Hugging Face's logo

uvegesistvan
/
EDG_bert_base_uncased

Text Classification
Transformers
TensorBoard
Safetensors
bert
Model card Files Metrics Community
uvegesistvan commited on
Commit
e71d3a5
·
verified ·
1 Parent(s): 648212d

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. checkpoint-1565/config.json +36 -0
  2. checkpoint-1565/model.safetensors +3 -0
  3. checkpoint-1565/optimizer.pt +3 -0
  4. checkpoint-1565/rng_state.pth +3 -0
  5. checkpoint-1565/scheduler.pt +3 -0
  6. checkpoint-1565/trainer_state.json +137 -0
  7. checkpoint-1565/training_args.bin +3 -0
  8. checkpoint-471/config.json +37 -0
  9. checkpoint-471/model.safetensors +3 -0
  10. checkpoint-471/optimizer.pt +3 -0
  11. checkpoint-471/rng_state.pth +3 -0
  12. checkpoint-471/scheduler.pt +3 -0
  13. checkpoint-471/trainer_state.json +99 -0
  14. checkpoint-471/training_args.bin +3 -0
  15. config.json +37 -0
  16. events.out.tfevents.1739872021.6f1d6bbb5082.6549.0 +3 -0
  17. events.out.tfevents.1739873014.6f1d6bbb5082.6549.1 +3 -0
  18. events.out.tfevents.1739874060.6f1d6bbb5082.6549.2 +3 -0
  19. model.safetensors +3 -0
  20. training_args.bin +3 -0
checkpoint-1565/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.48.3",
33
+ "type_vocab_size": 2,
34
+ "use_cache": true,
35
+ "vocab_size": 30522
36
+ }
checkpoint-1565/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a7554f291917e24d1b75468e6e19716bc602a6c86ba8b9d148e696b403c39b2
3
+ size 437961724
checkpoint-1565/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8159a39928fdb9a2d7d66ccf9be2885487cd7600ab4d7cbf1442d91f22ed9f50
3
+ size 876044474
checkpoint-1565/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cffe890a29cc9d12cbe4838984414ced04ba325f9f775d3c49cde4d03eb4b26
3
+ size 14244
checkpoint-1565/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c04eae154b0c3b34ecf0f95baa80f1b4438202f2050d60d86b8e0109dfe7bcbe
3
+ size 1064
checkpoint-1565/trainer_state.json ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8518154428697561,
3
+ "best_model_checkpoint": "model/checkpoint-1252",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1565,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 8.763400077819824,
14
+ "learning_rate": 1.7092150170648464e-05,
15
+ "loss": 0.9929,
16
+ "step": 313
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8242811501597445,
21
+ "eval_f1": 0.8190724938847023,
22
+ "eval_loss": 0.8321825861930847,
23
+ "eval_precision": 0.8210601694276454,
24
+ "eval_recall": 0.8242811501597445,
25
+ "eval_runtime": 3.3376,
26
+ "eval_samples_per_second": 93.779,
27
+ "eval_steps_per_second": 11.985,
28
+ "step": 313
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 0.7372869253158569,
33
+ "learning_rate": 1.281911262798635e-05,
34
+ "loss": 0.7181,
35
+ "step": 626
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8498402555910544,
40
+ "eval_f1": 0.8053276047082008,
41
+ "eval_loss": 1.3033751249313354,
42
+ "eval_precision": 0.857962395302651,
43
+ "eval_recall": 0.8498402555910544,
44
+ "eval_runtime": 3.3428,
45
+ "eval_samples_per_second": 93.635,
46
+ "eval_steps_per_second": 11.966,
47
+ "step": 626
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 86.433349609375,
52
+ "learning_rate": 8.546075085324232e-06,
53
+ "loss": 0.3916,
54
+ "step": 939
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8306709265175719,
59
+ "eval_f1": 0.8409538025804452,
60
+ "eval_loss": 1.007387399673462,
61
+ "eval_precision": 0.8585334191289256,
62
+ "eval_recall": 0.8306709265175719,
63
+ "eval_runtime": 3.3378,
64
+ "eval_samples_per_second": 93.773,
65
+ "eval_steps_per_second": 11.984,
66
+ "step": 939
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "grad_norm": 0.03480984643101692,
71
+ "learning_rate": 4.273037542662116e-06,
72
+ "loss": 0.1311,
73
+ "step": 1252
74
+ },
75
+ {
76
+ "epoch": 4.0,
77
+ "eval_accuracy": 0.8594249201277955,
78
+ "eval_f1": 0.8518154428697561,
79
+ "eval_loss": 1.7190024852752686,
80
+ "eval_precision": 0.8474117456400535,
81
+ "eval_recall": 0.8594249201277955,
82
+ "eval_runtime": 3.3488,
83
+ "eval_samples_per_second": 93.465,
84
+ "eval_steps_per_second": 11.944,
85
+ "step": 1252
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "grad_norm": 0.17574211955070496,
90
+ "learning_rate": 0.0,
91
+ "loss": 0.0597,
92
+ "step": 1565
93
+ },
94
+ {
95
+ "epoch": 5.0,
96
+ "eval_accuracy": 0.853035143769968,
97
+ "eval_f1": 0.842110528584532,
98
+ "eval_loss": 1.8323806524276733,
99
+ "eval_precision": 0.8375123279276634,
100
+ "eval_recall": 0.853035143769968,
101
+ "eval_runtime": 3.3685,
102
+ "eval_samples_per_second": 92.92,
103
+ "eval_steps_per_second": 11.875,
104
+ "step": 1565
105
+ }
106
+ ],
107
+ "logging_steps": 500,
108
+ "max_steps": 1565,
109
+ "num_input_tokens_seen": 0,
110
+ "num_train_epochs": 5,
111
+ "save_steps": 500,
112
+ "stateful_callbacks": {
113
+ "EarlyStoppingCallback": {
114
+ "args": {
115
+ "early_stopping_patience": 2,
116
+ "early_stopping_threshold": 0.0
117
+ },
118
+ "attributes": {
119
+ "early_stopping_patience_counter": 1
120
+ }
121
+ },
122
+ "TrainerControl": {
123
+ "args": {
124
+ "should_epoch_stop": false,
125
+ "should_evaluate": false,
126
+ "should_log": false,
127
+ "should_save": true,
128
+ "should_training_stop": true
129
+ },
130
+ "attributes": {}
131
+ }
132
+ },
133
+ "total_flos": 3288917721600000.0,
134
+ "train_batch_size": 8,
135
+ "trial_name": null,
136
+ "trial_params": null
137
+ }
checkpoint-1565/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74bd2c55bc9aa56eb085531a8dbb26972bca5c2f241f9513bcd73d35c224ae74
3
+ size 5240
checkpoint-471/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.49.0",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 30522
37
+ }
checkpoint-471/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7fa5157e50c51a2c86c4fcb45a72be5953238cb553279fb15571566638158b9
3
+ size 437961724
checkpoint-471/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d637bbe5b4759bdf1846a57f1365d08be4d3aeda8ffeae415ebd0ee4d03e3b
3
+ size 876044474
checkpoint-471/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68be0debaead2051cf9242a42030ec1282dac4c45aada12a151edba8dea371ce
3
+ size 14244
checkpoint-471/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a4981396181a43c6f3aec5d64e8424b38973866708ed99d108d63abc2242b17
3
+ size 1064
checkpoint-471/trainer_state.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8289012162572651,
3
+ "best_model_checkpoint": "model/checkpoint-471",
4
+ "epoch": 3.0,
5
+ "eval_steps": 50,
6
+ "global_step": 471,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "grad_norm": 4.966571807861328,
14
+ "learning_rate": 1.6927223719676552e-05,
15
+ "loss": 0.6737,
16
+ "step": 157
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8338658146964856,
21
+ "eval_f1": 0.7583239638877448,
22
+ "eval_loss": 0.4658426344394684,
23
+ "eval_precision": 0.6953321969194337,
24
+ "eval_recall": 0.8338658146964856,
25
+ "eval_runtime": 4.2259,
26
+ "eval_samples_per_second": 74.067,
27
+ "eval_steps_per_second": 4.733,
28
+ "step": 157
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 2.303415060043335,
33
+ "learning_rate": 8.463611859838276e-06,
34
+ "loss": 0.4314,
35
+ "step": 314
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8434504792332268,
40
+ "eval_f1": 0.7790813157791667,
41
+ "eval_loss": 0.4860698878765106,
42
+ "eval_precision": 0.7691538699371329,
43
+ "eval_recall": 0.8434504792332268,
44
+ "eval_runtime": 4.2642,
45
+ "eval_samples_per_second": 73.402,
46
+ "eval_steps_per_second": 4.69,
47
+ "step": 314
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 11.434114456176758,
52
+ "learning_rate": 0.0,
53
+ "loss": 0.286,
54
+ "step": 471
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8466453674121406,
59
+ "eval_f1": 0.8289012162572651,
60
+ "eval_loss": 0.4335961937904358,
61
+ "eval_precision": 0.8219730992689277,
62
+ "eval_recall": 0.8466453674121406,
63
+ "eval_runtime": 4.1847,
64
+ "eval_samples_per_second": 74.796,
65
+ "eval_steps_per_second": 4.779,
66
+ "step": 471
67
+ }
68
+ ],
69
+ "logging_steps": 50,
70
+ "max_steps": 471,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 3,
73
+ "save_steps": 50,
74
+ "stateful_callbacks": {
75
+ "EarlyStoppingCallback": {
76
+ "args": {
77
+ "early_stopping_patience": 2,
78
+ "early_stopping_threshold": 0.0
79
+ },
80
+ "attributes": {
81
+ "early_stopping_patience_counter": 0
82
+ }
83
+ },
84
+ "TrainerControl": {
85
+ "args": {
86
+ "should_epoch_stop": false,
87
+ "should_evaluate": false,
88
+ "should_log": false,
89
+ "should_save": true,
90
+ "should_training_stop": true
91
+ },
92
+ "attributes": {}
93
+ }
94
+ },
95
+ "total_flos": 986675316480000.0,
96
+ "train_batch_size": 16,
97
+ "trial_name": null,
98
+ "trial_params": null
99
+ }
checkpoint-471/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5badd6ed7ab007b43f216723b3854ddac444a41763d536c45b78ddba25ec682f
3
+ size 5240
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-base-uncased",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "LABEL_0": 0,
21
+ "LABEL_1": 1,
22
+ "LABEL_2": 2
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_position_embeddings": 512,
26
+ "model_type": "bert",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "position_embedding_type": "absolute",
31
+ "problem_type": "single_label_classification",
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.49.0",
34
+ "type_vocab_size": 2,
35
+ "use_cache": true,
36
+ "vocab_size": 30522
37
+ }
events.out.tfevents.1739872021.6f1d6bbb5082.6549.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ccc553d54deb5f3a85145f641ba6c29687163deb692c0541439653a549257ed
3
+ size 7559
events.out.tfevents.1739873014.6f1d6bbb5082.6549.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7c09a8953bd2928b3dcf0e904ebe8f3d8292455eba6d7b68c86bb095daa3acc
3
+ size 8927
events.out.tfevents.1739874060.6f1d6bbb5082.6549.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d8b7a5732b43b8343f21d1da9e4ba863bd8b670439bd6c7e63fb19bde13665
3
+ size 7559
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7fa5157e50c51a2c86c4fcb45a72be5953238cb553279fb15571566638158b9
3
+ size 437961724
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5badd6ed7ab007b43f216723b3854ddac444a41763d536c45b78ddba25ec682f
3
+ size 5240