Hugging Face's logo

Elkelouizajo
/
bert_mnli_10K

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
Elkelouizajo commited on
Commit
4c04de7
·
verified ·
1 Parent(s): 9b8fa52

Upload 22 files

Browse files
Files changed (22) 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
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 sha256:730b2426874a6826a86c182d2eaa775d4d79c8be26ce6ea56eace3a9d491bd02
3
+ size 1334372264
checkpoint-3500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c24e088aaddb321d5a48e7ae7f588ad32034ac67500d3b612c742e7f09ef000
3
+ size 2668979437
checkpoint-3500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:162b66a1f9aaa87d944de7f1614247bca7774950957f2214ca1ddc75b62578ab
3
+ size 14308
checkpoint-3500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30b1e472278fc2f43548761a36d308a7bdc54084dd222a2378d2dddceb5762b1
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": 3.5,
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": 0.5,
13
+ "grad_norm": 28.553239822387695,
14
+ "learning_rate": 0.18000000000000002,
15
+ "loss": 26.996,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "grad_norm": 15.302693367004395,
21
+ "learning_rate": 0.16000000000000003,
22
+ "loss": 27.5789,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.5,
27
+ "grad_norm": 3.7751123905181885,
28
+ "learning_rate": 0.13999999999999999,
29
+ "loss": 21.6633,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "grad_norm": 5.127112865447998,
35
+ "learning_rate": 0.12,
36
+ "loss": 20.7534,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 2.5,
41
+ "grad_norm": 22.80483055114746,
42
+ "learning_rate": 0.1,
43
+ "loss": 18.4192,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "grad_norm": 30.512271881103516,
49
+ "learning_rate": 0.08000000000000002,
50
+ "loss": 16.2861,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 3.5,
55
+ "grad_norm": 23.139978408813477,
56
+ "learning_rate": 0.06,
57
+ "loss": 14.2996,
58
+ "step": 3500
59
+ }
60
+ ],
61
+ "logging_steps": 500,
62
+ "max_steps": 5000,
63
+ "num_input_tokens_seen": 0,
64
+ "num_train_epochs": 5,
65
+ "save_steps": 500,
66
+ "total_flos": 2.608848658500403e+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:cab7d19cf015097b4d7ee18a0eba83daf203cf2190d9d3ca5bbf68e6a4e56bb0
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 sha256:0da561ad36b5872c350fe59962d7c6b8d20320a7f16ebf1274bf04d3dada0062
3
+ size 1334372264
checkpoint-4000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17643a7880ddd1bec6d7c4c86aefd76def967f8a79114a740ad45ae12b146cdb
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:e8ba7061752bbd15c435f7fd694b166b4b0683cfd0359f1752326f9887ad32fd
3
+ size 14308
checkpoint-4000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b372259c178663a9d7a1d3aee1c2d86d171346ded8401c7de850fa3de90b2e
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": 4.0,
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": 0.5,
13
+ "grad_norm": 28.553239822387695,
14
+ "learning_rate": 0.18000000000000002,
15
+ "loss": 26.996,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "grad_norm": 15.302693367004395,
21
+ "learning_rate": 0.16000000000000003,
22
+ "loss": 27.5789,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.5,
27
+ "grad_norm": 3.7751123905181885,
28
+ "learning_rate": 0.13999999999999999,
29
+ "loss": 21.6633,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "grad_norm": 5.127112865447998,
35
+ "learning_rate": 0.12,
36
+ "loss": 20.7534,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 2.5,
41
+ "grad_norm": 22.80483055114746,
42
+ "learning_rate": 0.1,
43
+ "loss": 18.4192,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "grad_norm": 30.512271881103516,
49
+ "learning_rate": 0.08000000000000002,
50
+ "loss": 16.2861,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 3.5,
55
+ "grad_norm": 23.139978408813477,
56
+ "learning_rate": 0.06,
57
+ "loss": 14.2996,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 4.0,
62
+ "grad_norm": 23.255733489990234,
63
+ "learning_rate": 0.04000000000000001,
64
+ "loss": 9.7249,
65
+ "step": 4000
66
+ }
67
+ ],
68
+ "logging_steps": 500,
69
+ "max_steps": 5000,
70
+ "num_input_tokens_seen": 0,
71
+ "num_train_epochs": 5,
72
+ "save_steps": 500,
73
+ "total_flos": 2.9814348175589376e+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:cab7d19cf015097b4d7ee18a0eba83daf203cf2190d9d3ca5bbf68e6a4e56bb0
3
+ size 4920
checkpoint-4000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff