Hugging Face's logo

yunyus
/
bert-base-uncased-finetuned-rte-run_1

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Model card Files Metrics Community
yunyus commited on
Commit
c533e20
·
verified ·
1 Parent(s): e8ec60a

Training in progress, epoch 1

Browse files
Files changed (39) hide show
  1. model.safetensors +1 -1
  2. run-8/checkpoint-156/config.json +27 -0
  3. run-8/checkpoint-156/model.safetensors +3 -0
  4. run-8/checkpoint-156/optimizer.pt +3 -0
  5. run-8/checkpoint-156/rng_state.pth +3 -0
  6. run-8/checkpoint-156/scheduler.pt +3 -0
  7. run-8/checkpoint-156/special_tokens_map.json +7 -0
  8. run-8/checkpoint-156/tokenizer.json +0 -0
  9. run-8/checkpoint-156/tokenizer_config.json +55 -0
  10. run-8/checkpoint-156/trainer_state.json +57 -0
  11. run-8/checkpoint-156/training_args.bin +3 -0
  12. run-8/checkpoint-156/vocab.txt +0 -0
  13. run-8/checkpoint-234/config.json +27 -0
  14. run-8/checkpoint-234/model.safetensors +3 -0
  15. run-8/checkpoint-234/optimizer.pt +3 -0
  16. run-8/checkpoint-234/rng_state.pth +3 -0
  17. run-8/checkpoint-234/scheduler.pt +3 -0
  18. run-8/checkpoint-234/special_tokens_map.json +7 -0
  19. run-8/checkpoint-234/tokenizer.json +0 -0
  20. run-8/checkpoint-234/tokenizer_config.json +55 -0
  21. run-8/checkpoint-234/trainer_state.json +66 -0
  22. run-8/checkpoint-234/training_args.bin +3 -0
  23. run-8/checkpoint-234/vocab.txt +0 -0
  24. run-9/checkpoint-156/model.safetensors +1 -1
  25. run-9/checkpoint-156/optimizer.pt +1 -1
  26. run-9/checkpoint-156/scheduler.pt +1 -1
  27. run-9/checkpoint-156/trainer_state.json +14 -14
  28. run-9/checkpoint-156/training_args.bin +1 -1
  29. run-9/checkpoint-234/model.safetensors +1 -1
  30. run-9/checkpoint-234/optimizer.pt +1 -1
  31. run-9/checkpoint-234/scheduler.pt +1 -1
  32. run-9/checkpoint-234/trainer_state.json +20 -20
  33. run-9/checkpoint-234/training_args.bin +1 -1
  34. run-9/checkpoint-78/model.safetensors +1 -1
  35. run-9/checkpoint-78/optimizer.pt +1 -1
  36. run-9/checkpoint-78/scheduler.pt +1 -1
  37. run-9/checkpoint-78/trainer_state.json +9 -9
  38. run-9/checkpoint-78/training_args.bin +1 -1
  39. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e8cb536bf79e94bea82e47c05257188d34ffa06a1d51188e7eaae013758e6d3
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98afe7fd06e95ea4e1c7fa3620b9b028ed95b6f4f315bd1cc2762bc34089d206
3
  size 437958648
run-8/checkpoint-156/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "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
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.44.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-8/checkpoint-156/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44cd91c5f2d69217279063ab5dc2af83f8c5226539a36506f4e62cd6568e9777
3
+ size 437958648
run-8/checkpoint-156/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c61d0f8781fa860452e92945533c1af414014704ce0157f15e6e65663ba21bc
3
+ size 876038394
run-8/checkpoint-156/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08b06d22713ab0eccf6163f8b0ec7376abad69fdc0b947461e0b301173cdd320
3
+ size 14244
run-8/checkpoint-156/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5085ed6ef67315d824d5d5480f05b6120e594a31a684f6501def785501842e3d
3
+ size 1064
run-8/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-8/checkpoint-156/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-156/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-8/checkpoint-156/trainer_state.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5848375451263538,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-8/checkpoint-156",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 156,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.5415162454873647,
14
+ "eval_loss": 0.6883169412612915,
15
+ "eval_runtime": 0.7604,
16
+ "eval_samples_per_second": 364.306,
17
+ "eval_steps_per_second": 11.837,
18
+ "step": 78
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.5848375451263538,
23
+ "eval_loss": 0.6742675304412842,
24
+ "eval_runtime": 0.6945,
25
+ "eval_samples_per_second": 398.826,
26
+ "eval_steps_per_second": 12.958,
27
+ "step": 156
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 234,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "stateful_callbacks": {
36
+ "TrainerControl": {
37
+ "args": {
38
+ "should_epoch_stop": false,
39
+ "should_evaluate": false,
40
+ "should_log": false,
41
+ "should_save": true,
42
+ "should_training_stop": false
43
+ },
44
+ "attributes": {}
45
+ }
46
+ },
47
+ "total_flos": 0,
48
+ "train_batch_size": 32,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "dropout_rate": 0.3667117294878569,
52
+ "learning_rate": 1.2518263409353602e-05,
53
+ "max_seq_length": 32,
54
+ "num_train_epochs": 3,
55
+ "per_device_train_batch_size": 32
56
+ }
57
+ }
run-8/checkpoint-156/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7f34a4ba9d363996796172c4079d7b53234858e152885ed794144295366d369
3
+ size 5240
run-8/checkpoint-156/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-234/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "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
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 512,
16
+ "model_type": "bert",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 0,
20
+ "position_embedding_type": "absolute",
21
+ "problem_type": "single_label_classification",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.44.2",
24
+ "type_vocab_size": 2,
25
+ "use_cache": true,
26
+ "vocab_size": 30522
27
+ }
run-8/checkpoint-234/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2702a0aa2acba9e66d30855a688b6f996ef41aaac0c3603ecdf9223788f455d3
3
+ size 437958648
run-8/checkpoint-234/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:024bf35ea0f38fd1727182ad473c6259a41063c556babd1a90b9057e080c0ec5
3
+ size 876038394
run-8/checkpoint-234/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5893971a43e53d8cccb69cbc77f5b88d424dd9d85114d1b21fc0c54c6cb446cf
3
+ size 14244
run-8/checkpoint-234/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:646a4604e450fef042faf17dc5e60056ca4b4e8faaeca5c99b26c72ba18c0109
3
+ size 1064
run-8/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-8/checkpoint-234/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-234/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "BertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-8/checkpoint-234/trainer_state.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5956678700361011,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-8/checkpoint-234",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 234,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.5415162454873647,
14
+ "eval_loss": 0.6883169412612915,
15
+ "eval_runtime": 0.7604,
16
+ "eval_samples_per_second": 364.306,
17
+ "eval_steps_per_second": 11.837,
18
+ "step": 78
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.5848375451263538,
23
+ "eval_loss": 0.6742675304412842,
24
+ "eval_runtime": 0.6945,
25
+ "eval_samples_per_second": 398.826,
26
+ "eval_steps_per_second": 12.958,
27
+ "step": 156
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.5956678700361011,
32
+ "eval_loss": 0.6689817905426025,
33
+ "eval_runtime": 0.7311,
34
+ "eval_samples_per_second": 378.893,
35
+ "eval_steps_per_second": 12.311,
36
+ "step": 234
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 234,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 3,
43
+ "save_steps": 500,
44
+ "stateful_callbacks": {
45
+ "TrainerControl": {
46
+ "args": {
47
+ "should_epoch_stop": false,
48
+ "should_evaluate": false,
49
+ "should_log": false,
50
+ "should_save": true,
51
+ "should_training_stop": true
52
+ },
53
+ "attributes": {}
54
+ }
55
+ },
56
+ "total_flos": 0,
57
+ "train_batch_size": 32,
58
+ "trial_name": null,
59
+ "trial_params": {
60
+ "dropout_rate": 0.3667117294878569,
61
+ "learning_rate": 1.2518263409353602e-05,
62
+ "max_seq_length": 32,
63
+ "num_train_epochs": 3,
64
+ "per_device_train_batch_size": 32
65
+ }
66
+ }
run-8/checkpoint-234/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7f34a4ba9d363996796172c4079d7b53234858e152885ed794144295366d369
3
+ size 5240
run-8/checkpoint-234/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-156/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8c3bf77875e3638ef1f392b43a6662bb7b2f03713a7fc2231233af80ba80d5c
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb179db056db4454434ab71cb0971ade18ee44b43eea1244350b5dbcc00956ce
3
  size 437958648
run-9/checkpoint-156/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:273b70bc4627e6457396679667d121fb7e58751e3ada7469c9a1947bc57ae7f8
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c4b050bfcb15220f7b4db20c9152b02b0cd1fd5331a83c5c30149a0c8769265
3
  size 876038394
run-9/checkpoint-156/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:184a8e879d5a8b67bc6ff15a5f4480f5bde2755086e20933e6e9849858bc428b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d2bb76bc324463c996e656169f51a764fcd5e57ae0c7a6ef86aa604b16c62a9
3
  size 1064
run-9/checkpoint-156/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.6498194945848376,
3
  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-9/checkpoint-156",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
@@ -10,20 +10,20 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.6064981949458483,
14
- "eval_loss": 0.6529371738433838,
15
- "eval_runtime": 0.696,
16
- "eval_samples_per_second": 397.999,
17
- "eval_steps_per_second": 12.931,
18
  "step": 78
19
  },
20
  {
21
  "epoch": 2.0,
22
- "eval_accuracy": 0.6498194945848376,
23
- "eval_loss": 0.6543754935264587,
24
- "eval_runtime": 0.6808,
25
- "eval_samples_per_second": 406.863,
26
- "eval_steps_per_second": 13.219,
27
  "step": 156
28
  }
29
  ],
@@ -48,9 +48,9 @@
48
  "train_batch_size": 32,
49
  "trial_name": null,
50
  "trial_params": {
51
- "dropout_rate": 0.2892402615402374,
52
- "learning_rate": 3.773085262586205e-05,
53
- "max_seq_length": 64,
54
  "num_train_epochs": 3,
55
  "per_device_train_batch_size": 32
56
  }
 
1
  {
2
+ "best_metric": 0.6137184115523465,
3
  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-9/checkpoint-156",
4
  "epoch": 2.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.5054151624548736,
14
+ "eval_loss": 0.6900145411491394,
15
+ "eval_runtime": 0.6981,
16
+ "eval_samples_per_second": 396.809,
17
+ "eval_steps_per_second": 12.893,
18
  "step": 78
19
  },
20
  {
21
  "epoch": 2.0,
22
+ "eval_accuracy": 0.6137184115523465,
23
+ "eval_loss": 0.6661680340766907,
24
+ "eval_runtime": 0.7198,
25
+ "eval_samples_per_second": 384.842,
26
+ "eval_steps_per_second": 12.504,
27
  "step": 156
28
  }
29
  ],
 
48
  "train_batch_size": 32,
49
  "trial_name": null,
50
  "trial_params": {
51
+ "dropout_rate": 0.125694513008831,
52
+ "learning_rate": 1.4156616791187443e-05,
53
+ "max_seq_length": 32,
54
  "num_train_epochs": 3,
55
  "per_device_train_batch_size": 32
56
  }
run-9/checkpoint-156/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d194138e61b5f886e352871a7e47275b103df8c119f4a23897fd240d2849d429
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a16a06adb8e308c26cff4228f1a43ea65427d72be663841c58f5585e5fc47e
3
  size 5240
run-9/checkpoint-234/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a1e560e7430b85bacc7bc47cf89ff0d97810cc737e1a24744e471915060c51d
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b619c01af20a0e7b8e5fe5b9e2d2774dbc989d41873f0900d321e716f8bf7e42
3
  size 437958648
run-9/checkpoint-234/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a8e1cd1b56a17ce7e7195970bc7a60ae0489f12b8c6deeef2abcdfa39b4a4d0
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749f0c206b38cedcbd947f041e278cd6fad57b4ca4f8c60c52083347007745e7
3
  size 876038394
run-9/checkpoint-234/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30e29737dd1f31e275d558cec3824f9275fd2e6ba0e270c7d09d2c83e3b6ff61
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e87e2d0197c7ec4f34c01e0cc4f8c77bb7fc75fdcfcd13f9a4304707e1076711
3
  size 1064
run-9/checkpoint-234/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "best_metric": 0.6714801444043321,
3
- "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-9/checkpoint-234",
4
  "epoch": 3.0,
5
  "eval_steps": 500,
6
  "global_step": 234,
@@ -10,29 +10,29 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.6064981949458483,
14
- "eval_loss": 0.6529371738433838,
15
- "eval_runtime": 0.696,
16
- "eval_samples_per_second": 397.999,
17
- "eval_steps_per_second": 12.931,
18
  "step": 78
19
  },
20
  {
21
  "epoch": 2.0,
22
- "eval_accuracy": 0.6498194945848376,
23
- "eval_loss": 0.6543754935264587,
24
- "eval_runtime": 0.6808,
25
- "eval_samples_per_second": 406.863,
26
- "eval_steps_per_second": 13.219,
27
  "step": 156
28
  },
29
  {
30
  "epoch": 3.0,
31
- "eval_accuracy": 0.6714801444043321,
32
- "eval_loss": 0.7442203760147095,
33
- "eval_runtime": 0.7215,
34
- "eval_samples_per_second": 383.923,
35
- "eval_steps_per_second": 12.474,
36
  "step": 234
37
  }
38
  ],
@@ -57,9 +57,9 @@
57
  "train_batch_size": 32,
58
  "trial_name": null,
59
  "trial_params": {
60
- "dropout_rate": 0.2892402615402374,
61
- "learning_rate": 3.773085262586205e-05,
62
- "max_seq_length": 64,
63
  "num_train_epochs": 3,
64
  "per_device_train_batch_size": 32
65
  }
 
1
  {
2
+ "best_metric": 0.6137184115523465,
3
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-9/checkpoint-156",
4
  "epoch": 3.0,
5
  "eval_steps": 500,
6
  "global_step": 234,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.5054151624548736,
14
+ "eval_loss": 0.6900145411491394,
15
+ "eval_runtime": 0.6981,
16
+ "eval_samples_per_second": 396.809,
17
+ "eval_steps_per_second": 12.893,
18
  "step": 78
19
  },
20
  {
21
  "epoch": 2.0,
22
+ "eval_accuracy": 0.6137184115523465,
23
+ "eval_loss": 0.6661680340766907,
24
+ "eval_runtime": 0.7198,
25
+ "eval_samples_per_second": 384.842,
26
+ "eval_steps_per_second": 12.504,
27
  "step": 156
28
  },
29
  {
30
  "epoch": 3.0,
31
+ "eval_accuracy": 0.5956678700361011,
32
+ "eval_loss": 0.6590597033500671,
33
+ "eval_runtime": 0.7498,
34
+ "eval_samples_per_second": 369.434,
35
+ "eval_steps_per_second": 12.003,
36
  "step": 234
37
  }
38
  ],
 
57
  "train_batch_size": 32,
58
  "trial_name": null,
59
  "trial_params": {
60
+ "dropout_rate": 0.125694513008831,
61
+ "learning_rate": 1.4156616791187443e-05,
62
+ "max_seq_length": 32,
63
  "num_train_epochs": 3,
64
  "per_device_train_batch_size": 32
65
  }
run-9/checkpoint-234/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d194138e61b5f886e352871a7e47275b103df8c119f4a23897fd240d2849d429
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a16a06adb8e308c26cff4228f1a43ea65427d72be663841c58f5585e5fc47e
3
  size 5240
run-9/checkpoint-78/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d78cab325391021ee719642bbdf50381f04c6d2732a045b119e940c6bf2c659
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98afe7fd06e95ea4e1c7fa3620b9b028ed95b6f4f315bd1cc2762bc34089d206
3
  size 437958648
run-9/checkpoint-78/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6860d48aa2bebf5b7c831f4b960b9a5be527a934862cc4e72c73f89c3cfecfe
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88dbef4fcb092861e6ca78764c9ed5ab33c28f3e8ca8e17d63d08131eaa3f1f7
3
  size 876038394
run-9/checkpoint-78/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:645ff7660bf29ad45263561a9fb2f69928f570b46ec13d525960e6341412781a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff0e31d59379c7c6bb97dbf4f561539efe510dfe5e1e089e1fb69ae188ad321f
3
  size 1064
run-9/checkpoint-78/trainer_state.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "best_metric": 0.6064981949458483,
3
  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-9/checkpoint-78",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
@@ -10,11 +10,11 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.6064981949458483,
14
- "eval_loss": 0.6529371738433838,
15
- "eval_runtime": 0.696,
16
- "eval_samples_per_second": 397.999,
17
- "eval_steps_per_second": 12.931,
18
  "step": 78
19
  }
20
  ],
@@ -39,9 +39,9 @@
39
  "train_batch_size": 32,
40
  "trial_name": null,
41
  "trial_params": {
42
- "dropout_rate": 0.2892402615402374,
43
- "learning_rate": 3.773085262586205e-05,
44
- "max_seq_length": 64,
45
  "num_train_epochs": 3,
46
  "per_device_train_batch_size": 32
47
  }
 
1
  {
2
+ "best_metric": 0.5054151624548736,
3
  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-9/checkpoint-78",
4
  "epoch": 1.0,
5
  "eval_steps": 500,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.5054151624548736,
14
+ "eval_loss": 0.6900145411491394,
15
+ "eval_runtime": 0.6981,
16
+ "eval_samples_per_second": 396.809,
17
+ "eval_steps_per_second": 12.893,
18
  "step": 78
19
  }
20
  ],
 
39
  "train_batch_size": 32,
40
  "trial_name": null,
41
  "trial_params": {
42
+ "dropout_rate": 0.125694513008831,
43
+ "learning_rate": 1.4156616791187443e-05,
44
+ "max_seq_length": 32,
45
  "num_train_epochs": 3,
46
  "per_device_train_batch_size": 32
47
  }
run-9/checkpoint-78/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d194138e61b5f886e352871a7e47275b103df8c119f4a23897fd240d2849d429
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a16a06adb8e308c26cff4228f1a43ea65427d72be663841c58f5585e5fc47e
3
  size 5240
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7f34a4ba9d363996796172c4079d7b53234858e152885ed794144295366d369
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63a16a06adb8e308c26cff4228f1a43ea65427d72be663841c58f5585e5fc47e
3
  size 5240