yunyus commited on
Commit
515eb97
·
verified ·
1 Parent(s): 0fe734a

Training in progress, epoch 1

Browse files
Files changed (35) hide show
  1. model.safetensors +1 -1
  2. run-10/checkpoint-117/config.json +26 -0
  3. run-10/checkpoint-117/model.safetensors +3 -0
  4. run-10/checkpoint-117/optimizer.pt +3 -0
  5. run-10/checkpoint-117/rng_state.pth +3 -0
  6. run-10/checkpoint-117/scheduler.pt +3 -0
  7. run-10/checkpoint-117/special_tokens_map.json +7 -0
  8. run-10/checkpoint-117/tokenizer.json +0 -0
  9. run-10/checkpoint-117/tokenizer_config.json +56 -0
  10. run-10/checkpoint-117/trainer_state.json +67 -0
  11. run-10/checkpoint-117/training_args.bin +3 -0
  12. run-10/checkpoint-117/vocab.txt +0 -0
  13. run-10/checkpoint-78/config.json +26 -0
  14. run-10/checkpoint-78/model.safetensors +3 -0
  15. run-10/checkpoint-78/optimizer.pt +3 -0
  16. run-10/checkpoint-78/rng_state.pth +3 -0
  17. run-10/checkpoint-78/scheduler.pt +3 -0
  18. run-10/checkpoint-78/special_tokens_map.json +7 -0
  19. run-10/checkpoint-78/tokenizer.json +0 -0
  20. run-10/checkpoint-78/tokenizer_config.json +56 -0
  21. run-10/checkpoint-78/trainer_state.json +58 -0
  22. run-10/checkpoint-78/training_args.bin +3 -0
  23. run-10/checkpoint-78/vocab.txt +0 -0
  24. run-11/checkpoint-39/config.json +26 -0
  25. run-11/checkpoint-39/model.safetensors +3 -0
  26. run-11/checkpoint-39/optimizer.pt +3 -0
  27. run-11/checkpoint-39/rng_state.pth +3 -0
  28. run-11/checkpoint-39/scheduler.pt +3 -0
  29. run-11/checkpoint-39/special_tokens_map.json +7 -0
  30. run-11/checkpoint-39/tokenizer.json +0 -0
  31. run-11/checkpoint-39/tokenizer_config.json +56 -0
  32. run-11/checkpoint-39/trainer_state.json +49 -0
  33. run-11/checkpoint-39/training_args.bin +3 -0
  34. run-11/checkpoint-39/vocab.txt +0 -0
  35. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e919bee3b5e5b26b64e45193b2fbb434807422323688ba22ce6334f66e22adff
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9771652dc709677d41f5360781b3d921daf5af708640694a740ec5d422c10a78
3
  size 437958648
run-10/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-10/checkpoint-117/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ae3d4403e8a18ef9bfbfe83558e5644ae01f859690052d2309ce49b5ee61770
3
+ size 437958648
run-10/checkpoint-117/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a1a42f1af44e9aae5ddca20720aa61e86db7960e458a91b4ef67e7faf3c032
3
+ size 876038394
run-10/checkpoint-117/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e6ef7001839c1d2af6340ecba7b523b0f2a4e44bd97f7e39ce88f55c07c8d7f
3
+ size 14244
run-10/checkpoint-117/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5667a6a36b23da3a85209e070b95a85cba00525a97768750061cf182c51a2b73
3
+ size 1064
run-10/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-10/checkpoint-117/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-10/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-10/checkpoint-117/trainer_state.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 117,
3
+ "best_metric": 0.5342960288808665,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-10/checkpoint-117",
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": 0.5234657039711191,
15
+ "eval_loss": 0.6923509836196899,
16
+ "eval_runtime": 2.067,
17
+ "eval_samples_per_second": 134.011,
18
+ "eval_steps_per_second": 2.419,
19
+ "step": 39
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.5090252707581228,
24
+ "eval_loss": 0.6922423243522644,
25
+ "eval_runtime": 2.0334,
26
+ "eval_samples_per_second": 136.226,
27
+ "eval_steps_per_second": 2.459,
28
+ "step": 78
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.5342960288808665,
33
+ "eval_loss": 0.6909230351448059,
34
+ "eval_runtime": 2.1754,
35
+ "eval_samples_per_second": 127.333,
36
+ "eval_steps_per_second": 2.298,
37
+ "step": 117
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 117,
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": 64,
59
+ "trial_name": null,
60
+ "trial_params": {
61
+ "dropout_rate": 0.49630651031124234,
62
+ "learning_rate": 9.76625259787508e-06,
63
+ "max_seq_length": 128,
64
+ "num_train_epochs": 3,
65
+ "per_device_train_batch_size": 64
66
+ }
67
+ }
run-10/checkpoint-117/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f5bf2a9c550e60293523385af2f0476c6aa20f80d692c1fcadab5f7ad74abbd
3
+ size 5432
run-10/checkpoint-117/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-10/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-10/checkpoint-78/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43e5ee49fd4a49921c482e8ea123d1adceaa31c5dadf6dea644d8c22212be5ae
3
+ size 437958648
run-10/checkpoint-78/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:165ed84b7573578ef659910a0ba1e7878ab91f05a6445f3ab5b812c18b0ddec3
3
+ size 876038394
run-10/checkpoint-78/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2359103b6aecc5a33be9630634e2521d802ca571eca1b4adeac3ec6496c46f19
3
+ size 14244
run-10/checkpoint-78/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da4e0086b8c017c60842bd9aa5c2daac713d8b4871e032cab36b9c3604d65cb
3
+ size 1064
run-10/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-10/checkpoint-78/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-10/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-10/checkpoint-78/trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 39,
3
+ "best_metric": 0.5234657039711191,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-10/checkpoint-39",
5
+ "epoch": 2.0,
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": 0.5234657039711191,
15
+ "eval_loss": 0.6923509836196899,
16
+ "eval_runtime": 2.067,
17
+ "eval_samples_per_second": 134.011,
18
+ "eval_steps_per_second": 2.419,
19
+ "step": 39
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.5090252707581228,
24
+ "eval_loss": 0.6922423243522644,
25
+ "eval_runtime": 2.0334,
26
+ "eval_samples_per_second": 136.226,
27
+ "eval_steps_per_second": 2.459,
28
+ "step": 78
29
+ }
30
+ ],
31
+ "logging_steps": 500,
32
+ "max_steps": 117,
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": 64,
50
+ "trial_name": null,
51
+ "trial_params": {
52
+ "dropout_rate": 0.49630651031124234,
53
+ "learning_rate": 9.76625259787508e-06,
54
+ "max_seq_length": 128,
55
+ "num_train_epochs": 3,
56
+ "per_device_train_batch_size": 64
57
+ }
58
+ }
run-10/checkpoint-78/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f5bf2a9c550e60293523385af2f0476c6aa20f80d692c1fcadab5f7ad74abbd
3
+ size 5432
run-10/checkpoint-78/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-39/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-11/checkpoint-39/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9771652dc709677d41f5360781b3d921daf5af708640694a740ec5d422c10a78
3
+ size 437958648
run-11/checkpoint-39/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ccdd114be010d0c01ed7ee4f2bd17ac1a435bc3ccc55dd91766765d7dce31e0
3
+ size 876038394
run-11/checkpoint-39/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb9d75225831e9955fede3b2d004809f8a35dbd2208354c70b53a96923288fdc
3
+ size 14244
run-11/checkpoint-39/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f413e02a782150bfd1dc31dcf286d3b29fd93d4dec1b4c5e79791ae4f00ce4c6
3
+ size 1064
run-11/checkpoint-39/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-11/checkpoint-39/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-11/checkpoint-39/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-11/checkpoint-39/trainer_state.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 39,
3
+ "best_metric": 0.5234657039711191,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-11/checkpoint-39",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 39,
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": 0.5234657039711191,
15
+ "eval_loss": 0.6922067999839783,
16
+ "eval_runtime": 2.0618,
17
+ "eval_samples_per_second": 134.346,
18
+ "eval_steps_per_second": 2.425,
19
+ "step": 39
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 117,
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": 64,
41
+ "trial_name": null,
42
+ "trial_params": {
43
+ "dropout_rate": 0.4705592476491812,
44
+ "learning_rate": 9.467017186149943e-06,
45
+ "max_seq_length": 128,
46
+ "num_train_epochs": 3,
47
+ "per_device_train_batch_size": 64
48
+ }
49
+ }
run-11/checkpoint-39/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5284bd6922ac3f6e3ea5641cface3bfce7f748ba98b57aa403e7d0ddad414c5e
3
+ size 5432
run-11/checkpoint-39/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f5bf2a9c550e60293523385af2f0476c6aa20f80d692c1fcadab5f7ad74abbd
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5284bd6922ac3f6e3ea5641cface3bfce7f748ba98b57aa403e7d0ddad414c5e
3
  size 5432