Tomkao0214 commited on
Commit
5d05bf6
·
1 Parent(s): e24c1ad

Training in progress, epoch 1

Browse files
Files changed (48) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-1072/config.json +25 -0
  3. run-0/checkpoint-1072/model.safetensors +3 -0
  4. run-0/checkpoint-1072/optimizer.pt +3 -0
  5. run-0/checkpoint-1072/rng_state.pth +3 -0
  6. run-0/checkpoint-1072/scheduler.pt +3 -0
  7. run-0/checkpoint-1072/special_tokens_map.json +7 -0
  8. run-0/checkpoint-1072/tokenizer.json +0 -0
  9. run-0/checkpoint-1072/tokenizer_config.json +55 -0
  10. run-0/checkpoint-1072/trainer_state.json +74 -0
  11. run-0/checkpoint-1072/training_args.bin +3 -0
  12. run-0/checkpoint-1072/vocab.txt +0 -0
  13. run-0/checkpoint-536/config.json +25 -0
  14. run-0/checkpoint-536/model.safetensors +3 -0
  15. run-0/checkpoint-536/optimizer.pt +3 -0
  16. run-0/checkpoint-536/rng_state.pth +3 -0
  17. run-0/checkpoint-536/scheduler.pt +3 -0
  18. run-0/checkpoint-536/special_tokens_map.json +7 -0
  19. run-0/checkpoint-536/tokenizer.json +0 -0
  20. run-0/checkpoint-536/tokenizer_config.json +55 -0
  21. run-0/checkpoint-536/trainer_state.json +50 -0
  22. run-0/checkpoint-536/training_args.bin +3 -0
  23. run-0/checkpoint-536/vocab.txt +0 -0
  24. run-0/checkpoint-804/config.json +25 -0
  25. run-0/checkpoint-804/model.safetensors +3 -0
  26. run-0/checkpoint-804/optimizer.pt +3 -0
  27. run-0/checkpoint-804/rng_state.pth +3 -0
  28. run-0/checkpoint-804/scheduler.pt +3 -0
  29. run-0/checkpoint-804/special_tokens_map.json +7 -0
  30. run-0/checkpoint-804/tokenizer.json +0 -0
  31. run-0/checkpoint-804/tokenizer_config.json +55 -0
  32. run-0/checkpoint-804/trainer_state.json +59 -0
  33. run-0/checkpoint-804/training_args.bin +3 -0
  34. run-0/checkpoint-804/vocab.txt +0 -0
  35. run-1/checkpoint-1069/config.json +25 -0
  36. run-1/checkpoint-1069/model.safetensors +3 -0
  37. run-1/checkpoint-1069/optimizer.pt +3 -0
  38. run-1/checkpoint-1069/rng_state.pth +3 -0
  39. run-1/checkpoint-1069/scheduler.pt +3 -0
  40. run-1/checkpoint-1069/special_tokens_map.json +7 -0
  41. run-1/checkpoint-1069/tokenizer.json +0 -0
  42. run-1/checkpoint-1069/tokenizer_config.json +55 -0
  43. run-1/checkpoint-1069/trainer_state.json +47 -0
  44. run-1/checkpoint-1069/training_args.bin +3 -0
  45. run-1/checkpoint-1069/vocab.txt +0 -0
  46. runs/Dec23_02-21-58_39bac3413ec0/events.out.tfevents.1703298522.39bac3413ec0.1762.2 +2 -2
  47. runs/Dec23_02-21-58_39bac3413ec0/events.out.tfevents.1703298667.39bac3413ec0.1762.3 +3 -0
  48. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f8dd4cecb4cef80f47d25d1214d5fd1317472524beb65bf87bf2640e9475dee
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07ef957426af2a57eaf352a50226ab82a687a3efded08839b20fb6f7da02210b
3
  size 267832560
run-0/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-0/checkpoint-1072/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60ee61c2eede092dfaaa4f9c4b501b68da513b528dd5d0c4f32354fa264512da
3
+ size 267832560
run-0/checkpoint-1072/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f4597481003d910fd25e4d9267c280afdbe3b6b0b8e3f1f36001a014abe0431
3
+ size 535727290
run-0/checkpoint-1072/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55789eeeab1d57fa316aba965ff002494f65a81e81d3233a6664d72f2bf4cfd2
3
+ size 14244
run-0/checkpoint-1072/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1afb8e162a8c2f966ef70af7f77808ff04cb089749bd1cab89095031a3b8fe86
3
+ size 1064
run-0/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-0/checkpoint-1072/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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-0/checkpoint-1072/trainer_state.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.06558874629318973,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/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": 0.604080080986023,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7727,
16
+ "eval_samples_per_second": 1349.827,
17
+ "eval_steps_per_second": 85.416,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 7.427160542349033e-07,
23
+ "loss": 0.6025,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.5788336396217346,
29
+ "eval_matthews_correlation": 0.0,
30
+ "eval_runtime": 0.8235,
31
+ "eval_samples_per_second": 1266.562,
32
+ "eval_steps_per_second": 80.147,
33
+ "step": 536
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_loss": 0.5639671087265015,
38
+ "eval_matthews_correlation": 0.0,
39
+ "eval_runtime": 0.7998,
40
+ "eval_samples_per_second": 1304.142,
41
+ "eval_steps_per_second": 82.525,
42
+ "step": 804
43
+ },
44
+ {
45
+ "epoch": 3.73,
46
+ "learning_rate": 9.348873409949831e-08,
47
+ "loss": 0.5514,
48
+ "step": 1000
49
+ },
50
+ {
51
+ "epoch": 4.0,
52
+ "eval_loss": 0.5608372688293457,
53
+ "eval_matthews_correlation": 0.06558874629318973,
54
+ "eval_runtime": 1.0156,
55
+ "eval_samples_per_second": 1027.008,
56
+ "eval_steps_per_second": 64.988,
57
+ "step": 1072
58
+ }
59
+ ],
60
+ "logging_steps": 500,
61
+ "max_steps": 1072,
62
+ "num_input_tokens_seen": 0,
63
+ "num_train_epochs": 4,
64
+ "save_steps": 500,
65
+ "total_flos": 191339584519236.0,
66
+ "train_batch_size": 32,
67
+ "trial_name": null,
68
+ "trial_params": {
69
+ "learning_rate": 1.3919433743703082e-06,
70
+ "num_train_epochs": 4,
71
+ "per_device_train_batch_size": 32,
72
+ "seed": 18
73
+ }
74
+ }
run-0/checkpoint-1072/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faa62b71b761979343160f3c19bdbaafa79adfa3f8ac924c9b49e00429c7888e
3
+ size 4792
run-0/checkpoint-1072/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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-0/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20adff3528d24a12c65c4fa13f6d0a3c9d40dda75e5749baa01c569b2ef618de
3
+ size 267832560
run-0/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bbf2d2765a78069756d1e3501776b8999aff87eb0659caa2a2a038670d4756c
3
+ size 535727290
run-0/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f1d39e331afb57e48b2f34e65822f70689110491c0f4be474d814c24ae33a56
3
+ size 14244
run-0/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f76a2568c8c51b15929b1c2a2dd7618cfdc525c08a383998a0e9925c1065d18
3
+ size 1064
run-0/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-0/checkpoint-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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-0/checkpoint-536/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-268",
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": 0.604080080986023,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7727,
16
+ "eval_samples_per_second": 1349.827,
17
+ "eval_steps_per_second": 85.416,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 7.427160542349033e-07,
23
+ "loss": 0.6025,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.5788336396217346,
29
+ "eval_matthews_correlation": 0.0,
30
+ "eval_runtime": 0.8235,
31
+ "eval_samples_per_second": 1266.562,
32
+ "eval_steps_per_second": 80.147,
33
+ "step": 536
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 1072,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 4,
40
+ "save_steps": 500,
41
+ "total_flos": 96169002895764.0,
42
+ "train_batch_size": 32,
43
+ "trial_name": null,
44
+ "trial_params": {
45
+ "learning_rate": 1.3919433743703082e-06,
46
+ "num_train_epochs": 4,
47
+ "per_device_train_batch_size": 32,
48
+ "seed": 18
49
+ }
50
+ }
run-0/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faa62b71b761979343160f3c19bdbaafa79adfa3f8ac924c9b49e00429c7888e
3
+ size 4792
run-0/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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-0/checkpoint-804/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be27d9b0ac48f553ad09ee63762c60af7f4931db41d14c685ddaca11e9f40011
3
+ size 267832560
run-0/checkpoint-804/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77c66702e5815f60f7c44397fd5ea9dee700b712ede6fd90f561ad0618577ffa
3
+ size 535727290
run-0/checkpoint-804/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84bbb652c9d321f9dcc2775f7b3dcae7e005ca60ab1c35ac24494fdae1d1812d
3
+ size 14244
run-0/checkpoint-804/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f14a352e4451fec1ecaed24a0396aef199cfe268c517863f3adbda7e2b7ad351
3
+ size 1064
run-0/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-0/checkpoint-804/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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-0/checkpoint-804/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-268",
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": 0.604080080986023,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7727,
16
+ "eval_samples_per_second": 1349.827,
17
+ "eval_steps_per_second": 85.416,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 7.427160542349033e-07,
23
+ "loss": 0.6025,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.5788336396217346,
29
+ "eval_matthews_correlation": 0.0,
30
+ "eval_runtime": 0.8235,
31
+ "eval_samples_per_second": 1266.562,
32
+ "eval_steps_per_second": 80.147,
33
+ "step": 536
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_loss": 0.5639671087265015,
38
+ "eval_matthews_correlation": 0.0,
39
+ "eval_runtime": 0.7998,
40
+ "eval_samples_per_second": 1304.142,
41
+ "eval_steps_per_second": 82.525,
42
+ "step": 804
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 1072,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 4,
49
+ "save_steps": 500,
50
+ "total_flos": 96169002895764.0,
51
+ "train_batch_size": 32,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 1.3919433743703082e-06,
55
+ "num_train_epochs": 4,
56
+ "per_device_train_batch_size": 32,
57
+ "seed": 18
58
+ }
59
+ }
run-0/checkpoint-804/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:faa62b71b761979343160f3c19bdbaafa79adfa3f8ac924c9b49e00429c7888e
3
+ size 4792
run-0/checkpoint-804/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1069/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-1/checkpoint-1069/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07ef957426af2a57eaf352a50226ab82a687a3efded08839b20fb6f7da02210b
3
+ size 267832560
run-1/checkpoint-1069/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a74bb4ff5f132d529b119a1eb8036677e80c065d5b5cbfcd7b419cd237fdcf73
3
+ size 535727290
run-1/checkpoint-1069/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f5e01cca190f82b1046e774d1354a1743092ecd99ac6b21e88213afc5479388
3
+ size 14244
run-1/checkpoint-1069/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4e5af0f6b6d97f3d9c21bcdfc68b82c80a259ebba48f2b1409679d1552bb46f
3
+ size 1064
run-1/checkpoint-1069/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-1/checkpoint-1069/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1069/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-1/checkpoint-1069/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1069",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1069,
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
+ "learning_rate": 1.378211193526262e-06,
14
+ "loss": 0.6228,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.94,
19
+ "learning_rate": 1.2359809361964104e-06,
20
+ "loss": 0.5739,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 0.5663976073265076,
26
+ "eval_matthews_correlation": 0.0,
27
+ "eval_runtime": 0.7509,
28
+ "eval_samples_per_second": 1388.989,
29
+ "eval_steps_per_second": 87.894,
30
+ "step": 1069
31
+ }
32
+ ],
33
+ "logging_steps": 500,
34
+ "max_steps": 5345,
35
+ "num_input_tokens_seen": 0,
36
+ "num_train_epochs": 5,
37
+ "save_steps": 500,
38
+ "total_flos": 37697323933152.0,
39
+ "train_batch_size": 8,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "learning_rate": 1.5204414508561137e-06,
43
+ "num_train_epochs": 5,
44
+ "per_device_train_batch_size": 8,
45
+ "seed": 38
46
+ }
47
+ }
run-1/checkpoint-1069/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993e710895c7c98b68e7ca3c281cd68e387ca778109cb5f069d17f6faa72b348
3
+ size 4792
run-1/checkpoint-1069/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-21-58_39bac3413ec0/events.out.tfevents.1703298522.39bac3413ec0.1762.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a90b4d29d25ec9fbba467bb051e7e75a8ee656b2d8027743b35523d59faa9f81
3
- size 4687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cee93028e1d29c765d60ee06f2888d6c7ebfdb326a4e921648fd02261feae78
3
+ size 6360
runs/Dec23_02-21-58_39bac3413ec0/events.out.tfevents.1703298667.39bac3413ec0.1762.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0455ba9b8b22431dcea8398d2c1ea25124fe3be0aa25d4fa7d0c4cd9b9eca0cf
3
+ size 5157
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:faa62b71b761979343160f3c19bdbaafa79adfa3f8ac924c9b49e00429c7888e
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993e710895c7c98b68e7ca3c281cd68e387ca778109cb5f069d17f6faa72b348
3
  size 4792