Hugging Face's logo

Alan-Shih
/
homework_1

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
trl
sft
text-generation-inference
8-bit precision
bitsandbytes
Model card Files
xet
Metrics Community
Alan-Shih commited on
Commit
73dbf32
·
verified ·
1 Parent(s): 93d3f52

Training in progress, epoch 3

Browse files
Files changed (24) hide show
  1. model.safetensors +1 -1
  2. run-3/checkpoint-2138/config.json +25 -0
  3. run-3/checkpoint-2138/model.safetensors +3 -0
  4. run-3/checkpoint-2138/optimizer.pt +3 -0
  5. run-3/checkpoint-2138/rng_state.pth +3 -0
  6. run-3/checkpoint-2138/scheduler.pt +3 -0
  7. run-3/checkpoint-2138/special_tokens_map.json +7 -0
  8. run-3/checkpoint-2138/tokenizer.json +0 -0
  9. run-3/checkpoint-2138/tokenizer_config.json +55 -0
  10. run-3/checkpoint-2138/trainer_state.json +72 -0
  11. run-3/checkpoint-2138/training_args.bin +3 -0
  12. run-3/checkpoint-2138/vocab.txt +0 -0
  13. run-3/checkpoint-3207/config.json +25 -0
  14. run-3/checkpoint-3207/model.safetensors +3 -0
  15. run-3/checkpoint-3207/optimizer.pt +3 -0
  16. run-3/checkpoint-3207/rng_state.pth +3 -0
  17. run-3/checkpoint-3207/scheduler.pt +3 -0
  18. run-3/checkpoint-3207/special_tokens_map.json +7 -0
  19. run-3/checkpoint-3207/tokenizer.json +0 -0
  20. run-3/checkpoint-3207/tokenizer_config.json +55 -0
  21. run-3/checkpoint-3207/trainer_state.json +95 -0
  22. run-3/checkpoint-3207/training_args.bin +3 -0
  23. run-3/checkpoint-3207/vocab.txt +0 -0
  24. runs/Mar23_02-09-13_2ed998b56e2c/events.out.tfevents.1711161152.2ed998b56e2c.195.5 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a44c5eeb49ab1b7725956e339f2ba8176c228fb3416b36946fe7eb5225e35670
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d565e3d8ad2e00f157561ec5c14773d00a882b3917ce3cdab12b1ce3e9688af
3
  size 267832560
run-3/checkpoint-2138/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-3/checkpoint-2138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bc8362cecabc411b1b054bafe6c2e14bb38b4370e486c1f0ae01f2822e65559
3
+ size 267832560
run-3/checkpoint-2138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed72a5653043901d6e240bb620712c55d0296c63a35a7a6f22b974ff4cc42c86
3
+ size 535727290
run-3/checkpoint-2138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff3abf8f232ae7f0858b09c06894cfb7f170b7a85d5c6fb87a6663c498a67d34
3
+ size 14308
run-3/checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb33c846f19f55ada1fb83877049485d06ab2aac8001e06129d5aff2cd1eac86
3
+ size 1064
run-3/checkpoint-2138/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-3/checkpoint-2138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-2138/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-3/checkpoint-2138/trainer_state.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.49547617383910947,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-2138",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2138,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.47,
13
+ "grad_norm": 10.753751754760742,
14
+ "learning_rate": 1.7977369076499405e-05,
15
+ "loss": 0.5382,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.94,
20
+ "grad_norm": 9.229598999023438,
21
+ "learning_rate": 1.612211942980184e-05,
22
+ "loss": 0.4947,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 0.4966508448123932,
28
+ "eval_matthews_correlation": 0.457686920201459,
29
+ "eval_runtime": 0.7777,
30
+ "eval_samples_per_second": 1341.196,
31
+ "eval_steps_per_second": 84.87,
32
+ "step": 1069
33
+ },
34
+ {
35
+ "epoch": 1.4,
36
+ "grad_norm": 11.25524616241455,
37
+ "learning_rate": 1.4266869783104275e-05,
38
+ "loss": 0.3692,
39
+ "step": 1500
40
+ },
41
+ {
42
+ "epoch": 1.87,
43
+ "grad_norm": 40.92118835449219,
44
+ "learning_rate": 1.2411620136406709e-05,
45
+ "loss": 0.3508,
46
+ "step": 2000
47
+ },
48
+ {
49
+ "epoch": 2.0,
50
+ "eval_loss": 0.6059253811836243,
51
+ "eval_matthews_correlation": 0.49547617383910947,
52
+ "eval_runtime": 0.8858,
53
+ "eval_samples_per_second": 1177.509,
54
+ "eval_steps_per_second": 74.512,
55
+ "step": 2138
56
+ }
57
+ ],
58
+ "logging_steps": 500,
59
+ "max_steps": 5345,
60
+ "num_input_tokens_seen": 0,
61
+ "num_train_epochs": 5,
62
+ "save_steps": 500,
63
+ "total_flos": 75329707793916.0,
64
+ "train_batch_size": 8,
65
+ "trial_name": null,
66
+ "trial_params": {
67
+ "learning_rate": 1.983261872319697e-05,
68
+ "num_train_epochs": 5,
69
+ "per_device_train_batch_size": 8,
70
+ "seed": 17
71
+ }
72
+ }
run-3/checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2ec969fae7bee101c572269723cfc78fdfbd9ddc8090a6c9907a585baa38d24
3
+ size 4984
run-3/checkpoint-2138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-3207/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-3/checkpoint-3207/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d565e3d8ad2e00f157561ec5c14773d00a882b3917ce3cdab12b1ce3e9688af
3
+ size 267832560
run-3/checkpoint-3207/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6dcbc0814b78eeedbaff8b289aa394555031c5a3ad7925fe57eebd8018e406c
3
+ size 535727290
run-3/checkpoint-3207/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b3301e3242e8b163cc09380550426d6b67861062ae70a17add6dff0035f123
3
+ size 14308
run-3/checkpoint-3207/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:552073b07693da8de7c4e5f4b9f4f240ddd09eef3c6d5ed5e85db7b9a2cd8ed7
3
+ size 1064
run-3/checkpoint-3207/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-3/checkpoint-3207/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-3207/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-3/checkpoint-3207/trainer_state.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.542244787638552,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-3207",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3207,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.47,
13
+ "grad_norm": 10.753751754760742,
14
+ "learning_rate": 1.7977369076499405e-05,
15
+ "loss": 0.5382,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.94,
20
+ "grad_norm": 9.229598999023438,
21
+ "learning_rate": 1.612211942980184e-05,
22
+ "loss": 0.4947,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 0.4966508448123932,
28
+ "eval_matthews_correlation": 0.457686920201459,
29
+ "eval_runtime": 0.7777,
30
+ "eval_samples_per_second": 1341.196,
31
+ "eval_steps_per_second": 84.87,
32
+ "step": 1069
33
+ },
34
+ {
35
+ "epoch": 1.4,
36
+ "grad_norm": 11.25524616241455,
37
+ "learning_rate": 1.4266869783104275e-05,
38
+ "loss": 0.3692,
39
+ "step": 1500
40
+ },
41
+ {
42
+ "epoch": 1.87,
43
+ "grad_norm": 40.92118835449219,
44
+ "learning_rate": 1.2411620136406709e-05,
45
+ "loss": 0.3508,
46
+ "step": 2000
47
+ },
48
+ {
49
+ "epoch": 2.0,
50
+ "eval_loss": 0.6059253811836243,
51
+ "eval_matthews_correlation": 0.49547617383910947,
52
+ "eval_runtime": 0.8858,
53
+ "eval_samples_per_second": 1177.509,
54
+ "eval_steps_per_second": 74.512,
55
+ "step": 2138
56
+ },
57
+ {
58
+ "epoch": 2.34,
59
+ "grad_norm": 0.43179455399513245,
60
+ "learning_rate": 1.0556370489709145e-05,
61
+ "loss": 0.2779,
62
+ "step": 2500
63
+ },
64
+ {
65
+ "epoch": 2.81,
66
+ "grad_norm": 33.96426010131836,
67
+ "learning_rate": 8.70112084301158e-06,
68
+ "loss": 0.2518,
69
+ "step": 3000
70
+ },
71
+ {
72
+ "epoch": 3.0,
73
+ "eval_loss": 0.8006073236465454,
74
+ "eval_matthews_correlation": 0.542244787638552,
75
+ "eval_runtime": 0.8024,
76
+ "eval_samples_per_second": 1299.782,
77
+ "eval_steps_per_second": 82.249,
78
+ "step": 3207
79
+ }
80
+ ],
81
+ "logging_steps": 500,
82
+ "max_steps": 5345,
83
+ "num_input_tokens_seen": 0,
84
+ "num_train_epochs": 5,
85
+ "save_steps": 500,
86
+ "total_flos": 113295847405200.0,
87
+ "train_batch_size": 8,
88
+ "trial_name": null,
89
+ "trial_params": {
90
+ "learning_rate": 1.983261872319697e-05,
91
+ "num_train_epochs": 5,
92
+ "per_device_train_batch_size": 8,
93
+ "seed": 17
94
+ }
95
+ }
run-3/checkpoint-3207/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2ec969fae7bee101c572269723cfc78fdfbd9ddc8090a6c9907a585baa38d24
3
+ size 4984
run-3/checkpoint-3207/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar23_02-09-13_2ed998b56e2c/events.out.tfevents.1711161152.2ed998b56e2c.195.5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1426773e53375623600c8cbad4de97a1c742ac44cec7f89fe4d86568c7ef925d
3
- size 5559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e16cf25412f6eafa5eeb91abe29830dbc60592b07b1753a79edc18b8cea03d50
3
+ size 7284