Hugging Face's logo

Duocas
/
CHT_LLM_Lesson

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files
xet
Metrics Community
Duocas commited on
Commit
38c12e5
·
verified ·
1 Parent(s): 2ef7b06

Training in progress, epoch 3

Browse files
Files changed (49) hide show
  1. run-6/checkpoint-134/config.json +25 -0
  2. run-6/checkpoint-134/model.safetensors +3 -0
  3. run-6/checkpoint-134/optimizer.pt +3 -0
  4. run-6/checkpoint-134/rng_state.pth +3 -0
  5. run-6/checkpoint-134/scheduler.pt +3 -0
  6. run-6/checkpoint-134/special_tokens_map.json +7 -0
  7. run-6/checkpoint-134/tokenizer.json +0 -0
  8. run-6/checkpoint-134/tokenizer_config.json +55 -0
  9. run-6/checkpoint-134/trainer_state.json +35 -0
  10. run-6/checkpoint-134/training_args.bin +3 -0
  11. run-6/checkpoint-134/vocab.txt +0 -0
  12. run-6/checkpoint-268/config.json +25 -0
  13. run-6/checkpoint-268/model.safetensors +3 -0
  14. run-6/checkpoint-268/optimizer.pt +3 -0
  15. run-6/checkpoint-268/rng_state.pth +3 -0
  16. run-6/checkpoint-268/scheduler.pt +3 -0
  17. run-6/checkpoint-268/special_tokens_map.json +7 -0
  18. run-6/checkpoint-268/tokenizer.json +0 -0
  19. run-6/checkpoint-268/tokenizer_config.json +55 -0
  20. run-6/checkpoint-268/trainer_state.json +44 -0
  21. run-6/checkpoint-268/training_args.bin +3 -0
  22. run-6/checkpoint-268/vocab.txt +0 -0
  23. run-6/checkpoint-402/config.json +25 -0
  24. run-6/checkpoint-402/model.safetensors +3 -0
  25. run-6/checkpoint-402/optimizer.pt +3 -0
  26. run-6/checkpoint-402/rng_state.pth +3 -0
  27. run-6/checkpoint-402/scheduler.pt +3 -0
  28. run-6/checkpoint-402/special_tokens_map.json +7 -0
  29. run-6/checkpoint-402/tokenizer.json +0 -0
  30. run-6/checkpoint-402/tokenizer_config.json +55 -0
  31. run-6/checkpoint-402/trainer_state.json +53 -0
  32. run-6/checkpoint-402/training_args.bin +3 -0
  33. run-6/checkpoint-402/vocab.txt +0 -0
  34. run-6/checkpoint-536/config.json +25 -0
  35. run-6/checkpoint-536/model.safetensors +3 -0
  36. run-6/checkpoint-536/optimizer.pt +3 -0
  37. run-6/checkpoint-536/rng_state.pth +3 -0
  38. run-6/checkpoint-536/scheduler.pt +3 -0
  39. run-6/checkpoint-536/special_tokens_map.json +7 -0
  40. run-6/checkpoint-536/tokenizer.json +0 -0
  41. run-6/checkpoint-536/tokenizer_config.json +55 -0
  42. run-6/checkpoint-536/trainer_state.json +69 -0
  43. run-6/checkpoint-536/training_args.bin +3 -0
  44. run-6/checkpoint-536/vocab.txt +0 -0
  45. runs/Mar04_02-28-38_78dd22f13cdf/events.out.tfevents.1709521159.78dd22f13cdf.294.8 +3 -0
  46. runs/Mar04_02-28-38_78dd22f13cdf/events.out.tfevents.1709521276.78dd22f13cdf.294.9 +3 -0
  47. runs/Mar04_02-28-38_78dd22f13cdf/events.out.tfevents.1709521298.78dd22f13cdf.294.10 +3 -0
  48. runs/Mar04_02-28-38_78dd22f13cdf/events.out.tfevents.1709521399.78dd22f13cdf.294.11 +3 -0
  49. runs/Mar04_02-28-38_78dd22f13cdf/events.out.tfevents.1709521421.78dd22f13cdf.294.12 +3 -0
run-6/checkpoint-134/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-134/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13b66499202ac478528e58a3a1358f1f914e167549a37431456d1293187d4b05
3
+ size 267832560
run-6/checkpoint-134/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc23182bf9b9ef4a0d0a887959a481181d4c2b5b5a17eaf79de05bf1c2de35e0
3
+ size 535727290
run-6/checkpoint-134/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a54004cbc6d9678ea40ad40223ca87b0f59f09bf57b5e845d0cf202ea314a346
3
+ size 14308
run-6/checkpoint-134/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c0474127a206b6ed1270dd06cf35b610f1bc42b5f7473f7cccadf0875f0c334
3
+ size 1064
run-6/checkpoint-134/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-6/checkpoint-134/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-134/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-6/checkpoint-134/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4971870184034438,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-134",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 134,
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": 0.45400816202163696,
14
+ "eval_matthews_correlation": 0.4971870184034438,
15
+ "eval_runtime": 0.7569,
16
+ "eval_samples_per_second": 1377.963,
17
+ "eval_steps_per_second": 87.196,
18
+ "step": 134
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 536,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 64,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 7.160112467126334e-05,
31
+ "num_train_epochs": 4,
32
+ "per_device_train_batch_size": 64,
33
+ "seed": 13
34
+ }
35
+ }
run-6/checkpoint-134/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4453a38d5213a2669482c00670ce1ec625dba90749f8177aae4dd3d277887226
3
+ size 4984
run-6/checkpoint-134/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-268/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a213bf6489c810baec0d692d5553466c2cf94c7b06ffb9cf0e0358f08eee26
3
+ size 267832560
run-6/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b68fa6c68c9383180f9bd2bf356bd1dd03ac60b9df6b8f8d3aa4c23b0b35157e
3
+ size 535727290
run-6/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7207a68078ec706453b51785c3b6d2f7cd4c2d8874e9395e8cfe293f0b845ecf
3
+ size 14308
run-6/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c8a6e38160e082e3fabfb5bf772ab081ccc9ba56fa9e914159adcace884963b
3
+ size 1064
run-6/checkpoint-268/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-6/checkpoint-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-268/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-6/checkpoint-268/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5032312800977334,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-268",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 268,
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": 0.45400816202163696,
14
+ "eval_matthews_correlation": 0.4971870184034438,
15
+ "eval_runtime": 0.7569,
16
+ "eval_samples_per_second": 1377.963,
17
+ "eval_steps_per_second": 87.196,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5047828555107117,
23
+ "eval_matthews_correlation": 0.5032312800977334,
24
+ "eval_runtime": 0.842,
25
+ "eval_samples_per_second": 1238.684,
26
+ "eval_steps_per_second": 78.383,
27
+ "step": 268
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 536,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 7.160112467126334e-05,
40
+ "num_train_epochs": 4,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 13
43
+ }
44
+ }
run-6/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4453a38d5213a2669482c00670ce1ec625dba90749f8177aae4dd3d277887226
3
+ size 4984
run-6/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-402/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-402/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dab21eb3106d5c197771c4ec411ae8525778593e736268a32e062237db733b13
3
+ size 267832560
run-6/checkpoint-402/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bdb3e60a4657ce0ca55f549f2f5dd7245586e88e852de113853731bcb46b9c7
3
+ size 535727290
run-6/checkpoint-402/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfd933d7c0c9e94bb9c1a910ac3d416d5bb34726af7848034fe7074e541083fd
3
+ size 14308
run-6/checkpoint-402/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f863e4a49afc0015df408fe0fd0de408e307da8bc23ac5b22775a2b92fb95ba8
3
+ size 1064
run-6/checkpoint-402/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-6/checkpoint-402/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-402/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-6/checkpoint-402/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5089318947112005,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-402",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 402,
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": 0.45400816202163696,
14
+ "eval_matthews_correlation": 0.4971870184034438,
15
+ "eval_runtime": 0.7569,
16
+ "eval_samples_per_second": 1377.963,
17
+ "eval_steps_per_second": 87.196,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5047828555107117,
23
+ "eval_matthews_correlation": 0.5032312800977334,
24
+ "eval_runtime": 0.842,
25
+ "eval_samples_per_second": 1238.684,
26
+ "eval_steps_per_second": 78.383,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5745963454246521,
32
+ "eval_matthews_correlation": 0.5089318947112005,
33
+ "eval_runtime": 0.8134,
34
+ "eval_samples_per_second": 1282.256,
35
+ "eval_steps_per_second": 81.14,
36
+ "step": 402
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 536,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 4,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 64,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 7.160112467126334e-05,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 13
52
+ }
53
+ }
run-6/checkpoint-402/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4453a38d5213a2669482c00670ce1ec625dba90749f8177aae4dd3d277887226
3
+ size 4984
run-6/checkpoint-402/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35f3d95df41740dbd649839b713e5aba59e4f172d881044fe2ca3aeccac841c7
3
+ size 267832560
run-6/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b84cd6e1a73617a5ec4253d3726a751ae25578a97a8d7f0423d13174d7a57d
3
+ size 535727290
run-6/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4447ed309289b6507e714c5f407c054229c390cfc79dc883952878638351fe2b
3
+ size 14308
run-6/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4a41dbd43703597905c099f1d96883a73b4096cf175903e9ba37c248cafe921
3
+ size 1064
run-6/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-6/checkpoint-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/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-6/checkpoint-536/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5089318947112005,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/checkpoint-402",
4
+ "epoch": 4.0,
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": 0.45400816202163696,
14
+ "eval_matthews_correlation": 0.4971870184034438,
15
+ "eval_runtime": 0.7569,
16
+ "eval_samples_per_second": 1377.963,
17
+ "eval_steps_per_second": 87.196,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5047828555107117,
23
+ "eval_matthews_correlation": 0.5032312800977334,
24
+ "eval_runtime": 0.842,
25
+ "eval_samples_per_second": 1238.684,
26
+ "eval_steps_per_second": 78.383,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5745963454246521,
32
+ "eval_matthews_correlation": 0.5089318947112005,
33
+ "eval_runtime": 0.8134,
34
+ "eval_samples_per_second": 1282.256,
35
+ "eval_steps_per_second": 81.14,
36
+ "step": 402
37
+ },
38
+ {
39
+ "epoch": 3.73,
40
+ "grad_norm": 3.759369134902954,
41
+ "learning_rate": 4.809030761502762e-06,
42
+ "loss": 0.2847,
43
+ "step": 500
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_loss": 0.7350723147392273,
48
+ "eval_matthews_correlation": 0.5055592530807526,
49
+ "eval_runtime": 0.8439,
50
+ "eval_samples_per_second": 1235.972,
51
+ "eval_steps_per_second": 78.211,
52
+ "step": 536
53
+ }
54
+ ],
55
+ "logging_steps": 500,
56
+ "max_steps": 536,
57
+ "num_input_tokens_seen": 0,
58
+ "num_train_epochs": 4,
59
+ "save_steps": 500,
60
+ "total_flos": 208996816074072.0,
61
+ "train_batch_size": 64,
62
+ "trial_name": null,
63
+ "trial_params": {
64
+ "learning_rate": 7.160112467126334e-05,
65
+ "num_train_epochs": 4,
66
+ "per_device_train_batch_size": 64,
67
+ "seed": 13
68
+ }
69
+ }
run-6/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4453a38d5213a2669482c00670ce1ec625dba90749f8177aae4dd3d277887226
3
+ size 4984
run-6/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar04_02-28-38_78dd22f13cdf/events.out.tfevents.1709521159.78dd22f13cdf.294.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15d12b0d17ca22b0949ff97968692cd38e59ce33935232b971c7f4fe0f9ad754
3
+ size 6466
runs/Mar04_02-28-38_78dd22f13cdf/events.out.tfevents.1709521276.78dd22f13cdf.294.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb3bbcb10b68dd7ceb4ad5c07fa45434593dd54d6cf1b0759f89847050d6b92c
3
+ size 4896
runs/Mar04_02-28-38_78dd22f13cdf/events.out.tfevents.1709521298.78dd22f13cdf.294.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28be128d126ca22d1796c151a71c722d5457c783490e09365ce72552ed3c0b17
3
+ size 5740
runs/Mar04_02-28-38_78dd22f13cdf/events.out.tfevents.1709521399.78dd22f13cdf.294.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e33d6df50fa116388a3227ab2f2294343d38282c5f26b136394e9f9e593d9c69
3
+ size 4897
runs/Mar04_02-28-38_78dd22f13cdf/events.out.tfevents.1709521421.78dd22f13cdf.294.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86c4b4ff9c57270fb02e0e42cfcc76814afe0512970ab8948ca36f29ea178d17
3
+ size 8452