Hugging Face's logo

Eva1209
/
HW1

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Eva1209 commited on
Commit
a9e22be
·
verified ·
1 Parent(s): a560236

Training in progress, epoch 1

Browse files
Files changed (36) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-2138/config.json +25 -0
  3. run-4/checkpoint-2138/model.safetensors +3 -0
  4. run-4/checkpoint-2138/optimizer.pt +3 -0
  5. run-4/checkpoint-2138/rng_state.pth +3 -0
  6. run-4/checkpoint-2138/scheduler.pt +3 -0
  7. run-4/checkpoint-2138/special_tokens_map.json +7 -0
  8. run-4/checkpoint-2138/tokenizer.json +0 -0
  9. run-4/checkpoint-2138/tokenizer_config.json +55 -0
  10. run-4/checkpoint-2138/trainer_state.json +72 -0
  11. run-4/checkpoint-2138/training_args.bin +3 -0
  12. run-4/checkpoint-2138/vocab.txt +0 -0
  13. run-4/checkpoint-3207/config.json +25 -0
  14. run-4/checkpoint-3207/model.safetensors +3 -0
  15. run-4/checkpoint-3207/optimizer.pt +3 -0
  16. run-4/checkpoint-3207/rng_state.pth +3 -0
  17. run-4/checkpoint-3207/scheduler.pt +3 -0
  18. run-4/checkpoint-3207/special_tokens_map.json +7 -0
  19. run-4/checkpoint-3207/tokenizer.json +0 -0
  20. run-4/checkpoint-3207/tokenizer_config.json +55 -0
  21. run-4/checkpoint-3207/trainer_state.json +95 -0
  22. run-4/checkpoint-3207/training_args.bin +3 -0
  23. run-4/checkpoint-3207/vocab.txt +0 -0
  24. run-5/checkpoint-535/config.json +25 -0
  25. run-5/checkpoint-535/model.safetensors +3 -0
  26. run-5/checkpoint-535/optimizer.pt +3 -0
  27. run-5/checkpoint-535/rng_state.pth +3 -0
  28. run-5/checkpoint-535/scheduler.pt +3 -0
  29. run-5/checkpoint-535/special_tokens_map.json +7 -0
  30. run-5/checkpoint-535/tokenizer.json +0 -0
  31. run-5/checkpoint-535/tokenizer_config.json +55 -0
  32. run-5/checkpoint-535/trainer_state.json +42 -0
  33. run-5/checkpoint-535/training_args.bin +3 -0
  34. run-5/checkpoint-535/vocab.txt +0 -0
  35. runs/Mar23_02-09-44_4cc37c544afe/events.out.tfevents.1711161518.4cc37c544afe.560.7 +3 -0
  36. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20ef9d80a26d16cc47c6ca4223348776489adca2ae7fb55c3c99c1b95b6d7b0e
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8969155d65cf950354c6cb0798e2264db8115da3606f3855006c388c74132442
3
  size 267832560
run-4/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": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-2138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:859e764bcb2d4f365071c6f60bc710ce8043494f4d42ba45b06af7bc98d35cfc
3
+ size 267832560
run-4/checkpoint-2138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc6f496714c51656d7e73da4fbbdcca9a161eb5e37464a688bc747353b9bf38d
3
+ size 535727290
run-4/checkpoint-2138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ba3991f738384abb1173f50ff8b4374fedc07528fbfccab8bc65128f37e0f45
3
+ size 14308
run-4/checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0aed9a0a85cebce8e3e643c8fc1159e868ebaa59748d934b41dcf87f46786b48
3
+ size 1064
run-4/checkpoint-2138/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-4/checkpoint-2138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-2138/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-4/checkpoint-2138/trainer_state.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.43881557658403864,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-2138",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2138,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.47,
13
+ "grad_norm": 4.060019016265869,
14
+ "learning_rate": 4.481496253268653e-05,
15
+ "loss": 0.5778,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.94,
20
+ "grad_norm": 12.268152236938477,
21
+ "learning_rate": 3.6537355858751076e-05,
22
+ "loss": 0.5395,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 0.4984060525894165,
28
+ "eval_matthews_correlation": 0.39596800444544106,
29
+ "eval_runtime": 0.6991,
30
+ "eval_samples_per_second": 1491.822,
31
+ "eval_steps_per_second": 94.401,
32
+ "step": 1069
33
+ },
34
+ {
35
+ "epoch": 1.4,
36
+ "grad_norm": 4.944720268249512,
37
+ "learning_rate": 2.8259749184815627e-05,
38
+ "loss": 0.3959,
39
+ "step": 1500
40
+ },
41
+ {
42
+ "epoch": 1.87,
43
+ "grad_norm": 9.598797798156738,
44
+ "learning_rate": 1.9982142510880178e-05,
45
+ "loss": 0.3603,
46
+ "step": 2000
47
+ },
48
+ {
49
+ "epoch": 2.0,
50
+ "eval_loss": 0.5668240785598755,
51
+ "eval_matthews_correlation": 0.43881557658403864,
52
+ "eval_runtime": 1.2379,
53
+ "eval_samples_per_second": 842.559,
54
+ "eval_steps_per_second": 53.316,
55
+ "step": 2138
56
+ }
57
+ ],
58
+ "logging_steps": 500,
59
+ "max_steps": 3207,
60
+ "num_input_tokens_seen": 0,
61
+ "num_train_epochs": 3,
62
+ "save_steps": 500,
63
+ "total_flos": 75430610695236.0,
64
+ "train_batch_size": 8,
65
+ "trial_name": null,
66
+ "trial_params": {
67
+ "learning_rate": 5.309256920662198e-05,
68
+ "num_train_epochs": 3,
69
+ "per_device_train_batch_size": 8,
70
+ "seed": 37
71
+ }
72
+ }
run-4/checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89a348413006cb985b3d7b21f158dfd19cf42a93cba0a4b8285ea33836d05e4d
3
+ size 4984
run-4/checkpoint-2138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-3207/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": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-3207/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a8e80278a224d537b019c50c6abd24ed037dde5d45fd294497f7dde5e4f3f7a
3
+ size 267832560
run-4/checkpoint-3207/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6bbccbcc750df6386924f85335ad8c0c54733a0df281722caa0561b1e2815cb
3
+ size 535727290
run-4/checkpoint-3207/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf1ed72d4f5a5f9c3d5b78bc354b73c4645483361c1cd16c43113daf27f05f66
3
+ size 14308
run-4/checkpoint-3207/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e1581bc1aec680f0cf1100655cb1861a5bdf9bb96311b86953744f9650db2c7
3
+ size 1064
run-4/checkpoint-3207/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-4/checkpoint-3207/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-3207/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-4/checkpoint-3207/trainer_state.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.47078712112764887,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-3207",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 3207,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.47,
13
+ "grad_norm": 4.060019016265869,
14
+ "learning_rate": 4.481496253268653e-05,
15
+ "loss": 0.5778,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.94,
20
+ "grad_norm": 12.268152236938477,
21
+ "learning_rate": 3.6537355858751076e-05,
22
+ "loss": 0.5395,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_loss": 0.4984060525894165,
28
+ "eval_matthews_correlation": 0.39596800444544106,
29
+ "eval_runtime": 0.6991,
30
+ "eval_samples_per_second": 1491.822,
31
+ "eval_steps_per_second": 94.401,
32
+ "step": 1069
33
+ },
34
+ {
35
+ "epoch": 1.4,
36
+ "grad_norm": 4.944720268249512,
37
+ "learning_rate": 2.8259749184815627e-05,
38
+ "loss": 0.3959,
39
+ "step": 1500
40
+ },
41
+ {
42
+ "epoch": 1.87,
43
+ "grad_norm": 9.598797798156738,
44
+ "learning_rate": 1.9982142510880178e-05,
45
+ "loss": 0.3603,
46
+ "step": 2000
47
+ },
48
+ {
49
+ "epoch": 2.0,
50
+ "eval_loss": 0.5668240785598755,
51
+ "eval_matthews_correlation": 0.43881557658403864,
52
+ "eval_runtime": 1.2379,
53
+ "eval_samples_per_second": 842.559,
54
+ "eval_steps_per_second": 53.316,
55
+ "step": 2138
56
+ },
57
+ {
58
+ "epoch": 2.34,
59
+ "grad_norm": 0.8520996570587158,
60
+ "learning_rate": 1.1704535836944727e-05,
61
+ "loss": 0.2352,
62
+ "step": 2500
63
+ },
64
+ {
65
+ "epoch": 2.81,
66
+ "grad_norm": 1.3932373523712158,
67
+ "learning_rate": 3.426929163009277e-06,
68
+ "loss": 0.2377,
69
+ "step": 3000
70
+ },
71
+ {
72
+ "epoch": 3.0,
73
+ "eval_loss": 0.8578255772590637,
74
+ "eval_matthews_correlation": 0.47078712112764887,
75
+ "eval_runtime": 1.3062,
76
+ "eval_samples_per_second": 798.53,
77
+ "eval_steps_per_second": 50.53,
78
+ "step": 3207
79
+ }
80
+ ],
81
+ "logging_steps": 500,
82
+ "max_steps": 3207,
83
+ "num_input_tokens_seen": 0,
84
+ "num_train_epochs": 3,
85
+ "save_steps": 500,
86
+ "total_flos": 112923282846480.0,
87
+ "train_batch_size": 8,
88
+ "trial_name": null,
89
+ "trial_params": {
90
+ "learning_rate": 5.309256920662198e-05,
91
+ "num_train_epochs": 3,
92
+ "per_device_train_batch_size": 8,
93
+ "seed": 37
94
+ }
95
+ }
run-4/checkpoint-3207/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89a348413006cb985b3d7b21f158dfd19cf42a93cba0a4b8285ea33836d05e4d
3
+ size 4984
run-4/checkpoint-3207/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-535/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": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-5/checkpoint-535/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8969155d65cf950354c6cb0798e2264db8115da3606f3855006c388c74132442
3
+ size 267832560
run-5/checkpoint-535/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f110ec3872c31fd8ebddb47daf5320194d36e30aa395c67124f2aabb9cd1b63
3
+ size 535727290
run-5/checkpoint-535/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:372160eb7af971801a663b846e79c51415b1d1e4e8d28cd20f11b22f42f568a3
3
+ size 14308
run-5/checkpoint-535/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4510e86c40a5aafc2dfe3533e850687ef43a360815545f9e68616858c3f85953
3
+ size 1064
run-5/checkpoint-535/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-535/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-535/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-535/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4033324209850535,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-535",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 535,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "grad_norm": 2.427436590194702,
14
+ "learning_rate": 6.891375784861594e-05,
15
+ "loss": 0.5578,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 0.5254166722297668,
21
+ "eval_matthews_correlation": 0.4033324209850535,
22
+ "eval_runtime": 0.7104,
23
+ "eval_samples_per_second": 1468.246,
24
+ "eval_steps_per_second": 92.909,
25
+ "step": 535
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 2140,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 4,
32
+ "save_steps": 500,
33
+ "total_flos": 42861482677632.0,
34
+ "train_batch_size": 16,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "learning_rate": 8.9924049875633e-05,
38
+ "num_train_epochs": 4,
39
+ "per_device_train_batch_size": 16,
40
+ "seed": 26
41
+ }
42
+ }
run-5/checkpoint-535/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:065753e9dc39d5af2256644ade7d8012bf9770422a44334aa2231d53b7b8504b
3
+ size 4984
run-5/checkpoint-535/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar23_02-09-44_4cc37c544afe/events.out.tfevents.1711161518.4cc37c544afe.560.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd7bdf27474b07b4c3187683767b0193feab2b133766fbe282a7ded0de4b97ce
3
+ size 7119
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89a348413006cb985b3d7b21f158dfd19cf42a93cba0a4b8285ea33836d05e4d
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:065753e9dc39d5af2256644ade7d8012bf9770422a44334aa2231d53b7b8504b
3
  size 4984