Hugging Face's logo

anamelchor
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
anamelchor commited on
Commit
5d48eff
·
verified ·
1 Parent(s): 138262c

Training in progress, epoch 1

Browse files
Files changed (38) hide show
  1. model.safetensors +1 -1
  2. run-5/checkpoint-54/config.json +25 -0
  3. run-5/checkpoint-54/model.safetensors +3 -0
  4. run-5/checkpoint-54/optimizer.pt +3 -0
  5. run-5/checkpoint-54/rng_state.pth +3 -0
  6. run-5/checkpoint-54/scheduler.pt +3 -0
  7. run-5/checkpoint-54/special_tokens_map.json +7 -0
  8. run-5/checkpoint-54/tokenizer.json +0 -0
  9. run-5/checkpoint-54/tokenizer_config.json +55 -0
  10. run-5/checkpoint-54/trainer_state.json +35 -0
  11. run-5/checkpoint-54/training_args.bin +3 -0
  12. run-5/checkpoint-54/vocab.txt +0 -0
  13. run-6/checkpoint-27/model.safetensors +1 -1
  14. run-6/checkpoint-27/optimizer.pt +1 -1
  15. run-6/checkpoint-27/rng_state.pth +2 -2
  16. run-6/checkpoint-27/scheduler.pt +1 -1
  17. run-6/checkpoint-27/trainer_state.json +9 -9
  18. run-6/checkpoint-27/training_args.bin +1 -1
  19. run-6/checkpoint-54/model.safetensors +1 -1
  20. run-6/checkpoint-54/optimizer.pt +1 -1
  21. run-6/checkpoint-54/rng_state.pth +1 -1
  22. run-6/checkpoint-54/scheduler.pt +1 -1
  23. run-6/checkpoint-54/trainer_state.json +21 -12
  24. run-6/checkpoint-54/training_args.bin +1 -1
  25. run-7/checkpoint-14/config.json +25 -0
  26. run-7/checkpoint-14/model.safetensors +3 -0
  27. run-7/checkpoint-14/optimizer.pt +3 -0
  28. run-7/checkpoint-14/rng_state.pth +3 -0
  29. run-7/checkpoint-14/scheduler.pt +3 -0
  30. run-7/checkpoint-14/special_tokens_map.json +7 -0
  31. run-7/checkpoint-14/tokenizer.json +0 -0
  32. run-7/checkpoint-14/tokenizer_config.json +55 -0
  33. run-7/checkpoint-14/trainer_state.json +35 -0
  34. run-7/checkpoint-14/training_args.bin +3 -0
  35. run-7/checkpoint-14/vocab.txt +0 -0
  36. runs/Feb28_18-10-00_5620ed9b2fff/events.out.tfevents.1709144992.5620ed9b2fff.209.8 +3 -0
  37. runs/Feb28_18-10-00_5620ed9b2fff/events.out.tfevents.1709145108.5620ed9b2fff.209.9 +3 -0
  38. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0004164835495c5eaf535f2d6dbb4f11ba41e53ee6ff1705d9b92cfd2c2783a8
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee4376a86f672a747e935bc5434d5af0dc7dd70266d7fc82bc2e3b6b08d6117f
3
  size 267832560
run-5/checkpoint-54/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-5/checkpoint-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0004164835495c5eaf535f2d6dbb4f11ba41e53ee6ff1705d9b92cfd2c2783a8
3
+ size 267832560
run-5/checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a9dd7b0dee8392d82e68c8452a3f37e93261182e409b94bbbbad26425d386c
3
+ size 535727290
run-5/checkpoint-54/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e692352ad9cda18d1eebb162ac33dda299d06c7b94655c005ac07a24068509c
3
+ size 14244
run-5/checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e66fc9ce3d0891c27fa0973f287b38da6a2b0f64669885b9462ed70099880b8
3
+ size 1064
run-5/checkpoint-54/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-5/checkpoint-54/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-54/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": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-5/checkpoint-54/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-54",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 54,
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_loss": 0.6550258994102478,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7466,
16
+ "eval_samples_per_second": 1396.954,
17
+ "eval_steps_per_second": 88.398,
18
+ "step": 54
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 108,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 2,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 16,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 1.7074545535093052e-06,
31
+ "num_train_epochs": 2,
32
+ "per_device_train_batch_size": 16,
33
+ "seed": 5
34
+ }
35
+ }
run-5/checkpoint-54/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b7fc4f9b29c3121dc6f8881746905e52cb427e9f9addbda370817c836d00f27
3
+ size 4984
run-5/checkpoint-54/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-27/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29af0fd1c86642810cfb5c9e0a1a5341cd29fd43201c1c76f8ffeb62ccb28960
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acc17bc06a10f8c67bcddc0d8669c5c7c70cd734b311e9e3bf82124ad210b3bf
3
  size 267832560
run-6/checkpoint-27/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7a27f192d3a71915bb299e5b2af84bad81e173aa435db67b8f8f7dcc38ea4f1
3
  size 535727290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c24135e92fd54b9d612423454863405cb4a2e2faaba0c2eb276770aee641a0
3
  size 535727290
run-6/checkpoint-27/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be2e61cfb32bd0131c8524d0f66b7881e91890fc6d136be5e1c3e92c518e8271
3
- size 14180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:515d2bbf0cab7e557f1851c2aeab37ee4f8de6776d226591dfc155e3f0173f42
3
+ size 14244
run-6/checkpoint-27/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78211af0617a93ef10e44f30f019475c4d114e491e90b3e31e0177e344910fbc
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c485603a4e3d141c0f35fd4a34e21ecfbe32a27f1e08cb3cfe084fc5252526d
3
  size 1064
run-6/checkpoint-27/trainer_state.json CHANGED
@@ -10,26 +10,26 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 0.6180562973022461,
14
  "eval_matthews_correlation": 0.0,
15
- "eval_runtime": 0.7927,
16
- "eval_samples_per_second": 1315.68,
17
- "eval_steps_per_second": 83.255,
18
  "step": 27
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 81,
23
  "num_input_tokens_seen": 0,
24
- "num_train_epochs": 3,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 32,
28
  "trial_name": null,
29
  "trial_params": {
30
- "learning_rate": 6.155006780291272e-06,
31
- "num_train_epochs": 3,
32
  "per_device_train_batch_size": 32,
33
- "seed": 10
34
  }
35
  }
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.582168698310852,
14
  "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7989,
16
+ "eval_samples_per_second": 1305.62,
17
+ "eval_steps_per_second": 82.618,
18
  "step": 27
19
  }
20
  ],
21
  "logging_steps": 500,
22
+ "max_steps": 54,
23
  "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 2,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
  "train_batch_size": 32,
28
  "trial_name": null,
29
  "trial_params": {
30
+ "learning_rate": 7.764293438711137e-05,
31
+ "num_train_epochs": 2,
32
  "per_device_train_batch_size": 32,
33
+ "seed": 5
34
  }
35
  }
run-6/checkpoint-27/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:576e8a633ebecf0dcad9ad36c9c1f24b8ae26286776e3e989c11ef48601b2eec
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f97ff7e5c223c4007c1d57357c940c7d0090cde32f40fc663e312cb6424669a
3
  size 4984
run-6/checkpoint-54/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:adc415e7336e010bc299576731c62139a7be8b8b4b5f382faaf406b3034c3675
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6efea3d3d8647bfdfda4a1e1ae7924b4b2926c426536f3b560eaf21c668c4fe2
3
  size 267832560
run-6/checkpoint-54/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da18ae300a745fcd111f45461dc6a23390facdc1f0803f3f0eeeccc833c91f62
3
  size 535727290
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25c5316ebbbabefc13fa3bbf92361e2d12365fea39315a323caef940fb66c96b
3
  size 535727290
run-6/checkpoint-54/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dd2c9f09417dd8fc54a482da6d2926a7da5940a89b7dab8d1b45e1891089a0b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3b6b92f846babc5f50fe3d11031d0ebd5dbc737ba60453f7b3e988b93bff876
3
  size 14244
run-6/checkpoint-54/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a214c56eb930ea86c7c18d0004e6631c3ef171b3f1d64c299c526c0048ee726
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70f0093d9dc6da2cbed1757c3a9212a9c4515ac80cbfe5fb7c9ad1047421ef05
3
  size 1064
run-6/checkpoint-54/trainer_state.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "best_metric": 0.0,
3
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-54",
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
  "global_step": 54,
7
  "is_hyper_param_search": true,
@@ -10,26 +10,35 @@
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_loss": 0.6037843227386475,
14
  "eval_matthews_correlation": 0.0,
15
- "eval_runtime": 0.7144,
16
- "eval_samples_per_second": 1459.998,
17
- "eval_steps_per_second": 92.387,
 
 
 
 
 
 
 
 
 
18
  "step": 54
19
  }
20
  ],
21
  "logging_steps": 500,
22
  "max_steps": 54,
23
  "num_input_tokens_seen": 0,
24
- "num_train_epochs": 1,
25
  "save_steps": 500,
26
  "total_flos": 0,
27
- "train_batch_size": 16,
28
  "trial_name": null,
29
  "trial_params": {
30
- "learning_rate": 1.5708631840677204e-05,
31
- "num_train_epochs": 1,
32
- "per_device_train_batch_size": 16,
33
- "seed": 23
34
  }
35
  }
 
1
  {
2
+ "best_metric": 0.2533031432170664,
3
  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-54",
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
  "global_step": 54,
7
  "is_hyper_param_search": true,
 
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_loss": 0.582168698310852,
14
  "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7989,
16
+ "eval_samples_per_second": 1305.62,
17
+ "eval_steps_per_second": 82.618,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5733588933944702,
23
+ "eval_matthews_correlation": 0.2533031432170664,
24
+ "eval_runtime": 0.7969,
25
+ "eval_samples_per_second": 1308.79,
26
+ "eval_steps_per_second": 82.819,
27
  "step": 54
28
  }
29
  ],
30
  "logging_steps": 500,
31
  "max_steps": 54,
32
  "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
  "save_steps": 500,
35
  "total_flos": 0,
36
+ "train_batch_size": 32,
37
  "trial_name": null,
38
  "trial_params": {
39
+ "learning_rate": 7.764293438711137e-05,
40
+ "num_train_epochs": 2,
41
+ "per_device_train_batch_size": 32,
42
+ "seed": 5
43
  }
44
  }
run-6/checkpoint-54/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d822948eb7fa279c8d3164ed8173dac19880642b68f84c1d3552ee5fc0f3a8f0
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f97ff7e5c223c4007c1d57357c940c7d0090cde32f40fc663e312cb6424669a
3
  size 4984
run-7/checkpoint-14/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-14/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee4376a86f672a747e935bc5434d5af0dc7dd70266d7fc82bc2e3b6b08d6117f
3
+ size 267832560
run-7/checkpoint-14/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d6514b31ab5f831e98717c0e7623d3d594f98aaf62a887bece402e2aab8b434
3
+ size 535727290
run-7/checkpoint-14/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e330aee525a109f44cc3bc5d4b1387583b6433498f1e92dc092c5b05018b03ae
3
+ size 14244
run-7/checkpoint-14/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:759b1c25919bdf574698a331b95eee8b577a1b96cd0128aef51fe832226be93e
3
+ size 1064
run-7/checkpoint-14/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-7/checkpoint-14/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-14/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": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-7/checkpoint-14/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-14",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 14,
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_loss": 0.6431679129600525,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7348,
16
+ "eval_samples_per_second": 1419.395,
17
+ "eval_steps_per_second": 89.818,
18
+ "step": 14
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 56,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 64,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 4.60411924649496e-06,
31
+ "num_train_epochs": 4,
32
+ "per_device_train_batch_size": 64,
33
+ "seed": 1
34
+ }
35
+ }
run-7/checkpoint-14/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7d52f65fbe73570d4e65781de9eeeae78b2e1bae82a19760059f92848fdfae9
3
+ size 4984
run-7/checkpoint-14/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb28_18-10-00_5620ed9b2fff/events.out.tfevents.1709144992.5620ed9b2fff.209.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:858570fb33d932e1aaa40653a21d27d0fda5616cee165fb8c1d87dd81930931b
3
+ size 5547
runs/Feb28_18-10-00_5620ed9b2fff/events.out.tfevents.1709145108.5620ed9b2fff.209.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df1cf5ceeab83d6b68fd042c0b33cee46077f2d395335ea2f90ea61fd386913f
3
+ size 6204
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b7fc4f9b29c3121dc6f8881746905e52cb427e9f9addbda370817c836d00f27
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7d52f65fbe73570d4e65781de9eeeae78b2e1bae82a19760059f92848fdfae9
3
  size 4984