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
cf8063b
·
verified ·
1 Parent(s): a9e22be

Training in progress, epoch 1

Browse files
Files changed (40) hide show
  1. model.safetensors +1 -1
  2. run-5/checkpoint-1070/config.json +25 -0
  3. run-5/checkpoint-1070/model.safetensors +3 -0
  4. run-5/checkpoint-1070/optimizer.pt +3 -0
  5. run-5/checkpoint-1070/rng_state.pth +3 -0
  6. run-5/checkpoint-1070/scheduler.pt +3 -0
  7. run-5/checkpoint-1070/special_tokens_map.json +7 -0
  8. run-5/checkpoint-1070/tokenizer.json +0 -0
  9. run-5/checkpoint-1070/tokenizer_config.json +55 -0
  10. run-5/checkpoint-1070/trainer_state.json +58 -0
  11. run-5/checkpoint-1070/training_args.bin +3 -0
  12. run-5/checkpoint-1070/vocab.txt +0 -0
  13. run-5/checkpoint-1605/config.json +25 -0
  14. run-5/checkpoint-1605/model.safetensors +3 -0
  15. run-5/checkpoint-1605/optimizer.pt +3 -0
  16. run-5/checkpoint-1605/rng_state.pth +3 -0
  17. run-5/checkpoint-1605/scheduler.pt +3 -0
  18. run-5/checkpoint-1605/special_tokens_map.json +7 -0
  19. run-5/checkpoint-1605/tokenizer.json +0 -0
  20. run-5/checkpoint-1605/tokenizer_config.json +55 -0
  21. run-5/checkpoint-1605/trainer_state.json +74 -0
  22. run-5/checkpoint-1605/training_args.bin +3 -0
  23. run-5/checkpoint-1605/vocab.txt +0 -0
  24. run-5/checkpoint-2140/config.json +25 -0
  25. run-5/checkpoint-2140/model.safetensors +3 -0
  26. run-5/checkpoint-2140/optimizer.pt +3 -0
  27. run-5/checkpoint-2140/rng_state.pth +3 -0
  28. run-5/checkpoint-2140/scheduler.pt +3 -0
  29. run-5/checkpoint-2140/special_tokens_map.json +7 -0
  30. run-5/checkpoint-2140/tokenizer.json +0 -0
  31. run-5/checkpoint-2140/tokenizer_config.json +55 -0
  32. run-5/checkpoint-2140/trainer_state.json +90 -0
  33. run-5/checkpoint-2140/training_args.bin +3 -0
  34. run-5/checkpoint-2140/vocab.txt +0 -0
  35. runs/Mar23_02-09-44_4cc37c544afe/events.out.tfevents.1711161719.4cc37c544afe.560.8 +3 -0
  36. runs/Mar23_02-09-44_4cc37c544afe/events.out.tfevents.1711161739.4cc37c544afe.560.9 +3 -0
  37. runs/Mar23_02-09-44_4cc37c544afe/events.out.tfevents.1711161790.4cc37c544afe.560.10 +3 -0
  38. runs/Mar23_02-09-44_4cc37c544afe/events.out.tfevents.1711161810.4cc37c544afe.560.11 +3 -0
  39. runs/Mar23_02-09-44_4cc37c544afe/events.out.tfevents.1711161977.4cc37c544afe.560.12 +3 -0
  40. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8969155d65cf950354c6cb0798e2264db8115da3606f3855006c388c74132442
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e9ad20a0bd5710a330976ae6a2da344cd0d1163c0b082aca7c3e79a15d39390
3
  size 267832560
run-5/checkpoint-1070/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-1070/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efb232c2525e332c91c7ceb9f3028ee2eacd9712dcec425b44c161ff7af2a392
3
+ size 267832560
run-5/checkpoint-1070/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8c3d1566f41d5c8d1a3a18a9bf1a23a1d87dd651407901d02299e12473edb58
3
+ size 535727290
run-5/checkpoint-1070/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cb9589bd1de0c000166482940c4a7b0f796fb6e819494e39c135079b150802b
3
+ size 14308
run-5/checkpoint-1070/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a61dc76d954876878b398b562f67ebd32f57c69d2fde8bfe6ade46b98c4db449
3
+ size 1064
run-5/checkpoint-1070/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-1070/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-1070/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-1070/trainer_state.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4744648934358445,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-1070",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1070,
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
+ "epoch": 1.87,
29
+ "grad_norm": 9.167702674865723,
30
+ "learning_rate": 4.790346582159888e-05,
31
+ "loss": 0.356,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_loss": 0.5107694864273071,
37
+ "eval_matthews_correlation": 0.4744648934358445,
38
+ "eval_runtime": 1.1779,
39
+ "eval_samples_per_second": 885.459,
40
+ "eval_steps_per_second": 56.031,
41
+ "step": 1070
42
+ }
43
+ ],
44
+ "logging_steps": 500,
45
+ "max_steps": 2140,
46
+ "num_input_tokens_seen": 0,
47
+ "num_train_epochs": 4,
48
+ "save_steps": 500,
49
+ "total_flos": 85425431159064.0,
50
+ "train_batch_size": 16,
51
+ "trial_name": null,
52
+ "trial_params": {
53
+ "learning_rate": 8.9924049875633e-05,
54
+ "num_train_epochs": 4,
55
+ "per_device_train_batch_size": 16,
56
+ "seed": 26
57
+ }
58
+ }
run-5/checkpoint-1070/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-1070/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-1605/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-1605/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57e23de1c705fe48f4da5d27db126913a64c89ac4b0aaeb60c5f627dab91e12e
3
+ size 267832560
run-5/checkpoint-1605/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae9455ccc12bd656a175d79effc73a0a33a8a957f1555997781e9f9857131708
3
+ size 535727290
run-5/checkpoint-1605/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab1efed8bfb8de8c6af7a1ad61b13bbba8a85f4e89721770029efdfa148f3e1d
3
+ size 14308
run-5/checkpoint-1605/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6f8335c9db9e185e5a875dda088f86e1c586ebdc0eedb36610c3cd0813c7f83
3
+ size 1064
run-5/checkpoint-1605/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-1605/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-1605/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-1605/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.48594322653502614,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-1605",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1605,
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
+ "epoch": 1.87,
29
+ "grad_norm": 9.167702674865723,
30
+ "learning_rate": 4.790346582159888e-05,
31
+ "loss": 0.356,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_loss": 0.5107694864273071,
37
+ "eval_matthews_correlation": 0.4744648934358445,
38
+ "eval_runtime": 1.1779,
39
+ "eval_samples_per_second": 885.459,
40
+ "eval_steps_per_second": 56.031,
41
+ "step": 1070
42
+ },
43
+ {
44
+ "epoch": 2.8,
45
+ "grad_norm": 5.444707870483398,
46
+ "learning_rate": 2.689317379458183e-05,
47
+ "loss": 0.2179,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_loss": 0.7949007749557495,
53
+ "eval_matthews_correlation": 0.48594322653502614,
54
+ "eval_runtime": 1.1637,
55
+ "eval_samples_per_second": 896.282,
56
+ "eval_steps_per_second": 56.716,
57
+ "step": 1605
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 2140,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 4,
64
+ "save_steps": 500,
65
+ "total_flos": 128086660386384.0,
66
+ "train_batch_size": 16,
67
+ "trial_name": null,
68
+ "trial_params": {
69
+ "learning_rate": 8.9924049875633e-05,
70
+ "num_train_epochs": 4,
71
+ "per_device_train_batch_size": 16,
72
+ "seed": 26
73
+ }
74
+ }
run-5/checkpoint-1605/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-1605/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-2140/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-2140/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aefbbc7bf39b6b353934c71b5e2bd126a372fa10d154c8555b58ecc24efa898a
3
+ size 267832560
run-5/checkpoint-2140/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cbc07b899935801264b90218f30c3cfa36dafdb97bf10e0424722738d3c58bf
3
+ size 535727290
run-5/checkpoint-2140/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d2bbe1d128e7e7ab25fbce5a61ca186ced67d321f7fe0d11623ea0502a5ca05
3
+ size 14308
run-5/checkpoint-2140/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22183dc0fe7df6f4baaf3ac607c9862bf4f0000804c15ceda5179046c5199e80
3
+ size 1064
run-5/checkpoint-2140/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-2140/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-2140/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-2140/trainer_state.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5115958993985192,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-2140",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2140,
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
+ "epoch": 1.87,
29
+ "grad_norm": 9.167702674865723,
30
+ "learning_rate": 4.790346582159888e-05,
31
+ "loss": 0.356,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_loss": 0.5107694864273071,
37
+ "eval_matthews_correlation": 0.4744648934358445,
38
+ "eval_runtime": 1.1779,
39
+ "eval_samples_per_second": 885.459,
40
+ "eval_steps_per_second": 56.031,
41
+ "step": 1070
42
+ },
43
+ {
44
+ "epoch": 2.8,
45
+ "grad_norm": 5.444707870483398,
46
+ "learning_rate": 2.689317379458183e-05,
47
+ "loss": 0.2179,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_loss": 0.7949007749557495,
53
+ "eval_matthews_correlation": 0.48594322653502614,
54
+ "eval_runtime": 1.1637,
55
+ "eval_samples_per_second": 896.282,
56
+ "eval_steps_per_second": 56.716,
57
+ "step": 1605
58
+ },
59
+ {
60
+ "epoch": 3.74,
61
+ "grad_norm": 0.30378222465515137,
62
+ "learning_rate": 5.882881767564775e-06,
63
+ "loss": 0.1143,
64
+ "step": 2000
65
+ },
66
+ {
67
+ "epoch": 4.0,
68
+ "eval_loss": 0.9291447997093201,
69
+ "eval_matthews_correlation": 0.5115958993985192,
70
+ "eval_runtime": 0.7761,
71
+ "eval_samples_per_second": 1343.864,
72
+ "eval_steps_per_second": 85.038,
73
+ "step": 2140
74
+ }
75
+ ],
76
+ "logging_steps": 500,
77
+ "max_steps": 2140,
78
+ "num_input_tokens_seen": 0,
79
+ "num_train_epochs": 4,
80
+ "save_steps": 500,
81
+ "total_flos": 170453201396772.0,
82
+ "train_batch_size": 16,
83
+ "trial_name": null,
84
+ "trial_params": {
85
+ "learning_rate": 8.9924049875633e-05,
86
+ "num_train_epochs": 4,
87
+ "per_device_train_batch_size": 16,
88
+ "seed": 26
89
+ }
90
+ }
run-5/checkpoint-2140/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-2140/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.1711161719.4cc37c544afe.560.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2a1305a051b7787f35a1cb3485c968a2de30499c860853eb072b44ee046a987
3
+ size 4918
runs/Mar23_02-09-44_4cc37c544afe/events.out.tfevents.1711161739.4cc37c544afe.560.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca249227e49aef967acf1dd05eeb76e54354c649330d80160d3d80b09149d23
3
+ size 5340
runs/Mar23_02-09-44_4cc37c544afe/events.out.tfevents.1711161790.4cc37c544afe.560.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07fed0143366a5d5da9e68d69512db8160a5ce16f0d675e6d8f8799103793f12
3
+ size 4919
runs/Mar23_02-09-44_4cc37c544afe/events.out.tfevents.1711161810.4cc37c544afe.560.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1326a0405bc86f5640e7654263629a2d5e128f11753e3833a69c2ecd510bc9a5
3
+ size 4919
runs/Mar23_02-09-44_4cc37c544afe/events.out.tfevents.1711161977.4cc37c544afe.560.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bf70be80122f1019f17c7540a80f61b25e9c6ab9c0948c0c0eba8d0801fbaf9
3
+ size 7363
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:065753e9dc39d5af2256644ade7d8012bf9770422a44334aa2231d53b7b8504b
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48274b221fff5652aa547d6614365662d9285f39f249964afe685924bacacf2d
3
  size 4984