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
df273ba
·
verified ·
1 Parent(s): e057a8a

Training in progress, epoch 1

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. model.safetensors +1 -1
  2. run-16/checkpoint-156/config.json +26 -0
  3. run-16/checkpoint-156/model.safetensors +3 -0
  4. run-16/checkpoint-156/optimizer.pt +3 -0
  5. run-16/checkpoint-156/rng_state.pth +3 -0
  6. run-16/checkpoint-156/scheduler.pt +3 -0
  7. run-16/checkpoint-156/special_tokens_map.json +7 -0
  8. run-16/checkpoint-156/tokenizer.json +0 -0
  9. run-16/checkpoint-156/tokenizer_config.json +56 -0
  10. run-16/checkpoint-156/trainer_state.json +58 -0
  11. run-16/checkpoint-156/training_args.bin +3 -0
  12. run-16/checkpoint-156/vocab.txt +0 -0
  13. run-21/checkpoint-156/config.json +26 -0
  14. run-21/checkpoint-156/model.safetensors +3 -0
  15. run-21/checkpoint-156/optimizer.pt +3 -0
  16. run-21/checkpoint-156/rng_state.pth +3 -0
  17. run-21/checkpoint-156/scheduler.pt +3 -0
  18. run-21/checkpoint-156/special_tokens_map.json +7 -0
  19. run-21/checkpoint-156/tokenizer.json +0 -0
  20. run-21/checkpoint-156/tokenizer_config.json +56 -0
  21. run-21/checkpoint-156/trainer_state.json +58 -0
  22. run-21/checkpoint-156/training_args.bin +3 -0
  23. run-21/checkpoint-156/vocab.txt +0 -0
  24. run-21/checkpoint-234/config.json +26 -0
  25. run-21/checkpoint-234/model.safetensors +3 -0
  26. run-21/checkpoint-234/optimizer.pt +3 -0
  27. run-21/checkpoint-234/rng_state.pth +3 -0
  28. run-21/checkpoint-234/scheduler.pt +3 -0
  29. run-21/checkpoint-234/special_tokens_map.json +7 -0
  30. run-21/checkpoint-234/tokenizer.json +0 -0
  31. run-21/checkpoint-234/tokenizer_config.json +56 -0
  32. run-21/checkpoint-234/trainer_state.json +67 -0
  33. run-21/checkpoint-234/training_args.bin +3 -0
  34. run-21/checkpoint-234/vocab.txt +0 -0
  35. run-21/checkpoint-78/config.json +26 -0
  36. run-21/checkpoint-78/model.safetensors +3 -0
  37. run-21/checkpoint-78/optimizer.pt +3 -0
  38. run-21/checkpoint-78/rng_state.pth +3 -0
  39. run-21/checkpoint-78/scheduler.pt +3 -0
  40. run-21/checkpoint-78/special_tokens_map.json +7 -0
  41. run-21/checkpoint-78/tokenizer.json +0 -0
  42. run-21/checkpoint-78/tokenizer_config.json +56 -0
  43. run-21/checkpoint-78/trainer_state.json +49 -0
  44. run-21/checkpoint-78/training_args.bin +3 -0
  45. run-21/checkpoint-78/vocab.txt +0 -0
  46. runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744025563.d0bdfe9fd409.3962.19 +3 -0
  47. runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744025583.d0bdfe9fd409.3962.20 +3 -0
  48. runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744025603.d0bdfe9fd409.3962.21 +3 -0
  49. runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744025623.d0bdfe9fd409.3962.22 +3 -0
  50. runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744025643.d0bdfe9fd409.3962.23 +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec493128300dfeffd8c28be239f3858c6b6d197cf032fbf1dc89e4cb9aff7b4b
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef4fbd0dbd6fcaa503b9227a0cb36fca2638e0e45d9d595ab5c6553147864a9d
3
  size 437958648
run-16/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-16/checkpoint-156/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ca90258f75812d90d37585c342789535bf5517775b9504ddc564f3f4b01284d
3
+ size 437958648
run-16/checkpoint-156/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89e2c6c955f070aba09a9051c1a5094ce7e93dc57cb7963fb2c8f38ddba71e32
3
+ size 876038394
run-16/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-16/checkpoint-156/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6de53698e0cacaefd67d2d6b985ef1d26cc6bbe0eaae4913975a7a8131f14de8
3
+ size 1064
run-16/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-16/checkpoint-156/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-16/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-16/checkpoint-156/trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 156,
3
+ "best_metric": 0.6353790613718412,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-16/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": 0.6101083032490975,
15
+ "eval_loss": 0.6572300791740417,
16
+ "eval_runtime": 0.6549,
17
+ "eval_samples_per_second": 422.965,
18
+ "eval_steps_per_second": 7.635,
19
+ "step": 78
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.6353790613718412,
24
+ "eval_loss": 0.6465311050415039,
25
+ "eval_runtime": 0.654,
26
+ "eval_samples_per_second": 423.563,
27
+ "eval_steps_per_second": 7.646,
28
+ "step": 156
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 312,
33
+ "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 4,
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": 0.48711092608463913,
53
+ "learning_rate": 2.4254477988032894e-05,
54
+ "max_length": 256,
55
+ "num_train_epochs": 4,
56
+ "per_device_train_batch_size": 32
57
+ }
58
+ }
run-16/checkpoint-156/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f55adfea05da3075a7965e776f5d2bab983243c073454ba57febf9a26b3adb2c
3
+ size 5432
run-16/checkpoint-156/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-21/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-21/checkpoint-156/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25e2f623503708c55d2c10ea6c3f91761600de354be0f8fb8b617f110a987c4a
3
+ size 437958648
run-21/checkpoint-156/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2f90d1ede8b88bec93fc935151e7543a4e6e528fcbd969512efdeac1ce574f
3
+ size 876038394
run-21/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-21/checkpoint-156/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c89064189cde46e54c834f1d594df9508048fd5ebe7af658d66b9bde852e88b0
3
+ size 1064
run-21/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-21/checkpoint-156/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-21/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-21/checkpoint-156/trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 78,
3
+ "best_metric": 0.6570397111913358,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-21/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": 0.6570397111913358,
15
+ "eval_loss": 0.6395881772041321,
16
+ "eval_runtime": 0.6552,
17
+ "eval_samples_per_second": 422.744,
18
+ "eval_steps_per_second": 7.631,
19
+ "step": 78
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.6498194945848376,
24
+ "eval_loss": 0.6425312757492065,
25
+ "eval_runtime": 0.658,
26
+ "eval_samples_per_second": 421.003,
27
+ "eval_steps_per_second": 7.599,
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": 0.21214519455345757,
53
+ "learning_rate": 4.6822290592000956e-05,
54
+ "max_length": 512,
55
+ "num_train_epochs": 3,
56
+ "per_device_train_batch_size": 32
57
+ }
58
+ }
run-21/checkpoint-156/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf4c10091cbbb034ecd78e0138aa88c90429d63f21581fcabc0823d04b8fefcc
3
+ size 5432
run-21/checkpoint-156/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-21/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-21/checkpoint-234/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e09f92e0c47a52a9c301e7c6e68743722d170e3a93cf520fe0195598a1b2db1f
3
+ size 437958648
run-21/checkpoint-234/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cab1b971b5688c794a4f770af23e1a686582c078b7451a66c28ef7f4a7bb165
3
+ size 876038394
run-21/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-21/checkpoint-234/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97de9d5ab6fe925c746c388eed6e9aced7244f3ea0fe7704766081722a0bb8bd
3
+ size 1064
run-21/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-21/checkpoint-234/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-21/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-21/checkpoint-234/trainer_state.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 234,
3
+ "best_metric": 0.6714801444043321,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-21/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": 0.6570397111913358,
15
+ "eval_loss": 0.6395881772041321,
16
+ "eval_runtime": 0.6552,
17
+ "eval_samples_per_second": 422.744,
18
+ "eval_steps_per_second": 7.631,
19
+ "step": 78
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.6498194945848376,
24
+ "eval_loss": 0.6425312757492065,
25
+ "eval_runtime": 0.658,
26
+ "eval_samples_per_second": 421.003,
27
+ "eval_steps_per_second": 7.599,
28
+ "step": 156
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.6714801444043321,
33
+ "eval_loss": 0.7632268071174622,
34
+ "eval_runtime": 0.6685,
35
+ "eval_samples_per_second": 414.351,
36
+ "eval_steps_per_second": 7.479,
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": 0.21214519455345757,
62
+ "learning_rate": 4.6822290592000956e-05,
63
+ "max_length": 512,
64
+ "num_train_epochs": 3,
65
+ "per_device_train_batch_size": 32
66
+ }
67
+ }
run-21/checkpoint-234/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf4c10091cbbb034ecd78e0138aa88c90429d63f21581fcabc0823d04b8fefcc
3
+ size 5432
run-21/checkpoint-234/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-21/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-21/checkpoint-78/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d46f7849794820bc02657e5b380f005b25c1104e799052857b3bd3f4e3a6a1
3
+ size 437958648
run-21/checkpoint-78/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de5c593868469ab7e3f32abc1a4741783441fe90e3fb2ebc0102a91180ef4216
3
+ size 876038394
run-21/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-21/checkpoint-78/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec0eaf1bc2e0f3438074e337ddb4e486afc23fef65e30b12d0e9e8886dfc3e25
3
+ size 1064
run-21/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-21/checkpoint-78/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-21/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-21/checkpoint-78/trainer_state.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 78,
3
+ "best_metric": 0.6570397111913358,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-21/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": 0.6570397111913358,
15
+ "eval_loss": 0.6395881772041321,
16
+ "eval_runtime": 0.6552,
17
+ "eval_samples_per_second": 422.744,
18
+ "eval_steps_per_second": 7.631,
19
+ "step": 78
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 234,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 3,
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": 0.21214519455345757,
44
+ "learning_rate": 4.6822290592000956e-05,
45
+ "max_length": 512,
46
+ "num_train_epochs": 3,
47
+ "per_device_train_batch_size": 32
48
+ }
49
+ }
run-21/checkpoint-78/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf4c10091cbbb034ecd78e0138aa88c90429d63f21581fcabc0823d04b8fefcc
3
+ size 5432
run-21/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.1744025563.d0bdfe9fd409.3962.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:118a2263ab7962ce397e344f96176c8b5ef302757487947c52901b3c0b73319c
3
+ size 5424
runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744025583.d0bdfe9fd409.3962.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cd249f0901bd918242016641f2c528c5986ec4eb27eac4cd41646a2971a2ab3
3
+ size 5419
runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744025603.d0bdfe9fd409.3962.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b737ef032323f8a9ad24749fe4822a3e61fa0548147f34f3160b433b7d221afb
3
+ size 5424
runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744025623.d0bdfe9fd409.3962.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:badad64f1d0cdebbdcd20bea7bd947bdc60c8f5f5970782d4203c387a234308b
3
+ size 5418
runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744025643.d0bdfe9fd409.3962.23 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c844c87cf77525e27deacc16c95527b0b962e8af4435b90074d519dd4225f36f
3
+ size 6419