Hugging Face's logo

AilingDAI
/
HM_1

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
AilingDAI commited on
Commit
5810abf
·
verified ·
1 Parent(s): 27d3d6f

Training in progress, epoch 1

Browse files
Files changed (50) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-268/config.json +25 -0
  3. run-4/checkpoint-268/model.safetensors +3 -0
  4. run-4/checkpoint-268/optimizer.pt +3 -0
  5. run-4/checkpoint-268/rng_state.pth +3 -0
  6. run-4/checkpoint-268/scheduler.pt +3 -0
  7. run-4/checkpoint-268/special_tokens_map.json +7 -0
  8. run-4/checkpoint-268/tokenizer.json +0 -0
  9. run-4/checkpoint-268/tokenizer_config.json +55 -0
  10. run-4/checkpoint-268/trainer_state.json +44 -0
  11. run-4/checkpoint-268/training_args.bin +3 -0
  12. run-4/checkpoint-268/vocab.txt +0 -0
  13. run-4/checkpoint-402/config.json +25 -0
  14. run-4/checkpoint-402/model.safetensors +3 -0
  15. run-4/checkpoint-402/optimizer.pt +3 -0
  16. run-4/checkpoint-402/rng_state.pth +3 -0
  17. run-4/checkpoint-402/scheduler.pt +3 -0
  18. run-4/checkpoint-402/special_tokens_map.json +7 -0
  19. run-4/checkpoint-402/tokenizer.json +0 -0
  20. run-4/checkpoint-402/tokenizer_config.json +55 -0
  21. run-4/checkpoint-402/trainer_state.json +53 -0
  22. run-4/checkpoint-402/training_args.bin +3 -0
  23. run-4/checkpoint-402/vocab.txt +0 -0
  24. run-4/checkpoint-536/config.json +25 -0
  25. run-4/checkpoint-536/model.safetensors +3 -0
  26. run-4/checkpoint-536/optimizer.pt +3 -0
  27. run-4/checkpoint-536/rng_state.pth +3 -0
  28. run-4/checkpoint-536/scheduler.pt +3 -0
  29. run-4/checkpoint-536/special_tokens_map.json +7 -0
  30. run-4/checkpoint-536/tokenizer.json +0 -0
  31. run-4/checkpoint-536/tokenizer_config.json +55 -0
  32. run-4/checkpoint-536/trainer_state.json +69 -0
  33. run-4/checkpoint-536/training_args.bin +3 -0
  34. run-4/checkpoint-536/vocab.txt +0 -0
  35. run-8/checkpoint-535/config.json +25 -0
  36. run-8/checkpoint-535/model.safetensors +3 -0
  37. run-8/checkpoint-535/optimizer.pt +3 -0
  38. run-8/checkpoint-535/rng_state.pth +3 -0
  39. run-8/checkpoint-535/scheduler.pt +3 -0
  40. run-8/checkpoint-535/special_tokens_map.json +7 -0
  41. run-8/checkpoint-535/tokenizer.json +0 -0
  42. run-8/checkpoint-535/tokenizer_config.json +55 -0
  43. run-8/checkpoint-535/trainer_state.json +42 -0
  44. run-8/checkpoint-535/training_args.bin +3 -0
  45. run-8/checkpoint-535/vocab.txt +0 -0
  46. runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711160934.52e0cb6c1736.459.7 +3 -0
  47. runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711161032.52e0cb6c1736.459.8 +3 -0
  48. runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711161053.52e0cb6c1736.459.9 +3 -0
  49. runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711161077.52e0cb6c1736.459.10 +3 -0
  50. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9113d76ba545fb086fb6a5e9e3fc213529275493d8432e21f9e80dab7fab4bca
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6af8ceaeaabc6af3df2cc1096d9f8e6aad1a69b3cf65efc9a9abc6aa1272efe
3
  size 267832560
run-4/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": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e657bedc472d931da383bc93033759e39d782a3e0e7cd9abe13f3bc4c46143a
3
+ size 267832560
run-4/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad08896f33a2c299807beee3087358844f9d04dbea4bead27029d19dc7901e2
3
+ size 535727290
run-4/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53079ad91e486c98e8caf2a5b821a40f9f8d0d282dd8358913897962422a16f7
3
+ size 14244
run-4/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03f05bff8a55c0f7097eb03e92e43538d77be976d278f5076184af3ff2efe4fe
3
+ size 1064
run-4/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-4/checkpoint-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-268/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5085739436587455,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/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": 0.46314120292663574,
14
+ "eval_matthews_correlation": 0.46741180953359257,
15
+ "eval_runtime": 0.803,
16
+ "eval_samples_per_second": 1298.905,
17
+ "eval_steps_per_second": 82.193,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.4754369258880615,
23
+ "eval_matthews_correlation": 0.5085739436587455,
24
+ "eval_runtime": 0.911,
25
+ "eval_samples_per_second": 1144.922,
26
+ "eval_steps_per_second": 72.45,
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": 3.0100334336501613e-05,
40
+ "num_train_epochs": 4,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 15
43
+ }
44
+ }
run-4/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:151c174a2ffa585401c97ac1e4a204237f812a0791c32e61c4a49909b4de743c
3
+ size 4984
run-4/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-402/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd861944962a7ca12ddc65030320bf25ca57b58901496084bdf7c87984a7bb7
3
+ size 267832560
run-4/checkpoint-402/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb74482855ba4cd450870a8579d0a7ebbbe2809d60be31da8100a6efa63c1789
3
+ size 535727290
run-4/checkpoint-402/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac757dfc09ac9ec253905d4baf960343b58ff78a80fc4bfed9bfd51e6293eebc
3
+ size 14244
run-4/checkpoint-402/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd20e26617a004bf5f514f0bd252f535049d65ae164d007f9691d77749db0ffe
3
+ size 1064
run-4/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-4/checkpoint-402/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-402/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5219614412677479,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/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": 0.46314120292663574,
14
+ "eval_matthews_correlation": 0.46741180953359257,
15
+ "eval_runtime": 0.803,
16
+ "eval_samples_per_second": 1298.905,
17
+ "eval_steps_per_second": 82.193,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.4754369258880615,
23
+ "eval_matthews_correlation": 0.5085739436587455,
24
+ "eval_runtime": 0.911,
25
+ "eval_samples_per_second": 1144.922,
26
+ "eval_steps_per_second": 72.45,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5176757574081421,
32
+ "eval_matthews_correlation": 0.5219614412677479,
33
+ "eval_runtime": 1.4636,
34
+ "eval_samples_per_second": 712.629,
35
+ "eval_steps_per_second": 45.094,
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": 3.0100334336501613e-05,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 15
52
+ }
53
+ }
run-4/checkpoint-402/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:151c174a2ffa585401c97ac1e4a204237f812a0791c32e61c4a49909b4de743c
3
+ size 4984
run-4/checkpoint-402/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea8cacf1b71cc9b48f3335e049573883a75657f52c6efe295d58b1150635a93b
3
+ size 267832560
run-4/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3695025f1335602162142fa91cdd4e9c5eba508747bb346069c7dea4b3b0e185
3
+ size 535727290
run-4/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd5c385b865c6d2a09d605a4ab3e2a71e227c207603025dffa2ea1cf040e0b84
3
+ size 14244
run-4/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92d36f610c3a758924bcd4750da07f7aa9c8658da208f59811eab69795a0b375
3
+ size 1064
run-4/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-4/checkpoint-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-536/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5219614412677479,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/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": 0.46314120292663574,
14
+ "eval_matthews_correlation": 0.46741180953359257,
15
+ "eval_runtime": 0.803,
16
+ "eval_samples_per_second": 1298.905,
17
+ "eval_steps_per_second": 82.193,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.4754369258880615,
23
+ "eval_matthews_correlation": 0.5085739436587455,
24
+ "eval_runtime": 0.911,
25
+ "eval_samples_per_second": 1144.922,
26
+ "eval_steps_per_second": 72.45,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5176757574081421,
32
+ "eval_matthews_correlation": 0.5219614412677479,
33
+ "eval_runtime": 1.4636,
34
+ "eval_samples_per_second": 712.629,
35
+ "eval_steps_per_second": 45.094,
36
+ "step": 402
37
+ },
38
+ {
39
+ "epoch": 3.73,
40
+ "grad_norm": 9.832540512084961,
41
+ "learning_rate": 2.0216642464814516e-06,
42
+ "loss": 0.3395,
43
+ "step": 500
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_loss": 0.5769934058189392,
48
+ "eval_matthews_correlation": 0.5182255730055916,
49
+ "eval_runtime": 0.8314,
50
+ "eval_samples_per_second": 1254.461,
51
+ "eval_steps_per_second": 79.381,
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": 208937050509444.0,
61
+ "train_batch_size": 64,
62
+ "trial_name": null,
63
+ "trial_params": {
64
+ "learning_rate": 3.0100334336501613e-05,
65
+ "num_train_epochs": 4,
66
+ "per_device_train_batch_size": 64,
67
+ "seed": 15
68
+ }
69
+ }
run-4/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:151c174a2ffa585401c97ac1e4a204237f812a0791c32e61c4a49909b4de743c
3
+ size 4984
run-4/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/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-8/checkpoint-535/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6af8ceaeaabc6af3df2cc1096d9f8e6aad1a69b3cf65efc9a9abc6aa1272efe
3
+ size 267832560
run-8/checkpoint-535/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3dc254617b0da3d1288b5ea4f900ebeb8972fcca8fc4b109de7676c66bd4769
3
+ size 535727290
run-8/checkpoint-535/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68a7d36e4cca67efc7952ac9a40b3453a63e7e1b68148f433410f222df5d3ae8
3
+ size 14308
run-8/checkpoint-535/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ffe4497edc0802dac9187bd2978ba40da82dba863090188b36601a60f1ae254
3
+ size 1064
run-8/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-8/checkpoint-535/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/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-8/checkpoint-535/trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.40824346633328423,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/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": 12.733132362365723,
14
+ "learning_rate": 4.1412896561923345e-05,
15
+ "loss": 0.5383,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_loss": 0.4885631799697876,
21
+ "eval_matthews_correlation": 0.40824346633328423,
22
+ "eval_runtime": 0.7542,
23
+ "eval_samples_per_second": 1382.997,
24
+ "eval_steps_per_second": 87.515,
25
+ "step": 535
26
+ }
27
+ ],
28
+ "logging_steps": 500,
29
+ "max_steps": 1605,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 3,
32
+ "save_steps": 500,
33
+ "total_flos": 152120179128480.0,
34
+ "train_batch_size": 16,
35
+ "trial_name": null,
36
+ "trial_params": {
37
+ "learning_rate": 6.0151763784513094e-05,
38
+ "num_train_epochs": 3,
39
+ "per_device_train_batch_size": 16,
40
+ "seed": 33
41
+ }
42
+ }
run-8/checkpoint-535/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f35b87dae681b4cabecc8611f7e21810b3ce0f859314ccdeac4709bfce1a14fe
3
+ size 4984
run-8/checkpoint-535/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711160934.52e0cb6c1736.459.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e51e9324b8f76b659d6e8eb6cb8257ae8b0f60f0a6b0f7ea28085f646ce1bb23
3
+ size 5764
runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711161032.52e0cb6c1736.459.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d47d2d3f919aa43662e5582dea01487706cf492e4e2e61f0c1b8360e70f8d0
3
+ size 4921
runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711161053.52e0cb6c1736.459.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe23d3dc077045a912b6de5402dbf54490f9e766e1553bc6823f57b42b5c5007
3
+ size 4922
runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711161077.52e0cb6c1736.459.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34c445d705171636030656d7ac6b1d27242c85e66cfbbd57d01c2dc80aaabeee
3
+ size 6579
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:151c174a2ffa585401c97ac1e4a204237f812a0791c32e61c4a49909b4de743c
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f35b87dae681b4cabecc8611f7e21810b3ce0f859314ccdeac4709bfce1a14fe
3
  size 4984