Hugging Face's logo

Elkelouizajo
/
bert_mnli_16000

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Model card Files Community
Elkelouizajo commited on
Commit
eeae17d
·
verified ·
1 Parent(s): 2784d3c

Upload 44 files

Browse files
Files changed (44) hide show
  1. checkpoint-2500/config.json +42 -0
  2. checkpoint-2500/model.safetensors +3 -0
  3. checkpoint-2500/optimizer.pt +3 -0
  4. checkpoint-2500/rng_state.pth +3 -0
  5. checkpoint-2500/scheduler.pt +3 -0
  6. checkpoint-2500/special_tokens_map.json +7 -0
  7. checkpoint-2500/tokenizer.json +0 -0
  8. checkpoint-2500/tokenizer_config.json +55 -0
  9. checkpoint-2500/trainer_state.json +56 -0
  10. checkpoint-2500/training_args.bin +3 -0
  11. checkpoint-2500/vocab.txt +0 -0
  12. checkpoint-3000/config.json +42 -0
  13. checkpoint-3000/model.safetensors +3 -0
  14. checkpoint-3000/optimizer.pt +3 -0
  15. checkpoint-3000/rng_state.pth +3 -0
  16. checkpoint-3000/scheduler.pt +3 -0
  17. checkpoint-3000/special_tokens_map.json +7 -0
  18. checkpoint-3000/tokenizer.json +0 -0
  19. checkpoint-3000/tokenizer_config.json +55 -0
  20. checkpoint-3000/trainer_state.json +63 -0
  21. checkpoint-3000/training_args.bin +3 -0
  22. checkpoint-3000/vocab.txt +0 -0
  23. checkpoint-3500/config.json +42 -0
  24. checkpoint-3500/model.safetensors +3 -0
  25. checkpoint-3500/optimizer.pt +3 -0
  26. checkpoint-3500/rng_state.pth +3 -0
  27. checkpoint-3500/scheduler.pt +3 -0
  28. checkpoint-3500/special_tokens_map.json +7 -0
  29. checkpoint-3500/tokenizer.json +0 -0
  30. checkpoint-3500/tokenizer_config.json +55 -0
  31. checkpoint-3500/trainer_state.json +70 -0
  32. checkpoint-3500/training_args.bin +3 -0
  33. checkpoint-3500/vocab.txt +0 -0
  34. checkpoint-4000/config.json +42 -0
  35. checkpoint-4000/model.safetensors +3 -0
  36. checkpoint-4000/optimizer.pt +3 -0
  37. checkpoint-4000/rng_state.pth +3 -0
  38. checkpoint-4000/scheduler.pt +3 -0
  39. checkpoint-4000/special_tokens_map.json +7 -0
  40. checkpoint-4000/tokenizer.json +0 -0
  41. checkpoint-4000/tokenizer_config.json +55 -0
  42. checkpoint-4000/trainer_state.json +77 -0
  43. checkpoint-4000/training_args.bin +3 -0
  44. checkpoint-4000/vocab.txt +0 -0
checkpoint-2500/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-large-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "finetuning_task": "text-classification",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "0",
16
+ "1": "1"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "0": 0,
22
+ "1": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.39.0.dev0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 28996
42
+ }
checkpoint-2500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1c8253b2db3991c4aa2ea1f82c056c4434fa2d86e2768f828c60de2448a5790
3
+ size 1334372264
checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2874785972c972122096861cb5a53a80b3eb5efb3a64e0aac3d14c0d77beda3e
3
+ size 2668968429
checkpoint-2500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c1f795e5f2fd7e807a84ebf40dd3957507d99988a67bf0b892eb01651999289
3
+ size 13990
checkpoint-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6baef63320527f049ee4ccdefbf1db2735d86002f2a22bcb062be60499bc5b3
3
+ size 1064
checkpoint-2500/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
+ }
checkpoint-2500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2500/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": false,
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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
checkpoint-2500/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.25,
5
+ "eval_steps": 500,
6
+ "global_step": 2500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.25,
13
+ "grad_norm": 9.530180931091309,
14
+ "learning_rate": 1.9e-05,
15
+ "loss": 0.7046,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 11.739270210266113,
21
+ "learning_rate": 1.8e-05,
22
+ "loss": 0.574,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 21.960508346557617,
28
+ "learning_rate": 1.7e-05,
29
+ "loss": 0.4031,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 1.2487173080444336,
35
+ "learning_rate": 1.6000000000000003e-05,
36
+ "loss": 0.38,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.25,
41
+ "grad_norm": 11.083433151245117,
42
+ "learning_rate": 1.5000000000000002e-05,
43
+ "loss": 0.2964,
44
+ "step": 2500
45
+ }
46
+ ],
47
+ "logging_steps": 500,
48
+ "max_steps": 10000,
49
+ "num_input_tokens_seen": 0,
50
+ "num_train_epochs": 5,
51
+ "save_steps": 500,
52
+ "total_flos": 4658025936754176.0,
53
+ "train_batch_size": 8,
54
+ "trial_name": null,
55
+ "trial_params": null
56
+ }
checkpoint-2500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c723a0cd71eedc1750912629ef866d84ce379f07f7fbfd5f98bcb6058f7ae473
3
+ size 4920
checkpoint-2500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3000/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-large-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "finetuning_task": "text-classification",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "0",
16
+ "1": "1"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "0": 0,
22
+ "1": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.39.0.dev0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 28996
42
+ }
checkpoint-3000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72b25690ca4861d1fb2e22f5d4e3f370bb7c8331d525dc8ffbf7d54b3fdb6c42
3
+ size 1334372264
checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a431e5969ea992c2606d41eaa15931413f25144b1de5cd29caa303a8d25a9e24
3
+ size 2668968429
checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a92075592a08d80524831ce1954d5f08a1c2b952f77dcbef96f3ac928bc5aac2
3
+ size 13990
checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6163b3d8b7a547ef67d1bbbc92c7ce9cd916267b781e285494744cebd47a915
3
+ size 1064
checkpoint-3000/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
+ }
checkpoint-3000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3000/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": false,
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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
checkpoint-3000/trainer_state.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.5,
5
+ "eval_steps": 500,
6
+ "global_step": 3000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.25,
13
+ "grad_norm": 9.530180931091309,
14
+ "learning_rate": 1.9e-05,
15
+ "loss": 0.7046,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 11.739270210266113,
21
+ "learning_rate": 1.8e-05,
22
+ "loss": 0.574,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 21.960508346557617,
28
+ "learning_rate": 1.7e-05,
29
+ "loss": 0.4031,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 1.2487173080444336,
35
+ "learning_rate": 1.6000000000000003e-05,
36
+ "loss": 0.38,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.25,
41
+ "grad_norm": 11.083433151245117,
42
+ "learning_rate": 1.5000000000000002e-05,
43
+ "loss": 0.2964,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.5,
48
+ "grad_norm": 0.22524116933345795,
49
+ "learning_rate": 1.4e-05,
50
+ "loss": 0.3073,
51
+ "step": 3000
52
+ }
53
+ ],
54
+ "logging_steps": 500,
55
+ "max_steps": 10000,
56
+ "num_input_tokens_seen": 0,
57
+ "num_train_epochs": 5,
58
+ "save_steps": 500,
59
+ "total_flos": 5589957300082176.0,
60
+ "train_batch_size": 8,
61
+ "trial_name": null,
62
+ "trial_params": null
63
+ }
checkpoint-3000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c723a0cd71eedc1750912629ef866d84ce379f07f7fbfd5f98bcb6058f7ae473
3
+ size 4920
checkpoint-3000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3500/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-large-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "finetuning_task": "text-classification",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "0",
16
+ "1": "1"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "0": 0,
22
+ "1": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.39.0.dev0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 28996
42
+ }
checkpoint-3500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79334e191abd9e6f780684f5461230c7268155ac71b5811f327353c6cc952f84
3
+ size 1334372264
checkpoint-3500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba4b4b1888355c7307bb8314a0f2596d412a250a4ff5b90fa08ec18975ce7fe
3
+ size 2668968429
checkpoint-3500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e8e3b576670a72b88749d8dc66befe03be80b1bda1bb0dc69f6b7ac46cccbbd
3
+ size 13990
checkpoint-3500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f638762bee87dec8c4c49ac6a6d5a45c7baf9f0a0a571304f4f483ca6ddfa3b7
3
+ size 1064
checkpoint-3500/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
+ }
checkpoint-3500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-3500/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": false,
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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
checkpoint-3500/trainer_state.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.75,
5
+ "eval_steps": 500,
6
+ "global_step": 3500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.25,
13
+ "grad_norm": 9.530180931091309,
14
+ "learning_rate": 1.9e-05,
15
+ "loss": 0.7046,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 11.739270210266113,
21
+ "learning_rate": 1.8e-05,
22
+ "loss": 0.574,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 21.960508346557617,
28
+ "learning_rate": 1.7e-05,
29
+ "loss": 0.4031,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 1.2487173080444336,
35
+ "learning_rate": 1.6000000000000003e-05,
36
+ "loss": 0.38,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.25,
41
+ "grad_norm": 11.083433151245117,
42
+ "learning_rate": 1.5000000000000002e-05,
43
+ "loss": 0.2964,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.5,
48
+ "grad_norm": 0.22524116933345795,
49
+ "learning_rate": 1.4e-05,
50
+ "loss": 0.3073,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 1.75,
55
+ "grad_norm": 1.0325411558151245,
56
+ "learning_rate": 1.3000000000000001e-05,
57
+ "loss": 0.3027,
58
+ "step": 3500
59
+ }
60
+ ],
61
+ "logging_steps": 500,
62
+ "max_steps": 10000,
63
+ "num_input_tokens_seen": 0,
64
+ "num_train_epochs": 5,
65
+ "save_steps": 500,
66
+ "total_flos": 6521888663410176.0,
67
+ "train_batch_size": 8,
68
+ "trial_name": null,
69
+ "trial_params": null
70
+ }
checkpoint-3500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c723a0cd71eedc1750912629ef866d84ce379f07f7fbfd5f98bcb6058f7ae473
3
+ size 4920
checkpoint-3500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4000/config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-large-cased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "finetuning_task": "text-classification",
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "0",
16
+ "1": "1"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "0": 0,
22
+ "1": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 16,
28
+ "num_hidden_layers": 24,
29
+ "pad_token_id": 0,
30
+ "pooler_fc_size": 768,
31
+ "pooler_num_attention_heads": 12,
32
+ "pooler_num_fc_layers": 3,
33
+ "pooler_size_per_head": 128,
34
+ "pooler_type": "first_token_transform",
35
+ "position_embedding_type": "absolute",
36
+ "problem_type": "single_label_classification",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.39.0.dev0",
39
+ "type_vocab_size": 2,
40
+ "use_cache": true,
41
+ "vocab_size": 28996
42
+ }
checkpoint-4000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31186c9765ae410c9f8a7c20dbf8f7b33d13598de893e9cc7202b60548163201
3
+ size 1334372264
checkpoint-4000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19cdc013c38602138b1195922adcac2add139e4011b006de183d9b5422289ec9
3
+ size 2668968429
checkpoint-4000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8d3bf70eedd74f6bc34c119441b593aebc611b2460978f70959776c3ae8ec93
3
+ size 13990
checkpoint-4000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31ef43b44bdea8cbae998a72dcc1b9fa99f1e6abe4027bffd4886c24e5a15a02
3
+ size 1064
checkpoint-4000/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
+ }
checkpoint-4000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4000/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": false,
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": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
checkpoint-4000/trainer_state.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.25,
13
+ "grad_norm": 9.530180931091309,
14
+ "learning_rate": 1.9e-05,
15
+ "loss": 0.7046,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 11.739270210266113,
21
+ "learning_rate": 1.8e-05,
22
+ "loss": 0.574,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 21.960508346557617,
28
+ "learning_rate": 1.7e-05,
29
+ "loss": 0.4031,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 1.2487173080444336,
35
+ "learning_rate": 1.6000000000000003e-05,
36
+ "loss": 0.38,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.25,
41
+ "grad_norm": 11.083433151245117,
42
+ "learning_rate": 1.5000000000000002e-05,
43
+ "loss": 0.2964,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.5,
48
+ "grad_norm": 0.22524116933345795,
49
+ "learning_rate": 1.4e-05,
50
+ "loss": 0.3073,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 1.75,
55
+ "grad_norm": 1.0325411558151245,
56
+ "learning_rate": 1.3000000000000001e-05,
57
+ "loss": 0.3027,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 2.0,
62
+ "grad_norm": 10.020037651062012,
63
+ "learning_rate": 1.2e-05,
64
+ "loss": 0.3056,
65
+ "step": 4000
66
+ }
67
+ ],
68
+ "logging_steps": 500,
69
+ "max_steps": 10000,
70
+ "num_input_tokens_seen": 0,
71
+ "num_train_epochs": 5,
72
+ "save_steps": 500,
73
+ "total_flos": 7452189146852352.0,
74
+ "train_batch_size": 8,
75
+ "trial_name": null,
76
+ "trial_params": null
77
+ }
checkpoint-4000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c723a0cd71eedc1750912629ef866d84ce379f07f7fbfd5f98bcb6058f7ae473
3
+ size 4920
checkpoint-4000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff