Hugging Face's logo

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

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files
xet
Metrics Community
berkayaltntas commited on
Commit
8562844
·
verified ·
1 Parent(s): 2b8337a

Training in progress, epoch 1

Browse files
Files changed (38) hide show
  1. model.safetensors +1 -1
  2. run-12/checkpoint-156/config.json +26 -0
  3. run-12/checkpoint-156/model.safetensors +3 -0
  4. run-12/checkpoint-156/optimizer.pt +3 -0
  5. run-12/checkpoint-156/rng_state.pth +3 -0
  6. run-12/checkpoint-156/scheduler.pt +3 -0
  7. run-12/checkpoint-156/special_tokens_map.json +7 -0
  8. run-12/checkpoint-156/tokenizer.json +0 -0
  9. run-12/checkpoint-156/tokenizer_config.json +56 -0
  10. run-12/checkpoint-156/trainer_state.json +58 -0
  11. run-12/checkpoint-156/training_args.bin +3 -0
  12. run-12/checkpoint-156/vocab.txt +0 -0
  13. run-12/checkpoint-234/config.json +26 -0
  14. run-12/checkpoint-234/model.safetensors +3 -0
  15. run-12/checkpoint-234/optimizer.pt +3 -0
  16. run-12/checkpoint-234/rng_state.pth +3 -0
  17. run-12/checkpoint-234/scheduler.pt +3 -0
  18. run-12/checkpoint-234/special_tokens_map.json +7 -0
  19. run-12/checkpoint-234/tokenizer.json +0 -0
  20. run-12/checkpoint-234/tokenizer_config.json +56 -0
  21. run-12/checkpoint-234/trainer_state.json +67 -0
  22. run-12/checkpoint-234/training_args.bin +3 -0
  23. run-12/checkpoint-234/vocab.txt +0 -0
  24. run-15/checkpoint-78/config.json +26 -0
  25. run-15/checkpoint-78/model.safetensors +3 -0
  26. run-15/checkpoint-78/optimizer.pt +3 -0
  27. run-15/checkpoint-78/rng_state.pth +3 -0
  28. run-15/checkpoint-78/scheduler.pt +3 -0
  29. run-15/checkpoint-78/special_tokens_map.json +7 -0
  30. run-15/checkpoint-78/tokenizer.json +0 -0
  31. run-15/checkpoint-78/tokenizer_config.json +56 -0
  32. run-15/checkpoint-78/trainer_state.json +49 -0
  33. run-15/checkpoint-78/training_args.bin +3 -0
  34. run-15/checkpoint-78/vocab.txt +0 -0
  35. runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744025240.d0bdfe9fd409.3962.15 +3 -0
  36. runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744025260.d0bdfe9fd409.3962.16 +3 -0
  37. runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744025280.d0bdfe9fd409.3962.17 +3 -0
  38. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b96a3b318f878c9cb0e567eb7ec6a7c53c25ad9a7cf56535c0d683b56c5faec
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bcaf71e1780dfcffe181a59a81cf521444c462461eea2bd4b24d418622c9d84
3
  size 437958648
run-12/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": "4.50.3",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-12/checkpoint-156/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:455c1fe01c21ad0b2709593066d649acc5c47af0033c10c47217733bec03d93b
3
+ size 437958648
run-12/checkpoint-156/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:350673653518c9178cb6b989b30c08facda540ea92c1d6ec216a8cf938c2840c
3
+ size 876038394
run-12/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-12/checkpoint-156/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e31c82696f5b84c01513c716c1a67107ef3051d11fdadf298f2fb81bc8e90388
3
+ size 1064
run-12/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-12/checkpoint-156/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-12/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-12/checkpoint-156/trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 78,
3
+ "best_metric": 0.6606498194945848,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-12/checkpoint-78",
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": 0.6606498194945848,
15
+ "eval_loss": 0.6413371562957764,
16
+ "eval_runtime": 0.6567,
17
+ "eval_samples_per_second": 421.822,
18
+ "eval_steps_per_second": 7.614,
19
+ "step": 78
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.631768953068592,
24
+ "eval_loss": 0.6564910411834717,
25
+ "eval_runtime": 0.6587,
26
+ "eval_samples_per_second": 420.504,
27
+ "eval_steps_per_second": 7.59,
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
+ "classifier_dropout": 0.19913678351398936,
53
+ "learning_rate": 4.296837445131292e-05,
54
+ "max_length": 512,
55
+ "num_train_epochs": 3,
56
+ "per_device_train_batch_size": 32
57
+ }
58
+ }
run-12/checkpoint-156/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cf69cbe3cf1db64142e5987f9e7f18efe26a07c78fc005f0ec8c365714fd43e
3
+ size 5432
run-12/checkpoint-156/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-12/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": "4.50.3",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-12/checkpoint-234/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0510d894fce50ebe3ff09724df9dde808dcc03a36866bdeac655c6c698accb87
3
+ size 437958648
run-12/checkpoint-234/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d9942fbcfe46260d6440b9641d2a4c6790c92a86d6838f6e96e8c71eca1c7c6
3
+ size 876038394
run-12/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-12/checkpoint-234/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0621c6f62f3075bcd6aa3474371b10c82aa838f24fe6e9747432c1980955dafe
3
+ size 1064
run-12/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-12/checkpoint-234/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-12/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-12/checkpoint-234/trainer_state.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 234,
3
+ "best_metric": 0.6642599277978339,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-12/checkpoint-234",
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": 0.6606498194945848,
15
+ "eval_loss": 0.6413371562957764,
16
+ "eval_runtime": 0.6567,
17
+ "eval_samples_per_second": 421.822,
18
+ "eval_steps_per_second": 7.614,
19
+ "step": 78
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.631768953068592,
24
+ "eval_loss": 0.6564910411834717,
25
+ "eval_runtime": 0.6587,
26
+ "eval_samples_per_second": 420.504,
27
+ "eval_steps_per_second": 7.59,
28
+ "step": 156
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.6642599277978339,
33
+ "eval_loss": 0.769026517868042,
34
+ "eval_runtime": 0.6562,
35
+ "eval_samples_per_second": 422.156,
36
+ "eval_steps_per_second": 7.62,
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
+ "classifier_dropout": 0.19913678351398936,
62
+ "learning_rate": 4.296837445131292e-05,
63
+ "max_length": 512,
64
+ "num_train_epochs": 3,
65
+ "per_device_train_batch_size": 32
66
+ }
67
+ }
run-12/checkpoint-234/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cf69cbe3cf1db64142e5987f9e7f18efe26a07c78fc005f0ec8c365714fd43e
3
+ size 5432
run-12/checkpoint-234/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-15/checkpoint-78/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": "4.50.3",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 30522
26
+ }
run-15/checkpoint-78/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bcaf71e1780dfcffe181a59a81cf521444c462461eea2bd4b24d418622c9d84
3
+ size 437958648
run-15/checkpoint-78/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfb9f678b747da80dae933658dbe92a925c16f25d7d87981c73cdc03f3b7eecc
3
+ size 876038394
run-15/checkpoint-78/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5ab796df965c74c106f46f16854d55804fecfe14c1d69ae73ebe7269fc9ed28
3
+ size 14244
run-15/checkpoint-78/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7326a6f3ae575a0b4b4a7ba7b0a239e797d392a28fd732800ba257fe7722dce
3
+ size 1064
run-15/checkpoint-78/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-15/checkpoint-78/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-15/checkpoint-78/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-15/checkpoint-78/trainer_state.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 78,
3
+ "best_metric": 0.6498194945848376,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-15/checkpoint-78",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 78,
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": 0.6498194945848376,
15
+ "eval_loss": 0.6520236730575562,
16
+ "eval_runtime": 0.6553,
17
+ "eval_samples_per_second": 422.697,
18
+ "eval_steps_per_second": 7.63,
19
+ "step": 78
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 312,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 4,
26
+ "save_steps": 500,
27
+ "stateful_callbacks": {
28
+ "TrainerControl": {
29
+ "args": {
30
+ "should_epoch_stop": false,
31
+ "should_evaluate": false,
32
+ "should_log": false,
33
+ "should_save": true,
34
+ "should_training_stop": false
35
+ },
36
+ "attributes": {}
37
+ }
38
+ },
39
+ "total_flos": 0,
40
+ "train_batch_size": 32,
41
+ "trial_name": null,
42
+ "trial_params": {
43
+ "classifier_dropout": 0.25486425341149616,
44
+ "learning_rate": 4.1246175140413976e-05,
45
+ "max_length": 512,
46
+ "num_train_epochs": 4,
47
+ "per_device_train_batch_size": 32
48
+ }
49
+ }
run-15/checkpoint-78/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b434855a287b719c5d235950a64bd30b0a88e8e2ae793dad99af6f50d0db8dc
3
+ size 5432
run-15/checkpoint-78/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744025240.d0bdfe9fd409.3962.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d18ca97b0c043cf0e4e5fa659abb65a2167f48865a412a1cbf4505d4d59f2125
3
+ size 5419
runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744025260.d0bdfe9fd409.3962.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2749bddb9ef9bffc1f349eb27ee90ef515689907821db2b8c4a8363dfd9ffee8
3
+ size 5425
runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744025280.d0bdfe9fd409.3962.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:639adcf9f05f75fbca90899f1858c4cccba326300bf2e732bded8f1400721a7a
3
+ size 6742
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cf69cbe3cf1db64142e5987f9e7f18efe26a07c78fc005f0ec8c365714fd43e
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b434855a287b719c5d235950a64bd30b0a88e8e2ae793dad99af6f50d0db8dc
3
  size 5432