Hugging Face's logo

RavingRabbit
/
eformConsult

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
RavingRabbit commited on
Commit
05076c5
·
1 Parent(s): 7b790f1

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-7/checkpoint-1072/config.json +25 -0
  3. run-7/checkpoint-1072/model.safetensors +3 -0
  4. run-7/checkpoint-1072/optimizer.pt +3 -0
  5. run-7/checkpoint-1072/rng_state.pth +3 -0
  6. run-7/checkpoint-1072/scheduler.pt +3 -0
  7. run-7/checkpoint-1072/special_tokens_map.json +7 -0
  8. run-7/checkpoint-1072/tokenizer.json +0 -0
  9. run-7/checkpoint-1072/tokenizer_config.json +55 -0
  10. run-7/checkpoint-1072/trainer_state.json +74 -0
  11. run-7/checkpoint-1072/training_args.bin +3 -0
  12. run-7/checkpoint-1072/vocab.txt +0 -0
  13. run-7/checkpoint-1340/config.json +25 -0
  14. run-7/checkpoint-1340/model.safetensors +3 -0
  15. run-7/checkpoint-1340/optimizer.pt +3 -0
  16. run-7/checkpoint-1340/rng_state.pth +3 -0
  17. run-7/checkpoint-1340/scheduler.pt +3 -0
  18. run-7/checkpoint-1340/special_tokens_map.json +7 -0
  19. run-7/checkpoint-1340/tokenizer.json +0 -0
  20. run-7/checkpoint-1340/tokenizer_config.json +55 -0
  21. run-7/checkpoint-1340/trainer_state.json +83 -0
  22. run-7/checkpoint-1340/training_args.bin +3 -0
  23. run-7/checkpoint-1340/vocab.txt +0 -0
  24. run-7/checkpoint-536/config.json +25 -0
  25. run-7/checkpoint-536/model.safetensors +3 -0
  26. run-7/checkpoint-536/optimizer.pt +3 -0
  27. run-7/checkpoint-536/rng_state.pth +3 -0
  28. run-7/checkpoint-536/scheduler.pt +3 -0
  29. run-7/checkpoint-536/special_tokens_map.json +7 -0
  30. run-7/checkpoint-536/tokenizer.json +0 -0
  31. run-7/checkpoint-536/tokenizer_config.json +55 -0
  32. run-7/checkpoint-536/trainer_state.json +50 -0
  33. run-7/checkpoint-536/training_args.bin +3 -0
  34. run-7/checkpoint-536/vocab.txt +0 -0
  35. run-7/checkpoint-804/config.json +25 -0
  36. run-7/checkpoint-804/model.safetensors +3 -0
  37. run-7/checkpoint-804/optimizer.pt +3 -0
  38. run-7/checkpoint-804/rng_state.pth +3 -0
  39. run-7/checkpoint-804/scheduler.pt +3 -0
  40. run-7/checkpoint-804/special_tokens_map.json +7 -0
  41. run-7/checkpoint-804/tokenizer.json +0 -0
  42. run-7/checkpoint-804/tokenizer_config.json +55 -0
  43. run-7/checkpoint-804/trainer_state.json +59 -0
  44. run-7/checkpoint-804/training_args.bin +3 -0
  45. run-7/checkpoint-804/vocab.txt +0 -0
  46. run-9/checkpoint-2138/config.json +25 -0
  47. run-9/checkpoint-2138/model.safetensors +3 -0
  48. run-9/checkpoint-2138/optimizer.pt +3 -0
  49. run-9/checkpoint-2138/rng_state.pth +3 -0
  50. run-9/checkpoint-2138/scheduler.pt +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bbccfaf894990dccdc4b38ffbd9fcb45b09a361fb64bb9e1c7d62f93da963d9
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f727964bda32bcd52472fc5eb69cbd526db0ab09eb55be468aaebb7c2433d3a
3
  size 267832560
run-7/checkpoint-1072/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-1072/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2461277a5787e87d8e5ba375d880c42afc7f0033d829734a5ab9c9be3120d0
3
+ size 267832560
run-7/checkpoint-1072/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9dadba11ff550d2cf34e12d13ae4a9e7826ddd9118116ff8e4702ef697f45b6
3
+ size 535727290
run-7/checkpoint-1072/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82452465a82ef781e978032312dad036986bb485c6d0f3b168634060f6b12e79
3
+ size 14308
run-7/checkpoint-1072/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4a5bb21311660e3aeff7cd51814043286d0dca39f9ae7b14a41b7b07437899
3
+ size 1064
run-7/checkpoint-1072/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-1072/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-1072/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-1072/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5221688848649157,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-1072",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1072,
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": 0.481789767742157,
14
+ "eval_matthews_correlation": 0.4368717152763518,
15
+ "eval_runtime": 0.7166,
16
+ "eval_samples_per_second": 1455.425,
17
+ "eval_steps_per_second": 92.098,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 3.509309760035438e-05,
23
+ "loss": 0.4167,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.5229902267456055,
29
+ "eval_matthews_correlation": 0.4746837140719997,
30
+ "eval_runtime": 0.7929,
31
+ "eval_samples_per_second": 1315.363,
32
+ "eval_steps_per_second": 83.235,
33
+ "step": 536
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_loss": 0.6462266445159912,
38
+ "eval_matthews_correlation": 0.5120519207329847,
39
+ "eval_runtime": 0.7953,
40
+ "eval_samples_per_second": 1311.521,
41
+ "eval_steps_per_second": 82.992,
42
+ "step": 804
43
+ },
44
+ {
45
+ "epoch": 3.73,
46
+ "learning_rate": 1.4204349028714865e-05,
47
+ "loss": 0.1554,
48
+ "step": 1000
49
+ },
50
+ {
51
+ "epoch": 4.0,
52
+ "eval_loss": 0.7052999138832092,
53
+ "eval_matthews_correlation": 0.5221688848649157,
54
+ "eval_runtime": 0.8041,
55
+ "eval_samples_per_second": 1297.093,
56
+ "eval_steps_per_second": 82.079,
57
+ "step": 1072
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 1340,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 5,
64
+ "save_steps": 500,
65
+ "total_flos": 191053175514720.0,
66
+ "train_batch_size": 32,
67
+ "trial_name": null,
68
+ "trial_params": {
69
+ "learning_rate": 5.598184617199388e-05,
70
+ "num_train_epochs": 5,
71
+ "per_device_train_batch_size": 32,
72
+ "seed": 17
73
+ }
74
+ }
run-7/checkpoint-1072/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:560fac8f5d39d8b0dacb14f8f353578d62fc56260087019ba9558b475d6bfc51
3
+ size 4792
run-7/checkpoint-1072/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-1340/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-1340/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c4441ad5de9dfc9537f6c825fcd610ff87e31c8fd4b36f728e05d22f786a478
3
+ size 267832560
run-7/checkpoint-1340/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbdd4f47ff3d1d35b0a4c170d27a1dfda10e1a32b43d9dc9b4fe4016edff2337
3
+ size 535727290
run-7/checkpoint-1340/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1c22661e8f1365a813dbb2e8cd720cdb895ed3ca243a145a1e942c0e2ac124b
3
+ size 14308
run-7/checkpoint-1340/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e51c56fd2e7998202e517bc5cf36773dcf2f1f15961749a23de2b7260abc0d
3
+ size 1064
run-7/checkpoint-1340/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-1340/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-1340/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-1340/trainer_state.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5221688848649157,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-1072",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1340,
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": 0.481789767742157,
14
+ "eval_matthews_correlation": 0.4368717152763518,
15
+ "eval_runtime": 0.7166,
16
+ "eval_samples_per_second": 1455.425,
17
+ "eval_steps_per_second": 92.098,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 3.509309760035438e-05,
23
+ "loss": 0.4167,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.5229902267456055,
29
+ "eval_matthews_correlation": 0.4746837140719997,
30
+ "eval_runtime": 0.7929,
31
+ "eval_samples_per_second": 1315.363,
32
+ "eval_steps_per_second": 83.235,
33
+ "step": 536
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_loss": 0.6462266445159912,
38
+ "eval_matthews_correlation": 0.5120519207329847,
39
+ "eval_runtime": 0.7953,
40
+ "eval_samples_per_second": 1311.521,
41
+ "eval_steps_per_second": 82.992,
42
+ "step": 804
43
+ },
44
+ {
45
+ "epoch": 3.73,
46
+ "learning_rate": 1.4204349028714865e-05,
47
+ "loss": 0.1554,
48
+ "step": 1000
49
+ },
50
+ {
51
+ "epoch": 4.0,
52
+ "eval_loss": 0.7052999138832092,
53
+ "eval_matthews_correlation": 0.5221688848649157,
54
+ "eval_runtime": 0.8041,
55
+ "eval_samples_per_second": 1297.093,
56
+ "eval_steps_per_second": 82.079,
57
+ "step": 1072
58
+ },
59
+ {
60
+ "epoch": 5.0,
61
+ "eval_loss": 0.9151925444602966,
62
+ "eval_matthews_correlation": 0.5100838064555473,
63
+ "eval_runtime": 1.0618,
64
+ "eval_samples_per_second": 982.329,
65
+ "eval_steps_per_second": 62.161,
66
+ "step": 1340
67
+ }
68
+ ],
69
+ "logging_steps": 500,
70
+ "max_steps": 1340,
71
+ "num_input_tokens_seen": 0,
72
+ "num_train_epochs": 5,
73
+ "save_steps": 500,
74
+ "total_flos": 191053175514720.0,
75
+ "train_batch_size": 32,
76
+ "trial_name": null,
77
+ "trial_params": {
78
+ "learning_rate": 5.598184617199388e-05,
79
+ "num_train_epochs": 5,
80
+ "per_device_train_batch_size": 32,
81
+ "seed": 17
82
+ }
83
+ }
run-7/checkpoint-1340/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:560fac8f5d39d8b0dacb14f8f353578d62fc56260087019ba9558b475d6bfc51
3
+ size 4792
run-7/checkpoint-1340/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-536/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cac9aecc424407a2e904d444b1e920445db25d7b94f9ea45fd1f6568b0bffcb0
3
+ size 267832560
run-7/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b230fcf3bda6bd2a1bf470ced22f64c0c2cdbc403740a8f79e027426c1fdfdc4
3
+ size 535727290
run-7/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0167e96419456249bf4ed9500338f0b1bcb214f0832d3d6ec81d59e6cb7529bf
3
+ size 14308
run-7/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff3b8eb16f025f7beba7b30529f1c25ffe2d326f7a57e7e3206479c8d32eadbd
3
+ size 1064
run-7/checkpoint-536/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-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-536/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-536/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4746837140719997,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-536",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 536,
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": 0.481789767742157,
14
+ "eval_matthews_correlation": 0.4368717152763518,
15
+ "eval_runtime": 0.7166,
16
+ "eval_samples_per_second": 1455.425,
17
+ "eval_steps_per_second": 92.098,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 3.509309760035438e-05,
23
+ "loss": 0.4167,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.5229902267456055,
29
+ "eval_matthews_correlation": 0.4746837140719997,
30
+ "eval_runtime": 0.7929,
31
+ "eval_samples_per_second": 1315.363,
32
+ "eval_steps_per_second": 83.235,
33
+ "step": 536
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 1340,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 5,
40
+ "save_steps": 500,
41
+ "total_flos": 95261911685436.0,
42
+ "train_batch_size": 32,
43
+ "trial_name": null,
44
+ "trial_params": {
45
+ "learning_rate": 5.598184617199388e-05,
46
+ "num_train_epochs": 5,
47
+ "per_device_train_batch_size": 32,
48
+ "seed": 17
49
+ }
50
+ }
run-7/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:560fac8f5d39d8b0dacb14f8f353578d62fc56260087019ba9558b475d6bfc51
3
+ size 4792
run-7/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-804/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-804/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8346ec21b7038c46783c1fa70446348e5354499b448cd7ceb4c755eeb81c2c7
3
+ size 267832560
run-7/checkpoint-804/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d323d9df16a1fd453836b29b2c2b282e6e2cedc23a7cf735639bc5fcbc3a885e
3
+ size 535727290
run-7/checkpoint-804/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1492dfaec3bdee1a6abaea64f607bd64b826dce0fea38a318bf3163cf75662e
3
+ size 14308
run-7/checkpoint-804/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f21724c860175b6c340c7bb3b12276a3b90387141881453c25ea1b10687d2eba
3
+ size 1064
run-7/checkpoint-804/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-804/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-804/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-804/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5120519207329847,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-804",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 804,
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": 0.481789767742157,
14
+ "eval_matthews_correlation": 0.4368717152763518,
15
+ "eval_runtime": 0.7166,
16
+ "eval_samples_per_second": 1455.425,
17
+ "eval_steps_per_second": 92.098,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 3.509309760035438e-05,
23
+ "loss": 0.4167,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.5229902267456055,
29
+ "eval_matthews_correlation": 0.4746837140719997,
30
+ "eval_runtime": 0.7929,
31
+ "eval_samples_per_second": 1315.363,
32
+ "eval_steps_per_second": 83.235,
33
+ "step": 536
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_loss": 0.6462266445159912,
38
+ "eval_matthews_correlation": 0.5120519207329847,
39
+ "eval_runtime": 0.7953,
40
+ "eval_samples_per_second": 1311.521,
41
+ "eval_steps_per_second": 82.992,
42
+ "step": 804
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 1340,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 5,
49
+ "save_steps": 500,
50
+ "total_flos": 95261911685436.0,
51
+ "train_batch_size": 32,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 5.598184617199388e-05,
55
+ "num_train_epochs": 5,
56
+ "per_device_train_batch_size": 32,
57
+ "seed": 17
58
+ }
59
+ }
run-7/checkpoint-804/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:560fac8f5d39d8b0dacb14f8f353578d62fc56260087019ba9558b475d6bfc51
3
+ size 4792
run-7/checkpoint-804/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-2138/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-9/checkpoint-2138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f727964bda32bcd52472fc5eb69cbd526db0ab09eb55be468aaebb7c2433d3a
3
+ size 267832560
run-9/checkpoint-2138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcc23dd22c22c0ec5671bebf77c29c56bf675f80cbf63e5f94a4c5ba255452ff
3
+ size 535727290
run-9/checkpoint-2138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69e0a553a49d736b29e905a2d4bf1244efc8e9ef91880c8ee0b1a1f54b22212d
3
+ size 14244
run-9/checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:455872e4b5a1a1cfb26158f781fa0176fa834e2656f9afa72289de8efc8c657e
3
+ size 1064