Hugging Face's logo

Elkelouizajo
/
bert_mnli_8000

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
Elkelouizajo commited on
Commit
6ed431d
·
verified ·
1 Parent(s): 8639d45

Upload 22 files

Browse files
Files changed (22) 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
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:d212efadb393cb99469424a297d0b1358f71f55bbb3e9e33a278aba847415ff7
3
+ size 1334372264
checkpoint-2500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5bfc36652d407a82a658e9506fe762fc549eb686b55f3dbb8a08510059be806
3
+ size 2668968429
checkpoint-2500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:883fabde14f30f627b5e2122d540ae5d64095850ecedccb973ef71bd237f62b7
3
+ size 13990
checkpoint-2500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b26b11b056389e26c7a590fe3e6d6a6d24910bcc36abcf212db05b6883c5c5
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": 2.5,
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": 0.5,
13
+ "grad_norm": 28.593961715698242,
14
+ "learning_rate": 1.8e-05,
15
+ "loss": 0.5987,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "grad_norm": 28.91183090209961,
21
+ "learning_rate": 1.6000000000000003e-05,
22
+ "loss": 0.4193,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.5,
27
+ "grad_norm": 14.28818130493164,
28
+ "learning_rate": 1.4e-05,
29
+ "loss": 0.327,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "grad_norm": 0.3224489390850067,
35
+ "learning_rate": 1.2e-05,
36
+ "loss": 0.3122,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 2.5,
41
+ "grad_norm": 197.5911102294922,
42
+ "learning_rate": 1e-05,
43
+ "loss": 0.1583,
44
+ "step": 2500
45
+ }
46
+ ],
47
+ "logging_steps": 500,
48
+ "max_steps": 5000,
49
+ "num_input_tokens_seen": 0,
50
+ "num_train_epochs": 5,
51
+ "save_steps": 500,
52
+ "total_flos": 4659656816640000.0,
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:d69eab8e307e3bfb72f9e64a0fa56858572083aec0cec6effaa7b5e35bab892d
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 sha256:28b7cee4b15dc84ca3fe780280d35236fdf5111c15a687064ac691ca1ef4d30f
3
+ size 1334372264
checkpoint-3000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a30ae42701eb1fa65db347fd6d2d57f626093e98a270ca53f51e1dfb97e4e96e
3
+ size 2668968429
checkpoint-3000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:344871fa7505b42381a3bc83bbf72d6830ac5f108fcd4229f2b0fff9857f0f70
3
+ size 13990
checkpoint-3000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f67948b4b4f855506777752c1cbbe8939b8cd843bc6cd868f45b4d59dea146
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": 3.0,
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": 0.5,
13
+ "grad_norm": 28.593961715698242,
14
+ "learning_rate": 1.8e-05,
15
+ "loss": 0.5987,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "grad_norm": 28.91183090209961,
21
+ "learning_rate": 1.6000000000000003e-05,
22
+ "loss": 0.4193,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.5,
27
+ "grad_norm": 14.28818130493164,
28
+ "learning_rate": 1.4e-05,
29
+ "loss": 0.327,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "grad_norm": 0.3224489390850067,
35
+ "learning_rate": 1.2e-05,
36
+ "loss": 0.3122,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 2.5,
41
+ "grad_norm": 197.5911102294922,
42
+ "learning_rate": 1e-05,
43
+ "loss": 0.1583,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "grad_norm": 0.19191676378250122,
49
+ "learning_rate": 8.000000000000001e-06,
50
+ "loss": 0.1589,
51
+ "step": 3000
52
+ }
53
+ ],
54
+ "logging_steps": 500,
55
+ "max_steps": 5000,
56
+ "num_input_tokens_seen": 0,
57
+ "num_train_epochs": 5,
58
+ "save_steps": 500,
59
+ "total_flos": 5591588179968000.0,
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:d69eab8e307e3bfb72f9e64a0fa56858572083aec0cec6effaa7b5e35bab892d
3
+ size 4920
checkpoint-3000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff