Hugging Face's logo

Elkelouizajo
/
BERT_mnli_50K

Safetensors
Model card Files
xet
 Community
Elkelouizajo commited on
Commit
86fcdd6
·
verified ·
1 Parent(s): c383276

Upload 44 files

Browse files
Files changed (44) hide show
  1. checkpoint-1500/config.json +42 -0
  2. checkpoint-1500/model.safetensors +3 -0
  3. checkpoint-1500/optimizer.pt +3 -0
  4. checkpoint-1500/rng_state.pth +3 -0
  5. checkpoint-1500/scheduler.pt +3 -0
  6. checkpoint-1500/special_tokens_map.json +7 -0
  7. checkpoint-1500/tokenizer.json +0 -0
  8. checkpoint-1500/tokenizer_config.json +55 -0
  9. checkpoint-1500/trainer_state.json +42 -0
  10. checkpoint-1500/training_args.bin +3 -0
  11. checkpoint-1500/vocab.txt +0 -0
  12. checkpoint-2000/config.json +42 -0
  13. checkpoint-2000/model.safetensors +3 -0
  14. checkpoint-2000/optimizer.pt +3 -0
  15. checkpoint-2000/rng_state.pth +3 -0
  16. checkpoint-2000/scheduler.pt +3 -0
  17. checkpoint-2000/special_tokens_map.json +7 -0
  18. checkpoint-2000/tokenizer.json +0 -0
  19. checkpoint-2000/tokenizer_config.json +55 -0
  20. checkpoint-2000/trainer_state.json +49 -0
  21. checkpoint-2000/training_args.bin +3 -0
  22. checkpoint-2000/vocab.txt +0 -0
  23. checkpoint-2500/config.json +42 -0
  24. checkpoint-2500/model.safetensors +3 -0
  25. checkpoint-2500/optimizer.pt +3 -0
  26. checkpoint-2500/rng_state.pth +3 -0
  27. checkpoint-2500/scheduler.pt +3 -0
  28. checkpoint-2500/special_tokens_map.json +7 -0
  29. checkpoint-2500/tokenizer.json +0 -0
  30. checkpoint-2500/tokenizer_config.json +55 -0
  31. checkpoint-2500/trainer_state.json +56 -0
  32. checkpoint-2500/training_args.bin +3 -0
  33. checkpoint-2500/vocab.txt +0 -0
  34. checkpoint-3000/config.json +42 -0
  35. checkpoint-3000/model.safetensors +3 -0
  36. checkpoint-3000/optimizer.pt +3 -0
  37. checkpoint-3000/rng_state.pth +3 -0
  38. checkpoint-3000/scheduler.pt +3 -0
  39. checkpoint-3000/special_tokens_map.json +7 -0
  40. checkpoint-3000/tokenizer.json +0 -0
  41. checkpoint-3000/tokenizer_config.json +55 -0
  42. checkpoint-3000/trainer_state.json +63 -0
  43. checkpoint-3000/training_args.bin +3 -0
  44. checkpoint-3000/vocab.txt +0 -0
checkpoint-1500/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-1500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e9a005a974c09951c4156504f63728cb71288d73d6304c08607ac99c4dbcc9d
3
+ size 1334372264
checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:723ccabee7363607f2b754493ccf3435cc3d6638416a0ea843352e6051c4e3b7
3
+ size 2668979437
checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63f8df2fdcdc0bfb22f955cca5a1d60f698868a88b346bdb6d1dadaac5200397
3
+ size 14308
checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb54deab0046c1d0c95e20f50e45ff7e85f0d2cc667a2060b1310901d1e9c021
3
+ size 1064
checkpoint-1500/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-1500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1500/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-1500/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.3,
5
+ "eval_steps": 500,
6
+ "global_step": 1500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1,
13
+ "grad_norm": 0.0,
14
+ "learning_rate": 0.196,
15
+ "loss": 0.5157,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.2,
20
+ "grad_norm": 0.0,
21
+ "learning_rate": 0.192,
22
+ "loss": 0.8239,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.3,
27
+ "grad_norm": 0.0,
28
+ "learning_rate": 0.188,
29
+ "loss": 1.3562,
30
+ "step": 1500
31
+ }
32
+ ],
33
+ "logging_steps": 500,
34
+ "max_steps": 25000,
35
+ "num_input_tokens_seen": 0,
36
+ "num_train_epochs": 5,
37
+ "save_steps": 500,
38
+ "total_flos": 1.1183176359936e+16,
39
+ "train_batch_size": 8,
40
+ "trial_name": null,
41
+ "trial_params": null
42
+ }
checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d36c5af714d22ff6bcf6c92de8b9caa9e0a8a2a7e6f9b67efe8b380779b7fc
3
+ size 4920
checkpoint-1500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/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-2000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae4984e32d96db863698d600ca232f4b0bb109456214e24920c442c03941360a
3
+ size 1334372264
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ca889e3d99a30bf92913b2ec9730552fedf4ec80b73a33aefb14775f8ef25b1
3
+ size 2668979437
checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4ab790c460723116d7793eb8d3a5147f5ea297065dc42ac254b85fe3dd2c2db
3
+ size 14308
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cce76ede73c8afb640528d912b249e5417e9db074f14f00de1c883127783c14b
3
+ size 1064
checkpoint-2000/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-2000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/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-2000/trainer_state.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.4,
5
+ "eval_steps": 500,
6
+ "global_step": 2000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1,
13
+ "grad_norm": 0.0,
14
+ "learning_rate": 0.196,
15
+ "loss": 0.5157,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.2,
20
+ "grad_norm": 0.0,
21
+ "learning_rate": 0.192,
22
+ "loss": 0.8239,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.3,
27
+ "grad_norm": 0.0,
28
+ "learning_rate": 0.188,
29
+ "loss": 1.3562,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.4,
34
+ "grad_norm": 0.0,
35
+ "learning_rate": 0.18400000000000002,
36
+ "loss": 0.0,
37
+ "step": 2000
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 25000,
42
+ "num_input_tokens_seen": 0,
43
+ "num_train_epochs": 5,
44
+ "save_steps": 500,
45
+ "total_flos": 1.4910901813248e+16,
46
+ "train_batch_size": 8,
47
+ "trial_name": null,
48
+ "trial_params": null
49
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d36c5af714d22ff6bcf6c92de8b9caa9e0a8a2a7e6f9b67efe8b380779b7fc
3
+ size 4920
checkpoint-2000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
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 sha256:918cfd3a08e7dfda3637edcfe22d371fa585a373fa9446da3cd9fe7f6b720fbc
3
+ size 1334372264
checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d67097ae7de203e59ea638b8457d3061d7cf31a9e37efd9b4de1b474c99d6d7e
3
+ size 2668979437
checkpoint-2500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2960a0d2f748da275f6894b99dabe6b53d2f4f118caad6794f39c51e395bb65
3
+ size 14308
checkpoint-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3297125575548953c24b9ba792f6972dd47b64b7ea7e042144a31b3008b11fc6
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": 0.5,
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": 0.1,
13
+ "grad_norm": 0.0,
14
+ "learning_rate": 0.196,
15
+ "loss": 0.5157,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.2,
20
+ "grad_norm": 0.0,
21
+ "learning_rate": 0.192,
22
+ "loss": 0.8239,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.3,
27
+ "grad_norm": 0.0,
28
+ "learning_rate": 0.188,
29
+ "loss": 1.3562,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.4,
34
+ "grad_norm": 0.0,
35
+ "learning_rate": 0.18400000000000002,
36
+ "loss": 0.0,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.5,
41
+ "grad_norm": 0.0,
42
+ "learning_rate": 0.18000000000000002,
43
+ "loss": 1.27,
44
+ "step": 2500
45
+ }
46
+ ],
47
+ "logging_steps": 500,
48
+ "max_steps": 25000,
49
+ "num_input_tokens_seen": 0,
50
+ "num_train_epochs": 5,
51
+ "save_steps": 500,
52
+ "total_flos": 1.863862726656e+16,
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:b8d36c5af714d22ff6bcf6c92de8b9caa9e0a8a2a7e6f9b67efe8b380779b7fc
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 sha256:918cfd3a08e7dfda3637edcfe22d371fa585a373fa9446da3cd9fe7f6b720fbc
3
+ size 1334372264
checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9a49c1c8526e29b89aaafe0406330ab917bbca9e297ee915efb6c75dad2799e
3
+ size 2668979437
checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4972f54896929b80c24de396d2361ff2ffd54f1a377259401f6826f9baa9b6fe
3
+ size 14308
checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40b065a3a1fea8adf5ec7b5361c60484d6b93c9c5a41311b318abd5314af7884
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": 0.6,
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": 0.1,
13
+ "grad_norm": 0.0,
14
+ "learning_rate": 0.196,
15
+ "loss": 0.5157,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.2,
20
+ "grad_norm": 0.0,
21
+ "learning_rate": 0.192,
22
+ "loss": 0.8239,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.3,
27
+ "grad_norm": 0.0,
28
+ "learning_rate": 0.188,
29
+ "loss": 1.3562,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.4,
34
+ "grad_norm": 0.0,
35
+ "learning_rate": 0.18400000000000002,
36
+ "loss": 0.0,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.5,
41
+ "grad_norm": 0.0,
42
+ "learning_rate": 0.18000000000000002,
43
+ "loss": 1.27,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.6,
48
+ "grad_norm": 0.0,
49
+ "learning_rate": 0.17600000000000002,
50
+ "loss": 0.0,
51
+ "step": 3000
52
+ }
53
+ ],
54
+ "logging_steps": 500,
55
+ "max_steps": 25000,
56
+ "num_input_tokens_seen": 0,
57
+ "num_train_epochs": 5,
58
+ "save_steps": 500,
59
+ "total_flos": 2.2366352719872e+16,
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:b8d36c5af714d22ff6bcf6c92de8b9caa9e0a8a2a7e6f9b67efe8b380779b7fc
3
+ size 4920
checkpoint-3000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff