Hugging Face's logo

Elkelouizajo
/
bert_mnli_augmented

Safetensors
bert
Generated from Trainer
Model card Files Community
Elkelouizajo commited on
Commit
ae8c07d
·
verified ·
1 Parent(s): bc980bd

Upload 22 files

Browse files
Files changed (22) hide show
  1. checkpoint-5000/config.json +42 -0
  2. checkpoint-5000/model.safetensors +3 -0
  3. checkpoint-5000/optimizer.pt +3 -0
  4. checkpoint-5000/rng_state.pth +3 -0
  5. checkpoint-5000/scheduler.pt +3 -0
  6. checkpoint-5000/special_tokens_map.json +7 -0
  7. checkpoint-5000/tokenizer.json +0 -0
  8. checkpoint-5000/tokenizer_config.json +55 -0
  9. checkpoint-5000/trainer_state.json +91 -0
  10. checkpoint-5000/training_args.bin +3 -0
  11. checkpoint-5000/vocab.txt +0 -0
  12. checkpoint-5500/config.json +42 -0
  13. checkpoint-5500/model.safetensors +3 -0
  14. checkpoint-5500/optimizer.pt +3 -0
  15. checkpoint-5500/rng_state.pth +3 -0
  16. checkpoint-5500/scheduler.pt +3 -0
  17. checkpoint-5500/special_tokens_map.json +7 -0
  18. checkpoint-5500/tokenizer.json +0 -0
  19. checkpoint-5500/tokenizer_config.json +55 -0
  20. checkpoint-5500/trainer_state.json +98 -0
  21. checkpoint-5500/training_args.bin +3 -0
  22. checkpoint-5500/vocab.txt +0 -0
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:d4dbc0868269a0bff153cbc826af20ce10a3af303fb80dc8e667fe0f12cc5abd
3
+ size 1334372264
checkpoint-5000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38228180adb39c88ce962d37e13e18c8d6c1476db16d8b39bd60ccd77d29b8cc
3
+ size 2668968429
checkpoint-5000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a5ab86623310b2804b2a5c06c695d9ecd945805dbf62a9705cbe97c1cd3b98c
3
+ size 13990
checkpoint-5000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dc7264836cfbe49744e976b843625336333b4f90846c7944ae99fc0bf9a02ca
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": 2.498750624687656,
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": 0.25,
13
+ "grad_norm": 1.5337328910827637,
14
+ "learning_rate": 1.900049975012494e-05,
15
+ "loss": 0.4281,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 1.992353081703186,
21
+ "learning_rate": 1.8000999500249876e-05,
22
+ "loss": 0.2656,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 1.4741365909576416,
28
+ "learning_rate": 1.7001499250374815e-05,
29
+ "loss": 0.263,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 0.5607998967170715,
35
+ "learning_rate": 1.600199900049975e-05,
36
+ "loss": 0.2228,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.25,
41
+ "grad_norm": 56.73757553100586,
42
+ "learning_rate": 1.500249875062469e-05,
43
+ "loss": 0.1552,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.5,
48
+ "grad_norm": 10.09034252166748,
49
+ "learning_rate": 1.4002998500749626e-05,
50
+ "loss": 0.1395,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 1.75,
55
+ "grad_norm": 49.66099166870117,
56
+ "learning_rate": 1.3003498250874565e-05,
57
+ "loss": 0.1396,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 2.0,
62
+ "grad_norm": 1.33147394657135,
63
+ "learning_rate": 1.2003998000999502e-05,
64
+ "loss": 0.1468,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 2.25,
69
+ "grad_norm": 0.00538645638152957,
70
+ "learning_rate": 1.100449775112444e-05,
71
+ "loss": 0.0595,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 2.5,
76
+ "grad_norm": 1.2792365550994873,
77
+ "learning_rate": 1.0004997501249377e-05,
78
+ "loss": 0.0529,
79
+ "step": 5000
80
+ }
81
+ ],
82
+ "logging_steps": 500,
83
+ "max_steps": 10005,
84
+ "num_input_tokens_seen": 0,
85
+ "num_train_epochs": 5,
86
+ "save_steps": 500,
87
+ "total_flos": 9316051873508352.0,
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 sha256:1fa413c015ab4e81047ee7566efb44836d3f954f40726365f4c18a1bb17ec28e
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 sha256:236605f2272f74167a04bfd27cebfb784fa390381607dea7542be093790dfa72
3
+ size 1334372264
checkpoint-5500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2260cd5b85e98501a80e20d38fff258be7e24b0556ec2e804c5657cce58cbf8b
3
+ size 2668968429
checkpoint-5500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e437f951beddbfcd60d5d39f6ae640fb6fd98b4b45258b2be068011c14a9b3f
3
+ size 13990
checkpoint-5500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc32ecb948bacea013d2fd6697ff8ceb983834ecd0cdc80fcf05b994e4f51fee
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
+ }
checkpoint-5500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-5500/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-5500/trainer_state.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.7486256871564216,
5
+ "eval_steps": 500,
6
+ "global_step": 5500,
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": 1.5337328910827637,
14
+ "learning_rate": 1.900049975012494e-05,
15
+ "loss": 0.4281,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.5,
20
+ "grad_norm": 1.992353081703186,
21
+ "learning_rate": 1.8000999500249876e-05,
22
+ "loss": 0.2656,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.75,
27
+ "grad_norm": 1.4741365909576416,
28
+ "learning_rate": 1.7001499250374815e-05,
29
+ "loss": 0.263,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 1.0,
34
+ "grad_norm": 0.5607998967170715,
35
+ "learning_rate": 1.600199900049975e-05,
36
+ "loss": 0.2228,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 1.25,
41
+ "grad_norm": 56.73757553100586,
42
+ "learning_rate": 1.500249875062469e-05,
43
+ "loss": 0.1552,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 1.5,
48
+ "grad_norm": 10.09034252166748,
49
+ "learning_rate": 1.4002998500749626e-05,
50
+ "loss": 0.1395,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 1.75,
55
+ "grad_norm": 49.66099166870117,
56
+ "learning_rate": 1.3003498250874565e-05,
57
+ "loss": 0.1396,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 2.0,
62
+ "grad_norm": 1.33147394657135,
63
+ "learning_rate": 1.2003998000999502e-05,
64
+ "loss": 0.1468,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 2.25,
69
+ "grad_norm": 0.00538645638152957,
70
+ "learning_rate": 1.100449775112444e-05,
71
+ "loss": 0.0595,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 2.5,
76
+ "grad_norm": 1.2792365550994873,
77
+ "learning_rate": 1.0004997501249377e-05,
78
+ "loss": 0.0529,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 2.75,
83
+ "grad_norm": 0.09408382326364517,
84
+ "learning_rate": 9.005497251374314e-06,
85
+ "loss": 0.0578,
86
+ "step": 5500
87
+ }
88
+ ],
89
+ "logging_steps": 500,
90
+ "max_steps": 10005,
91
+ "num_input_tokens_seen": 0,
92
+ "num_train_epochs": 5,
93
+ "save_steps": 500,
94
+ "total_flos": 1.0247983236836352e+16,
95
+ "train_batch_size": 8,
96
+ "trial_name": null,
97
+ "trial_params": null
98
+ }
checkpoint-5500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fa413c015ab4e81047ee7566efb44836d3f954f40726365f4c18a1bb17ec28e
3
+ size 4920
checkpoint-5500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff