Hugging Face's logo

Elkelouizajo
/
BERT_mnli_50K

Safetensors
Model card Files
xet
Community
Elkelouizajo commited on
Commit
daab24f
·
verified ·
1 Parent(s): 86fcdd6

Upload 55 files

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-3500/config.json +42 -0
  2. checkpoint-3500/model.safetensors +3 -0
  3. checkpoint-3500/optimizer.pt +3 -0
  4. checkpoint-3500/rng_state.pth +3 -0
  5. checkpoint-3500/scheduler.pt +3 -0
  6. checkpoint-3500/special_tokens_map.json +7 -0
  7. checkpoint-3500/tokenizer.json +0 -0
  8. checkpoint-3500/tokenizer_config.json +55 -0
  9. checkpoint-3500/trainer_state.json +70 -0
  10. checkpoint-3500/training_args.bin +3 -0
  11. checkpoint-3500/vocab.txt +0 -0
  12. checkpoint-4000/config.json +42 -0
  13. checkpoint-4000/model.safetensors +3 -0
  14. checkpoint-4000/optimizer.pt +3 -0
  15. checkpoint-4000/rng_state.pth +3 -0
  16. checkpoint-4000/scheduler.pt +3 -0
  17. checkpoint-4000/special_tokens_map.json +7 -0
  18. checkpoint-4000/tokenizer.json +0 -0
  19. checkpoint-4000/tokenizer_config.json +55 -0
  20. checkpoint-4000/trainer_state.json +77 -0
  21. checkpoint-4000/training_args.bin +3 -0
  22. checkpoint-4000/vocab.txt +0 -0
  23. checkpoint-4500/config.json +42 -0
  24. checkpoint-4500/model.safetensors +3 -0
  25. checkpoint-4500/optimizer.pt +3 -0
  26. checkpoint-4500/rng_state.pth +3 -0
  27. checkpoint-4500/scheduler.pt +3 -0
  28. checkpoint-4500/special_tokens_map.json +7 -0
  29. checkpoint-4500/tokenizer.json +0 -0
  30. checkpoint-4500/tokenizer_config.json +55 -0
  31. checkpoint-4500/trainer_state.json +84 -0
  32. checkpoint-4500/training_args.bin +3 -0
  33. checkpoint-4500/vocab.txt +0 -0
  34. checkpoint-5000/config.json +42 -0
  35. checkpoint-5000/model.safetensors +3 -0
  36. checkpoint-5000/optimizer.pt +3 -0
  37. checkpoint-5000/rng_state.pth +3 -0
  38. checkpoint-5000/scheduler.pt +3 -0
  39. checkpoint-5000/special_tokens_map.json +7 -0
  40. checkpoint-5000/tokenizer.json +0 -0
  41. checkpoint-5000/tokenizer_config.json +55 -0
  42. checkpoint-5000/trainer_state.json +91 -0
  43. checkpoint-5000/training_args.bin +3 -0
  44. checkpoint-5000/vocab.txt +0 -0
  45. checkpoint-5500/config.json +42 -0
  46. checkpoint-5500/model.safetensors +3 -0
  47. checkpoint-5500/optimizer.pt +3 -0
  48. checkpoint-5500/rng_state.pth +3 -0
  49. checkpoint-5500/scheduler.pt +3 -0
  50. checkpoint-5500/special_tokens_map.json +7 -0
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 sha256:918cfd3a08e7dfda3637edcfe22d371fa585a373fa9446da3cd9fe7f6b720fbc
3
+ size 1334372264
checkpoint-3500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a399485fd1b440fdecab81ff10ac609c313db2077c02b915fc78ae1c114e656a
3
+ size 2668979437
checkpoint-3500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe5df72bfdf41c5a0194a43cd3433c3a3352c645fd48a9310e946f7aac26c26a
3
+ size 14308
checkpoint-3500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eabc2be9caaaa9eda1adf1cb7bc539da3f22b6616bd743c48154b2ee13ec9d74
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": 0.7,
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": 0.1,
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
+ "epoch": 0.7,
55
+ "grad_norm": 0.0,
56
+ "learning_rate": 0.17200000000000001,
57
+ "loss": 0.0,
58
+ "step": 3500
59
+ }
60
+ ],
61
+ "logging_steps": 500,
62
+ "max_steps": 25000,
63
+ "num_input_tokens_seen": 0,
64
+ "num_train_epochs": 5,
65
+ "save_steps": 500,
66
+ "total_flos": 2.6094078173184e+16,
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:b8d36c5af714d22ff6bcf6c92de8b9caa9e0a8a2a7e6f9b67efe8b380779b7fc
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 sha256:918cfd3a08e7dfda3637edcfe22d371fa585a373fa9446da3cd9fe7f6b720fbc
3
+ size 1334372264
checkpoint-4000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e636a6412806be4842e9115fba28a54386006204b36cbe8e9790dcf860700a
3
+ size 2668979437
checkpoint-4000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2910292b66ca5cbcd50a793581bb475160b7dcf64cfbcb3f0f7ddbbe4a3362ee
3
+ size 14308
checkpoint-4000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cbd8496bde8c68e56fb2d8543ea6dd60f30f75084efc77bc368bdebfbc4c2bb
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": 0.8,
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": 0.1,
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
+ "epoch": 0.7,
55
+ "grad_norm": 0.0,
56
+ "learning_rate": 0.17200000000000001,
57
+ "loss": 0.0,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.8,
62
+ "grad_norm": 0.0,
63
+ "learning_rate": 0.168,
64
+ "loss": 0.0,
65
+ "step": 4000
66
+ }
67
+ ],
68
+ "logging_steps": 500,
69
+ "max_steps": 25000,
70
+ "num_input_tokens_seen": 0,
71
+ "num_train_epochs": 5,
72
+ "save_steps": 500,
73
+ "total_flos": 2.9821803626496e+16,
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:b8d36c5af714d22ff6bcf6c92de8b9caa9e0a8a2a7e6f9b67efe8b380779b7fc
3
+ size 4920
checkpoint-4000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4500/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-4500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bca19bdf02572046e199c8463a0869fa52e24b8c40c084a07d3bd6866f7edac
3
+ size 1334372264
checkpoint-4500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef65309c0834288ce49c7012ac139297d70139dd984ee781beb3f3fe4cc1f227
3
+ size 2668979437
checkpoint-4500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aab134346f3650e8f84fadbeaff10f6f0f31e7354735acec45700b25184f83ad
3
+ size 14308
checkpoint-4500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c728ca88354d011206c199daf0a20110cc190ae5ac7b3415c5d5b4b85ac0a4b0
3
+ size 1064
checkpoint-4500/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-4500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-4500/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-4500/trainer_state.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9,
5
+ "eval_steps": 500,
6
+ "global_step": 4500,
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
+ "epoch": 0.7,
55
+ "grad_norm": 0.0,
56
+ "learning_rate": 0.17200000000000001,
57
+ "loss": 0.0,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.8,
62
+ "grad_norm": 0.0,
63
+ "learning_rate": 0.168,
64
+ "loss": 0.0,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.9,
69
+ "grad_norm": 0.0,
70
+ "learning_rate": 0.164,
71
+ "loss": 1.3465,
72
+ "step": 4500
73
+ }
74
+ ],
75
+ "logging_steps": 500,
76
+ "max_steps": 25000,
77
+ "num_input_tokens_seen": 0,
78
+ "num_train_epochs": 5,
79
+ "save_steps": 500,
80
+ "total_flos": 3.3549529079808e+16,
81
+ "train_batch_size": 8,
82
+ "trial_name": null,
83
+ "trial_params": null
84
+ }
checkpoint-4500/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-4500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-5000/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-5000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bbf288d65bd2d5d8fe7e4f222a9dac2de0cc66984008466c235c3833223bcf7
3
+ size 1334372264
checkpoint-5000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8431649130281af95f7fe809d40adb15200e41082cffb0a3b253121e548fee1b
3
+ size 2668979437
checkpoint-5000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fb1d9dccc6df156bf79f2165da3b0191f25e93bdef8f4ae016b19c55147ccb0
3
+ size 14308
checkpoint-5000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d8779a0e602d6b5553a34546c8adc81b2a9a8132f35a901e91077493a54db68
3
+ size 1064
checkpoint-5000/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-5000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-5000/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-5000/trainer_state.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5000,
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
+ "epoch": 0.7,
55
+ "grad_norm": 0.0,
56
+ "learning_rate": 0.17200000000000001,
57
+ "loss": 0.0,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.8,
62
+ "grad_norm": 0.0,
63
+ "learning_rate": 0.168,
64
+ "loss": 0.0,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.9,
69
+ "grad_norm": 0.0,
70
+ "learning_rate": 0.164,
71
+ "loss": 1.3465,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 1.0,
76
+ "grad_norm": 0.0,
77
+ "learning_rate": 0.16000000000000003,
78
+ "loss": 1.0492,
79
+ "step": 5000
80
+ }
81
+ ],
82
+ "logging_steps": 500,
83
+ "max_steps": 25000,
84
+ "num_input_tokens_seen": 0,
85
+ "num_train_epochs": 5,
86
+ "save_steps": 500,
87
+ "total_flos": 3.727725453312e+16,
88
+ "train_batch_size": 8,
89
+ "trial_name": null,
90
+ "trial_params": null
91
+ }
checkpoint-5000/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-5000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-5500/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-5500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a582ead9e3325151f57f4fc326360ddbdf24c3aa84ab8d71474a60fdc3f9f9a
3
+ size 1334372264
checkpoint-5500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28c6a6da0122bc1d37884b50cd80d63f465c019354c0f835782fd3449837381f
3
+ size 2668979437
checkpoint-5500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff65a06692ddd18526b4a103275f8877b315025bec5ac5bbafc1f78612e09a01
3
+ size 14308
checkpoint-5500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81f80562878fc34e65412e152545c21b736b7724ac11c5405d7b8dccdb0a2b27
3
+ size 1064
checkpoint-5500/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
+ }