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
279718c
·
verified ·
1 Parent(s): d648ba1

Training in progress, epoch 1

Browse files
Files changed (29) hide show
  1. model.safetensors +1 -1
  2. run-8/checkpoint-117/config.json +26 -0
  3. run-8/checkpoint-117/model.safetensors +3 -0
  4. run-8/checkpoint-117/optimizer.pt +3 -0
  5. run-8/checkpoint-117/rng_state.pth +3 -0
  6. run-8/checkpoint-117/scheduler.pt +3 -0
  7. run-8/checkpoint-117/special_tokens_map.json +7 -0
  8. run-8/checkpoint-117/tokenizer.json +0 -0
  9. run-8/checkpoint-117/tokenizer_config.json +56 -0
  10. run-8/checkpoint-117/trainer_state.json +67 -0
  11. run-8/checkpoint-117/training_args.bin +3 -0
  12. run-8/checkpoint-117/vocab.txt +0 -0
  13. run-8/checkpoint-78/config.json +26 -0
  14. run-8/checkpoint-78/model.safetensors +3 -0
  15. run-8/checkpoint-78/optimizer.pt +3 -0
  16. run-8/checkpoint-78/rng_state.pth +3 -0
  17. run-8/checkpoint-78/scheduler.pt +3 -0
  18. run-8/checkpoint-78/special_tokens_map.json +7 -0
  19. run-8/checkpoint-78/tokenizer.json +0 -0
  20. run-8/checkpoint-78/tokenizer_config.json +56 -0
  21. run-8/checkpoint-78/trainer_state.json +58 -0
  22. run-8/checkpoint-78/training_args.bin +3 -0
  23. run-8/checkpoint-78/vocab.txt +0 -0
  24. run-9/checkpoint-39/model.safetensors +1 -1
  25. run-9/checkpoint-39/optimizer.pt +1 -1
  26. run-9/checkpoint-39/scheduler.pt +1 -1
  27. run-9/checkpoint-39/trainer_state.json +11 -11
  28. run-9/checkpoint-39/training_args.bin +1 -1
  29. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1aead69210ced61866ee980a1487046be39a09dc89a2306d474db96ffd4c3c18
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e068aaa45121b6aecfc30029bef2f3cf5735f93aca884345a3a20b25a47c371
3
  size 437958648
run-8/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-8/checkpoint-117/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa1d92c6335ff7f4b3ab9848911c3bcccc310201286667f5e3797e0b4b6c4253
3
+ size 437958648
run-8/checkpoint-117/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df2fc75793fbf67a34a88a8a9b707339abd490d25bae653911614508d6e1e987
3
+ size 876038394
run-8/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-8/checkpoint-117/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a73f642cfea6feffaaf3409f1911a0dfc488335b40a92a8607ceb0394a425e35
3
+ size 1064
run-8/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-8/checkpoint-117/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/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-8/checkpoint-117/trainer_state.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 117,
3
+ "best_metric": 0.5523465703971119,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-8/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": 0.5342960288808665,
15
+ "eval_loss": 0.6908717751502991,
16
+ "eval_runtime": 1.9685,
17
+ "eval_samples_per_second": 140.717,
18
+ "eval_steps_per_second": 2.54,
19
+ "step": 39
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.5270758122743683,
24
+ "eval_loss": 0.6904876232147217,
25
+ "eval_runtime": 1.9797,
26
+ "eval_samples_per_second": 139.92,
27
+ "eval_steps_per_second": 2.526,
28
+ "step": 78
29
+ },
30
+ {
31
+ "epoch": 3.0,
32
+ "eval_accuracy": 0.5523465703971119,
33
+ "eval_loss": 0.6890818476676941,
34
+ "eval_runtime": 1.9954,
35
+ "eval_samples_per_second": 138.819,
36
+ "eval_steps_per_second": 2.506,
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": 0.34293444726782196,
62
+ "learning_rate": 9.002340084037376e-06,
63
+ "max_seq_length": 256,
64
+ "num_train_epochs": 3,
65
+ "per_device_train_batch_size": 64
66
+ }
67
+ }
run-8/checkpoint-117/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0700a167b6e74e336c767640e8ddec156e025d797cb99c1bdd6c0819e5b0d1f1
3
+ size 5432
run-8/checkpoint-117/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/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-8/checkpoint-78/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a835fc0e7ef159c1df113e13db93c9f54edf4f9a8e065bd55f369bcce0af1c7d
3
+ size 437958648
run-8/checkpoint-78/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cf0a9f1477f66e21943110f49acca41926b475c84133cc24f661ef3ca6b2215
3
+ size 876038394
run-8/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-8/checkpoint-78/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:665dedd5c3c2ebb68b64755541413fd3fb9fa477e0601f424cdd6be6a02a3db0
3
+ size 1064
run-8/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-8/checkpoint-78/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/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-8/checkpoint-78/trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 39,
3
+ "best_metric": 0.5342960288808665,
4
+ "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-8/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": 0.5342960288808665,
15
+ "eval_loss": 0.6908717751502991,
16
+ "eval_runtime": 1.9685,
17
+ "eval_samples_per_second": 140.717,
18
+ "eval_steps_per_second": 2.54,
19
+ "step": 39
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.5270758122743683,
24
+ "eval_loss": 0.6904876232147217,
25
+ "eval_runtime": 1.9797,
26
+ "eval_samples_per_second": 139.92,
27
+ "eval_steps_per_second": 2.526,
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": 0.34293444726782196,
53
+ "learning_rate": 9.002340084037376e-06,
54
+ "max_seq_length": 256,
55
+ "num_train_epochs": 3,
56
+ "per_device_train_batch_size": 64
57
+ }
58
+ }
run-8/checkpoint-78/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0700a167b6e74e336c767640e8ddec156e025d797cb99c1bdd6c0819e5b0d1f1
3
+ size 5432
run-8/checkpoint-78/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-39/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f895eaca790c42e01c17ead932e51f0dd98425af9621c50aeca5f7d21a3bc9c9
3
  size 437958648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e068aaa45121b6aecfc30029bef2f3cf5735f93aca884345a3a20b25a47c371
3
  size 437958648
run-9/checkpoint-39/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b09fc1b6526c274a8e8fe3d42f44d5fcfa78f8c65ebac96f21556c2cf93fbab2
3
  size 876038394
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69cf1c595ef5356ac6e02a9938c061be09703d123410e2e97124e7870be59bee
3
  size 876038394
run-9/checkpoint-39/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a0803ad287b9b18c2fea1ee8bac96c6d0f066fd3d158d907e7d789df504820b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:863094d7738dac21eff2d22ba5974aeada7b089feb15f5f7a8a981a8d721fbdb
3
  size 1064
run-9/checkpoint-39/trainer_state.json CHANGED
@@ -12,17 +12,17 @@
12
  {
13
  "epoch": 1.0,
14
  "eval_accuracy": 0.4729241877256318,
15
- "eval_loss": 0.7208108901977539,
16
- "eval_runtime": 2.0113,
17
- "eval_samples_per_second": 137.72,
18
- "eval_steps_per_second": 2.486,
19
  "step": 39
20
  }
21
  ],
22
  "logging_steps": 500,
23
- "max_steps": 78,
24
  "num_input_tokens_seen": 0,
25
- "num_train_epochs": 2,
26
  "save_steps": 500,
27
  "stateful_callbacks": {
28
  "TrainerControl": {
@@ -31,7 +31,7 @@
31
  "should_evaluate": false,
32
  "should_log": false,
33
  "should_save": true,
34
- "should_training_stop": false
35
  },
36
  "attributes": {}
37
  }
@@ -40,10 +40,10 @@
40
  "train_batch_size": 64,
41
  "trial_name": null,
42
  "trial_params": {
43
- "dropout_rate": 0.2684169145768369,
44
- "learning_rate": 1.481500826666273e-06,
45
- "max_seq_length": 64,
46
- "num_train_epochs": 2,
47
  "per_device_train_batch_size": 64
48
  }
49
  }
 
12
  {
13
  "epoch": 1.0,
14
  "eval_accuracy": 0.4729241877256318,
15
+ "eval_loss": 0.7188401222229004,
16
+ "eval_runtime": 2.0097,
17
+ "eval_samples_per_second": 137.835,
18
+ "eval_steps_per_second": 2.488,
19
  "step": 39
20
  }
21
  ],
22
  "logging_steps": 500,
23
+ "max_steps": 39,
24
  "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 1,
26
  "save_steps": 500,
27
  "stateful_callbacks": {
28
  "TrainerControl": {
 
31
  "should_evaluate": false,
32
  "should_log": false,
33
  "should_save": true,
34
+ "should_training_stop": true
35
  },
36
  "attributes": {}
37
  }
 
40
  "train_batch_size": 64,
41
  "trial_name": null,
42
  "trial_params": {
43
+ "dropout_rate": 0.4641439010524123,
44
+ "learning_rate": 2.8044548571922558e-06,
45
+ "max_seq_length": 256,
46
+ "num_train_epochs": 1,
47
  "per_device_train_batch_size": 64
48
  }
49
  }
run-9/checkpoint-39/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44a07a14f8d822acb854025696a4756c71c914ef6c94583f3ef9e20a9ad193e5
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d0e563508cb62b339d598e1afeee9807b70c476b4224bf1df33008273029593
3
  size 5432
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0700a167b6e74e336c767640e8ddec156e025d797cb99c1bdd6c0819e5b0d1f1
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d0e563508cb62b339d598e1afeee9807b70c476b4224bf1df33008273029593
3
  size 5432