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
7034158
·
verified ·
1 Parent(s): f7be1a0

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-6/checkpoint-117/config.json +26 -0
  3. run-6/checkpoint-117/model.safetensors +3 -0
  4. run-6/checkpoint-117/optimizer.pt +3 -0
  5. run-6/checkpoint-117/rng_state.pth +3 -0
  6. run-6/checkpoint-117/scheduler.pt +3 -0
  7. run-6/checkpoint-117/special_tokens_map.json +7 -0
  8. run-6/checkpoint-117/tokenizer.json +0 -0
  9. run-6/checkpoint-117/tokenizer_config.json +56 -0
  10. run-6/checkpoint-117/trainer_state.json +67 -0
  11. run-6/checkpoint-117/training_args.bin +3 -0
  12. run-6/checkpoint-117/vocab.txt +0 -0
  13. run-6/checkpoint-156/config.json +1 -1
  14. run-6/checkpoint-156/model.safetensors +1 -1
  15. run-6/checkpoint-156/optimizer.pt +1 -1
  16. run-6/checkpoint-156/rng_state.pth +1 -1
  17. run-6/checkpoint-156/scheduler.pt +1 -1
  18. run-6/checkpoint-156/trainer_state.json +42 -22
  19. run-6/checkpoint-156/training_args.bin +1 -1
  20. run-6/checkpoint-195/config.json +26 -0
  21. run-6/checkpoint-195/model.safetensors +3 -0
  22. run-6/checkpoint-195/optimizer.pt +3 -0
  23. run-6/checkpoint-195/rng_state.pth +3 -0
  24. run-6/checkpoint-195/scheduler.pt +3 -0
  25. run-6/checkpoint-195/special_tokens_map.json +7 -0
  26. run-6/checkpoint-195/tokenizer.json +0 -0
  27. run-6/checkpoint-195/tokenizer_config.json +56 -0
  28. run-6/checkpoint-195/trainer_state.json +85 -0
  29. run-6/checkpoint-195/training_args.bin +3 -0
  30. run-6/checkpoint-195/vocab.txt +0 -0
  31. run-6/checkpoint-78/config.json +1 -1
  32. run-6/checkpoint-78/model.safetensors +1 -1
  33. run-6/checkpoint-78/optimizer.pt +1 -1
  34. run-6/checkpoint-78/scheduler.pt +1 -1
  35. run-6/checkpoint-78/trainer_state.json +19 -17
  36. run-6/checkpoint-78/training_args.bin +1 -1
  37. run-7/checkpoint-117/model.safetensors +1 -1
  38. run-7/checkpoint-117/optimizer.pt +1 -1
  39. run-7/checkpoint-117/scheduler.pt +1 -1
  40. run-7/checkpoint-117/trainer_state.json +19 -19
  41. run-7/checkpoint-117/training_args.bin +1 -1
  42. run-7/checkpoint-156/model.safetensors +1 -1
  43. run-7/checkpoint-156/optimizer.pt +1 -1
  44. run-7/checkpoint-156/scheduler.pt +1 -1
  45. run-7/checkpoint-156/trainer_state.json +24 -24
  46. run-7/checkpoint-156/training_args.bin +1 -1
  47. run-7/checkpoint-195/model.safetensors +1 -1
  48. run-7/checkpoint-195/optimizer.pt +1 -1
  49. run-7/checkpoint-195/scheduler.pt +1 -1
  50. run-7/checkpoint-195/trainer_state.json +29 -29
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57afd1d5d2aaf3f81e921aa5e455611bb98a78a16b703b1dff9007f0be161f86
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbe22d40da7e5f9da1e96eae60554e510934b908b8c92cd31733a2874d3f483e
3
  size 437958648
run-6/checkpoint-117/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-6/checkpoint-117/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9e7f74d46b32c8d2f0076ec31ace82bf49497460b4f27517e9674d1c39eddd8
3
+ size 437958648
run-6/checkpoint-117/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b405340175d5bcf34ed87d34189b9e2bb54d21c948fa2a929402c5be6ec2fdee
3
+ size 876038394
run-6/checkpoint-117/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:066817b2001cdf2cab3204d72b7658f8308ed56a8eab94345bd5ce0742b9b7f7
3
+ size 14244
run-6/checkpoint-117/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e9dbb9cc4ed759cb224abe50df0e547d0121b53700136189150fe57d392f12b
3
+ size 1064
run-6/checkpoint-117/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-6/checkpoint-117/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-117/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-6/checkpoint-117/trainer_state.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 39,
3
+ "best_metric": 0.5270758122743683,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-6/checkpoint-39",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 117,
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": 0.5270758122743683,
15
+ "eval_loss": 0.6918498277664185,
16
+ "eval_runtime": 0.638,
17
+ "eval_samples_per_second": 434.177,
18
+ "eval_steps_per_second": 14.107,
19
+ "step": 39
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.4729241877256318,
24
+ "eval_loss": 6.468245983123779,
25
+ "eval_runtime": 0.6389,
26
+ "eval_samples_per_second": 433.545,
27
+ "eval_steps_per_second": 14.086,
28
+ "step": 78
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.4729241877256318,
33
+ "eval_loss": 0.7129499912261963,
34
+ "eval_runtime": 0.6418,
35
+ "eval_samples_per_second": 431.567,
36
+ "eval_steps_per_second": 14.022,
37
+ "step": 117
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 195,
42
+ "num_input_tokens_seen": 0,
43
+ "num_train_epochs": 5,
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": false
53
+ },
54
+ "attributes": {}
55
+ }
56
+ },
57
+ "total_flos": 0,
58
+ "train_batch_size": 64,
59
+ "trial_name": null,
60
+ "trial_params": {
61
+ "dropout_rate": 0.0134,
62
+ "learning_rate": 0.05,
63
+ "max_length": 32,
64
+ "num_train_epochs": 5,
65
+ "per_device_train_batch_size": 64
66
+ }
67
+ }
run-6/checkpoint-117/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99cfd8ed47c6deda5dd532724592f1d8997b2921756d80eddbdaca287b3e257
3
+ size 5432
run-6/checkpoint-117/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-156/config.json CHANGED
@@ -19,7 +19,7 @@
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
 
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
run-6/checkpoint-156/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef617ae762ed830e635c59faf6429240723f867f7cc5df9cfc9ec41280f42eb5
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2318a07f6b7d5d1bf3a1f6b40d3abae127c8953f573ac215284dabee4df7d9fe
3
  size 437958648
run-6/checkpoint-156/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6acfb9c3eafd40c59f5f97583bf5c768ab5be3140bc91cdd91fd72f01e974ce
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a21aec7d555adf3c55b3aebf9bea77aa3474e2627f886c06cc532a346e13a395
3
  size 876038394
run-6/checkpoint-156/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4a64755083f7633da1abd1de577e641d7084f1c57535fb19884090b3171beb5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f61eb961c8bdfdb65315b87a5752740304715f4131aaf57d9e9514dcd94c88a
3
  size 14244
run-6/checkpoint-156/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7e1aba096a235697970b9d37756fcb54254791f4ef393e3d60c843f2d522c0d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba302ee87ff243e8cfe6b6e2e707141cb28f6780ae017be334f60d61b5d54260
3
  size 1064
run-6/checkpoint-156/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_global_step": 78,
3
- "best_metric": 0.6389891696750902,
4
- "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-6/checkpoint-78",
5
- "epoch": 2.0,
6
  "eval_steps": 500,
7
  "global_step": 156,
8
  "is_hyper_param_search": true,
@@ -11,27 +11,45 @@
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
- "eval_accuracy": 0.6389891696750902,
15
- "eval_loss": 0.6449670195579529,
16
- "eval_runtime": 0.6575,
17
- "eval_samples_per_second": 421.317,
18
- "eval_steps_per_second": 7.605,
19
- "step": 78
20
  },
21
  {
22
  "epoch": 2.0,
23
- "eval_accuracy": 0.6353790613718412,
24
- "eval_loss": 0.6602867841720581,
25
- "eval_runtime": 0.6588,
26
- "eval_samples_per_second": 420.431,
27
- "eval_steps_per_second": 7.589,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  "step": 156
29
  }
30
  ],
31
  "logging_steps": 500,
32
- "max_steps": 156,
33
  "num_input_tokens_seen": 0,
34
- "num_train_epochs": 2,
35
  "save_steps": 500,
36
  "stateful_callbacks": {
37
  "TrainerControl": {
@@ -40,17 +58,19 @@
40
  "should_evaluate": false,
41
  "should_log": false,
42
  "should_save": true,
43
- "should_training_stop": true
44
  },
45
  "attributes": {}
46
  }
47
  },
48
  "total_flos": 0,
49
- "train_batch_size": 32,
50
  "trial_name": null,
51
  "trial_params": {
52
- "learning_rate": 9.000538935456095e-05,
53
- "num_train_epochs": 2,
54
- "per_device_train_batch_size": 32
 
 
55
  }
56
  }
 
1
  {
2
+ "best_global_step": 39,
3
+ "best_metric": 0.5270758122743683,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-6/checkpoint-39",
5
+ "epoch": 4.0,
6
  "eval_steps": 500,
7
  "global_step": 156,
8
  "is_hyper_param_search": true,
 
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
+ "eval_accuracy": 0.5270758122743683,
15
+ "eval_loss": 0.6918498277664185,
16
+ "eval_runtime": 0.638,
17
+ "eval_samples_per_second": 434.177,
18
+ "eval_steps_per_second": 14.107,
19
+ "step": 39
20
  },
21
  {
22
  "epoch": 2.0,
23
+ "eval_accuracy": 0.4729241877256318,
24
+ "eval_loss": 6.468245983123779,
25
+ "eval_runtime": 0.6389,
26
+ "eval_samples_per_second": 433.545,
27
+ "eval_steps_per_second": 14.086,
28
+ "step": 78
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.4729241877256318,
33
+ "eval_loss": 0.7129499912261963,
34
+ "eval_runtime": 0.6418,
35
+ "eval_samples_per_second": 431.567,
36
+ "eval_steps_per_second": 14.022,
37
+ "step": 117
38
+ },
39
+ {
40
+ "epoch": 4.0,
41
+ "eval_accuracy": 0.4729241877256318,
42
+ "eval_loss": 0.9733805060386658,
43
+ "eval_runtime": 0.6368,
44
+ "eval_samples_per_second": 435.019,
45
+ "eval_steps_per_second": 14.134,
46
  "step": 156
47
  }
48
  ],
49
  "logging_steps": 500,
50
+ "max_steps": 195,
51
  "num_input_tokens_seen": 0,
52
+ "num_train_epochs": 5,
53
  "save_steps": 500,
54
  "stateful_callbacks": {
55
  "TrainerControl": {
 
58
  "should_evaluate": false,
59
  "should_log": false,
60
  "should_save": true,
61
+ "should_training_stop": false
62
  },
63
  "attributes": {}
64
  }
65
  },
66
  "total_flos": 0,
67
+ "train_batch_size": 64,
68
  "trial_name": null,
69
  "trial_params": {
70
+ "dropout_rate": 0.0134,
71
+ "learning_rate": 0.05,
72
+ "max_length": 32,
73
+ "num_train_epochs": 5,
74
+ "per_device_train_batch_size": 64
75
  }
76
  }
run-6/checkpoint-156/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:948f1b584f2607cf63fcd760bd1c3049931cca36538225a945beabc67b931485
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99cfd8ed47c6deda5dd532724592f1d8997b2921756d80eddbdaca287b3e257
3
  size 5432
run-6/checkpoint-195/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-6/checkpoint-195/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e68c8a888661be47d9365fdfa694944ffb3f6a64208b5a1527a9b83f04f49d59
3
+ size 437958648
run-6/checkpoint-195/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b80c1de7e4ed4fe975152ec98a1cf7510a34c0f6a47f27493a70fd039bd4e56
3
+ size 876038394
run-6/checkpoint-195/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bbb6e5a1853917bf71d3d48a24e968159b0799ccecda9429d3e1eac0a721ce5
3
+ size 14244
run-6/checkpoint-195/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:752f5a084edce7f72f09d3a1b263e8d262206382cd7e907850fe343dd9fe7226
3
+ size 1064
run-6/checkpoint-195/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-6/checkpoint-195/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-195/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-6/checkpoint-195/trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 39,
3
+ "best_metric": 0.5270758122743683,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-6/checkpoint-39",
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 195,
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": 0.5270758122743683,
15
+ "eval_loss": 0.6918498277664185,
16
+ "eval_runtime": 0.638,
17
+ "eval_samples_per_second": 434.177,
18
+ "eval_steps_per_second": 14.107,
19
+ "step": 39
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.4729241877256318,
24
+ "eval_loss": 6.468245983123779,
25
+ "eval_runtime": 0.6389,
26
+ "eval_samples_per_second": 433.545,
27
+ "eval_steps_per_second": 14.086,
28
+ "step": 78
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.4729241877256318,
33
+ "eval_loss": 0.7129499912261963,
34
+ "eval_runtime": 0.6418,
35
+ "eval_samples_per_second": 431.567,
36
+ "eval_steps_per_second": 14.022,
37
+ "step": 117
38
+ },
39
+ {
40
+ "epoch": 4.0,
41
+ "eval_accuracy": 0.4729241877256318,
42
+ "eval_loss": 0.9733805060386658,
43
+ "eval_runtime": 0.6368,
44
+ "eval_samples_per_second": 435.019,
45
+ "eval_steps_per_second": 14.134,
46
+ "step": 156
47
+ },
48
+ {
49
+ "epoch": 5.0,
50
+ "eval_accuracy": 0.4729241877256318,
51
+ "eval_loss": 0.7346399426460266,
52
+ "eval_runtime": 0.6421,
53
+ "eval_samples_per_second": 431.427,
54
+ "eval_steps_per_second": 14.017,
55
+ "step": 195
56
+ }
57
+ ],
58
+ "logging_steps": 500,
59
+ "max_steps": 195,
60
+ "num_input_tokens_seen": 0,
61
+ "num_train_epochs": 5,
62
+ "save_steps": 500,
63
+ "stateful_callbacks": {
64
+ "TrainerControl": {
65
+ "args": {
66
+ "should_epoch_stop": false,
67
+ "should_evaluate": false,
68
+ "should_log": false,
69
+ "should_save": true,
70
+ "should_training_stop": true
71
+ },
72
+ "attributes": {}
73
+ }
74
+ },
75
+ "total_flos": 0,
76
+ "train_batch_size": 64,
77
+ "trial_name": null,
78
+ "trial_params": {
79
+ "dropout_rate": 0.0134,
80
+ "learning_rate": 0.05,
81
+ "max_length": 32,
82
+ "num_train_epochs": 5,
83
+ "per_device_train_batch_size": 64
84
+ }
85
+ }
run-6/checkpoint-195/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99cfd8ed47c6deda5dd532724592f1d8997b2921756d80eddbdaca287b3e257
3
+ size 5432
run-6/checkpoint-195/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-78/config.json CHANGED
@@ -19,7 +19,7 @@
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
 
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
run-6/checkpoint-78/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb1ba5c8089724d0d7f4bcf542f63a7e62dd7b03fb7b0815005b3d794e25fd24
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d8ef02cdb5bfd921d3ad7cbe7efad3e5045fe73a53087e95d7200fbba683564
3
  size 437958648
run-6/checkpoint-78/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c6827b667b79d074df0df65b191ef0334701a4bd9c6e21bc9f0862c0cb3ac9c
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41424c73dadb08a4680e48d2eeb7e918f31cd36616ae5e18736f9570bb4a9563
3
  size 876038394
run-6/checkpoint-78/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67bcf98a98ab76470c935b8832145270959789541c75629573da5ffe7cb94209
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:562900fbc54f61683673f7d45f332e2421789e473397b69e96adb452a1719746
3
  size 1064
run-6/checkpoint-78/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_global_step": 78,
3
- "best_metric": 0.6389891696750902,
4
- "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-6/checkpoint-78",
5
  "epoch": 2.0,
6
  "eval_steps": 500,
7
  "global_step": 78,
@@ -11,27 +11,27 @@
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
- "eval_accuracy": 0.6101083032490975,
15
- "eval_loss": 0.6483533978462219,
16
- "eval_runtime": 0.6678,
17
- "eval_samples_per_second": 414.792,
18
- "eval_steps_per_second": 13.477,
19
  "step": 39
20
  },
21
  {
22
  "epoch": 2.0,
23
- "eval_accuracy": 0.6389891696750902,
24
- "eval_loss": 0.6526868343353271,
25
- "eval_runtime": 0.6398,
26
- "eval_samples_per_second": 432.973,
27
- "eval_steps_per_second": 14.068,
28
  "step": 78
29
  }
30
  ],
31
  "logging_steps": 500,
32
- "max_steps": 585,
33
  "num_input_tokens_seen": 0,
34
- "num_train_epochs": 15,
35
  "save_steps": 500,
36
  "stateful_callbacks": {
37
  "TrainerControl": {
@@ -49,8 +49,10 @@
49
  "train_batch_size": 64,
50
  "trial_name": null,
51
  "trial_params": {
52
- "learning_rate": 4.797258707523021e-05,
53
- "num_train_epochs": 15,
 
 
54
  "per_device_train_batch_size": 64
55
  }
56
  }
 
1
  {
2
+ "best_global_step": 39,
3
+ "best_metric": 0.5270758122743683,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-6/checkpoint-39",
5
  "epoch": 2.0,
6
  "eval_steps": 500,
7
  "global_step": 78,
 
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
+ "eval_accuracy": 0.5270758122743683,
15
+ "eval_loss": 0.6918498277664185,
16
+ "eval_runtime": 0.638,
17
+ "eval_samples_per_second": 434.177,
18
+ "eval_steps_per_second": 14.107,
19
  "step": 39
20
  },
21
  {
22
  "epoch": 2.0,
23
+ "eval_accuracy": 0.4729241877256318,
24
+ "eval_loss": 6.468245983123779,
25
+ "eval_runtime": 0.6389,
26
+ "eval_samples_per_second": 433.545,
27
+ "eval_steps_per_second": 14.086,
28
  "step": 78
29
  }
30
  ],
31
  "logging_steps": 500,
32
+ "max_steps": 195,
33
  "num_input_tokens_seen": 0,
34
+ "num_train_epochs": 5,
35
  "save_steps": 500,
36
  "stateful_callbacks": {
37
  "TrainerControl": {
 
49
  "train_batch_size": 64,
50
  "trial_name": null,
51
  "trial_params": {
52
+ "dropout_rate": 0.0134,
53
+ "learning_rate": 0.05,
54
+ "max_length": 32,
55
+ "num_train_epochs": 5,
56
  "per_device_train_batch_size": 64
57
  }
58
  }
run-6/checkpoint-78/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f932c25ae644f210e4526f3c1be14c7f7fe52253969f112e7a5e335bb77ad857
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99cfd8ed47c6deda5dd532724592f1d8997b2921756d80eddbdaca287b3e257
3
  size 5432
run-7/checkpoint-117/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98cbfabd8d6b0fef2b6fba269ac9d39d4ea630595bae16400f9418a6261f192e
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb23933936205a388c85e4a0992c5106684781f4174f4ea21f8c303a16f2167c
3
  size 437958648
run-7/checkpoint-117/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96c281f8d7a717f149c3442f1d69c8a4b2d482fc714e94549bd9c2a2dc48319d
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82b9da665ade5efa1bec8caba1e0cb3e291187eb520665bf94ca8c84b3caeaa7
3
  size 876038394
run-7/checkpoint-117/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:559b836f03dcf7d70d909be4e1b1884d7a179bf75c9ce12e87613f62fcbdc96a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:213d65bdad97baf6366493a7a3a463531cccd1c4d60c8879d9ff92c9ab239122
3
  size 1064
run-7/checkpoint-117/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_global_step": 117,
3
- "best_metric": 0.6967509025270758,
4
- "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-7/checkpoint-117",
5
  "epoch": 3.0,
6
  "eval_steps": 500,
7
  "global_step": 117,
@@ -11,29 +11,29 @@
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
- "eval_accuracy": 0.6173285198555957,
15
- "eval_loss": 0.6418094635009766,
16
- "eval_runtime": 0.6336,
17
- "eval_samples_per_second": 437.175,
18
- "eval_steps_per_second": 14.204,
19
  "step": 39
20
  },
21
  {
22
  "epoch": 2.0,
23
- "eval_accuracy": 0.6931407942238267,
24
- "eval_loss": 0.6396294832229614,
25
- "eval_runtime": 0.6372,
26
- "eval_samples_per_second": 434.705,
27
- "eval_steps_per_second": 14.124,
28
  "step": 78
29
  },
30
  {
31
  "epoch": 3.0,
32
- "eval_accuracy": 0.6967509025270758,
33
- "eval_loss": 0.7631913423538208,
34
- "eval_runtime": 0.6402,
35
- "eval_samples_per_second": 432.658,
36
- "eval_steps_per_second": 14.057,
37
  "step": 117
38
  }
39
  ],
@@ -59,7 +59,7 @@
59
  "trial_name": null,
60
  "trial_params": {
61
  "dropout_rate": 0.0134,
62
- "learning_rate": 7.861951862379219e-05,
63
  "max_length": 32,
64
  "num_train_epochs": 5,
65
  "per_device_train_batch_size": 64
 
1
  {
2
+ "best_global_step": 39,
3
+ "best_metric": 0.5270758122743683,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-7/checkpoint-39",
5
  "epoch": 3.0,
6
  "eval_steps": 500,
7
  "global_step": 117,
 
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
+ "eval_accuracy": 0.5270758122743683,
15
+ "eval_loss": 0.6919082403182983,
16
+ "eval_runtime": 0.638,
17
+ "eval_samples_per_second": 434.189,
18
+ "eval_steps_per_second": 14.107,
19
  "step": 39
20
  },
21
  {
22
  "epoch": 2.0,
23
+ "eval_accuracy": 0.4729241877256318,
24
+ "eval_loss": 0.7309694290161133,
25
+ "eval_runtime": 0.6392,
26
+ "eval_samples_per_second": 433.372,
27
+ "eval_steps_per_second": 14.081,
28
  "step": 78
29
  },
30
  {
31
  "epoch": 3.0,
32
+ "eval_accuracy": 0.5270758122743683,
33
+ "eval_loss": 0.7194660902023315,
34
+ "eval_runtime": 0.6371,
35
+ "eval_samples_per_second": 434.804,
36
+ "eval_steps_per_second": 14.127,
37
  "step": 117
38
  }
39
  ],
 
59
  "trial_name": null,
60
  "trial_params": {
61
  "dropout_rate": 0.0134,
62
+ "learning_rate": 0.00075,
63
  "max_length": 32,
64
  "num_train_epochs": 5,
65
  "per_device_train_batch_size": 64
run-7/checkpoint-117/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a52b74f601b4c559bc526f47cc5b6005cecb6b167f14b31320a05220649298f
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8c4929bc89061837cba9f5ad6241df21ef41da84ff54fbbce16b48384710dd6
3
  size 5432
run-7/checkpoint-156/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8693e8bc94385e6951091409ac3a6fd26bf0a3c6f60a1c6b912decba5dc41a46
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ace75bca042e91142ab751abae56a1747af84a9590fece33592501f159fffe3
3
  size 437958648
run-7/checkpoint-156/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c97623c6e49eaa1eddc4bc6854413f437e09ecfec64c93e255f00bf3da21b72
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18adc394acfafbfc30fcfd5fced8103f153c573157ca49e4d4da3fa2bc069967
3
  size 876038394
run-7/checkpoint-156/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4f407a12432a7a373fc8556f7830e23a246a008573d22696c9201e02df418a4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67fe0b1d36ef7d0f2f4dd956a90f35f78a77bd8cd8b87288ae2bcb46997ec147
3
  size 1064
run-7/checkpoint-156/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_global_step": 117,
3
- "best_metric": 0.6967509025270758,
4
- "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-7/checkpoint-117",
5
  "epoch": 4.0,
6
  "eval_steps": 500,
7
  "global_step": 156,
@@ -11,38 +11,38 @@
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
- "eval_accuracy": 0.6173285198555957,
15
- "eval_loss": 0.6418094635009766,
16
- "eval_runtime": 0.6336,
17
- "eval_samples_per_second": 437.175,
18
- "eval_steps_per_second": 14.204,
19
  "step": 39
20
  },
21
  {
22
  "epoch": 2.0,
23
- "eval_accuracy": 0.6931407942238267,
24
- "eval_loss": 0.6396294832229614,
25
- "eval_runtime": 0.6372,
26
- "eval_samples_per_second": 434.705,
27
- "eval_steps_per_second": 14.124,
28
  "step": 78
29
  },
30
  {
31
  "epoch": 3.0,
32
- "eval_accuracy": 0.6967509025270758,
33
- "eval_loss": 0.7631913423538208,
34
- "eval_runtime": 0.6402,
35
- "eval_samples_per_second": 432.658,
36
- "eval_steps_per_second": 14.057,
37
  "step": 117
38
  },
39
  {
40
  "epoch": 4.0,
41
- "eval_accuracy": 0.6714801444043321,
42
- "eval_loss": 1.014952540397644,
43
- "eval_runtime": 0.6346,
44
- "eval_samples_per_second": 436.474,
45
- "eval_steps_per_second": 14.181,
46
  "step": 156
47
  }
48
  ],
@@ -68,7 +68,7 @@
68
  "trial_name": null,
69
  "trial_params": {
70
  "dropout_rate": 0.0134,
71
- "learning_rate": 7.861951862379219e-05,
72
  "max_length": 32,
73
  "num_train_epochs": 5,
74
  "per_device_train_batch_size": 64
 
1
  {
2
+ "best_global_step": 39,
3
+ "best_metric": 0.5270758122743683,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-7/checkpoint-39",
5
  "epoch": 4.0,
6
  "eval_steps": 500,
7
  "global_step": 156,
 
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
+ "eval_accuracy": 0.5270758122743683,
15
+ "eval_loss": 0.6919082403182983,
16
+ "eval_runtime": 0.638,
17
+ "eval_samples_per_second": 434.189,
18
+ "eval_steps_per_second": 14.107,
19
  "step": 39
20
  },
21
  {
22
  "epoch": 2.0,
23
+ "eval_accuracy": 0.4729241877256318,
24
+ "eval_loss": 0.7309694290161133,
25
+ "eval_runtime": 0.6392,
26
+ "eval_samples_per_second": 433.372,
27
+ "eval_steps_per_second": 14.081,
28
  "step": 78
29
  },
30
  {
31
  "epoch": 3.0,
32
+ "eval_accuracy": 0.5270758122743683,
33
+ "eval_loss": 0.7194660902023315,
34
+ "eval_runtime": 0.6371,
35
+ "eval_samples_per_second": 434.804,
36
+ "eval_steps_per_second": 14.127,
37
  "step": 117
38
  },
39
  {
40
  "epoch": 4.0,
41
+ "eval_accuracy": 0.4729241877256318,
42
+ "eval_loss": 0.7069047689437866,
43
+ "eval_runtime": 0.642,
44
+ "eval_samples_per_second": 431.431,
45
+ "eval_steps_per_second": 14.018,
46
  "step": 156
47
  }
48
  ],
 
68
  "trial_name": null,
69
  "trial_params": {
70
  "dropout_rate": 0.0134,
71
+ "learning_rate": 0.00075,
72
  "max_length": 32,
73
  "num_train_epochs": 5,
74
  "per_device_train_batch_size": 64
run-7/checkpoint-156/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a52b74f601b4c559bc526f47cc5b6005cecb6b167f14b31320a05220649298f
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8c4929bc89061837cba9f5ad6241df21ef41da84ff54fbbce16b48384710dd6
3
  size 5432
run-7/checkpoint-195/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cb4eec593ca08d7af0090cb679a3ff1b67e0d67b814b11eb1e07c8219e08294
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f94eabf6042830f2b3123db50f2fe5d383e73dd7221879d560c58b44a643df6a
3
  size 437958648
run-7/checkpoint-195/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9fae267f6283dd5c1360a7af0f88717bf843b4b9254ca401e64c13765b7296f
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ded55dc803957b78dfa0f6030e4ec46c731961578e54538fc4a40cfb2641684e
3
  size 876038394
run-7/checkpoint-195/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2110173fbe6eb0d98c03f0d17fb832612579d27e7e9e9e987a13ddedeeda5d4d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6200587a999c197a87247f066d9ce62813bde6b6f589dded4e1e36dceeea6c89
3
  size 1064
run-7/checkpoint-195/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_global_step": 117,
3
- "best_metric": 0.6967509025270758,
4
- "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-7/checkpoint-117",
5
  "epoch": 5.0,
6
  "eval_steps": 500,
7
  "global_step": 195,
@@ -11,47 +11,47 @@
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
- "eval_accuracy": 0.6173285198555957,
15
- "eval_loss": 0.6418094635009766,
16
- "eval_runtime": 0.6336,
17
- "eval_samples_per_second": 437.175,
18
- "eval_steps_per_second": 14.204,
19
  "step": 39
20
  },
21
  {
22
  "epoch": 2.0,
23
- "eval_accuracy": 0.6931407942238267,
24
- "eval_loss": 0.6396294832229614,
25
- "eval_runtime": 0.6372,
26
- "eval_samples_per_second": 434.705,
27
- "eval_steps_per_second": 14.124,
28
  "step": 78
29
  },
30
  {
31
  "epoch": 3.0,
32
- "eval_accuracy": 0.6967509025270758,
33
- "eval_loss": 0.7631913423538208,
34
- "eval_runtime": 0.6402,
35
- "eval_samples_per_second": 432.658,
36
- "eval_steps_per_second": 14.057,
37
  "step": 117
38
  },
39
  {
40
  "epoch": 4.0,
41
- "eval_accuracy": 0.6714801444043321,
42
- "eval_loss": 1.014952540397644,
43
- "eval_runtime": 0.6346,
44
- "eval_samples_per_second": 436.474,
45
- "eval_steps_per_second": 14.181,
46
  "step": 156
47
  },
48
  {
49
  "epoch": 5.0,
50
- "eval_accuracy": 0.6714801444043321,
51
- "eval_loss": 1.1212284564971924,
52
- "eval_runtime": 0.6347,
53
- "eval_samples_per_second": 436.413,
54
- "eval_steps_per_second": 14.179,
55
  "step": 195
56
  }
57
  ],
@@ -77,7 +77,7 @@
77
  "trial_name": null,
78
  "trial_params": {
79
  "dropout_rate": 0.0134,
80
- "learning_rate": 7.861951862379219e-05,
81
  "max_length": 32,
82
  "num_train_epochs": 5,
83
  "per_device_train_batch_size": 64
 
1
  {
2
+ "best_global_step": 39,
3
+ "best_metric": 0.5270758122743683,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-7/checkpoint-39",
5
  "epoch": 5.0,
6
  "eval_steps": 500,
7
  "global_step": 195,
 
11
  "log_history": [
12
  {
13
  "epoch": 1.0,
14
+ "eval_accuracy": 0.5270758122743683,
15
+ "eval_loss": 0.6919082403182983,
16
+ "eval_runtime": 0.638,
17
+ "eval_samples_per_second": 434.189,
18
+ "eval_steps_per_second": 14.107,
19
  "step": 39
20
  },
21
  {
22
  "epoch": 2.0,
23
+ "eval_accuracy": 0.4729241877256318,
24
+ "eval_loss": 0.7309694290161133,
25
+ "eval_runtime": 0.6392,
26
+ "eval_samples_per_second": 433.372,
27
+ "eval_steps_per_second": 14.081,
28
  "step": 78
29
  },
30
  {
31
  "epoch": 3.0,
32
+ "eval_accuracy": 0.5270758122743683,
33
+ "eval_loss": 0.7194660902023315,
34
+ "eval_runtime": 0.6371,
35
+ "eval_samples_per_second": 434.804,
36
+ "eval_steps_per_second": 14.127,
37
  "step": 117
38
  },
39
  {
40
  "epoch": 4.0,
41
+ "eval_accuracy": 0.4729241877256318,
42
+ "eval_loss": 0.7069047689437866,
43
+ "eval_runtime": 0.642,
44
+ "eval_samples_per_second": 431.431,
45
+ "eval_steps_per_second": 14.018,
46
  "step": 156
47
  },
48
  {
49
  "epoch": 5.0,
50
+ "eval_accuracy": 0.4729241877256318,
51
+ "eval_loss": 0.693695604801178,
52
+ "eval_runtime": 0.6384,
53
+ "eval_samples_per_second": 433.898,
54
+ "eval_steps_per_second": 14.098,
55
  "step": 195
56
  }
57
  ],
 
77
  "trial_name": null,
78
  "trial_params": {
79
  "dropout_rate": 0.0134,
80
+ "learning_rate": 0.00075,
81
  "max_length": 32,
82
  "num_train_epochs": 5,
83
  "per_device_train_batch_size": 64