Hugging Face's logo

uvegesistvan
/
EDG_bert_large_uncased

Text Classification
Transformers
TensorBoard
Safetensors
bert
Model card Files
xet
Metrics Community
uvegesistvan commited on
Commit
0f190ac
·
verified ·
1 Parent(s): 5e27c5d

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. checkpoint-314/config.json +37 -0
  2. checkpoint-314/model.safetensors +3 -0
  3. checkpoint-314/optimizer.pt +3 -0
  4. checkpoint-314/rng_state.pth +3 -0
  5. checkpoint-314/scheduler.pt +3 -0
  6. checkpoint-314/trainer_state.json +80 -0
  7. checkpoint-314/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.1740140762.07d6f98d1ab7.784.2 +3 -0
  17. model.safetensors +3 -0
  18. training_args.bin +3 -0
checkpoint-314/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-large-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": 1024,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
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": 16,
28
+ "num_hidden_layers": 24,
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-314/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec7a9b0683ae512ca29480e2fbb43c7eaa268609c94be2fe2b7aa29208e59f70
3
+ size 1340626860
checkpoint-314/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:475b9fab2ea9c97731f34a71d0e1bd7da160f7e43b673df8595759a087a195e1
3
+ size 2681488557
checkpoint-314/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f137f42c5b61f5a17c9249e026dea7f7d397f2fa54c6f809218fe30af740d604
3
+ size 14244
checkpoint-314/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:248add3643a368a3edd8857559d2626e363ac8e81bd77ae509f1529eeb27d0a9
3
+ size 1064
checkpoint-314/trainer_state.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7794396222680878,
3
+ "best_model_checkpoint": "model/checkpoint-314",
4
+ "epoch": 2.0,
5
+ "eval_steps": 50,
6
+ "global_step": 314,
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": 3.9800825119018555,
14
+ "learning_rate": 1.6927223719676552e-05,
15
+ "loss": 0.6026,
16
+ "step": 157
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8338658146964856,
21
+ "eval_f1": 0.7583239638877448,
22
+ "eval_loss": 0.4550146460533142,
23
+ "eval_precision": 0.6953321969194337,
24
+ "eval_recall": 0.8338658146964856,
25
+ "eval_runtime": 13.2332,
26
+ "eval_samples_per_second": 23.653,
27
+ "eval_steps_per_second": 1.511,
28
+ "step": 157
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 0.458461195230484,
33
+ "learning_rate": 8.463611859838276e-06,
34
+ "loss": 0.3677,
35
+ "step": 314
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8370607028753994,
40
+ "eval_f1": 0.7794396222680878,
41
+ "eval_loss": 0.5186702609062195,
42
+ "eval_precision": 0.7375077069670983,
43
+ "eval_recall": 0.8370607028753994,
44
+ "eval_runtime": 13.1993,
45
+ "eval_samples_per_second": 23.713,
46
+ "eval_steps_per_second": 1.515,
47
+ "step": 314
48
+ }
49
+ ],
50
+ "logging_steps": 50,
51
+ "max_steps": 471,
52
+ "num_input_tokens_seen": 0,
53
+ "num_train_epochs": 3,
54
+ "save_steps": 50,
55
+ "stateful_callbacks": {
56
+ "EarlyStoppingCallback": {
57
+ "args": {
58
+ "early_stopping_patience": 2,
59
+ "early_stopping_threshold": 0.0
60
+ },
61
+ "attributes": {
62
+ "early_stopping_patience_counter": 0
63
+ }
64
+ },
65
+ "TrainerControl": {
66
+ "args": {
67
+ "should_epoch_stop": false,
68
+ "should_evaluate": false,
69
+ "should_log": false,
70
+ "should_save": true,
71
+ "should_training_stop": false
72
+ },
73
+ "attributes": {}
74
+ }
75
+ },
76
+ "total_flos": 2329836280320000.0,
77
+ "train_batch_size": 16,
78
+ "trial_name": null,
79
+ "trial_params": null
80
+ }
checkpoint-314/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5badd6ed7ab007b43f216723b3854ddac444a41763d536c45b78ddba25ec682f
3
+ size 5240
checkpoint-471/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google-bert/bert-large-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": 1024,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
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": 16,
28
+ "num_hidden_layers": 24,
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 sha256:1a7d4a7950a50a30ba82f60a176e9c68a934ec0c0e1a92254975c0d180f4dd0d
3
+ size 1340626860
checkpoint-471/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23b21cb914416a182b903c57617e122f08e534a6e98d723fd907e3c7aab0aaf8
3
+ size 2681488557
checkpoint-471/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3222d896ae9dbef5ef4cfb92a0d4ee99a73de89028898aae5806d08aec1f7d5
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": 0.8446599690186122,
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": 3.9800825119018555,
14
+ "learning_rate": 1.6927223719676552e-05,
15
+ "loss": 0.6026,
16
+ "step": 157
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.8338658146964856,
21
+ "eval_f1": 0.7583239638877448,
22
+ "eval_loss": 0.4550146460533142,
23
+ "eval_precision": 0.6953321969194337,
24
+ "eval_recall": 0.8338658146964856,
25
+ "eval_runtime": 13.2332,
26
+ "eval_samples_per_second": 23.653,
27
+ "eval_steps_per_second": 1.511,
28
+ "step": 157
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "grad_norm": 0.458461195230484,
33
+ "learning_rate": 8.463611859838276e-06,
34
+ "loss": 0.3677,
35
+ "step": 314
36
+ },
37
+ {
38
+ "epoch": 2.0,
39
+ "eval_accuracy": 0.8370607028753994,
40
+ "eval_f1": 0.7794396222680878,
41
+ "eval_loss": 0.5186702609062195,
42
+ "eval_precision": 0.7375077069670983,
43
+ "eval_recall": 0.8370607028753994,
44
+ "eval_runtime": 13.1993,
45
+ "eval_samples_per_second": 23.713,
46
+ "eval_steps_per_second": 1.515,
47
+ "step": 314
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "grad_norm": 31.189651489257812,
52
+ "learning_rate": 0.0,
53
+ "loss": 0.1735,
54
+ "step": 471
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_accuracy": 0.8466453674121406,
59
+ "eval_f1": 0.8446599690186122,
60
+ "eval_loss": 0.4975687265396118,
61
+ "eval_precision": 0.845583764062025,
62
+ "eval_recall": 0.8466453674121406,
63
+ "eval_runtime": 13.2128,
64
+ "eval_samples_per_second": 23.689,
65
+ "eval_steps_per_second": 1.514,
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": 3494754420480000.0,
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-large-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": 1024,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
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": 16,
28
+ "num_hidden_layers": 24,
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.1740140762.07d6f98d1ab7.784.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be93622c883aad6c780b1d8301165e7c3e15e84149c324d2bc3f67fda76b9a9
3
+ size 7561
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7d4a7950a50a30ba82f60a176e9c68a934ec0c0e1a92254975c0d180f4dd0d
3
+ size 1340626860
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5badd6ed7ab007b43f216723b3854ddac444a41763d536c45b78ddba25ec682f
3
+ size 5240