Hugging Face's logo

hizella
/
aBERT_test

Fill-Mask
Transformers
PyTorch
TensorBoard
albert
Model card Files
xet
Metrics Community
1
hizella commited on
Commit
b57185e
·
1 Parent(s): 8aca303

First abERT version - modified

Browse files
Files changed (36) hide show
  1. aBERT_albert/checkpoint-2002/config.json +32 -0
  2. aBERT_albert/checkpoint-2002/optimizer.pt +3 -0
  3. aBERT_albert/checkpoint-2002/pytorch_model.bin +3 -0
  4. aBERT_albert/checkpoint-2002/rng_state.pth +3 -0
  5. aBERT_albert/checkpoint-2002/scheduler.pt +3 -0
  6. aBERT_albert/checkpoint-2002/trainer_state.json +40 -0
  7. aBERT_albert/checkpoint-2002/training_args.bin +3 -0
  8. aBERT_albert/checkpoint-3003/config.json +32 -0
  9. aBERT_albert/checkpoint-3003/optimizer.pt +3 -0
  10. aBERT_albert/checkpoint-3003/pytorch_model.bin +3 -0
  11. aBERT_albert/checkpoint-3003/rng_state.pth +3 -0
  12. aBERT_albert/checkpoint-3003/scheduler.pt +3 -0
  13. aBERT_albert/checkpoint-3003/trainer_state.json +52 -0
  14. aBERT_albert/checkpoint-3003/training_args.bin +3 -0
  15. aBERT_albert/runs/Nov12_15-08-21_588f645600fb/1636729706.827277/events.out.tfevents.1636729706.588f645600fb.72.1 +3 -0
  16. aBERT_albert/runs/Nov12_15-08-21_588f645600fb/events.out.tfevents.1636729706.588f645600fb.72.0 +3 -0
  17. aBERT_albert/runs/Nov12_15-25-01_588f645600fb/1636730705.4966695/events.out.tfevents.1636730705.588f645600fb.72.3 +3 -0
  18. aBERT_albert/runs/Nov12_15-25-01_588f645600fb/events.out.tfevents.1636730705.588f645600fb.72.2 +3 -0
  19. aBERT_albert/runs/Nov12_15-31-11_588f645600fb/1636731074.3929214/events.out.tfevents.1636731074.588f645600fb.72.5 +3 -0
  20. aBERT_albert/runs/Nov12_15-31-11_588f645600fb/events.out.tfevents.1636731074.588f645600fb.72.4 +3 -0
  21. aBERT_albert/runs/Nov12_15-42-23_588f645600fb/1636731746.5490618/events.out.tfevents.1636731746.588f645600fb.72.7 +3 -0
  22. aBERT_albert/runs/Nov12_15-42-23_588f645600fb/events.out.tfevents.1636731746.588f645600fb.72.6 +3 -0
  23. aBERT_albert/runs/Nov12_16-01-20_588f645600fb/1636732883.3480775/events.out.tfevents.1636732883.588f645600fb.72.9 +3 -0
  24. aBERT_albert/runs/Nov12_16-01-20_588f645600fb/events.out.tfevents.1636732883.588f645600fb.72.8 +3 -0
  25. added_tokens.json +1 -0
  26. config.json +31 -0
  27. optimizer.pt +3 -0
  28. pytorch_model.bin +3 -0
  29. rng_state.pth +3 -0
  30. scheduler.pt +3 -0
  31. special_tokens_map.json +1 -0
  32. spiece.model +3 -0
  33. spiece.vocab +0 -0
  34. tokenizer_config.json +1 -0
  35. trainer_state.json +52 -0
  36. training_args.bin +3 -0
aBERT_albert/checkpoint-2002/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AlbertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0,
6
+ "bos_token_id": 2,
7
+ "classifier_dropout_prob": 0.1,
8
+ "down_scale_factor": 1,
9
+ "embedding_size": 128,
10
+ "eos_token_id": 3,
11
+ "gap_size": 0,
12
+ "hidden_act": "gelu_new",
13
+ "hidden_dropout_prob": 0,
14
+ "hidden_size": 768,
15
+ "initializer_range": 0.02,
16
+ "inner_group_num": 1,
17
+ "intermediate_size": 3072,
18
+ "layer_norm_eps": 1e-12,
19
+ "max_position_embeddings": 512,
20
+ "model_type": "albert",
21
+ "net_structure_type": 0,
22
+ "num_attention_heads": 12,
23
+ "num_hidden_groups": 1,
24
+ "num_hidden_layers": 12,
25
+ "num_memory_blocks": 0,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.12.3",
30
+ "type_vocab_size": 2,
31
+ "vocab_size": 30000
32
+ }
aBERT_albert/checkpoint-2002/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79e2d380ba8e96076e087ba1aee6965498998f2b8043d35a755f9c324b05e6da
3
+ size 89789181
aBERT_albert/checkpoint-2002/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8049999b409fa863d1905105613923c7095eb1ddb902e7981890c876978461a
3
+ size 44902222
aBERT_albert/checkpoint-2002/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41149e8ed8789369b53281381ad196879e1d80020b7363cdb1871cb81a42568b
3
+ size 14503
aBERT_albert/checkpoint-2002/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f3fa053573253b741c54d691d1ef44f7695d202cf55166013e5a53512b137b8
3
+ size 623
aBERT_albert/checkpoint-2002/trainer_state.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "global_step": 2002,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.5,
12
+ "learning_rate": 4.167499167499168e-05,
13
+ "loss": 8.825,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "learning_rate": 3.334998334998335e-05,
19
+ "loss": 7.1815,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.5,
24
+ "learning_rate": 2.5024975024975027e-05,
25
+ "loss": 6.9532,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "learning_rate": 1.6699966699966702e-05,
31
+ "loss": 6.7979,
32
+ "step": 2000
33
+ }
34
+ ],
35
+ "max_steps": 3003,
36
+ "num_train_epochs": 3,
37
+ "total_flos": 20211252614976.0,
38
+ "trial_name": null,
39
+ "trial_params": null
40
+ }
aBERT_albert/checkpoint-2002/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e74d494bb0d03f53b17fe3db4bb1a504ab726e3733a21b31e815b480f66ae8d2
3
+ size 2799
aBERT_albert/checkpoint-3003/config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AlbertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0,
6
+ "bos_token_id": 2,
7
+ "classifier_dropout_prob": 0.1,
8
+ "down_scale_factor": 1,
9
+ "embedding_size": 128,
10
+ "eos_token_id": 3,
11
+ "gap_size": 0,
12
+ "hidden_act": "gelu_new",
13
+ "hidden_dropout_prob": 0,
14
+ "hidden_size": 768,
15
+ "initializer_range": 0.02,
16
+ "inner_group_num": 1,
17
+ "intermediate_size": 3072,
18
+ "layer_norm_eps": 1e-12,
19
+ "max_position_embeddings": 512,
20
+ "model_type": "albert",
21
+ "net_structure_type": 0,
22
+ "num_attention_heads": 12,
23
+ "num_hidden_groups": 1,
24
+ "num_hidden_layers": 12,
25
+ "num_memory_blocks": 0,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.12.3",
30
+ "type_vocab_size": 2,
31
+ "vocab_size": 30000
32
+ }
aBERT_albert/checkpoint-3003/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef44f509b6612b43998c7c56afbd987ddef5c066e278397d3db447a88ba99c1d
3
+ size 89789181
aBERT_albert/checkpoint-3003/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56b28f5b09d5d5819711d737fce6e7f9cd86d3688f11dd4a1553ee72816f7614
3
+ size 44902222
aBERT_albert/checkpoint-3003/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61f0dadcac6bef092147dddb64ae3c904671c7e45ecba39a8da55d26432f3219
3
+ size 14503
aBERT_albert/checkpoint-3003/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d2316cb2dc93aa51287fd95e99a983fbde7c85d8f1969003818f823c51a9a21
3
+ size 623
aBERT_albert/checkpoint-3003/trainer_state.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 3003,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.5,
12
+ "learning_rate": 4.167499167499168e-05,
13
+ "loss": 8.825,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "learning_rate": 3.334998334998335e-05,
19
+ "loss": 7.1815,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.5,
24
+ "learning_rate": 2.5024975024975027e-05,
25
+ "loss": 6.9532,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "learning_rate": 1.6699966699966702e-05,
31
+ "loss": 6.7979,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 2.5,
36
+ "learning_rate": 8.374958374958376e-06,
37
+ "loss": 6.7027,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 4.9950049950049954e-08,
43
+ "loss": 6.7203,
44
+ "step": 3000
45
+ }
46
+ ],
47
+ "max_steps": 3003,
48
+ "num_train_epochs": 3,
49
+ "total_flos": 30316878922464.0,
50
+ "trial_name": null,
51
+ "trial_params": null
52
+ }
aBERT_albert/checkpoint-3003/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e74d494bb0d03f53b17fe3db4bb1a504ab726e3733a21b31e815b480f66ae8d2
3
+ size 2799
aBERT_albert/runs/Nov12_15-08-21_588f645600fb/1636729706.827277/events.out.tfevents.1636729706.588f645600fb.72.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe330f3c20feff50675dca1e0208c15709e44dd32a00a8d30807b9f3670f38a7
3
+ size 4495
aBERT_albert/runs/Nov12_15-08-21_588f645600fb/events.out.tfevents.1636729706.588f645600fb.72.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0efcee4ce4d9a58f15c8f15b6615bbe2b0c429d19e0ebd672dbbadb34dcd7d2c
3
+ size 4546
aBERT_albert/runs/Nov12_15-25-01_588f645600fb/1636730705.4966695/events.out.tfevents.1636730705.588f645600fb.72.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3680d78befc2712d771495cac91c77e792571c4aa4e3ec4ed5c70a104afbf8d
3
+ size 4495
aBERT_albert/runs/Nov12_15-25-01_588f645600fb/events.out.tfevents.1636730705.588f645600fb.72.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b063c70dca7c3dd712298373c0d1d9d1ab28a0e7ea2b8a1ef6575a9e7bcff96
3
+ size 3788
aBERT_albert/runs/Nov12_15-31-11_588f645600fb/1636731074.3929214/events.out.tfevents.1636731074.588f645600fb.72.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bc9121c142d2d8dd24e19a76f1deb854774e8fceeb5bee224494df9254fa34b
3
+ size 4495
aBERT_albert/runs/Nov12_15-31-11_588f645600fb/events.out.tfevents.1636731074.588f645600fb.72.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d4472b3780a5516dcdfd41427b46a613ef03278cfa80e2585c80835babb5cb3
3
+ size 3789
aBERT_albert/runs/Nov12_15-42-23_588f645600fb/1636731746.5490618/events.out.tfevents.1636731746.588f645600fb.72.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0965005fe283862b5bc53e123c41b643ca9de43170d768aa0ec98b1b94addf1
3
+ size 4495
aBERT_albert/runs/Nov12_15-42-23_588f645600fb/events.out.tfevents.1636731746.588f645600fb.72.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8650a9d8901c58d5e56e5c15ef94598e3650fd8eef817dde8d241bca49202011
3
+ size 3790
aBERT_albert/runs/Nov12_16-01-20_588f645600fb/1636732883.3480775/events.out.tfevents.1636732883.588f645600fb.72.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81c738d46ca8afae1553629a74f5ece37e7b2e39672fe30b715ea76c8c280621
3
+ size 4495
aBERT_albert/runs/Nov12_16-01-20_588f645600fb/events.out.tfevents.1636732883.588f645600fb.72.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe35d59e72da755dab3a3322df0472cc73e2ae88e6c9961476c1b625854cf82b
3
+ size 3279
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"[CLS]": 12811, "[SEP]": 12812, "<pad>": 12813, "[MASK]": 12814}
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AlbertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0,
6
+ "bos_token_id": 2,
7
+ "classifier_dropout_prob": 0.1,
8
+ "down_scale_factor": 1,
9
+ "embedding_size": 128,
10
+ "eos_token_id": 3,
11
+ "gap_size": 0,
12
+ "hidden_act": "gelu_new",
13
+ "hidden_dropout_prob": 0,
14
+ "hidden_size": 768,
15
+ "initializer_range": 0.02,
16
+ "inner_group_num": 1,
17
+ "intermediate_size": 3072,
18
+ "layer_norm_eps": 1e-12,
19
+ "max_position_embeddings": 512,
20
+ "model_type": "albert",
21
+ "net_structure_type": 0,
22
+ "num_attention_heads": 12,
23
+ "num_hidden_groups": 1,
24
+ "num_hidden_layers": 12,
25
+ "num_memory_blocks": 0,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "transformers_version": "4.12.3",
29
+ "type_vocab_size": 2,
30
+ "vocab_size": 30000
31
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef44f509b6612b43998c7c56afbd987ddef5c066e278397d3db447a88ba99c1d
3
+ size 89789181
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56b28f5b09d5d5819711d737fce6e7f9cd86d3688f11dd4a1553ee72816f7614
3
+ size 44902222
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61f0dadcac6bef092147dddb64ae3c904671c7e45ecba39a8da55d26432f3219
3
+ size 14503
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d2316cb2dc93aa51287fd95e99a983fbde7c85d8f1969003818f823c51a9a21
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true}}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82f70bed802282fef4dd7e47fd90db5d24e844c84b73ca6358a0257578905351
3
+ size 447557
spiece.vocab ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "aBERT", "tokenizer_class": "AlbertTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 3003,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.5,
12
+ "learning_rate": 4.167499167499168e-05,
13
+ "loss": 8.825,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "learning_rate": 3.334998334998335e-05,
19
+ "loss": 7.1815,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 1.5,
24
+ "learning_rate": 2.5024975024975027e-05,
25
+ "loss": 6.9532,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 2.0,
30
+ "learning_rate": 1.6699966699966702e-05,
31
+ "loss": 6.7979,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 2.5,
36
+ "learning_rate": 8.374958374958376e-06,
37
+ "loss": 6.7027,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 3.0,
42
+ "learning_rate": 4.9950049950049954e-08,
43
+ "loss": 6.7203,
44
+ "step": 3000
45
+ }
46
+ ],
47
+ "max_steps": 3003,
48
+ "num_train_epochs": 3,
49
+ "total_flos": 30316878922464.0,
50
+ "trial_name": null,
51
+ "trial_params": null
52
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e74d494bb0d03f53b17fe3db4bb1a504ab726e3733a21b31e815b480f66ae8d2
3
+ size 2799