json-parser==0.2.1.1.post4
159
+ - pillow==10.4.0
160
+ - portalocker==2.10.1
161
+ - prometheus-client==0.21.0
162
+ - prometheus-fastapi-instrumentator==7.0.0
163
+ - prompt-toolkit==3.0.36
164
+ - propcache==0.2.0
165
+ - proto-plus==1.25.0
166
+ - protobuf==4.25.3
167
+ - py-cpuinfo==9.0.0
168
+ - pyairports==2.1.1
169
+ - pyarrow==18.0.0
170
+ - pyarrow-hotfix==0.6
171
+ - pyasn1==0.6.1
172
+ - pyasn1-modules==0.4.1
173
+ - pycountry==24.6.1
174
+ - pycparser==2.22
175
+ - pycryptodomex==3.21.0
176
+ - pydantic==2.9.2
177
+ - pydantic-core==2.23.4
178
+ - pyjwt==2.10.0
179
+ - pynacl==1.5.0
180
+ - pyopenssl==24.2.1
181
+ - pyparsing==3.2.0
182
+ - python-dateutil==2.9.0
183
+ - python-dotenv==1.0.1
184
+ - python-snappy==0.7.3
185
+ - pytz==2024.2
186
+ - pyyaml==6.0.2
187
+ - quantile-python==1.1
188
+ - questionary==2.0.1
189
+ - ray==2.39.0
190
+ - referencing==0.35.1
191
+ - regex==2023.12.25
192
+ - requests==2.32.3
193
+ - rich==13.9.4
194
+ - rotary-emb==0.5.2
195
+ - rpds-py==0.21.0
196
+ - rsa==4.9
197
+ - ruamel-yaml==0.18.6
198
+ - ruamel-yaml-clib==0.2.12
199
+ - s3transfer==0.10.3
200
+ - safetensors==0.4.5
201
+ - sentencepiece==0.1.99
202
+ - sentry-sdk==2.18.0
203
+ - setproctitle==1.3.4
204
+ - shapely==2.0.6
205
+ - smmap==5.0.1
206
+ - sniffio==1.3.1
207
+ - starlette==0.41.3
208
+ - sympy==1.13.1
209
+ - tiktoken==0.7.0
210
+ - tokenizers==0.19.1
211
+ - torch==2.4.1
212
+ - torchvision==0.19.1
213
+ - tqdm==4.66.4
214
+ - transformers==4.44.2
215
+ - triton==3.0.0
216
+ - types-python-dateutil==2.9.0.20241003
217
+ - tzdata==2024.2
218
+ - urllib3==2.2.3
219
+ - uvicorn==0.32.0
220
+ - uvloop==0.21.0
221
+ - validators==0.34.0
222
+ - vertexai==1.71.1
223
+ - wandb==0.17.3
224
+ - watchfiles==0.24.0
225
+ - websockets==11.0.3
226
+ - xformers==0.0.28.post1
227
+ - xxhash==3.5.0
228
+ - yarl==1.17.2
229
+ - zipp==3.21.0
230
+ - zstandard==0.22.0
231
+ - zstd==1.5.5.1
232
+ prefix: /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final
wandb/run-20241225_152744-sac86tlv/files/config.yaml ADDED
@@ -0,0 +1,705 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wandb_version: 1
2
+
3
+ _wandb:
4
+ desc: null
5
+ value:
6
+ python_version: 3.10.0
7
+ cli_version: 0.17.3
8
+ framework: huggingface
9
+ huggingface_version: 4.44.2
10
+ is_jupyter_run: false
11
+ is_kaggle_kernel: false
12
+ start_time: 1735140464
13
+ t:
14
+ 1:
15
+ - 1
16
+ - 11
17
+ - 41
18
+ - 49
19
+ - 51
20
+ - 55
21
+ - 71
22
+ - 105
23
+ 2:
24
+ - 1
25
+ - 11
26
+ - 41
27
+ - 49
28
+ - 51
29
+ - 55
30
+ - 71
31
+ - 105
32
+ 3:
33
+ - 7
34
+ - 13
35
+ - 19
36
+ - 23
37
+ - 66
38
+ 4: 3.10.0
39
+ 5: 0.17.3
40
+ 6: 4.44.2
41
+ 8:
42
+ - 5
43
+ 9:
44
+ 1: transformers_trainer
45
+ 13: linux-x86_64
46
+ m:
47
+ - 1: train/global_step
48
+ 6:
49
+ - 3
50
+ - 1: train/loss
51
+ 5: 1
52
+ 6:
53
+ - 1
54
+ - 1: train/grad_norm
55
+ 5: 1
56
+ 6:
57
+ - 1
58
+ - 1: train/learning_rate
59
+ 5: 1
60
+ 6:
61
+ - 1
62
+ - 1: train/epoch
63
+ 5: 1
64
+ 6:
65
+ - 1
66
+ - 1: train/num_input_tokens_seen
67
+ 5: 1
68
+ 6:
69
+ - 1
70
+ vocab_size:
71
+ desc: null
72
+ value: 128256
73
+ max_position_embeddings:
74
+ desc: null
75
+ value: 524288
76
+ hidden_size:
77
+ desc: null
78
+ value: 4096
79
+ intermediate_size:
80
+ desc: null
81
+ value: 14336
82
+ num_hidden_layers:
83
+ desc: null
84
+ value: 32
85
+ num_attention_heads:
86
+ desc: null
87
+ value: 32
88
+ num_key_value_heads:
89
+ desc: null
90
+ value: 8
91
+ hidden_act:
92
+ desc: null
93
+ value: silu
94
+ initializer_range:
95
+ desc: null
96
+ value: 0.02
97
+ rms_norm_eps:
98
+ desc: null
99
+ value: 1.0e-05
100
+ pretraining_tp:
101
+ desc: null
102
+ value: 1
103
+ use_cache:
104
+ desc: null
105
+ value: true
106
+ rope_theta:
107
+ desc: null
108
+ value: 128000000.0
109
+ rope_scaling:
110
+ desc: null
111
+ value: null
112
+ attention_bias:
113
+ desc: null
114
+ value: false
115
+ attention_dropout:
116
+ desc: null
117
+ value: 0.0
118
+ mlp_bias:
119
+ desc: null
120
+ value: false
121
+ return_dict:
122
+ desc: null
123
+ value: true
124
+ output_hidden_states:
125
+ desc: null
126
+ value: false
127
+ output_attentions:
128
+ desc: null
129
+ value: false
130
+ torchscript:
131
+ desc: null
132
+ value: false
133
+ torch_dtype:
134
+ desc: null
135
+ value: float32
136
+ use_bfloat16:
137
+ desc: null
138
+ value: false
139
+ tf_legacy_loss:
140
+ desc: null
141
+ value: false
142
+ pruned_heads:
143
+ desc: null
144
+ value: {}
145
+ tie_word_embeddings:
146
+ desc: null
147
+ value: false
148
+ chunk_size_feed_forward:
149
+ desc: null
150
+ value: 0
151
+ is_encoder_decoder:
152
+ desc: null
153
+ value: false
154
+ is_decoder:
155
+ desc: null
156
+ value: false
157
+ cross_attention_hidden_size:
158
+ desc: null
159
+ value: null
160
+ add_cross_attention:
161
+ desc: null
162
+ value: false
163
+ tie_encoder_decoder:
164
+ desc: null
165
+ value: false
166
+ max_length:
167
+ desc: null
168
+ value: 20
169
+ min_length:
170
+ desc: null
171
+ value: 0
172
+ do_sample:
173
+ desc: null
174
+ value: false
175
+ early_stopping:
176
+ desc: null
177
+ value: false
178
+ num_beams:
179
+ desc: null
180
+ value: 1
181
+ num_beam_groups:
182
+ desc: null
183
+ value: 1
184
+ diversity_penalty:
185
+ desc: null
186
+ value: 0.0
187
+ temperature:
188
+ desc: null
189
+ value: 1.0
190
+ top_k:
191
+ desc: null
192
+ value: 50
193
+ top_p:
194
+ desc: null
195
+ value: 1.0
196
+ typical_p:
197
+ desc: null
198
+ value: 1.0
199
+ repetition_penalty:
200
+ desc: null
201
+ value: 1.0
202
+ length_penalty:
203
+ desc: null
204
+ value: 1.0
205
+ no_repeat_ngram_size:
206
+ desc: null
207
+ value: 0
208
+ encoder_no_repeat_ngram_size:
209
+ desc: null
210
+ value: 0
211
+ bad_words_ids:
212
+ desc: null
213
+ value: null
214
+ num_return_sequences:
215
+ desc: null
216
+ value: 1
217
+ output_scores:
218
+ desc: null
219
+ value: false
220
+ return_dict_in_generate:
221
+ desc: null
222
+ value: false
223
+ forced_bos_token_id:
224
+ desc: null
225
+ value: null
226
+ forced_eos_token_id:
227
+ desc: null
228
+ value: null
229
+ remove_invalid_values:
230
+ desc: null
231
+ value: false
232
+ exponential_decay_length_penalty:
233
+ desc: null
234
+ value: null
235
+ suppress_tokens:
236
+ desc: null
237
+ value: null
238
+ begin_suppress_tokens:
239
+ desc: null
240
+ value: null
241
+ architectures:
242
+ desc: null
243
+ value:
244
+ - LlamaForCausalLM
245
+ finetuning_task:
246
+ desc: null
247
+ value: null
248
+ id2label:
249
+ desc: null
250
+ value:
251
+ '0': LABEL_0
252
+ '1': LABEL_1
253
+ label2id:
254
+ desc: null
255
+ value:
256
+ LABEL_0: 0
257
+ LABEL_1: 1
258
+ tokenizer_class:
259
+ desc: null
260
+ value: null
261
+ prefix:
262
+ desc: null
263
+ value: null
264
+ bos_token_id:
265
+ desc: null
266
+ value: 128000
267
+ pad_token_id:
268
+ desc: null
269
+ value: 0
270
+ eos_token_id:
271
+ desc: null
272
+ value: 128009
273
+ sep_token_id:
274
+ desc: null
275
+ value: null
276
+ decoder_start_token_id:
277
+ desc: null
278
+ value: null
279
+ task_specific_params:
280
+ desc: null
281
+ value: null
282
+ problem_type:
283
+ desc: null
284
+ value: null
285
+ _name_or_path:
286
+ desc: null
287
+ value: /scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/
288
+ transformers_version:
289
+ desc: null
290
+ value: 4.44.2
291
+ model_type:
292
+ desc: null
293
+ value: llama
294
+ output_dir:
295
+ desc: null
296
+ value: /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_
297
+ overwrite_output_dir:
298
+ desc: null
299
+ value: false
300
+ do_train:
301
+ desc: null
302
+ value: true
303
+ do_eval:
304
+ desc: null
305
+ value: false
306
+ do_predict:
307
+ desc: null
308
+ value: false
309
+ eval_strategy:
310
+ desc: null
311
+ value: 'no'
312
+ prediction_loss_only:
313
+ desc: null
314
+ value: false
315
+ per_device_train_batch_size:
316
+ desc: null
317
+ value: 1
318
+ per_device_eval_batch_size:
319
+ desc: null
320
+ value: 8
321
+ per_gpu_train_batch_size:
322
+ desc: null
323
+ value: null
324
+ per_gpu_eval_batch_size:
325
+ desc: null
326
+ value: null
327
+ gradient_accumulation_steps:
328
+ desc: null
329
+ value: 2
330
+ eval_accumulation_steps:
331
+ desc: null
332
+ value: null
333
+ eval_delay:
334
+ desc: null
335
+ value: 0
336
+ torch_empty_cache_steps:
337
+ desc: null
338
+ value: null
339
+ learning_rate:
340
+ desc: null
341
+ value: 1.0e-06
342
+ weight_decay:
343
+ desc: null
344
+ value: 0.1
345
+ adam_beta1:
346
+ desc: null
347
+ value: 0.9
348
+ adam_beta2:
349
+ desc: null
350
+ value: 0.95
351
+ adam_epsilon:
352
+ desc: null
353
+ value: 1.0e-08
354
+ max_grad_norm:
355
+ desc: null
356
+ value: 1.0
357
+ num_train_epochs:
358
+ desc: null
359
+ value: 1.0
360
+ max_steps:
361
+ desc: null
362
+ value: -1
363
+ lr_scheduler_type:
364
+ desc: null
365
+ value: cosine
366
+ lr_scheduler_kwargs:
367
+ desc: null
368
+ value: {}
369
+ warmup_ratio:
370
+ desc: null
371
+ value: 0.05
372
+ warmup_steps:
373
+ desc: null
374
+ value: 0
375
+ log_level:
376
+ desc: null
377
+ value: info
378
+ log_level_replica:
379
+ desc: null
380
+ value: warning
381
+ log_on_each_node:
382
+ desc: null
383
+ value: true
384
+ logging_dir:
385
+ desc: null
386
+ value: /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/runs/Dec25_15-21-22_gpu020
387
+ logging_strategy:
388
+ desc: null
389
+ value: steps
390
+ logging_first_step:
391
+ desc: null
392
+ value: false
393
+ logging_steps:
394
+ desc: null
395
+ value: 1.0
396
+ logging_nan_inf_filter:
397
+ desc: null
398
+ value: true
399
+ save_strategy:
400
+ desc: null
401
+ value: steps
402
+ save_steps:
403
+ desc: null
404
+ value: 200
405
+ save_total_limit:
406
+ desc: null
407
+ value: null
408
+ save_safetensors:
409
+ desc: null
410
+ value: true
411
+ save_on_each_node:
412
+ desc: null
413
+ value: false
414
+ save_only_model:
415
+ desc: null
416
+ value: false
417
+ restore_callback_states_from_checkpoint:
418
+ desc: null
419
+ value: false
420
+ no_cuda:
421
+ desc: null
422
+ value: false
423
+ use_cpu:
424
+ desc: null
425
+ value: false
426
+ use_mps_device:
427
+ desc: null
428
+ value: false
429
+ seed:
430
+ desc: null
431
+ value: 42
432
+ data_seed:
433
+ desc: null
434
+ value: null
435
+ jit_mode_eval:
436
+ desc: null
437
+ value: false
438
+ use_ipex:
439
+ desc: null
440
+ value: false
441
+ bf16:
442
+ desc: null
443
+ value: true
444
+ fp16:
445
+ desc: null
446
+ value: false
447
+ fp16_opt_level:
448
+ desc: null
449
+ value: O1
450
+ half_precision_backend:
451
+ desc: null
452
+ value: auto
453
+ bf16_full_eval:
454
+ desc: null
455
+ value: false
456
+ fp16_full_eval:
457
+ desc: null
458
+ value: false
459
+ tf32:
460
+ desc: null
461
+ value: null
462
+ local_rank:
463
+ desc: null
464
+ value: 0
465
+ ddp_backend:
466
+ desc: null
467
+ value: null
468
+ tpu_num_cores:
469
+ desc: null
470
+ value: null
471
+ tpu_metrics_debug:
472
+ desc: null
473
+ value: false
474
+ debug:
475
+ desc: null
476
+ value: []
477
+ dataloader_drop_last:
478
+ desc: null
479
+ value: false
480
+ eval_steps:
481
+ desc: null
482
+ value: null
483
+ dataloader_num_workers:
484
+ desc: null
485
+ value: 1
486
+ dataloader_prefetch_factor:
487
+ desc: null
488
+ value: null
489
+ past_index:
490
+ desc: null
491
+ value: -1
492
+ run_name:
493
+ desc: null
494
+ value: balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_
495
+ disable_tqdm:
496
+ desc: null
497
+ value: true
498
+ remove_unused_columns:
499
+ desc: null
500
+ value: false
501
+ label_names:
502
+ desc: null
503
+ value: null
504
+ load_best_model_at_end:
505
+ desc: null
506
+ value: false
507
+ metric_for_best_model:
508
+ desc: null
509
+ value: null
510
+ greater_is_better:
511
+ desc: null
512
+ value: null
513
+ ignore_data_skip:
514
+ desc: null
515
+ value: true
516
+ fsdp:
517
+ desc: null
518
+ value:
519
+ - auto_wrap
520
+ - offload
521
+ fsdp_min_num_params:
522
+ desc: null
523
+ value: 0
524
+ fsdp_config:
525
+ desc: null
526
+ value:
527
+ min_num_params: 0
528
+ xla: false
529
+ xla_fsdp_v2: false
530
+ xla_fsdp_grad_ckpt: false
531
+ fsdp_transformer_layer_cls_to_wrap:
532
+ desc: null
533
+ value: null
534
+ accelerator_config:
535
+ desc: null
536
+ value:
537
+ split_batches: false
538
+ dispatch_batches: null
539
+ even_batches: true
540
+ use_seedable_sampler: true
541
+ non_blocking: false
542
+ gradient_accumulation_kwargs: null
543
+ deepspeed:
544
+ desc: null
545
+ value: null
546
+ label_smoothing_factor:
547
+ desc: null
548
+ value: 0.0
549
+ optim:
550
+ desc: null
551
+ value: adamw_torch
552
+ optim_args:
553
+ desc: null
554
+ value: null
555
+ adafactor:
556
+ desc: null
557
+ value: false
558
+ group_by_length:
559
+ desc: null
560
+ value: false
561
+ length_column_name:
562
+ desc: null
563
+ value: length
564
+ report_to:
565
+ desc: null
566
+ value:
567
+ - wandb
568
+ ddp_find_unused_parameters:
569
+ desc: null
570
+ value: false
571
+ ddp_bucket_cap_mb:
572
+ desc: null
573
+ value: null
574
+ ddp_broadcast_buffers:
575
+ desc: null
576
+ value: null
577
+ dataloader_pin_memory:
578
+ desc: null
579
+ value: true
580
+ dataloader_persistent_workers:
581
+ desc: null
582
+ value: false
583
+ skip_memory_metrics:
584
+ desc: null
585
+ value: true
586
+ use_legacy_prediction_loop:
587
+ desc: null
588
+ value: false
589
+ push_to_hub:
590
+ desc: null
591
+ value: false
592
+ resume_from_checkpoint:
593
+ desc: null
594
+ value: null
595
+ hub_model_id:
596
+ desc: null
597
+ value: null
598
+ hub_strategy:
599
+ desc: null
600
+ value: every_save
601
+ hub_token:
602
+ desc: null
603
+ value: <HUB_TOKEN>
604
+ hub_private_repo:
605
+ desc: null
606
+ value: false
607
+ hub_always_push:
608
+ desc: null
609
+ value: false
610
+ gradient_checkpointing:
611
+ desc: null
612
+ value: true
613
+ gradient_checkpointing_kwargs:
614
+ desc: null
615
+ value: null
616
+ include_inputs_for_metrics:
617
+ desc: null
618
+ value: false
619
+ eval_do_concat_batches:
620
+ desc: null
621
+ value: true
622
+ fp16_backend:
623
+ desc: null
624
+ value: auto
625
+ evaluation_strategy:
626
+ desc: null
627
+ value: null
628
+ push_to_hub_model_id:
629
+ desc: null
630
+ value: null
631
+ push_to_hub_organization:
632
+ desc: null
633
+ value: null
634
+ push_to_hub_token:
635
+ desc: null
636
+ value: <PUSH_TO_HUB_TOKEN>
637
+ mp_parameters:
638
+ desc: null
639
+ value: ''
640
+ auto_find_batch_size:
641
+ desc: null
642
+ value: false
643
+ full_determinism:
644
+ desc: null
645
+ value: false
646
+ torchdynamo:
647
+ desc: null
648
+ value: null
649
+ ray_scope:
650
+ desc: null
651
+ value: last
652
+ ddp_timeout:
653
+ desc: null
654
+ value: 1800
655
+ torch_compile:
656
+ desc: null
657
+ value: false
658
+ torch_compile_backend:
659
+ desc: null
660
+ value: null
661
+ torch_compile_mode:
662
+ desc: null
663
+ value: null
664
+ dispatch_batches:
665
+ desc: null
666
+ value: null
667
+ split_batches:
668
+ desc: null
669
+ value: null
670
+ include_tokens_per_second:
671
+ desc: null
672
+ value: false
673
+ include_num_input_tokens_seen:
674
+ desc: null
675
+ value: false
676
+ neftune_noise_alpha:
677
+ desc: null
678
+ value: null
679
+ optim_target_modules:
680
+ desc: null
681
+ value: null
682
+ batch_eval_metrics:
683
+ desc: null
684
+ value: false
685
+ eval_on_start:
686
+ desc: null
687
+ value: false
688
+ eval_use_gather_object:
689
+ desc: null
690
+ value: false
691
+ min_lr_ratio:
692
+ desc: null
693
+ value: 0.1
694
+ cuda_empty_cache:
695
+ desc: null
696
+ value: true
697
+ streaming_dataset:
698
+ desc: null
699
+ value: true
700
+ seq_parallel_size:
701
+ desc: null
702
+ value: 8
703
+ model/num_parameters:
704
+ desc: null
705
+ value: 1003782656
wandb/run-20241225_152744-sac86tlv/files/output.log ADDED
The diff for this file is too large to render. See raw diff
 
wandb/run-20241225_152744-sac86tlv/files/requirements.txt ADDED
@@ -0,0 +1,242 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Brotli==1.1.0
2
+ GitPython==3.1.43
3
+ Jinja2==3.1.4
4
+ MarkupSafe==3.0.2
5
+ PyJWT==2.10.0
6
+ PyNaCl==1.5.0
7
+ PyYAML==6.0.2
8
+ Pygments==2.18.0
9
+ accelerate==0.32.1
10
+ aiohappyeyeballs==2.4.3
11
+ aiohttp==3.11.2
12
+ aioprometheus==23.12.0
13
+ aiosignal==1.3.1
14
+ annotated-types==0.7.0
15
+ anthropic==0.39.0
16
+ anyio==4.6.2.post1
17
+ argcomplete==3.5.1
18
+ arrow==1.3.0
19
+ asttokens==2.4.1
20
+ async-timeout==5.0.1
21
+ attrs==24.2.0
22
+ autocommand==2.2.2
23
+ azure-core==1.32.0
24
+ azure-identity==1.19.0
25
+ azure-storage-blob==12.24.0
26
+ azure-storage-file-datalake==12.18.0
27
+ backoff==2.2.1
28
+ backports.tarfile==1.2.0
29
+ bcrypt==4.2.0
30
+ blobfile==3.0.0
31
+ boto3==1.35.63
32
+ botocore==1.35.63
33
+ cachetools==5.5.0
34
+ certifi==2024.8.30
35
+ cffi==1.17.1
36
+ charset-normalizer==3.4.0
37
+ circuitbreaker==2.0.0
38
+ click==8.1.7
39
+ cloudpickle==3.1.0
40
+ comm==0.2.2
41
+ compressed-tensors==0.8.0
42
+ contourpy==1.3.1
43
+ cramjam==2.9.0
44
+ cryptography==43.0.3
45
+ cycler==0.12.1
46
+ datasets==2.20.0
47
+ debugpy==1.8.11
48
+ decorator==5.1.1
49
+ dill==0.3.8
50
+ diskcache==5.6.3
51
+ distro==1.9.0
52
+ docker-pycreds==0.4.0
53
+ docstring_parser==0.16
54
+ einops==0.8.0
55
+ exceptiongroup==1.2.2
56
+ executing==2.1.0
57
+ fastapi==0.115.5
58
+ filelock==3.16.1
59
+ flash-attn==2.6.1
60
+ fonttools==4.55.0
61
+ frozenlist==1.5.0
62
+ fsspec==2024.5.0
63
+ gguf==0.10.0
64
+ gitdb==4.0.11
65
+ google-api-core==2.23.0
66
+ google-auth==2.36.0
67
+ google-cloud-aiplatform==1.71.1
68
+ google-cloud-bigquery==3.27.0
69
+ google-cloud-core==2.4.1
70
+ google-cloud-resource-manager==1.13.1
71
+ google-cloud-storage==2.10.0
72
+ google-crc32c==1.6.0
73
+ google-resumable-media==2.7.2
74
+ googleapis-common-protos==1.66.0
75
+ gql==3.5.0
76
+ graphql-core==3.2.5
77
+ grpc-google-iam-v1==0.13.1
78
+ grpcio-status==1.62.3
79
+ grpcio==1.68.0
80
+ h11==0.14.0
81
+ httpcore==1.0.7
82
+ httptools==0.6.4
83
+ httpx==0.27.2
84
+ huggingface-hub==0.26.2
85
+ idna==3.10
86
+ importlib_metadata==8.0.0
87
+ importlib_metadata==8.5.0
88
+ inflect==7.3.1
89
+ interegular==0.3.3
90
+ ipykernel==6.29.5
91
+ ipython==8.18.0
92
+ isodate==0.7.2
93
+ jaraco.collections==5.1.0
94
+ jaraco.context==5.3.0
95
+ jaraco.functools==4.0.1
96
+ jaraco.text==3.12.1
97
+ jedi==0.19.2
98
+ jiter==0.7.1
99
+ jmespath==1.0.1
100
+ jsonschema-specifications==2024.10.1
101
+ jsonschema==4.23.0
102
+ jupyter_client==8.6.3
103
+ jupyter_core==5.7.2
104
+ kiwisolver==1.4.7
105
+ lark==1.2.2
106
+ llvmlite==0.43.0
107
+ lm-format-enforcer==0.10.9
108
+ lxml==5.3.0
109
+ markdown-it-py==3.0.0
110
+ matplotlib-inline==0.1.7
111
+ matplotlib==3.9.2
112
+ mdurl==0.1.2
113
+ more-itertools==10.3.0
114
+ mosaicml-cli==0.5.34
115
+ mosaicml-streaming==0.8.1
116
+ mpmath==1.3.0
117
+ msal-extensions==1.2.0
118
+ msal==1.31.1
119
+ msgpack==1.1.0
120
+ msgspec==0.18.6
121
+ multidict==6.1.0
122
+ multiprocess==0.70.16
123
+ nest-asyncio==1.6.0
124
+ networkx==3.4.2
125
+ ninja==1.11.1.1
126
+ numba==0.60.0
127
+ numpy==1.26.3
128
+ nvidia-cublas-cu12==12.1.3.1
129
+ nvidia-cuda-cupti-cu12==12.1.105
130
+ nvidia-cuda-nvrtc-cu12==12.1.105
131
+ nvidia-cuda-runtime-cu12==12.1.105
132
+ nvidia-cudnn-cu12==9.1.0.70
133
+ nvidia-cufft-cu12==11.0.2.54
134
+ nvidia-curand-cu12==10.3.2.106
135
+ nvidia-cusolver-cu12==11.4.5.107
136
+ nvidia-cusparse-cu12==12.1.0.106
137
+ nvidia-ml-py==12.560.30
138
+ nvidia-nccl-cu12==2.20.5
139
+ nvidia-nvjitlink-cu12==12.4.127
140
+ nvidia-nvtx-cu12==12.1.105
141
+ oci==2.138.1
142
+ openai==1.54.5
143
+ opencv-python-headless==4.10.0.84
144
+ orjson==3.10.11
145
+ outlines==0.0.46
146
+ packaging==24.1
147
+ packaging==24.2
148
+ pandas==2.2.1
149
+ paramiko==3.5.0
150
+ parso==0.8.4
151
+ partial-json-parser==0.2.1.1.post4
152
+ pexpect==4.9.0
153
+ pillow==10.4.0
154
+ pip==24.3.1
155
+ platformdirs==4.2.2
156
+ platformdirs==4.3.6
157
+ portalocker==2.10.1
158
+ prometheus-fastapi-instrumentator==7.0.0
159
+ prometheus_client==0.21.0
160
+ prompt-toolkit==3.0.36
161
+ propcache==0.2.0
162
+ proto-plus==1.25.0
163
+ protobuf==4.25.3
164
+ psutil==6.1.0
165
+ ptyprocess==0.7.0
166
+ pure_eval==0.2.3
167
+ py-cpuinfo==9.0.0
168
+ pyOpenSSL==24.2.1
169
+ pyairports==2.1.1
170
+ pyarrow-hotfix==0.6
171
+ pyarrow==18.0.0
172
+ pyasn1==0.6.1
173
+ pyasn1_modules==0.4.1
174
+ pycountry==24.6.1
175
+ pycparser==2.22
176
+ pycryptodomex==3.21.0
177
+ pydantic==2.9.2
178
+ pydantic_core==2.23.4
179
+ pyparsing==3.2.0
180
+ python-dateutil==2.9.0
181
+ python-dotenv==1.0.1
182
+ python-snappy==0.7.3
183
+ pytz==2024.2
184
+ pyzmq==26.2.0
185
+ quantile-python==1.1
186
+ questionary==2.0.1
187
+ ray==2.39.0
188
+ referencing==0.35.1
189
+ regex==2023.12.25
190
+ requests==2.32.3
191
+ rich==13.9.4
192
+ rotary-emb==0.5.2
193
+ rpds-py==0.21.0
194
+ rsa==4.9
195
+ ruamel.yaml.clib==0.2.12
196
+ ruamel.yaml==0.18.6
197
+ s3transfer==0.10.3
198
+ safetensors==0.4.5
199
+ sentencepiece==0.1.99
200
+ sentry-sdk==2.18.0
201
+ setproctitle==1.3.4
202
+ setuptools==75.6.0
203
+ shapely==2.0.6
204
+ six==1.16.0
205
+ smmap==5.0.1
206
+ sniffio==1.3.1
207
+ stack-data==0.6.3
208
+ starlette==0.41.3
209
+ sympy==1.13.1
210
+ tiktoken==0.7.0
211
+ tokenizers==0.19.1
212
+ tomli==2.0.1
213
+ torch==2.4.1
214
+ torchvision==0.19.1
215
+ tornado==6.4.1
216
+ tqdm==4.66.4
217
+ traitlets==5.14.3
218
+ transformers==4.44.2
219
+ triton==3.0.0
220
+ typeguard==4.3.0
221
+ types-python-dateutil==2.9.0.20241003
222
+ typing_extensions==4.12.2
223
+ typing_extensions==4.12.2
224
+ tzdata==2024.2
225
+ urllib3==2.2.3
226
+ uvicorn==0.32.0
227
+ uvloop==0.21.0
228
+ validators==0.34.0
229
+ vertexai==1.71.1
230
+ wandb==0.17.3
231
+ watchfiles==0.24.0
232
+ wcwidth==0.2.13
233
+ websockets==11.0.3
234
+ wheel==0.43.0
235
+ wheel==0.45.1
236
+ xformers==0.0.28.post1
237
+ xxhash==3.5.0
238
+ yarl==1.17.2
239
+ zipp==3.19.2
240
+ zipp==3.21.0
241
+ zstandard==0.22.0
242
+ zstd==1.5.5.1
wandb/run-20241225_152744-sac86tlv/files/wandb-metadata.json ADDED
@@ -0,0 +1,705 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-6.8.0-48-generic-x86_64-with-glibc2.39",
3
+ "python": "3.10.0",
4
+ "heartbeatAt": "2024-12-25T15:27:44.870156",
5
+ "startedAt": "2024-12-25T15:27:44.387439",
6
+ "docker": null,
7
+ "cuda": null,
8
+ "args": [
9
+ "--model_family",
10
+ "llama",
11
+ "--apply_instruct_masks",
12
+ "--token_scaled_loss",
13
+ "--seq_parallel_size",
14
+ "8",
15
+ "--report_to",
16
+ "wandb",
17
+ "--do_train",
18
+ "--model_name_or_path",
19
+ "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
20
+ "--config_name",
21
+ "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
22
+ "--tokenizer_name",
23
+ "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
24
+ "--run_name",
25
+ "balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_",
26
+ "--output_dir",
27
+ "/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_",
28
+ "--config_overrides_json",
29
+ "",
30
+ "--gradient_accumulation_steps",
31
+ "2",
32
+ "--per_device_train_batch_size",
33
+ "1",
34
+ "--bf16",
35
+ "--learning_rate",
36
+ "1e-6",
37
+ "--min_lr_ratio",
38
+ "0.1",
39
+ "--lr_scheduler_type",
40
+ "cosine",
41
+ "--max_grad_norm",
42
+ "1.0",
43
+ "--adam_beta1",
44
+ "0.9",
45
+ "--adam_beta2",
46
+ "0.95",
47
+ "--weight_decay",
48
+ "0.1",
49
+ "--warmup_ratio",
50
+ "0.05",
51
+ "--optim",
52
+ "adamw_torch",
53
+ "--logging_steps",
54
+ "1",
55
+ "--log_level",
56
+ "info",
57
+ "--save_steps",
58
+ "200",
59
+ "--dataloader_num_workers",
60
+ "1",
61
+ "--disable_tqdm",
62
+ "true",
63
+ "--use_fast_tokenizer",
64
+ "false",
65
+ "--remove_unused_columns",
66
+ "false",
67
+ "--ddp_find_unused_parameters",
68
+ "false",
69
+ "--fsdp",
70
+ "auto_wrap offload",
71
+ "--gradient_checkpointing",
72
+ "--tokenized_mds_train",
73
+ "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/data/ft/bookclaim_balanced_pack_complete",
74
+ "--cuda_empty_cache",
75
+ "--num_train_epochs",
76
+ "1"
77
+ ],
78
+ "state": "running",
79
+ "program": "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py",
80
+ "codePathLocal": "finetune.py",
81
+ "codePath": "prolong-final/finetune.py",
82
+ "git": {
83
+ "remote": "https://github.com/chtmp223/BookGen-dev.git",
84
+ "commit": "438e68ae65a707227d28baa427c5f6fdb0932c7b"
85
+ },
86
+ "email": "[email protected]",
87
+ "root": "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev",
88
+ "host": "gpu020",
89
+ "username": "ctpham_umass_edu",
90
+ "executable": "/scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final/bin/python3.10",
91
+ "cpu_count": 112,
92
+ "cpu_count_logical": 112,
93
+ "cpu_freq": {
94
+ "current": 997.5532857142858,
95
+ "min": 800.0,
96
+ "max": 3800.0
97
+ },
98
+ "cpu_freq_per_core": [
99
+ {
100
+ "current": 765.075,
101
+ "min": 800.0,
102
+ "max": 3800.0
103
+ },
104
+ {
105
+ "current": 800.0,
106
+ "min": 800.0,
107
+ "max": 3800.0
108
+ },
109
+ {
110
+ "current": 800.0,
111
+ "min": 800.0,
112
+ "max": 3800.0
113
+ },
114
+ {
115
+ "current": 783.551,
116
+ "min": 800.0,
117
+ "max": 3800.0
118
+ },
119
+ {
120
+ "current": 800.0,
121
+ "min": 800.0,
122
+ "max": 3800.0
123
+ },
124
+ {
125
+ "current": 800.0,
126
+ "min": 800.0,
127
+ "max": 3800.0
128
+ },
129
+ {
130
+ "current": 791.32,
131
+ "min": 800.0,
132
+ "max": 3800.0
133
+ },
134
+ {
135
+ "current": 800.0,
136
+ "min": 800.0,
137
+ "max": 3800.0
138
+ },
139
+ {
140
+ "current": 791.402,
141
+ "min": 800.0,
142
+ "max": 3800.0
143
+ },
144
+ {
145
+ "current": 788.612,
146
+ "min": 800.0,
147
+ "max": 3800.0
148
+ },
149
+ {
150
+ "current": 800.0,
151
+ "min": 800.0,
152
+ "max": 3800.0
153
+ },
154
+ {
155
+ "current": 800.0,
156
+ "min": 800.0,
157
+ "max": 3800.0
158
+ },
159
+ {
160
+ "current": 800.0,
161
+ "min": 800.0,
162
+ "max": 3800.0
163
+ },
164
+ {
165
+ "current": 800.0,
166
+ "min": 800.0,
167
+ "max": 3800.0
168
+ },
169
+ {
170
+ "current": 800.0,
171
+ "min": 800.0,
172
+ "max": 3800.0
173
+ },
174
+ {
175
+ "current": 800.0,
176
+ "min": 800.0,
177
+ "max": 3800.0
178
+ },
179
+ {
180
+ "current": 800.0,
181
+ "min": 800.0,
182
+ "max": 3800.0
183
+ },
184
+ {
185
+ "current": 800.0,
186
+ "min": 800.0,
187
+ "max": 3800.0
188
+ },
189
+ {
190
+ "current": 800.0,
191
+ "min": 800.0,
192
+ "max": 3800.0
193
+ },
194
+ {
195
+ "current": 800.0,
196
+ "min": 800.0,
197
+ "max": 3800.0
198
+ },
199
+ {
200
+ "current": 800.0,
201
+ "min": 800.0,
202
+ "max": 3800.0
203
+ },
204
+ {
205
+ "current": 800.0,
206
+ "min": 800.0,
207
+ "max": 3800.0
208
+ },
209
+ {
210
+ "current": 800.0,
211
+ "min": 800.0,
212
+ "max": 3800.0
213
+ },
214
+ {
215
+ "current": 783.817,
216
+ "min": 800.0,
217
+ "max": 3800.0
218
+ },
219
+ {
220
+ "current": 800.0,
221
+ "min": 800.0,
222
+ "max": 3800.0
223
+ },
224
+ {
225
+ "current": 800.0,
226
+ "min": 800.0,
227
+ "max": 3800.0
228
+ },
229
+ {
230
+ "current": 1700.0,
231
+ "min": 800.0,
232
+ "max": 3800.0
233
+ },
234
+ {
235
+ "current": 800.0,
236
+ "min": 800.0,
237
+ "max": 3800.0
238
+ },
239
+ {
240
+ "current": 800.0,
241
+ "min": 800.0,
242
+ "max": 3800.0
243
+ },
244
+ {
245
+ "current": 783.39,
246
+ "min": 800.0,
247
+ "max": 3800.0
248
+ },
249
+ {
250
+ "current": 800.0,
251
+ "min": 800.0,
252
+ "max": 3800.0
253
+ },
254
+ {
255
+ "current": 783.853,
256
+ "min": 800.0,
257
+ "max": 3800.0
258
+ },
259
+ {
260
+ "current": 800.0,
261
+ "min": 800.0,
262
+ "max": 3800.0
263
+ },
264
+ {
265
+ "current": 800.0,
266
+ "min": 800.0,
267
+ "max": 3800.0
268
+ },
269
+ {
270
+ "current": 800.0,
271
+ "min": 800.0,
272
+ "max": 3800.0
273
+ },
274
+ {
275
+ "current": 800.0,
276
+ "min": 800.0,
277
+ "max": 3800.0
278
+ },
279
+ {
280
+ "current": 800.0,
281
+ "min": 800.0,
282
+ "max": 3800.0
283
+ },
284
+ {
285
+ "current": 800.0,
286
+ "min": 800.0,
287
+ "max": 3800.0
288
+ },
289
+ {
290
+ "current": 1600.0,
291
+ "min": 800.0,
292
+ "max": 3800.0
293
+ },
294
+ {
295
+ "current": 800.0,
296
+ "min": 800.0,
297
+ "max": 3800.0
298
+ },
299
+ {
300
+ "current": 1995.789,
301
+ "min": 800.0,
302
+ "max": 3800.0
303
+ },
304
+ {
305
+ "current": 800.0,
306
+ "min": 800.0,
307
+ "max": 3800.0
308
+ },
309
+ {
310
+ "current": 2400.0,
311
+ "min": 800.0,
312
+ "max": 3800.0
313
+ },
314
+ {
315
+ "current": 800.0,
316
+ "min": 800.0,
317
+ "max": 3800.0
318
+ },
319
+ {
320
+ "current": 2400.0,
321
+ "min": 800.0,
322
+ "max": 3800.0
323
+ },
324
+ {
325
+ "current": 800.0,
326
+ "min": 800.0,
327
+ "max": 3800.0
328
+ },
329
+ {
330
+ "current": 2400.0,
331
+ "min": 800.0,
332
+ "max": 3800.0
333
+ },
334
+ {
335
+ "current": 800.0,
336
+ "min": 800.0,
337
+ "max": 3800.0
338
+ },
339
+ {
340
+ "current": 2400.0,
341
+ "min": 800.0,
342
+ "max": 3800.0
343
+ },
344
+ {
345
+ "current": 3800.0,
346
+ "min": 800.0,
347
+ "max": 3800.0
348
+ },
349
+ {
350
+ "current": 800.0,
351
+ "min": 800.0,
352
+ "max": 3800.0
353
+ },
354
+ {
355
+ "current": 784.222,
356
+ "min": 800.0,
357
+ "max": 3800.0
358
+ },
359
+ {
360
+ "current": 2400.0,
361
+ "min": 800.0,
362
+ "max": 3800.0
363
+ },
364
+ {
365
+ "current": 800.0,
366
+ "min": 800.0,
367
+ "max": 3800.0
368
+ },
369
+ {
370
+ "current": 2054.42,
371
+ "min": 800.0,
372
+ "max": 3800.0
373
+ },
374
+ {
375
+ "current": 800.0,
376
+ "min": 800.0,
377
+ "max": 3800.0
378
+ },
379
+ {
380
+ "current": 1998.667,
381
+ "min": 800.0,
382
+ "max": 3800.0
383
+ },
384
+ {
385
+ "current": 3800.0,
386
+ "min": 800.0,
387
+ "max": 3800.0
388
+ },
389
+ {
390
+ "current": 2009.408,
391
+ "min": 800.0,
392
+ "max": 3800.0
393
+ },
394
+ {
395
+ "current": 800.0,
396
+ "min": 800.0,
397
+ "max": 3800.0
398
+ },
399
+ {
400
+ "current": 1991.42,
401
+ "min": 800.0,
402
+ "max": 3800.0
403
+ },
404
+ {
405
+ "current": 800.0,
406
+ "min": 800.0,
407
+ "max": 3800.0
408
+ },
409
+ {
410
+ "current": 800.0,
411
+ "min": 800.0,
412
+ "max": 3800.0
413
+ },
414
+ {
415
+ "current": 800.0,
416
+ "min": 800.0,
417
+ "max": 3800.0
418
+ },
419
+ {
420
+ "current": 783.068,
421
+ "min": 800.0,
422
+ "max": 3800.0
423
+ },
424
+ {
425
+ "current": 800.0,
426
+ "min": 800.0,
427
+ "max": 3800.0
428
+ },
429
+ {
430
+ "current": 800.0,
431
+ "min": 800.0,
432
+ "max": 3800.0
433
+ },
434
+ {
435
+ "current": 800.0,
436
+ "min": 800.0,
437
+ "max": 3800.0
438
+ },
439
+ {
440
+ "current": 800.0,
441
+ "min": 800.0,
442
+ "max": 3800.0
443
+ },
444
+ {
445
+ "current": 800.0,
446
+ "min": 800.0,
447
+ "max": 3800.0
448
+ },
449
+ {
450
+ "current": 800.0,
451
+ "min": 800.0,
452
+ "max": 3800.0
453
+ },
454
+ {
455
+ "current": 800.0,
456
+ "min": 800.0,
457
+ "max": 3800.0
458
+ },
459
+ {
460
+ "current": 800.0,
461
+ "min": 800.0,
462
+ "max": 3800.0
463
+ },
464
+ {
465
+ "current": 800.0,
466
+ "min": 800.0,
467
+ "max": 3800.0
468
+ },
469
+ {
470
+ "current": 783.462,
471
+ "min": 800.0,
472
+ "max": 3800.0
473
+ },
474
+ {
475
+ "current": 800.0,
476
+ "min": 800.0,
477
+ "max": 3800.0
478
+ },
479
+ {
480
+ "current": 800.0,
481
+ "min": 800.0,
482
+ "max": 3800.0
483
+ },
484
+ {
485
+ "current": 800.0,
486
+ "min": 800.0,
487
+ "max": 3800.0
488
+ },
489
+ {
490
+ "current": 800.0,
491
+ "min": 800.0,
492
+ "max": 3800.0
493
+ },
494
+ {
495
+ "current": 800.0,
496
+ "min": 800.0,
497
+ "max": 3800.0
498
+ },
499
+ {
500
+ "current": 800.0,
501
+ "min": 800.0,
502
+ "max": 3800.0
503
+ },
504
+ {
505
+ "current": 800.0,
506
+ "min": 800.0,
507
+ "max": 3800.0
508
+ },
509
+ {
510
+ "current": 800.0,
511
+ "min": 800.0,
512
+ "max": 3800.0
513
+ },
514
+ {
515
+ "current": 800.0,
516
+ "min": 800.0,
517
+ "max": 3800.0
518
+ },
519
+ {
520
+ "current": 800.0,
521
+ "min": 800.0,
522
+ "max": 3800.0
523
+ },
524
+ {
525
+ "current": 800.0,
526
+ "min": 800.0,
527
+ "max": 3800.0
528
+ },
529
+ {
530
+ "current": 800.0,
531
+ "min": 800.0,
532
+ "max": 3800.0
533
+ },
534
+ {
535
+ "current": 800.0,
536
+ "min": 800.0,
537
+ "max": 3800.0
538
+ },
539
+ {
540
+ "current": 800.0,
541
+ "min": 800.0,
542
+ "max": 3800.0
543
+ },
544
+ {
545
+ "current": 800.0,
546
+ "min": 800.0,
547
+ "max": 3800.0
548
+ },
549
+ {
550
+ "current": 800.0,
551
+ "min": 800.0,
552
+ "max": 3800.0
553
+ },
554
+ {
555
+ "current": 800.0,
556
+ "min": 800.0,
557
+ "max": 3800.0
558
+ },
559
+ {
560
+ "current": 800.0,
561
+ "min": 800.0,
562
+ "max": 3800.0
563
+ },
564
+ {
565
+ "current": 800.0,
566
+ "min": 800.0,
567
+ "max": 3800.0
568
+ },
569
+ {
570
+ "current": 800.0,
571
+ "min": 800.0,
572
+ "max": 3800.0
573
+ },
574
+ {
575
+ "current": 800.0,
576
+ "min": 800.0,
577
+ "max": 3800.0
578
+ },
579
+ {
580
+ "current": 800.0,
581
+ "min": 800.0,
582
+ "max": 3800.0
583
+ },
584
+ {
585
+ "current": 800.0,
586
+ "min": 800.0,
587
+ "max": 3800.0
588
+ },
589
+ {
590
+ "current": 800.0,
591
+ "min": 800.0,
592
+ "max": 3800.0
593
+ },
594
+ {
595
+ "current": 800.0,
596
+ "min": 800.0,
597
+ "max": 3800.0
598
+ },
599
+ {
600
+ "current": 800.0,
601
+ "min": 800.0,
602
+ "max": 3800.0
603
+ },
604
+ {
605
+ "current": 800.0,
606
+ "min": 800.0,
607
+ "max": 3800.0
608
+ },
609
+ {
610
+ "current": 800.0,
611
+ "min": 800.0,
612
+ "max": 3800.0
613
+ },
614
+ {
615
+ "current": 800.0,
616
+ "min": 800.0,
617
+ "max": 3800.0
618
+ },
619
+ {
620
+ "current": 800.0,
621
+ "min": 800.0,
622
+ "max": 3800.0
623
+ },
624
+ {
625
+ "current": 800.0,
626
+ "min": 800.0,
627
+ "max": 3800.0
628
+ },
629
+ {
630
+ "current": 800.0,
631
+ "min": 800.0,
632
+ "max": 3800.0
633
+ },
634
+ {
635
+ "current": 800.0,
636
+ "min": 800.0,
637
+ "max": 3800.0
638
+ },
639
+ {
640
+ "current": 800.0,
641
+ "min": 800.0,
642
+ "max": 3800.0
643
+ },
644
+ {
645
+ "current": 800.0,
646
+ "min": 800.0,
647
+ "max": 3800.0
648
+ },
649
+ {
650
+ "current": 800.0,
651
+ "min": 800.0,
652
+ "max": 3800.0
653
+ },
654
+ {
655
+ "current": 800.0,
656
+ "min": 800.0,
657
+ "max": 3800.0
658
+ }
659
+ ],
660
+ "disk": {
661
+ "/": {
662
+ "total": 438.487850189209,
663
+ "used": 18.09857940673828
664
+ }
665
+ },
666
+ "gpu": "NVIDIA A100-SXM4-80GB",
667
+ "gpu_count": 8,
668
+ "gpu_devices": [
669
+ {
670
+ "name": "NVIDIA A100-SXM4-80GB",
671
+ "memory_total": 85899345920
672
+ },
673
+ {
674
+ "name": "NVIDIA A100-SXM4-80GB",
675
+ "memory_total": 85899345920
676
+ },
677
+ {
678
+ "name": "NVIDIA A100-SXM4-80GB",
679
+ "memory_total": 85899345920
680
+ },
681
+ {
682
+ "name": "NVIDIA A100-SXM4-80GB",
683
+ "memory_total": 85899345920
684
+ },
685
+ {
686
+ "name": "NVIDIA A100-SXM4-80GB",
687
+ "memory_total": 85899345920
688
+ },
689
+ {
690
+ "name": "NVIDIA A100-SXM4-80GB",
691
+ "memory_total": 85899345920
692
+ },
693
+ {
694
+ "name": "NVIDIA A100-SXM4-80GB",
695
+ "memory_total": 85899345920
696
+ },
697
+ {
698
+ "name": "NVIDIA A100-SXM4-80GB",
699
+ "memory_total": 85899345920
700
+ }
701
+ ],
702
+ "memory": {
703
+ "total": 2015.3287239074707
704
+ }
705
+ }
wandb/run-20241225_152744-sac86tlv/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train/loss": 0.3707, "train/grad_norm": 19.094097137451172, "train/learning_rate": 3.1585738590718157e-07, "train/epoch": 0.4735557363710334, "train/num_input_tokens_seen": 5339348992, "train/global_step": 2546, "_timestamp": 1735196422.1364121, "_runtime": 55957.73042821884, "_step": 1745}
wandb/run-20241225_152744-sac86tlv/logs/debug-internal.log ADDED
The diff for this file is too large to render. See raw diff
 
wandb/run-20241225_152744-sac86tlv/logs/debug.log ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-12-25 15:27:44,398 INFO MainThread:315136 [wandb_setup.py:_flush():76] Current SDK version is 0.17.3
2
+ 2024-12-25 15:27:44,398 INFO MainThread:315136 [wandb_setup.py:_flush():76] Configure stats pid to 315136
3
+ 2024-12-25 15:27:44,398 INFO MainThread:315136 [wandb_setup.py:_flush():76] Loading settings from /home/ctpham_umass_edu/.config/wandb/settings
4
+ 2024-12-25 15:27:44,398 INFO MainThread:315136 [wandb_setup.py:_flush():76] Loading settings from /work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/wandb/settings
5
+ 2024-12-25 15:27:44,398 INFO MainThread:315136 [wandb_setup.py:_flush():76] Loading settings from environment variables: {'root_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'project': 'prolong', 'api_key': '***REDACTED***', 'mode': 'online'}
6
+ 2024-12-25 15:27:44,398 INFO MainThread:315136 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
7
+ 2024-12-25 15:27:44,398 INFO MainThread:315136 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'prolong-final/finetune.py', 'program_abspath': '/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py', 'program': '/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py'}
8
+ 2024-12-25 15:27:44,398 INFO MainThread:315136 [wandb_setup.py:_flush():76] Applying login settings: {}
9
+ 2024-12-25 15:27:44,399 INFO MainThread:315136 [wandb_init.py:_log_setup():520] Logging user logs to /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/wandb/run-20241225_152744-sac86tlv/logs/debug.log
10
+ 2024-12-25 15:27:44,399 INFO MainThread:315136 [wandb_init.py:_log_setup():521] Logging internal logs to /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/wandb/run-20241225_152744-sac86tlv/logs/debug-internal.log
11
+ 2024-12-25 15:27:44,399 INFO MainThread:315136 [wandb_init.py:init():560] calling init triggers
12
+ 2024-12-25 15:27:44,399 INFO MainThread:315136 [wandb_init.py:init():567] wandb.init called with sweep_config: {}
13
+ config: {}
14
+ 2024-12-25 15:27:44,399 INFO MainThread:315136 [wandb_init.py:init():610] starting backend
15
+ 2024-12-25 15:27:44,399 INFO MainThread:315136 [wandb_init.py:init():614] setting up manager
16
+ 2024-12-25 15:27:44,402 INFO MainThread:315136 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
17
+ 2024-12-25 15:27:44,405 INFO MainThread:315136 [wandb_init.py:init():622] backend started and connected
18
+ 2024-12-25 15:27:44,414 INFO MainThread:315136 [wandb_init.py:init():711] updated telemetry
19
+ 2024-12-25 15:27:44,442 INFO MainThread:315136 [wandb_init.py:init():744] communicating run to backend with 90.0 second timeout
20
+ 2024-12-25 15:27:44,703 INFO MainThread:315136 [wandb_run.py:_on_init():2402] communicating current version
21
+ 2024-12-25 15:27:44,769 INFO MainThread:315136 [wandb_run.py:_on_init():2411] got version response upgrade_message: "wandb version 0.19.1 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
22
+
23
+ 2024-12-25 15:27:44,769 INFO MainThread:315136 [wandb_init.py:init():795] starting run threads in backend
24
+ 2024-12-25 15:27:52,193 INFO MainThread:315136 [wandb_run.py:_console_start():2380] atexit reg
25
+ 2024-12-25 15:27:52,193 INFO MainThread:315136 [wandb_run.py:_redirect():2235] redirect: wrap_raw
26
+ 2024-12-25 15:27:52,194 INFO MainThread:315136 [wandb_run.py:_redirect():2300] Wrapping output streams.
27
+ 2024-12-25 15:27:52,194 INFO MainThread:315136 [wandb_run.py:_redirect():2325] Redirects installed.
28
+ 2024-12-25 15:27:52,195 INFO MainThread:315136 [wandb_init.py:init():838] run started, returning control to user process
29
+ 2024-12-25 15:27:52,197 INFO MainThread:315136 [wandb_run.py:_config_callback():1382] config_cb None None {'vocab_size': 128256, 'max_position_embeddings': 524288, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'pretraining_tp': 1, 'use_cache': True, 'rope_theta': 128000000.0, 'rope_scaling': None, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['LlamaForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 128000, 'pad_token_id': 0, 'eos_token_id': 128009, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': '/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/', 'transformers_version': '4.44.2', 'model_type': 'llama', 'output_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'overwrite_output_dir': False, 'do_train': True, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 1e-06, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.95, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.05, 'warmup_steps': 0, 'log_level': 'info', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/runs/Dec25_15-21-22_gpu020', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1.0, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 200, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 1, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'disable_tqdm': True, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': True, 'fsdp': ['auto_wrap', 'offload'], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': False, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'eval_use_gather_object': False, 'min_lr_ratio': 0.1, 'cuda_empty_cache': True, 'streaming_dataset': True, 'seq_parallel_size': 8}
30
+ 2024-12-25 15:27:52,199 INFO MainThread:315136 [wandb_config.py:__setitem__():151] config set model/num_parameters = 1003782656 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x74e6e91a2da0>>
31
+ 2024-12-25 15:27:52,200 INFO MainThread:315136 [wandb_run.py:_config_callback():1382] config_cb model/num_parameters 1003782656 None
wandb/run-20241225_152744-sac86tlv/run-sac86tlv.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf10a3dda753a2585274da80ad47f6378f71e6ae1d836e595dcf4f0c9d35cb2a
3
+ size 11275886
wandb/run-20241226_145403-c7ovtvny/files/conda-environment.yaml ADDED
@@ -0,0 +1,232 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ name: /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final
2
+ channels:
3
+ - conda-forge
4
+ dependencies:
5
+ - _libgcc_mutex=0.1=conda_forge
6
+ - _openmp_mutex=4.5=2_gnu
7
+ - bzip2=1.0.8=h4bc722e_7
8
+ - ca-certificates=2024.12.14=hbcca054_0
9
+ - ld_impl_linux-64=2.43=h712a8e2_2
10
+ - libffi=3.4.2=h7f98852_5
11
+ - libgcc=14.2.0=h77fa898_1
12
+ - libgcc-ng=14.2.0=h69a702a_1
13
+ - libgomp=14.2.0=h77fa898_1
14
+ - liblzma=5.6.3=hb9d3cd8_1
15
+ - liblzma-devel=5.6.3=hb9d3cd8_1
16
+ - libnsl=2.0.1=hd590300_0
17
+ - libsqlite=3.47.2=hee588c1_0
18
+ - libuuid=2.38.1=h0b41bf4_0
19
+ - libzlib=1.3.1=hb9d3cd8_2
20
+ - ncurses=6.5=he02047a_1
21
+ - openssl=3.4.0=hb9d3cd8_0
22
+ - pip=24.3.1=pyh8b19718_2
23
+ - python=3.10.0=h543edf9_3_cpython
24
+ - readline=8.2=h8228510_1
25
+ - setuptools=75.6.0=pyhff2d567_1
26
+ - sqlite=3.47.2=h9eae976_0
27
+ - tk=8.6.13=noxft_h4845f30_101
28
+ - wheel=0.45.1=pyhd8ed1ab_1
29
+ - xz=5.6.3=hbcc6ac9_1
30
+ - xz-gpl-tools=5.6.3=hbcc6ac9_1
31
+ - xz-tools=5.6.3=hb9d3cd8_1
32
+ - pip:
33
+ - accelerate==0.32.1
34
+ - aiohappyeyeballs==2.4.3
35
+ - aiohttp==3.11.2
36
+ - aioprometheus==23.12.0
37
+ - aiosignal==1.3.1
38
+ - annotated-types==0.7.0
39
+ - anthropic==0.39.0
40
+ - anyio==4.6.2.post1
41
+ - argcomplete==3.5.1
42
+ - arrow==1.3.0
43
+ - async-timeout==5.0.1
44
+ - attrs==24.2.0
45
+ - azure-core==1.32.0
46
+ - azure-identity==1.19.0
47
+ - azure-storage-blob==12.24.0
48
+ - azure-storage-file-datalake==12.18.0
49
+ - backoff==2.2.1
50
+ - bcrypt==4.2.0
51
+ - blobfile==3.0.0
52
+ - boto3==1.35.63
53
+ - botocore==1.35.63
54
+ - brotli==1.1.0
55
+ - cachetools==5.5.0
56
+ - certifi==2024.8.30
57
+ - cffi==1.17.1
58
+ - charset-normalizer==3.4.0
59
+ - circuitbreaker==2.0.0
60
+ - click==8.1.7
61
+ - cloudpickle==3.1.0
62
+ - compressed-tensors==0.8.0
63
+ - contourpy==1.3.1
64
+ - cramjam==2.9.0
65
+ - cryptography==43.0.3
66
+ - cycler==0.12.1
67
+ - datasets==2.20.0
68
+ - debugpy==1.8.11
69
+ - dill==0.3.8
70
+ - diskcache==5.6.3
71
+ - distro==1.9.0
72
+ - docker-pycreds==0.4.0
73
+ - docstring-parser==0.16
74
+ - einops==0.8.0
75
+ - fastapi==0.115.5
76
+ - filelock==3.16.1
77
+ - flash-attn==2.6.1
78
+ - fonttools==4.55.0
79
+ - frozenlist==1.5.0
80
+ - fsspec==2024.5.0
81
+ - gguf==0.10.0
82
+ - gitdb==4.0.11
83
+ - gitpython==3.1.43
84
+ - google-api-core==2.23.0
85
+ - google-auth==2.36.0
86
+ - google-cloud-aiplatform==1.71.1
87
+ - google-cloud-bigquery==3.27.0
88
+ - google-cloud-core==2.4.1
89
+ - google-cloud-resource-manager==1.13.1
90
+ - google-cloud-storage==2.10.0
91
+ - google-crc32c==1.6.0
92
+ - google-resumable-media==2.7.2
93
+ - googleapis-common-protos==1.66.0
94
+ - gql==3.5.0
95
+ - graphql-core==3.2.5
96
+ - grpc-google-iam-v1==0.13.1
97
+ - grpcio==1.68.0
98
+ - grpcio-status==1.62.3
99
+ - h11==0.14.0
100
+ - httpcore==1.0.7
101
+ - httptools==0.6.4
102
+ - httpx==0.27.2
103
+ - huggingface-hub==0.26.2
104
+ - idna==3.10
105
+ - importlib-metadata==8.5.0
106
+ - interegular==0.3.3
107
+ - ipython==8.18.0
108
+ - isodate==0.7.2
109
+ - jedi==0.19.2
110
+ - jinja2==3.1.4
111
+ - jiter==0.7.1
112
+ - jmespath==1.0.1
113
+ - jsonschema==4.23.0
114
+ - jsonschema-specifications==2024.10.1
115
+ - kiwisolver==1.4.7
116
+ - lark==1.2.2
117
+ - llvmlite==0.43.0
118
+ - lm-format-enforcer==0.10.9
119
+ - lxml==5.3.0
120
+ - markdown-it-py==3.0.0
121
+ - markupsafe==3.0.2
122
+ - matplotlib==3.9.2
123
+ - mdurl==0.1.2
124
+ - mosaicml-cli==0.5.34
125
+ - mosaicml-streaming==0.8.1
126
+ - mpmath==1.3.0
127
+ - msal==1.31.1
128
+ - msal-extensions==1.2.0
129
+ - msgpack==1.1.0
130
+ - msgspec==0.18.6
131
+ - multidict==6.1.0
132
+ - multiprocess==0.70.16
133
+ - networkx==3.4.2
134
+ - ninja==1.11.1.1
135
+ - numba==0.60.0
136
+ - numpy==1.26.3
137
+ - nvidia-cublas-cu12==12.1.3.1
138
+ - nvidia-cuda-cupti-cu12==12.1.105
139
+ - nvidia-cuda-nvrtc-cu12==12.1.105
140
+ - nvidia-cuda-runtime-cu12==12.1.105
141
+ - nvidia-cudnn-cu12==9.1.0.70
142
+ - nvidia-cufft-cu12==11.0.2.54
143
+ - nvidia-curand-cu12==10.3.2.106
144
+ - nvidia-cusolver-cu12==11.4.5.107
145
+ - nvidia-cusparse-cu12==12.1.0.106
146
+ - nvidia-ml-py==12.560.30
147
+ - nvidia-nccl-cu12==2.20.5
148
+ - nvidia-nvjitlink-cu12==12.4.127
149
+ - nvidia-nvtx-cu12==12.1.105
150
+ - oci==2.138.1
151
+ - openai==1.54.5
152
+ - opencv-python-headless==4.10.0.84
153
+ - orjson==3.10.11
154
+ - outlines==0.0.46
155
+ - packaging==24.1
156
+ - pandas==2.2.1
157
+ - paramiko==3.5.0
158
+ - partial-json-parser==0.2.1.1.post4
159
+ - pillow==10.4.0
160
+ - portalocker==2.10.1
161
+ - prometheus-client==0.21.0
162
+ - prometheus-fastapi-instrumentator==7.0.0
163
+ - prompt-toolkit==3.0.36
164
+ - propcache==0.2.0
165
+ - proto-plus==1.25.0
166
+ - protobuf==4.25.3
167
+ - py-cpuinfo==9.0.0
168
+ - pyairports==2.1.1
169
+ - pyarrow==18.0.0
170
+ - pyarrow-hotfix==0.6
171
+ - pyasn1==0.6.1
172
+ - pyasn1-modules==0.4.1
173
+ - pycountry==24.6.1
174
+ - pycparser==2.22
175
+ - pycryptodomex==3.21.0
176
+ - pydantic==2.9.2
177
+ - pydantic-core==2.23.4
178
+ - pyjwt==2.10.0
179
+ - pynacl==1.5.0
180
+ - pyopenssl==24.2.1
181
+ - pyparsing==3.2.0
182
+ - python-dateutil==2.9.0
183
+ - python-dotenv==1.0.1
184
+ - python-snappy==0.7.3
185
+ - pytz==2024.2
186
+ - pyyaml==6.0.2
187
+ - quantile-python==1.1
188
+ - questionary==2.0.1
189
+ - ray==2.39.0
190
+ - referencing==0.35.1
191
+ - regex==2023.12.25
192
+ - requests==2.32.3
193
+ - rich==13.9.4
194
+ - rotary-emb==0.5.2
195
+ - rpds-py==0.21.0
196
+ - rsa==4.9
197
+ - ruamel-yaml==0.18.6
198
+ - ruamel-yaml-clib==0.2.12
199
+ - s3transfer==0.10.3
200
+ - safetensors==0.4.5
201
+ - sentencepiece==0.1.99
202
+ - sentry-sdk==2.18.0
203
+ - setproctitle==1.3.4
204
+ - shapely==2.0.6
205
+ - smmap==5.0.1
206
+ - sniffio==1.3.1
207
+ - starlette==0.41.3
208
+ - sympy==1.13.1
209
+ - tiktoken==0.7.0
210
+ - tokenizers==0.19.1
211
+ - torch==2.4.1
212
+ - torchvision==0.19.1
213
+ - tqdm==4.66.4
214
+ - transformers==4.44.2
215
+ - triton==3.0.0
216
+ - types-python-dateutil==2.9.0.20241003
217
+ - tzdata==2024.2
218
+ - urllib3==2.2.3
219
+ - uvicorn==0.32.0
220
+ - uvloop==0.21.0
221
+ - validators==0.34.0
222
+ - vertexai==1.71.1
223
+ - wandb==0.17.3
224
+ - watchfiles==0.24.0
225
+ - websockets==11.0.3
226
+ - xformers==0.0.28.post1
227
+ - xxhash==3.5.0
228
+ - yarl==1.17.2
229
+ - zipp==3.21.0
230
+ - zstandard==0.22.0
231
+ - zstd==1.5.5.1
232
+ prefix: /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final
wandb/run-20241226_145403-c7ovtvny/files/config.yaml ADDED
@@ -0,0 +1,705 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ wandb_version: 1
2
+
3
+ _wandb:
4
+ desc: null
5
+ value:
6
+ python_version: 3.10.0
7
+ cli_version: 0.17.3
8
+ framework: huggingface
9
+ huggingface_version: 4.44.2
10
+ is_jupyter_run: false
11
+ is_kaggle_kernel: false
12
+ start_time: 1735224843
13
+ t:
14
+ 1:
15
+ - 1
16
+ - 11
17
+ - 41
18
+ - 49
19
+ - 51
20
+ - 55
21
+ - 71
22
+ - 105
23
+ 2:
24
+ - 1
25
+ - 11
26
+ - 41
27
+ - 49
28
+ - 51
29
+ - 55
30
+ - 71
31
+ - 105
32
+ 3:
33
+ - 7
34
+ - 13
35
+ - 19
36
+ - 23
37
+ - 66
38
+ 4: 3.10.0
39
+ 5: 0.17.3
40
+ 6: 4.44.2
41
+ 8:
42
+ - 5
43
+ 9:
44
+ 1: transformers_trainer
45
+ 13: linux-x86_64
46
+ m:
47
+ - 1: train/global_step
48
+ 6:
49
+ - 3
50
+ - 1: train/loss
51
+ 5: 1
52
+ 6:
53
+ - 1
54
+ - 1: train/grad_norm
55
+ 5: 1
56
+ 6:
57
+ - 1
58
+ - 1: train/learning_rate
59
+ 5: 1
60
+ 6:
61
+ - 1
62
+ - 1: train/epoch
63
+ 5: 1
64
+ 6:
65
+ - 1
66
+ - 1: train/num_input_tokens_seen
67
+ 5: 1
68
+ 6:
69
+ - 1
70
+ vocab_size:
71
+ desc: null
72
+ value: 128256
73
+ max_position_embeddings:
74
+ desc: null
75
+ value: 524288
76
+ hidden_size:
77
+ desc: null
78
+ value: 4096
79
+ intermediate_size:
80
+ desc: null
81
+ value: 14336
82
+ num_hidden_layers:
83
+ desc: null
84
+ value: 32
85
+ num_attention_heads:
86
+ desc: null
87
+ value: 32
88
+ num_key_value_heads:
89
+ desc: null
90
+ value: 8
91
+ hidden_act:
92
+ desc: null
93
+ value: silu
94
+ initializer_range:
95
+ desc: null
96
+ value: 0.02
97
+ rms_norm_eps:
98
+ desc: null
99
+ value: 1.0e-05
100
+ pretraining_tp:
101
+ desc: null
102
+ value: 1
103
+ use_cache:
104
+ desc: null
105
+ value: true
106
+ rope_theta:
107
+ desc: null
108
+ value: 128000000.0
109
+ rope_scaling:
110
+ desc: null
111
+ value: null
112
+ attention_bias:
113
+ desc: null
114
+ value: false
115
+ attention_dropout:
116
+ desc: null
117
+ value: 0.0
118
+ mlp_bias:
119
+ desc: null
120
+ value: false
121
+ return_dict:
122
+ desc: null
123
+ value: true
124
+ output_hidden_states:
125
+ desc: null
126
+ value: false
127
+ output_attentions:
128
+ desc: null
129
+ value: false
130
+ torchscript:
131
+ desc: null
132
+ value: false
133
+ torch_dtype:
134
+ desc: null
135
+ value: float32
136
+ use_bfloat16:
137
+ desc: null
138
+ value: false
139
+ tf_legacy_loss:
140
+ desc: null
141
+ value: false
142
+ pruned_heads:
143
+ desc: null
144
+ value: {}
145
+ tie_word_embeddings:
146
+ desc: null
147
+ value: false
148
+ chunk_size_feed_forward:
149
+ desc: null
150
+ value: 0
151
+ is_encoder_decoder:
152
+ desc: null
153
+ value: false
154
+ is_decoder:
155
+ desc: null
156
+ value: false
157
+ cross_attention_hidden_size:
158
+ desc: null
159
+ value: null
160
+ add_cross_attention:
161
+ desc: null
162
+ value: false
163
+ tie_encoder_decoder:
164
+ desc: null
165
+ value: false
166
+ max_length:
167
+ desc: null
168
+ value: 20
169
+ min_length:
170
+ desc: null
171
+ value: 0
172
+ do_sample:
173
+ desc: null
174
+ value: false
175
+ early_stopping:
176
+ desc: null
177
+ value: false
178
+ num_beams:
179
+ desc: null
180
+ value: 1
181
+ num_beam_groups:
182
+ desc: null
183
+ value: 1
184
+ diversity_penalty:
185
+ desc: null
186
+ value: 0.0
187
+ temperature:
188
+ desc: null
189
+ value: 1.0
190
+ top_k:
191
+ desc: null
192
+ value: 50
193
+ top_p:
194
+ desc: null
195
+ value: 1.0
196
+ typical_p:
197
+ desc: null
198
+ value: 1.0
199
+ repetition_penalty:
200
+ desc: null
201
+ value: 1.0
202
+ length_penalty:
203
+ desc: null
204
+ value: 1.0
205
+ no_repeat_ngram_size:
206
+ desc: null
207
+ value: 0
208
+ encoder_no_repeat_ngram_size:
209
+ desc: null
210
+ value: 0
211
+ bad_words_ids:
212
+ desc: null
213
+ value: null
214
+ num_return_sequences:
215
+ desc: null
216
+ value: 1
217
+ output_scores:
218
+ desc: null
219
+ value: false
220
+ return_dict_in_generate:
221
+ desc: null
222
+ value: false
223
+ forced_bos_token_id:
224
+ desc: null
225
+ value: null
226
+ forced_eos_token_id:
227
+ desc: null
228
+ value: null
229
+ remove_invalid_values:
230
+ desc: null
231
+ value: false
232
+ exponential_decay_length_penalty:
233
+ desc: null
234
+ value: null
235
+ suppress_tokens:
236
+ desc: null
237
+ value: null
238
+ begin_suppress_tokens:
239
+ desc: null
240
+ value: null
241
+ architectures:
242
+ desc: null
243
+ value:
244
+ - LlamaForCausalLM
245
+ finetuning_task:
246
+ desc: null
247
+ value: null
248
+ id2label:
249
+ desc: null
250
+ value:
251
+ '0': LABEL_0
252
+ '1': LABEL_1
253
+ label2id:
254
+ desc: null
255
+ value:
256
+ LABEL_0: 0
257
+ LABEL_1: 1
258
+ tokenizer_class:
259
+ desc: null
260
+ value: null
261
+ prefix:
262
+ desc: null
263
+ value: null
264
+ bos_token_id:
265
+ desc: null
266
+ value: 128000
267
+ pad_token_id:
268
+ desc: null
269
+ value: 0
270
+ eos_token_id:
271
+ desc: null
272
+ value: 128009
273
+ sep_token_id:
274
+ desc: null
275
+ value: null
276
+ decoder_start_token_id:
277
+ desc: null
278
+ value: null
279
+ task_specific_params:
280
+ desc: null
281
+ value: null
282
+ problem_type:
283
+ desc: null
284
+ value: null
285
+ _name_or_path:
286
+ desc: null
287
+ value: /scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/
288
+ transformers_version:
289
+ desc: null
290
+ value: 4.44.2
291
+ model_type:
292
+ desc: null
293
+ value: llama
294
+ output_dir:
295
+ desc: null
296
+ value: /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_
297
+ overwrite_output_dir:
298
+ desc: null
299
+ value: false
300
+ do_train:
301
+ desc: null
302
+ value: true
303
+ do_eval:
304
+ desc: null
305
+ value: false
306
+ do_predict:
307
+ desc: null
308
+ value: false
309
+ eval_strategy:
310
+ desc: null
311
+ value: 'no'
312
+ prediction_loss_only:
313
+ desc: null
314
+ value: false
315
+ per_device_train_batch_size:
316
+ desc: null
317
+ value: 1
318
+ per_device_eval_batch_size:
319
+ desc: null
320
+ value: 8
321
+ per_gpu_train_batch_size:
322
+ desc: null
323
+ value: null
324
+ per_gpu_eval_batch_size:
325
+ desc: null
326
+ value: null
327
+ gradient_accumulation_steps:
328
+ desc: null
329
+ value: 2
330
+ eval_accumulation_steps:
331
+ desc: null
332
+ value: null
333
+ eval_delay:
334
+ desc: null
335
+ value: 0
336
+ torch_empty_cache_steps:
337
+ desc: null
338
+ value: null
339
+ learning_rate:
340
+ desc: null
341
+ value: 1.0e-06
342
+ weight_decay:
343
+ desc: null
344
+ value: 0.1
345
+ adam_beta1:
346
+ desc: null
347
+ value: 0.9
348
+ adam_beta2:
349
+ desc: null
350
+ value: 0.95
351
+ adam_epsilon:
352
+ desc: null
353
+ value: 1.0e-08
354
+ max_grad_norm:
355
+ desc: null
356
+ value: 1.0
357
+ num_train_epochs:
358
+ desc: null
359
+ value: 1.0
360
+ max_steps:
361
+ desc: null
362
+ value: -1
363
+ lr_scheduler_type:
364
+ desc: null
365
+ value: cosine
366
+ lr_scheduler_kwargs:
367
+ desc: null
368
+ value: {}
369
+ warmup_ratio:
370
+ desc: null
371
+ value: 0.05
372
+ warmup_steps:
373
+ desc: null
374
+ value: 0
375
+ log_level:
376
+ desc: null
377
+ value: info
378
+ log_level_replica:
379
+ desc: null
380
+ value: warning
381
+ log_on_each_node:
382
+ desc: null
383
+ value: true
384
+ logging_dir:
385
+ desc: null
386
+ value: /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/runs/Dec26_14-47-22_gpu021
387
+ logging_strategy:
388
+ desc: null
389
+ value: steps
390
+ logging_first_step:
391
+ desc: null
392
+ value: false
393
+ logging_steps:
394
+ desc: null
395
+ value: 1.0
396
+ logging_nan_inf_filter:
397
+ desc: null
398
+ value: true
399
+ save_strategy:
400
+ desc: null
401
+ value: steps
402
+ save_steps:
403
+ desc: null
404
+ value: 200
405
+ save_total_limit:
406
+ desc: null
407
+ value: null
408
+ save_safetensors:
409
+ desc: null
410
+ value: true
411
+ save_on_each_node:
412
+ desc: null
413
+ value: false
414
+ save_only_model:
415
+ desc: null
416
+ value: false
417
+ restore_callback_states_from_checkpoint:
418
+ desc: null
419
+ value: false
420
+ no_cuda:
421
+ desc: null
422
+ value: false
423
+ use_cpu:
424
+ desc: null
425
+ value: false
426
+ use_mps_device:
427
+ desc: null
428
+ value: false
429
+ seed:
430
+ desc: null
431
+ value: 42
432
+ data_seed:
433
+ desc: null
434
+ value: null
435
+ jit_mode_eval:
436
+ desc: null
437
+ value: false
438
+ use_ipex:
439
+ desc: null
440
+ value: false
441
+ bf16:
442
+ desc: null
443
+ value: true
444
+ fp16:
445
+ desc: null
446
+ value: false
447
+ fp16_opt_level:
448
+ desc: null
449
+ value: O1
450
+ half_precision_backend:
451
+ desc: null
452
+ value: auto
453
+ bf16_full_eval:
454
+ desc: null
455
+ value: false
456
+ fp16_full_eval:
457
+ desc: null
458
+ value: false
459
+ tf32:
460
+ desc: null
461
+ value: null
462
+ local_rank:
463
+ desc: null
464
+ value: 0
465
+ ddp_backend:
466
+ desc: null
467
+ value: null
468
+ tpu_num_cores:
469
+ desc: null
470
+ value: null
471
+ tpu_metrics_debug:
472
+ desc: null
473
+ value: false
474
+ debug:
475
+ desc: null
476
+ value: []
477
+ dataloader_drop_last:
478
+ desc: null
479
+ value: false
480
+ eval_steps:
481
+ desc: null
482
+ value: null
483
+ dataloader_num_workers:
484
+ desc: null
485
+ value: 1
486
+ dataloader_prefetch_factor:
487
+ desc: null
488
+ value: null
489
+ past_index:
490
+ desc: null
491
+ value: -1
492
+ run_name:
493
+ desc: null
494
+ value: balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_
495
+ disable_tqdm:
496
+ desc: null
497
+ value: true
498
+ remove_unused_columns:
499
+ desc: null
500
+ value: false
501
+ label_names:
502
+ desc: null
503
+ value: null
504
+ load_best_model_at_end:
505
+ desc: null
506
+ value: false
507
+ metric_for_best_model:
508
+ desc: null
509
+ value: null
510
+ greater_is_better:
511
+ desc: null
512
+ value: null
513
+ ignore_data_skip:
514
+ desc: null
515
+ value: true
516
+ fsdp:
517
+ desc: null
518
+ value:
519
+ - auto_wrap
520
+ - offload
521
+ fsdp_min_num_params:
522
+ desc: null
523
+ value: 0
524
+ fsdp_config:
525
+ desc: null
526
+ value:
527
+ min_num_params: 0
528
+ xla: false
529
+ xla_fsdp_v2: false
530
+ xla_fsdp_grad_ckpt: false
531
+ fsdp_transformer_layer_cls_to_wrap:
532
+ desc: null
533
+ value: null
534
+ accelerator_config:
535
+ desc: null
536
+ value:
537
+ split_batches: false
538
+ dispatch_batches: null
539
+ even_batches: true
540
+ use_seedable_sampler: true
541
+ non_blocking: false
542
+ gradient_accumulation_kwargs: null
543
+ deepspeed:
544
+ desc: null
545
+ value: null
546
+ label_smoothing_factor:
547
+ desc: null
548
+ value: 0.0
549
+ optim:
550
+ desc: null
551
+ value: adamw_torch
552
+ optim_args:
553
+ desc: null
554
+ value: null
555
+ adafactor:
556
+ desc: null
557
+ value: false
558
+ group_by_length:
559
+ desc: null
560
+ value: false
561
+ length_column_name:
562
+ desc: null
563
+ value: length
564
+ report_to:
565
+ desc: null
566
+ value:
567
+ - wandb
568
+ ddp_find_unused_parameters:
569
+ desc: null
570
+ value: false
571
+ ddp_bucket_cap_mb:
572
+ desc: null
573
+ value: null
574
+ ddp_broadcast_buffers:
575
+ desc: null
576
+ value: null
577
+ dataloader_pin_memory:
578
+ desc: null
579
+ value: true
580
+ dataloader_persistent_workers:
581
+ desc: null
582
+ value: false
583
+ skip_memory_metrics:
584
+ desc: null
585
+ value: true
586
+ use_legacy_prediction_loop:
587
+ desc: null
588
+ value: false
589
+ push_to_hub:
590
+ desc: null
591
+ value: false
592
+ resume_from_checkpoint:
593
+ desc: null
594
+ value: null
595
+ hub_model_id:
596
+ desc: null
597
+ value: null
598
+ hub_strategy:
599
+ desc: null
600
+ value: every_save
601
+ hub_token:
602
+ desc: null
603
+ value: <HUB_TOKEN>
604
+ hub_private_repo:
605
+ desc: null
606
+ value: false
607
+ hub_always_push:
608
+ desc: null
609
+ value: false
610
+ gradient_checkpointing:
611
+ desc: null
612
+ value: true
613
+ gradient_checkpointing_kwargs:
614
+ desc: null
615
+ value: null
616
+ include_inputs_for_metrics:
617
+ desc: null
618
+ value: false
619
+ eval_do_concat_batches:
620
+ desc: null
621
+ value: true
622
+ fp16_backend:
623
+ desc: null
624
+ value: auto
625
+ evaluation_strategy:
626
+ desc: null
627
+ value: null
628
+ push_to_hub_model_id:
629
+ desc: null
630
+ value: null
631
+ push_to_hub_organization:
632
+ desc: null
633
+ value: null
634
+ push_to_hub_token:
635
+ desc: null
636
+ value: <PUSH_TO_HUB_TOKEN>
637
+ mp_parameters:
638
+ desc: null
639
+ value: ''
640
+ auto_find_batch_size:
641
+ desc: null
642
+ value: false
643
+ full_determinism:
644
+ desc: null
645
+ value: false
646
+ torchdynamo:
647
+ desc: null
648
+ value: null
649
+ ray_scope:
650
+ desc: null
651
+ value: last
652
+ ddp_timeout:
653
+ desc: null
654
+ value: 1800
655
+ torch_compile:
656
+ desc: null
657
+ value: false
658
+ torch_compile_backend:
659
+ desc: null
660
+ value: null
661
+ torch_compile_mode:
662
+ desc: null
663
+ value: null
664
+ dispatch_batches:
665
+ desc: null
666
+ value: null
667
+ split_batches:
668
+ desc: null
669
+ value: null
670
+ include_tokens_per_second:
671
+ desc: null
672
+ value: false
673
+ include_num_input_tokens_seen:
674
+ desc: null
675
+ value: false
676
+ neftune_noise_alpha:
677
+ desc: null
678
+ value: null
679
+ optim_target_modules:
680
+ desc: null
681
+ value: null
682
+ batch_eval_metrics:
683
+ desc: null
684
+ value: false
685
+ eval_on_start:
686
+ desc: null
687
+ value: false
688
+ eval_use_gather_object:
689
+ desc: null
690
+ value: false
691
+ min_lr_ratio:
692
+ desc: null
693
+ value: 0.1
694
+ cuda_empty_cache:
695
+ desc: null
696
+ value: true
697
+ streaming_dataset:
698
+ desc: null
699
+ value: true
700
+ seq_parallel_size:
701
+ desc: null
702
+ value: 8
703
+ model/num_parameters:
704
+ desc: null
705
+ value: 1003782656
wandb/run-20241226_145403-c7ovtvny/files/output.log ADDED
The diff for this file is too large to render. See raw diff
 
wandb/run-20241226_145403-c7ovtvny/files/requirements.txt ADDED
@@ -0,0 +1,242 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Brotli==1.1.0
2
+ GitPython==3.1.43
3
+ Jinja2==3.1.4
4
+ MarkupSafe==3.0.2
5
+ PyJWT==2.10.0
6
+ PyNaCl==1.5.0
7
+ PyYAML==6.0.2
8
+ Pygments==2.18.0
9
+ accelerate==0.32.1
10
+ aiohappyeyeballs==2.4.3
11
+ aiohttp==3.11.2
12
+ aioprometheus==23.12.0
13
+ aiosignal==1.3.1
14
+ annotated-types==0.7.0
15
+ anthropic==0.39.0
16
+ anyio==4.6.2.post1
17
+ argcomplete==3.5.1
18
+ arrow==1.3.0
19
+ asttokens==2.4.1
20
+ async-timeout==5.0.1
21
+ attrs==24.2.0
22
+ autocommand==2.2.2
23
+ azure-core==1.32.0
24
+ azure-identity==1.19.0
25
+ azure-storage-blob==12.24.0
26
+ azure-storage-file-datalake==12.18.0
27
+ backoff==2.2.1
28
+ backports.tarfile==1.2.0
29
+ bcrypt==4.2.0
30
+ blobfile==3.0.0
31
+ boto3==1.35.63
32
+ botocore==1.35.63
33
+ cachetools==5.5.0
34
+ certifi==2024.8.30
35
+ cffi==1.17.1
36
+ charset-normalizer==3.4.0
37
+ circuitbreaker==2.0.0
38
+ click==8.1.7
39
+ cloudpickle==3.1.0
40
+ comm==0.2.2
41
+ compressed-tensors==0.8.0
42
+ contourpy==1.3.1
43
+ cramjam==2.9.0
44
+ cryptography==43.0.3
45
+ cycler==0.12.1
46
+ datasets==2.20.0
47
+ debugpy==1.8.11
48
+ decorator==5.1.1
49
+ dill==0.3.8
50
+ diskcache==5.6.3
51
+ distro==1.9.0
52
+ docker-pycreds==0.4.0
53
+ docstring_parser==0.16
54
+ einops==0.8.0
55
+ exceptiongroup==1.2.2
56
+ executing==2.1.0
57
+ fastapi==0.115.5
58
+ filelock==3.16.1
59
+ flash-attn==2.6.1
60
+ fonttools==4.55.0
61
+ frozenlist==1.5.0
62
+ fsspec==2024.5.0
63
+ gguf==0.10.0
64
+ gitdb==4.0.11
65
+ google-api-core==2.23.0
66
+ google-auth==2.36.0
67
+ google-cloud-aiplatform==1.71.1
68
+ google-cloud-bigquery==3.27.0
69
+ google-cloud-core==2.4.1
70
+ google-cloud-resource-manager==1.13.1
71
+ google-cloud-storage==2.10.0
72
+ google-crc32c==1.6.0
73
+ google-resumable-media==2.7.2
74
+ googleapis-common-protos==1.66.0
75
+ gql==3.5.0
76
+ graphql-core==3.2.5
77
+ grpc-google-iam-v1==0.13.1
78
+ grpcio-status==1.62.3
79
+ grpcio==1.68.0
80
+ h11==0.14.0
81
+ httpcore==1.0.7
82
+ httptools==0.6.4
83
+ httpx==0.27.2
84
+ huggingface-hub==0.26.2
85
+ idna==3.10
86
+ importlib_metadata==8.0.0
87
+ importlib_metadata==8.5.0
88
+ inflect==7.3.1
89
+ interegular==0.3.3
90
+ ipykernel==6.29.5
91
+ ipython==8.18.0
92
+ isodate==0.7.2
93
+ jaraco.collections==5.1.0
94
+ jaraco.context==5.3.0
95
+ jaraco.functools==4.0.1
96
+ jaraco.text==3.12.1
97
+ jedi==0.19.2
98
+ jiter==0.7.1
99
+ jmespath==1.0.1
100
+ jsonschema-specifications==2024.10.1
101
+ jsonschema==4.23.0
102
+ jupyter_client==8.6.3
103
+ jupyter_core==5.7.2
104
+ kiwisolver==1.4.7
105
+ lark==1.2.2
106
+ llvmlite==0.43.0
107
+ lm-format-enforcer==0.10.9
108
+ lxml==5.3.0
109
+ markdown-it-py==3.0.0
110
+ matplotlib-inline==0.1.7
111
+ matplotlib==3.9.2
112
+ mdurl==0.1.2
113
+ more-itertools==10.3.0
114
+ mosaicml-cli==0.5.34
115
+ mosaicml-streaming==0.8.1
116
+ mpmath==1.3.0
117
+ msal-extensions==1.2.0
118
+ msal==1.31.1
119
+ msgpack==1.1.0
120
+ msgspec==0.18.6
121
+ multidict==6.1.0
122
+ multiprocess==0.70.16
123
+ nest-asyncio==1.6.0
124
+ networkx==3.4.2
125
+ ninja==1.11.1.1
126
+ numba==0.60.0
127
+ numpy==1.26.3
128
+ nvidia-cublas-cu12==12.1.3.1
129
+ nvidia-cuda-cupti-cu12==12.1.105
130
+ nvidia-cuda-nvrtc-cu12==12.1.105
131
+ nvidia-cuda-runtime-cu12==12.1.105
132
+ nvidia-cudnn-cu12==9.1.0.70
133
+ nvidia-cufft-cu12==11.0.2.54
134
+ nvidia-curand-cu12==10.3.2.106
135
+ nvidia-cusolver-cu12==11.4.5.107
136
+ nvidia-cusparse-cu12==12.1.0.106
137
+ nvidia-ml-py==12.560.30
138
+ nvidia-nccl-cu12==2.20.5
139
+ nvidia-nvjitlink-cu12==12.4.127
140
+ nvidia-nvtx-cu12==12.1.105
141
+ oci==2.138.1
142
+ openai==1.54.5
143
+ opencv-python-headless==4.10.0.84
144
+ orjson==3.10.11
145
+ outlines==0.0.46
146
+ packaging==24.1
147
+ packaging==24.2
148
+ pandas==2.2.1
149
+ paramiko==3.5.0
150
+ parso==0.8.4
151
+ partial-json-parser==0.2.1.1.post4
152
+ pexpect==4.9.0
153
+ pillow==10.4.0
154
+ pip==24.3.1
155
+ platformdirs==4.2.2
156
+ platformdirs==4.3.6
157
+ portalocker==2.10.1
158
+ prometheus-fastapi-instrumentator==7.0.0
159
+ prometheus_client==0.21.0
160
+ prompt-toolkit==3.0.36
161
+ propcache==0.2.0
162
+ proto-plus==1.25.0
163
+ protobuf==4.25.3
164
+ psutil==6.1.0
165
+ ptyprocess==0.7.0
166
+ pure_eval==0.2.3
167
+ py-cpuinfo==9.0.0
168
+ pyOpenSSL==24.2.1
169
+ pyairports==2.1.1
170
+ pyarrow-hotfix==0.6
171
+ pyarrow==18.0.0
172
+ pyasn1==0.6.1
173
+ pyasn1_modules==0.4.1
174
+ pycountry==24.6.1
175
+ pycparser==2.22
176
+ pycryptodomex==3.21.0
177
+ pydantic==2.9.2
178
+ pydantic_core==2.23.4
179
+ pyparsing==3.2.0
180
+ python-dateutil==2.9.0
181
+ python-dotenv==1.0.1
182
+ python-snappy==0.7.3
183
+ pytz==2024.2
184
+ pyzmq==26.2.0
185
+ quantile-python==1.1
186
+ questionary==2.0.1
187
+ ray==2.39.0
188
+ referencing==0.35.1
189
+ regex==2023.12.25
190
+ requests==2.32.3
191
+ rich==13.9.4
192
+ rotary-emb==0.5.2
193
+ rpds-py==0.21.0
194
+ rsa==4.9
195
+ ruamel.yaml.clib==0.2.12
196
+ ruamel.yaml==0.18.6
197
+ s3transfer==0.10.3
198
+ safetensors==0.4.5
199
+ sentencepiece==0.1.99
200
+ sentry-sdk==2.18.0
201
+ setproctitle==1.3.4
202
+ setuptools==75.6.0
203
+ shapely==2.0.6
204
+ six==1.16.0
205
+ smmap==5.0.1
206
+ sniffio==1.3.1
207
+ stack-data==0.6.3
208
+ starlette==0.41.3
209
+ sympy==1.13.1
210
+ tiktoken==0.7.0
211
+ tokenizers==0.19.1
212
+ tomli==2.0.1
213
+ torch==2.4.1
214
+ torchvision==0.19.1
215
+ tornado==6.4.1
216
+ tqdm==4.66.4
217
+ traitlets==5.14.3
218
+ transformers==4.44.2
219
+ triton==3.0.0
220
+ typeguard==4.3.0
221
+ types-python-dateutil==2.9.0.20241003
222
+ typing_extensions==4.12.2
223
+ typing_extensions==4.12.2
224
+ tzdata==2024.2
225
+ urllib3==2.2.3
226
+ uvicorn==0.32.0
227
+ uvloop==0.21.0
228
+ validators==0.34.0
229
+ vertexai==1.71.1
230
+ wandb==0.17.3
231
+ watchfiles==0.24.0
232
+ wcwidth==0.2.13
233
+ websockets==11.0.3
234
+ wheel==0.43.0
235
+ wheel==0.45.1
236
+ xformers==0.0.28.post1
237
+ xxhash==3.5.0
238
+ yarl==1.17.2
239
+ zipp==3.19.2
240
+ zipp==3.21.0
241
+ zstandard==0.22.0
242
+ zstd==1.5.5.1
wandb/run-20241226_145403-c7ovtvny/files/wandb-metadata.json ADDED
@@ -0,0 +1,705 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-6.8.0-48-generic-x86_64-with-glibc2.39",
3
+ "python": "3.10.0",
4
+ "heartbeatAt": "2024-12-26T14:54:03.533915",
5
+ "startedAt": "2024-12-26T14:54:03.029672",
6
+ "docker": null,
7
+ "cuda": null,
8
+ "args": [
9
+ "--model_family",
10
+ "llama",
11
+ "--apply_instruct_masks",
12
+ "--token_scaled_loss",
13
+ "--seq_parallel_size",
14
+ "8",
15
+ "--report_to",
16
+ "wandb",
17
+ "--do_train",
18
+ "--model_name_or_path",
19
+ "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
20
+ "--config_name",
21
+ "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
22
+ "--tokenizer_name",
23
+ "/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/",
24
+ "--run_name",
25
+ "balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_",
26
+ "--output_dir",
27
+ "/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_",
28
+ "--config_overrides_json",
29
+ "",
30
+ "--gradient_accumulation_steps",
31
+ "2",
32
+ "--per_device_train_batch_size",
33
+ "1",
34
+ "--bf16",
35
+ "--learning_rate",
36
+ "1e-6",
37
+ "--min_lr_ratio",
38
+ "0.1",
39
+ "--lr_scheduler_type",
40
+ "cosine",
41
+ "--max_grad_norm",
42
+ "1.0",
43
+ "--adam_beta1",
44
+ "0.9",
45
+ "--adam_beta2",
46
+ "0.95",
47
+ "--weight_decay",
48
+ "0.1",
49
+ "--warmup_ratio",
50
+ "0.05",
51
+ "--optim",
52
+ "adamw_torch",
53
+ "--logging_steps",
54
+ "1",
55
+ "--log_level",
56
+ "info",
57
+ "--save_steps",
58
+ "200",
59
+ "--dataloader_num_workers",
60
+ "1",
61
+ "--disable_tqdm",
62
+ "true",
63
+ "--use_fast_tokenizer",
64
+ "false",
65
+ "--remove_unused_columns",
66
+ "false",
67
+ "--ddp_find_unused_parameters",
68
+ "false",
69
+ "--fsdp",
70
+ "auto_wrap offload",
71
+ "--gradient_checkpointing",
72
+ "--tokenized_mds_train",
73
+ "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/data/ft/bookclaim_balanced_pack_complete",
74
+ "--cuda_empty_cache",
75
+ "--num_train_epochs",
76
+ "1"
77
+ ],
78
+ "state": "running",
79
+ "program": "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py",
80
+ "codePathLocal": "finetune.py",
81
+ "codePath": "prolong-final/finetune.py",
82
+ "git": {
83
+ "remote": "https://github.com/chtmp223/BookGen-dev.git",
84
+ "commit": "438e68ae65a707227d28baa427c5f6fdb0932c7b"
85
+ },
86
+ "email": "[email protected]",
87
+ "root": "/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev",
88
+ "host": "gpu021",
89
+ "username": "ctpham_umass_edu",
90
+ "executable": "/scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final/bin/python3.10",
91
+ "cpu_count": 112,
92
+ "cpu_count_logical": 112,
93
+ "cpu_freq": {
94
+ "current": 903.8299553571429,
95
+ "min": 800.0,
96
+ "max": 3800.0
97
+ },
98
+ "cpu_freq_per_core": [
99
+ {
100
+ "current": 790.24,
101
+ "min": 800.0,
102
+ "max": 3800.0
103
+ },
104
+ {
105
+ "current": 800.0,
106
+ "min": 800.0,
107
+ "max": 3800.0
108
+ },
109
+ {
110
+ "current": 1600.0,
111
+ "min": 800.0,
112
+ "max": 3800.0
113
+ },
114
+ {
115
+ "current": 800.0,
116
+ "min": 800.0,
117
+ "max": 3800.0
118
+ },
119
+ {
120
+ "current": 1700.0,
121
+ "min": 800.0,
122
+ "max": 3800.0
123
+ },
124
+ {
125
+ "current": 784.117,
126
+ "min": 800.0,
127
+ "max": 3800.0
128
+ },
129
+ {
130
+ "current": 800.0,
131
+ "min": 800.0,
132
+ "max": 3800.0
133
+ },
134
+ {
135
+ "current": 800.0,
136
+ "min": 800.0,
137
+ "max": 3800.0
138
+ },
139
+ {
140
+ "current": 800.0,
141
+ "min": 800.0,
142
+ "max": 3800.0
143
+ },
144
+ {
145
+ "current": 787.786,
146
+ "min": 800.0,
147
+ "max": 3800.0
148
+ },
149
+ {
150
+ "current": 1800.0,
151
+ "min": 800.0,
152
+ "max": 3800.0
153
+ },
154
+ {
155
+ "current": 800.0,
156
+ "min": 800.0,
157
+ "max": 3800.0
158
+ },
159
+ {
160
+ "current": 1000.0,
161
+ "min": 800.0,
162
+ "max": 3800.0
163
+ },
164
+ {
165
+ "current": 800.0,
166
+ "min": 800.0,
167
+ "max": 3800.0
168
+ },
169
+ {
170
+ "current": 800.0,
171
+ "min": 800.0,
172
+ "max": 3800.0
173
+ },
174
+ {
175
+ "current": 800.0,
176
+ "min": 800.0,
177
+ "max": 3800.0
178
+ },
179
+ {
180
+ "current": 800.0,
181
+ "min": 800.0,
182
+ "max": 3800.0
183
+ },
184
+ {
185
+ "current": 800.0,
186
+ "min": 800.0,
187
+ "max": 3800.0
188
+ },
189
+ {
190
+ "current": 800.0,
191
+ "min": 800.0,
192
+ "max": 3800.0
193
+ },
194
+ {
195
+ "current": 800.0,
196
+ "min": 800.0,
197
+ "max": 3800.0
198
+ },
199
+ {
200
+ "current": 800.0,
201
+ "min": 800.0,
202
+ "max": 3800.0
203
+ },
204
+ {
205
+ "current": 800.0,
206
+ "min": 800.0,
207
+ "max": 3800.0
208
+ },
209
+ {
210
+ "current": 892.512,
211
+ "min": 800.0,
212
+ "max": 3800.0
213
+ },
214
+ {
215
+ "current": 800.0,
216
+ "min": 800.0,
217
+ "max": 3800.0
218
+ },
219
+ {
220
+ "current": 1400.0,
221
+ "min": 800.0,
222
+ "max": 3800.0
223
+ },
224
+ {
225
+ "current": 800.0,
226
+ "min": 800.0,
227
+ "max": 3800.0
228
+ },
229
+ {
230
+ "current": 800.0,
231
+ "min": 800.0,
232
+ "max": 3800.0
233
+ },
234
+ {
235
+ "current": 800.0,
236
+ "min": 800.0,
237
+ "max": 3800.0
238
+ },
239
+ {
240
+ "current": 790.711,
241
+ "min": 800.0,
242
+ "max": 3800.0
243
+ },
244
+ {
245
+ "current": 800.0,
246
+ "min": 800.0,
247
+ "max": 3800.0
248
+ },
249
+ {
250
+ "current": 800.0,
251
+ "min": 800.0,
252
+ "max": 3800.0
253
+ },
254
+ {
255
+ "current": 800.0,
256
+ "min": 800.0,
257
+ "max": 3800.0
258
+ },
259
+ {
260
+ "current": 790.69,
261
+ "min": 800.0,
262
+ "max": 3800.0
263
+ },
264
+ {
265
+ "current": 800.0,
266
+ "min": 800.0,
267
+ "max": 3800.0
268
+ },
269
+ {
270
+ "current": 800.0,
271
+ "min": 800.0,
272
+ "max": 3800.0
273
+ },
274
+ {
275
+ "current": 800.0,
276
+ "min": 800.0,
277
+ "max": 3800.0
278
+ },
279
+ {
280
+ "current": 800.0,
281
+ "min": 800.0,
282
+ "max": 3800.0
283
+ },
284
+ {
285
+ "current": 800.0,
286
+ "min": 800.0,
287
+ "max": 3800.0
288
+ },
289
+ {
290
+ "current": 800.0,
291
+ "min": 800.0,
292
+ "max": 3800.0
293
+ },
294
+ {
295
+ "current": 800.0,
296
+ "min": 800.0,
297
+ "max": 3800.0
298
+ },
299
+ {
300
+ "current": 1300.0,
301
+ "min": 800.0,
302
+ "max": 3800.0
303
+ },
304
+ {
305
+ "current": 800.0,
306
+ "min": 800.0,
307
+ "max": 3800.0
308
+ },
309
+ {
310
+ "current": 2400.0,
311
+ "min": 800.0,
312
+ "max": 3800.0
313
+ },
314
+ {
315
+ "current": 800.0,
316
+ "min": 800.0,
317
+ "max": 3800.0
318
+ },
319
+ {
320
+ "current": 1100.0,
321
+ "min": 800.0,
322
+ "max": 3800.0
323
+ },
324
+ {
325
+ "current": 800.0,
326
+ "min": 800.0,
327
+ "max": 3800.0
328
+ },
329
+ {
330
+ "current": 1782.468,
331
+ "min": 800.0,
332
+ "max": 3800.0
333
+ },
334
+ {
335
+ "current": 800.0,
336
+ "min": 800.0,
337
+ "max": 3800.0
338
+ },
339
+ {
340
+ "current": 1100.0,
341
+ "min": 800.0,
342
+ "max": 3800.0
343
+ },
344
+ {
345
+ "current": 800.0,
346
+ "min": 800.0,
347
+ "max": 3800.0
348
+ },
349
+ {
350
+ "current": 1700.0,
351
+ "min": 800.0,
352
+ "max": 3800.0
353
+ },
354
+ {
355
+ "current": 800.0,
356
+ "min": 800.0,
357
+ "max": 3800.0
358
+ },
359
+ {
360
+ "current": 800.0,
361
+ "min": 800.0,
362
+ "max": 3800.0
363
+ },
364
+ {
365
+ "current": 800.0,
366
+ "min": 800.0,
367
+ "max": 3800.0
368
+ },
369
+ {
370
+ "current": 800.0,
371
+ "min": 800.0,
372
+ "max": 3800.0
373
+ },
374
+ {
375
+ "current": 800.0,
376
+ "min": 800.0,
377
+ "max": 3800.0
378
+ },
379
+ {
380
+ "current": 800.0,
381
+ "min": 800.0,
382
+ "max": 3800.0
383
+ },
384
+ {
385
+ "current": 800.0,
386
+ "min": 800.0,
387
+ "max": 3800.0
388
+ },
389
+ {
390
+ "current": 800.0,
391
+ "min": 800.0,
392
+ "max": 3800.0
393
+ },
394
+ {
395
+ "current": 800.0,
396
+ "min": 800.0,
397
+ "max": 3800.0
398
+ },
399
+ {
400
+ "current": 800.0,
401
+ "min": 800.0,
402
+ "max": 3800.0
403
+ },
404
+ {
405
+ "current": 800.0,
406
+ "min": 800.0,
407
+ "max": 3800.0
408
+ },
409
+ {
410
+ "current": 1000.0,
411
+ "min": 800.0,
412
+ "max": 3800.0
413
+ },
414
+ {
415
+ "current": 800.0,
416
+ "min": 800.0,
417
+ "max": 3800.0
418
+ },
419
+ {
420
+ "current": 800.0,
421
+ "min": 800.0,
422
+ "max": 3800.0
423
+ },
424
+ {
425
+ "current": 800.0,
426
+ "min": 800.0,
427
+ "max": 3800.0
428
+ },
429
+ {
430
+ "current": 800.0,
431
+ "min": 800.0,
432
+ "max": 3800.0
433
+ },
434
+ {
435
+ "current": 784.039,
436
+ "min": 800.0,
437
+ "max": 3800.0
438
+ },
439
+ {
440
+ "current": 782.714,
441
+ "min": 800.0,
442
+ "max": 3800.0
443
+ },
444
+ {
445
+ "current": 783.793,
446
+ "min": 800.0,
447
+ "max": 3800.0
448
+ },
449
+ {
450
+ "current": 800.0,
451
+ "min": 800.0,
452
+ "max": 3800.0
453
+ },
454
+ {
455
+ "current": 800.0,
456
+ "min": 800.0,
457
+ "max": 3800.0
458
+ },
459
+ {
460
+ "current": 800.0,
461
+ "min": 800.0,
462
+ "max": 3800.0
463
+ },
464
+ {
465
+ "current": 800.0,
466
+ "min": 800.0,
467
+ "max": 3800.0
468
+ },
469
+ {
470
+ "current": 800.0,
471
+ "min": 800.0,
472
+ "max": 3800.0
473
+ },
474
+ {
475
+ "current": 800.0,
476
+ "min": 800.0,
477
+ "max": 3800.0
478
+ },
479
+ {
480
+ "current": 800.0,
481
+ "min": 800.0,
482
+ "max": 3800.0
483
+ },
484
+ {
485
+ "current": 800.0,
486
+ "min": 800.0,
487
+ "max": 3800.0
488
+ },
489
+ {
490
+ "current": 800.0,
491
+ "min": 800.0,
492
+ "max": 3800.0
493
+ },
494
+ {
495
+ "current": 800.0,
496
+ "min": 800.0,
497
+ "max": 3800.0
498
+ },
499
+ {
500
+ "current": 800.0,
501
+ "min": 800.0,
502
+ "max": 3800.0
503
+ },
504
+ {
505
+ "current": 800.0,
506
+ "min": 800.0,
507
+ "max": 3800.0
508
+ },
509
+ {
510
+ "current": 800.0,
511
+ "min": 800.0,
512
+ "max": 3800.0
513
+ },
514
+ {
515
+ "current": 800.0,
516
+ "min": 800.0,
517
+ "max": 3800.0
518
+ },
519
+ {
520
+ "current": 800.0,
521
+ "min": 800.0,
522
+ "max": 3800.0
523
+ },
524
+ {
525
+ "current": 800.0,
526
+ "min": 800.0,
527
+ "max": 3800.0
528
+ },
529
+ {
530
+ "current": 800.0,
531
+ "min": 800.0,
532
+ "max": 3800.0
533
+ },
534
+ {
535
+ "current": 800.0,
536
+ "min": 800.0,
537
+ "max": 3800.0
538
+ },
539
+ {
540
+ "current": 800.0,
541
+ "min": 800.0,
542
+ "max": 3800.0
543
+ },
544
+ {
545
+ "current": 800.0,
546
+ "min": 800.0,
547
+ "max": 3800.0
548
+ },
549
+ {
550
+ "current": 800.0,
551
+ "min": 800.0,
552
+ "max": 3800.0
553
+ },
554
+ {
555
+ "current": 800.0,
556
+ "min": 800.0,
557
+ "max": 3800.0
558
+ },
559
+ {
560
+ "current": 800.0,
561
+ "min": 800.0,
562
+ "max": 3800.0
563
+ },
564
+ {
565
+ "current": 800.0,
566
+ "min": 800.0,
567
+ "max": 3800.0
568
+ },
569
+ {
570
+ "current": 800.0,
571
+ "min": 800.0,
572
+ "max": 3800.0
573
+ },
574
+ {
575
+ "current": 794.544,
576
+ "min": 800.0,
577
+ "max": 3800.0
578
+ },
579
+ {
580
+ "current": 800.0,
581
+ "min": 800.0,
582
+ "max": 3800.0
583
+ },
584
+ {
585
+ "current": 784.441,
586
+ "min": 800.0,
587
+ "max": 3800.0
588
+ },
589
+ {
590
+ "current": 800.0,
591
+ "min": 800.0,
592
+ "max": 3800.0
593
+ },
594
+ {
595
+ "current": 800.0,
596
+ "min": 800.0,
597
+ "max": 3800.0
598
+ },
599
+ {
600
+ "current": 800.0,
601
+ "min": 800.0,
602
+ "max": 3800.0
603
+ },
604
+ {
605
+ "current": 800.0,
606
+ "min": 800.0,
607
+ "max": 3800.0
608
+ },
609
+ {
610
+ "current": 800.0,
611
+ "min": 800.0,
612
+ "max": 3800.0
613
+ },
614
+ {
615
+ "current": 800.0,
616
+ "min": 800.0,
617
+ "max": 3800.0
618
+ },
619
+ {
620
+ "current": 800.0,
621
+ "min": 800.0,
622
+ "max": 3800.0
623
+ },
624
+ {
625
+ "current": 800.0,
626
+ "min": 800.0,
627
+ "max": 3800.0
628
+ },
629
+ {
630
+ "current": 800.0,
631
+ "min": 800.0,
632
+ "max": 3800.0
633
+ },
634
+ {
635
+ "current": 800.0,
636
+ "min": 800.0,
637
+ "max": 3800.0
638
+ },
639
+ {
640
+ "current": 800.0,
641
+ "min": 800.0,
642
+ "max": 3800.0
643
+ },
644
+ {
645
+ "current": 800.0,
646
+ "min": 800.0,
647
+ "max": 3800.0
648
+ },
649
+ {
650
+ "current": 800.0,
651
+ "min": 800.0,
652
+ "max": 3800.0
653
+ },
654
+ {
655
+ "current": 800.0,
656
+ "min": 800.0,
657
+ "max": 3800.0
658
+ }
659
+ ],
660
+ "disk": {
661
+ "/": {
662
+ "total": 438.487850189209,
663
+ "used": 16.265323638916016
664
+ }
665
+ },
666
+ "gpu": "NVIDIA A100-SXM4-80GB",
667
+ "gpu_count": 8,
668
+ "gpu_devices": [
669
+ {
670
+ "name": "NVIDIA A100-SXM4-80GB",
671
+ "memory_total": 85899345920
672
+ },
673
+ {
674
+ "name": "NVIDIA A100-SXM4-80GB",
675
+ "memory_total": 85899345920
676
+ },
677
+ {
678
+ "name": "NVIDIA A100-SXM4-80GB",
679
+ "memory_total": 85899345920
680
+ },
681
+ {
682
+ "name": "NVIDIA A100-SXM4-80GB",
683
+ "memory_total": 85899345920
684
+ },
685
+ {
686
+ "name": "NVIDIA A100-SXM4-80GB",
687
+ "memory_total": 85899345920
688
+ },
689
+ {
690
+ "name": "NVIDIA A100-SXM4-80GB",
691
+ "memory_total": 85899345920
692
+ },
693
+ {
694
+ "name": "NVIDIA A100-SXM4-80GB",
695
+ "memory_total": 85899345920
696
+ },
697
+ {
698
+ "name": "NVIDIA A100-SXM4-80GB",
699
+ "memory_total": 85899345920
700
+ }
701
+ ],
702
+ "memory": {
703
+ "total": 2015.3287200927734
704
+ }
705
+ }
wandb/run-20241226_145403-c7ovtvny/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"train/loss": 0.4968, "train/grad_norm": 16.78160285949707, "train/learning_rate": 1.4057417934619453e-07, "train/epoch": 0.21969080553295361, "train/num_input_tokens_seen": 6731857920, "train/global_step": 3210, "_timestamp": 1735250926.6301687, "_runtime": 26083.580728769302, "_step": 809}
wandb/run-20241226_145403-c7ovtvny/logs/debug-internal.log ADDED
The diff for this file is too large to render. See raw diff
 
wandb/run-20241226_145403-c7ovtvny/logs/debug.log ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2024-12-26 14:54:03,041 INFO MainThread:821408 [wandb_setup.py:_flush():76] Current SDK version is 0.17.3
2
+ 2024-12-26 14:54:03,041 INFO MainThread:821408 [wandb_setup.py:_flush():76] Configure stats pid to 821408
3
+ 2024-12-26 14:54:03,041 INFO MainThread:821408 [wandb_setup.py:_flush():76] Loading settings from /home/ctpham_umass_edu/.config/wandb/settings
4
+ 2024-12-26 14:54:03,041 INFO MainThread:821408 [wandb_setup.py:_flush():76] Loading settings from /work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/wandb/settings
5
+ 2024-12-26 14:54:03,041 INFO MainThread:821408 [wandb_setup.py:_flush():76] Loading settings from environment variables: {'root_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'project': 'prolong', 'api_key': '***REDACTED***', 'mode': 'online'}
6
+ 2024-12-26 14:54:03,042 INFO MainThread:821408 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
7
+ 2024-12-26 14:54:03,042 INFO MainThread:821408 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'prolong-final/finetune.py', 'program_abspath': '/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py', 'program': '/work/pi_miyyer_umass_edu/ctpham/BookClaim-dev/prolong-final/finetune.py'}
8
+ 2024-12-26 14:54:03,042 INFO MainThread:821408 [wandb_setup.py:_flush():76] Applying login settings: {}
9
+ 2024-12-26 14:54:03,042 INFO MainThread:821408 [wandb_init.py:_log_setup():520] Logging user logs to /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/wandb/run-20241226_145403-c7ovtvny/logs/debug.log
10
+ 2024-12-26 14:54:03,042 INFO MainThread:821408 [wandb_init.py:_log_setup():521] Logging internal logs to /scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/wandb/run-20241226_145403-c7ovtvny/logs/debug-internal.log
11
+ 2024-12-26 14:54:03,042 INFO MainThread:821408 [wandb_init.py:init():560] calling init triggers
12
+ 2024-12-26 14:54:03,042 INFO MainThread:821408 [wandb_init.py:init():567] wandb.init called with sweep_config: {}
13
+ config: {}
14
+ 2024-12-26 14:54:03,042 INFO MainThread:821408 [wandb_init.py:init():610] starting backend
15
+ 2024-12-26 14:54:03,042 INFO MainThread:821408 [wandb_init.py:init():614] setting up manager
16
+ 2024-12-26 14:54:03,045 INFO MainThread:821408 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
17
+ 2024-12-26 14:54:03,048 INFO MainThread:821408 [wandb_init.py:init():622] backend started and connected
18
+ 2024-12-26 14:54:03,057 INFO MainThread:821408 [wandb_init.py:init():711] updated telemetry
19
+ 2024-12-26 14:54:03,100 INFO MainThread:821408 [wandb_init.py:init():744] communicating run to backend with 90.0 second timeout
20
+ 2024-12-26 14:54:03,347 INFO MainThread:821408 [wandb_run.py:_on_init():2402] communicating current version
21
+ 2024-12-26 14:54:03,407 INFO MainThread:821408 [wandb_run.py:_on_init():2411] got version response upgrade_message: "wandb version 0.19.1 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
22
+
23
+ 2024-12-26 14:54:03,407 INFO MainThread:821408 [wandb_init.py:init():795] starting run threads in backend
24
+ 2024-12-26 14:54:11,326 INFO MainThread:821408 [wandb_run.py:_console_start():2380] atexit reg
25
+ 2024-12-26 14:54:11,326 INFO MainThread:821408 [wandb_run.py:_redirect():2235] redirect: wrap_raw
26
+ 2024-12-26 14:54:11,326 INFO MainThread:821408 [wandb_run.py:_redirect():2300] Wrapping output streams.
27
+ 2024-12-26 14:54:11,326 INFO MainThread:821408 [wandb_run.py:_redirect():2325] Redirects installed.
28
+ 2024-12-26 14:54:11,328 INFO MainThread:821408 [wandb_init.py:init():838] run started, returning control to user process
29
+ 2024-12-26 14:54:11,330 INFO MainThread:821408 [wandb_run.py:_config_callback():1382] config_cb None None {'vocab_size': 128256, 'max_position_embeddings': 524288, 'hidden_size': 4096, 'intermediate_size': 14336, 'num_hidden_layers': 32, 'num_attention_heads': 32, 'num_key_value_heads': 8, 'hidden_act': 'silu', 'initializer_range': 0.02, 'rms_norm_eps': 1e-05, 'pretraining_tp': 1, 'use_cache': True, 'rope_theta': 128000000.0, 'rope_scaling': None, 'attention_bias': False, 'attention_dropout': 0.0, 'mlp_bias': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['LlamaForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 128000, 'pad_token_id': 0, 'eos_token_id': 128009, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': '/scratch3/workspace/ctpham_umass_edu-ft/models/Llama-3-8B-ProLong-512k-Base/', 'transformers_version': '4.44.2', 'model_type': 'llama', 'output_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'overwrite_output_dir': False, 'do_train': True, 'do_eval': False, 'do_predict': False, 'eval_strategy': 'no', 'prediction_loss_only': False, 'per_device_train_batch_size': 1, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 1e-06, 'weight_decay': 0.1, 'adam_beta1': 0.9, 'adam_beta2': 0.95, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.05, 'warmup_steps': 0, 'log_level': 'info', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/scratch3/workspace/ctpham_umass_edu-ft/balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_/runs/Dec26_14-47-22_gpu021', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1.0, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 200, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': None, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': None, 'dataloader_num_workers': 1, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': 'balanced_prolong-512K-base_bsz-16_lr-1e-6_epochs-1_', 'disable_tqdm': True, 'remove_unused_columns': False, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': True, 'fsdp': ['auto_wrap', 'offload'], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'adamw_torch', 'optim_args': None, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': False, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'hub_always_push': False, 'gradient_checkpointing': True, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'eval_use_gather_object': False, 'min_lr_ratio': 0.1, 'cuda_empty_cache': True, 'streaming_dataset': True, 'seq_parallel_size': 8}
30
+ 2024-12-26 14:54:11,333 INFO MainThread:821408 [wandb_config.py:__setitem__():151] config set model/num_parameters = 1003782656 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7d56b9546da0>>
31
+ 2024-12-26 14:54:11,333 INFO MainThread:821408 [wandb_run.py:_config_callback():1382] config_cb model/num_parameters 1003782656 None
wandb/run-20241226_145403-c7ovtvny/run-c7ovtvny.wandb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4515d1b5896835583655b9ecdfda579f01b8079e4399415d206f76bff8f05046
3
+ size 5248016
wandb/run-20241226_224836-fta6xses/files/conda-environment.yaml ADDED
@@ -0,0 +1,232 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ name: /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final
2
+ channels:
3
+ - conda-forge
4
+ dependencies:
5
+ - _libgcc_mutex=0.1=conda_forge
6
+ - _openmp_mutex=4.5=2_gnu
7
+ - bzip2=1.0.8=h4bc722e_7
8
+ - ca-certificates=2024.12.14=hbcca054_0
9
+ - ld_impl_linux-64=2.43=h712a8e2_2
10
+ - libffi=3.4.2=h7f98852_5
11
+ - libgcc=14.2.0=h77fa898_1
12
+ - libgcc-ng=14.2.0=h69a702a_1
13
+ - libgomp=14.2.0=h77fa898_1
14
+ - liblzma=5.6.3=hb9d3cd8_1
15
+ - liblzma-devel=5.6.3=hb9d3cd8_1
16
+ - libnsl=2.0.1=hd590300_0
17
+ - libsqlite=3.47.2=hee588c1_0
18
+ - libuuid=2.38.1=h0b41bf4_0
19
+ - libzlib=1.3.1=hb9d3cd8_2
20
+ - ncurses=6.5=he02047a_1
21
+ - openssl=3.4.0=hb9d3cd8_0
22
+ - pip=24.3.1=pyh8b19718_2
23
+ - python=3.10.0=h543edf9_3_cpython
24
+ - readline=8.2=h8228510_1
25
+ - setuptools=75.6.0=pyhff2d567_1
26
+ - sqlite=3.47.2=h9eae976_0
27
+ - tk=8.6.13=noxft_h4845f30_101
28
+ - wheel=0.45.1=pyhd8ed1ab_1
29
+ - xz=5.6.3=hbcc6ac9_1
30
+ - xz-gpl-tools=5.6.3=hbcc6ac9_1
31
+ - xz-tools=5.6.3=hb9d3cd8_1
32
+ - pip:
33
+ - accelerate==0.32.1
34
+ - aiohappyeyeballs==2.4.3
35
+ - aiohttp==3.11.2
36
+ - aioprometheus==23.12.0
37
+ - aiosignal==1.3.1
38
+ - annotated-types==0.7.0
39
+ - anthropic==0.39.0
40
+ - anyio==4.6.2.post1
41
+ - argcomplete==3.5.1
42
+ - arrow==1.3.0
43
+ - async-timeout==5.0.1
44
+ - attrs==24.2.0
45
+ - azure-core==1.32.0
46
+ - azure-identity==1.19.0
47
+ - azure-storage-blob==12.24.0
48
+ - azure-storage-file-datalake==12.18.0
49
+ - backoff==2.2.1
50
+ - bcrypt==4.2.0
51
+ - blobfile==3.0.0
52
+ - boto3==1.35.63
53
+ - botocore==1.35.63
54
+ - brotli==1.1.0
55
+ - cachetools==5.5.0
56
+ - certifi==2024.8.30
57
+ - cffi==1.17.1
58
+ - charset-normalizer==3.4.0
59
+ - circuitbreaker==2.0.0
60
+ - click==8.1.7
61
+ - cloudpickle==3.1.0
62
+ - compressed-tensors==0.8.0
63
+ - contourpy==1.3.1
64
+ - cramjam==2.9.0
65
+ - cryptography==43.0.3
66
+ - cycler==0.12.1
67
+ - datasets==2.20.0
68
+ - debugpy==1.8.11
69
+ - dill==0.3.8
70
+ - diskcache==5.6.3
71
+ - distro==1.9.0
72
+ - docker-pycreds==0.4.0
73
+ - docstring-parser==0.16
74
+ - einops==0.8.0
75
+ - fastapi==0.115.5
76
+ - filelock==3.16.1
77
+ - flash-attn==2.6.1
78
+ - fonttools==4.55.0
79
+ - frozenlist==1.5.0
80
+ - fsspec==2024.5.0
81
+ - gguf==0.10.0
82
+ - gitdb==4.0.11
83
+ - gitpython==3.1.43
84
+ - google-api-core==2.23.0
85
+ - google-auth==2.36.0
86
+ - google-cloud-aiplatform==1.71.1
87
+ - google-cloud-bigquery==3.27.0
88
+ - google-cloud-core==2.4.1
89
+ - google-cloud-resource-manager==1.13.1
90
+ - google-cloud-storage==2.10.0
91
+ - google-crc32c==1.6.0
92
+ - google-resumable-media==2.7.2
93
+ - googleapis-common-protos==1.66.0
94
+ - gql==3.5.0
95
+ - graphql-core==3.2.5
96
+ - grpc-google-iam-v1==0.13.1
97
+ - grpcio==1.68.0
98
+ - grpcio-status==1.62.3
99
+ - h11==0.14.0
100
+ - httpcore==1.0.7
101
+ - httptools==0.6.4
102
+ - httpx==0.27.2
103
+ - huggingface-hub==0.26.2
104
+ - idna==3.10
105
+ - importlib-metadata==8.5.0
106
+ - interegular==0.3.3
107
+ - ipython==8.18.0
108
+ - isodate==0.7.2
109
+ - jedi==0.19.2
110
+ - jinja2==3.1.4
111
+ - jiter==0.7.1
112
+ - jmespath==1.0.1
113
+ - jsonschema==4.23.0
114
+ - jsonschema-specifications==2024.10.1
115
+ - kiwisolver==1.4.7
116
+ - lark==1.2.2
117
+ - llvmlite==0.43.0
118
+ - lm-format-enforcer==0.10.9
119
+ - lxml==5.3.0
120
+ - markdown-it-py==3.0.0
121
+ - markupsafe==3.0.2
122
+ - matplotlib==3.9.2
123
+ - mdurl==0.1.2
124
+ - mosaicml-cli==0.5.34
125
+ - mosaicml-streaming==0.8.1
126
+ - mpmath==1.3.0
127
+ - msal==1.31.1
128
+ - msal-extensions==1.2.0
129
+ - msgpack==1.1.0
130
+ - msgspec==0.18.6
131
+ - multidict==6.1.0
132
+ - multiprocess==0.70.16
133
+ - networkx==3.4.2
134
+ - ninja==1.11.1.1
135
+ - numba==0.60.0
136
+ - numpy==1.26.3
137
+ - nvidia-cublas-cu12==12.1.3.1
138
+ - nvidia-cuda-cupti-cu12==12.1.105
139
+ - nvidia-cuda-nvrtc-cu12==12.1.105
140
+ - nvidia-cuda-runtime-cu12==12.1.105
141
+ - nvidia-cudnn-cu12==9.1.0.70
142
+ - nvidia-cufft-cu12==11.0.2.54
143
+ - nvidia-curand-cu12==10.3.2.106
144
+ - nvidia-cusolver-cu12==11.4.5.107
145
+ - nvidia-cusparse-cu12==12.1.0.106
146
+ - nvidia-ml-py==12.560.30
147
+ - nvidia-nccl-cu12==2.20.5
148
+ - nvidia-nvjitlink-cu12==12.4.127
149
+ - nvidia-nvtx-cu12==12.1.105
150
+ - oci==2.138.1
151
+ - openai==1.54.5
152
+ - opencv-python-headless==4.10.0.84
153
+ - orjson==3.10.11
154
+ - outlines==0.0.46
155
+ - packaging==24.1
156
+ - pandas==2.2.1
157
+ - paramiko==3.5.0
158
+ - partial-json-parser==0.2.1.1.post4
159
+ - pillow==10.4.0
160
+ - portalocker==2.10.1
161
+ - prometheus-client==0.21.0
162
+ - prometheus-fastapi-instrumentator==7.0.0
163
+ - prompt-toolkit==3.0.36
164
+ - propcache==0.2.0
165
+ - proto-plus==1.25.0
166
+ - protobuf==4.25.3
167
+ - py-cpuinfo==9.0.0
168
+ - pyairports==2.1.1
169
+ - pyarrow==18.0.0
170
+ - pyarrow-hotfix==0.6
171
+ - pyasn1==0.6.1
172
+ - pyasn1-modules==0.4.1
173
+ - pycountry==24.6.1
174
+ - pycparser==2.22
175
+ - pycryptodomex==3.21.0
176
+ - pydantic==2.9.2
177
+ - pydantic-core==2.23.4
178
+ - pyjwt==2.10.0
179
+ - pynacl==1.5.0
180
+ - pyopenssl==24.2.1
181
+ - pyparsing==3.2.0
182
+ - python-dateutil==2.9.0
183
+ - python-dotenv==1.0.1
184
+ - python-snappy==0.7.3
185
+ - pytz==2024.2
186
+ - pyyaml==6.0.2
187
+ - quantile-python==1.1
188
+ - questionary==2.0.1
189
+ - ray==2.39.0
190
+ - referencing==0.35.1
191
+ - regex==2023.12.25
192
+ - requests==2.32.3
193
+ - rich==13.9.4
194
+ - rotary-emb==0.5.2
195
+ - rpds-py==0.21.0
196
+ - rsa==4.9
197
+ - ruamel-yaml==0.18.6
198
+ - ruamel-yaml-clib==0.2.12
199
+ - s3transfer==0.10.3
200
+ - safetensors==0.4.5
201
+ - sentencepiece==0.1.99
202
+ - sentry-sdk==2.18.0
203
+ - setproctitle==1.3.4
204
+ - shapely==2.0.6
205
+ - smmap==5.0.1
206
+ - sniffio==1.3.1
207
+ - starlette==0.41.3
208
+ - sympy==1.13.1
209
+ - tiktoken==0.7.0
210
+ - tokenizers==0.19.1
211
+ - torch==2.4.1
212
+ - torchvision==0.19.1
213
+ - tqdm==4.66.4
214
+ - transformers==4.44.2
215
+ - triton==3.0.0
216
+ - types-python-dateutil==2.9.0.20241003
217
+ - tzdata==2024.2
218
+ - urllib3==2.2.3
219
+ - uvicorn==0.32.0
220
+ - uvloop==0.21.0
221
+ - validators==0.34.0
222
+ - vertexai==1.71.1
223
+ - wandb==0.17.3
224
+ - watchfiles==0.24.0
225
+ - websockets==11.0.3
226
+ - xformers==0.0.28.post1
227
+ - xxhash==3.5.0
228
+ - yarl==1.17.2
229
+ - zipp==3.21.0
230
+ - zstandard==0.22.0
231
+ - zstd==1.5.5.1
232
+ prefix: /scratch3/workspace/ctpham_umass_edu-ft/envs/prolong-final