Hugging Face's logo

samil24
/
bert-base-uncased-finetuned-rte-run_3

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
samil24 commited on
Commit
71443ad
·
verified ·
1 Parent(s): f8fd688

Training in progress, epoch 1

Browse files
Files changed (29) hide show
  1. model.safetensors +1 -1
  2. run-10/checkpoint-156/config.json +26 -0
  3. run-10/checkpoint-156/model.safetensors +3 -0
  4. run-10/checkpoint-156/optimizer.pt +3 -0
  5. run-10/checkpoint-156/rng_state.pth +3 -0
  6. run-10/checkpoint-156/scheduler.pt +3 -0
  7. run-10/checkpoint-156/special_tokens_map.json +7 -0
  8. run-10/checkpoint-156/tokenizer.json +0 -0
  9. run-10/checkpoint-156/tokenizer_config.json +56 -0
  10. run-10/checkpoint-156/trainer_state.json +56 -0
  11. run-10/checkpoint-156/training_args.bin +3 -0
  12. run-10/checkpoint-156/vocab.txt +0 -0
  13. run-10/checkpoint-234/config.json +26 -0
  14. run-10/checkpoint-234/model.safetensors +3 -0
  15. run-10/checkpoint-234/optimizer.pt +3 -0
  16. run-10/checkpoint-234/rng_state.pth +3 -0
  17. run-10/checkpoint-234/scheduler.pt +3 -0
  18. run-10/checkpoint-234/special_tokens_map.json +7 -0
  19. run-10/checkpoint-234/tokenizer.json +0 -0
  20. run-10/checkpoint-234/tokenizer_config.json +56 -0
  21. run-10/checkpoint-234/trainer_state.json +65 -0
  22. run-10/checkpoint-234/training_args.bin +3 -0
  23. run-10/checkpoint-234/vocab.txt +0 -0
  24. runs/Apr01_18-57-28_1357c7d90830/events.out.tfevents.1743540286.1357c7d90830.592.80 +3 -0
  25. runs/Apr01_18-57-28_1357c7d90830/events.out.tfevents.1743540305.1357c7d90830.592.81 +3 -0
  26. runs/Apr01_18-57-28_1357c7d90830/events.out.tfevents.1743540324.1357c7d90830.592.82 +3 -0
  27. runs/Apr01_18-57-28_1357c7d90830/events.out.tfevents.1743540344.1357c7d90830.592.83 +3 -0
  28. runs/Apr01_18-57-28_1357c7d90830/events.out.tfevents.1743541466.1357c7d90830.592.84 +3 -0
  29. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00eaebd3225be5bdab052ca99f06a3ee249d38e00565732ec0924c5f4bcd5e9e
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80af645029bb1bfec916028468f6711e61d19185b928d1cf902d5a75ca98475b
3
  size 437958648
run-10/checkpoint-156/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.50.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-10/checkpoint-156/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22fe109a57273476b3238ca7f666b8a75751891666006fd366417b301a36a785
3
+ size 437958648
run-10/checkpoint-156/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56636ed32df8941e807bf4545ab1dce21be66019f6bd1447157e7b2ec4d63266
3
+ size 876038394
run-10/checkpoint-156/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a64755083f7633da1abd1de577e641d7084f1c57535fb19884090b3171beb5
3
+ size 14244
run-10/checkpoint-156/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51aeeaaf7e81558043e91e4e0ffd625d21eae7ef35b7bd7bdc62d163318afda8
3
+ size 1064
run-10/checkpoint-156/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
+ }
run-10/checkpoint-156/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-10/checkpoint-156/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
run-10/checkpoint-156/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 156,
3
+ "best_metric": 0.6498194945848376,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-10/checkpoint-156",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 156,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.628158844765343,
15
+ "eval_loss": 0.6613978743553162,
16
+ "eval_runtime": 0.6597,
17
+ "eval_samples_per_second": 419.887,
18
+ "eval_steps_per_second": 7.579,
19
+ "step": 78
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.6498194945848376,
24
+ "eval_loss": 0.670578122138977,
25
+ "eval_runtime": 0.6582,
26
+ "eval_samples_per_second": 420.876,
27
+ "eval_steps_per_second": 7.597,
28
+ "step": 156
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 234,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 3,
35
+ "save_steps": 500,
36
+ "stateful_callbacks": {
37
+ "TrainerControl": {
38
+ "args": {
39
+ "should_epoch_stop": false,
40
+ "should_evaluate": false,
41
+ "should_log": false,
42
+ "should_save": true,
43
+ "should_training_stop": false
44
+ },
45
+ "attributes": {}
46
+ }
47
+ },
48
+ "total_flos": 0,
49
+ "train_batch_size": 32,
50
+ "trial_name": null,
51
+ "trial_params": {
52
+ "learning_rate": 9.913053557998736e-05,
53
+ "num_train_epochs": 3,
54
+ "per_device_train_batch_size": 32
55
+ }
56
+ }
run-10/checkpoint-156/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8f223fbd5e6148fb7fbb4a3dbd630a034ee4975a28493eb0230468b789e437c
3
+ size 5432
run-10/checkpoint-156/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-10/checkpoint-234/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.50.2",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-10/checkpoint-234/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c87d096d0318484461f6eb9deed6a686528ea41ae19ff50931342568eaed850
3
+ size 437958648
run-10/checkpoint-234/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6af0f144d17cdc0923661da7c5a8efb0396b17c33fca326284a0583d36f25a71
3
+ size 876038394
run-10/checkpoint-234/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a1bc48d819eb79a8f5fd91d99147914c98b62b1316d8be312ce4a6ce90c4038
3
+ size 14244
run-10/checkpoint-234/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:781d05c2ca6c2aa01d6d9a42a28ed93bbe136ea3f3a0dd5f812fecb1034851c9
3
+ size 1064
run-10/checkpoint-234/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
+ }
run-10/checkpoint-234/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-10/checkpoint-234/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
run-10/checkpoint-234/trainer_state.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 156,
3
+ "best_metric": 0.6498194945848376,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-10/checkpoint-156",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 234,
8
+ "is_hyper_param_search": true,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.628158844765343,
15
+ "eval_loss": 0.6613978743553162,
16
+ "eval_runtime": 0.6597,
17
+ "eval_samples_per_second": 419.887,
18
+ "eval_steps_per_second": 7.579,
19
+ "step": 78
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.6498194945848376,
24
+ "eval_loss": 0.670578122138977,
25
+ "eval_runtime": 0.6582,
26
+ "eval_samples_per_second": 420.876,
27
+ "eval_steps_per_second": 7.597,
28
+ "step": 156
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.6425992779783394,
33
+ "eval_loss": 0.9183883666992188,
34
+ "eval_runtime": 0.6591,
35
+ "eval_samples_per_second": 420.239,
36
+ "eval_steps_per_second": 7.586,
37
+ "step": 234
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 234,
42
+ "num_input_tokens_seen": 0,
43
+ "num_train_epochs": 3,
44
+ "save_steps": 500,
45
+ "stateful_callbacks": {
46
+ "TrainerControl": {
47
+ "args": {
48
+ "should_epoch_stop": false,
49
+ "should_evaluate": false,
50
+ "should_log": false,
51
+ "should_save": true,
52
+ "should_training_stop": true
53
+ },
54
+ "attributes": {}
55
+ }
56
+ },
57
+ "total_flos": 0,
58
+ "train_batch_size": 32,
59
+ "trial_name": null,
60
+ "trial_params": {
61
+ "learning_rate": 9.913053557998736e-05,
62
+ "num_train_epochs": 3,
63
+ "per_device_train_batch_size": 32
64
+ }
65
+ }
run-10/checkpoint-234/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8f223fbd5e6148fb7fbb4a3dbd630a034ee4975a28493eb0230468b789e437c
3
+ size 5432
run-10/checkpoint-234/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr01_18-57-28_1357c7d90830/events.out.tfevents.1743540286.1357c7d90830.592.80 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ba2a61f5bdec1ac72b0a928b89398061f711165e88e1537f7ab314beb162cb8
3
+ size 5418
runs/Apr01_18-57-28_1357c7d90830/events.out.tfevents.1743540305.1357c7d90830.592.81 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c63960c5e50776b3b36dc4c90314dca532544a0ff294a0e0bd84a4b1051ff10
3
+ size 5418
runs/Apr01_18-57-28_1357c7d90830/events.out.tfevents.1743540324.1357c7d90830.592.82 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:006b2145ffda574266acff7fa129e0a2fab1ea5c13f568daf7655fbd2bd26640
3
+ size 5419
runs/Apr01_18-57-28_1357c7d90830/events.out.tfevents.1743540344.1357c7d90830.592.83 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f2997c59f3461bef3d9f5eae0daa82e7da3a8d5968df61a38bbec9c6dcd29b4
3
+ size 5419
runs/Apr01_18-57-28_1357c7d90830/events.out.tfevents.1743541466.1357c7d90830.592.84 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b86fda7afd9e196eb8ec0ffeb4583d22acae79b4ee5e827b2bd0e4f9edec2fca
3
+ size 6419
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8f223fbd5e6148fb7fbb4a3dbd630a034ee4975a28493eb0230468b789e437c
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a36973883c8e4a04fbb28b84d7c646cb1aed232027e999f254dc9d94f8e0011d
3
  size 5432