Hugging Face's logo

halu1003
/
LLMClassWork1

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
Metrics Community
halu1003 commited on
Commit
007b1ae
·
1 Parent(s): cea9859

Training in progress, epoch 1

Browse files
Files changed (49) hide show
  1. model.safetensors +1 -1
  2. run-4/checkpoint-134/config.json +25 -0
  3. run-4/checkpoint-134/model.safetensors +3 -0
  4. run-4/checkpoint-134/optimizer.pt +3 -0
  5. run-4/checkpoint-134/rng_state.pth +3 -0
  6. run-4/checkpoint-134/scheduler.pt +3 -0
  7. run-4/checkpoint-134/special_tokens_map.json +7 -0
  8. run-4/checkpoint-134/tokenizer.json +0 -0
  9. run-4/checkpoint-134/tokenizer_config.json +55 -0
  10. run-4/checkpoint-134/trainer_state.json +35 -0
  11. run-4/checkpoint-134/training_args.bin +3 -0
  12. run-4/checkpoint-134/vocab.txt +0 -0
  13. run-4/checkpoint-268/config.json +25 -0
  14. run-4/checkpoint-268/model.safetensors +3 -0
  15. run-4/checkpoint-268/optimizer.pt +3 -0
  16. run-4/checkpoint-268/rng_state.pth +3 -0
  17. run-4/checkpoint-268/scheduler.pt +3 -0
  18. run-4/checkpoint-268/special_tokens_map.json +7 -0
  19. run-4/checkpoint-268/tokenizer.json +0 -0
  20. run-4/checkpoint-268/tokenizer_config.json +55 -0
  21. run-4/checkpoint-268/trainer_state.json +44 -0
  22. run-4/checkpoint-268/training_args.bin +3 -0
  23. run-4/checkpoint-268/vocab.txt +0 -0
  24. run-4/checkpoint-402/config.json +25 -0
  25. run-4/checkpoint-402/model.safetensors +3 -0
  26. run-4/checkpoint-402/optimizer.pt +3 -0
  27. run-4/checkpoint-402/rng_state.pth +3 -0
  28. run-4/checkpoint-402/scheduler.pt +3 -0
  29. run-4/checkpoint-402/special_tokens_map.json +7 -0
  30. run-4/checkpoint-402/tokenizer.json +0 -0
  31. run-4/checkpoint-402/tokenizer_config.json +55 -0
  32. run-4/checkpoint-402/trainer_state.json +53 -0
  33. run-4/checkpoint-402/training_args.bin +3 -0
  34. run-4/checkpoint-402/vocab.txt +0 -0
  35. run-6/checkpoint-1069/config.json +25 -0
  36. run-6/checkpoint-1069/model.safetensors +3 -0
  37. run-6/checkpoint-1069/optimizer.pt +3 -0
  38. run-6/checkpoint-1069/rng_state.pth +3 -0
  39. run-6/checkpoint-1069/scheduler.pt +3 -0
  40. run-6/checkpoint-1069/special_tokens_map.json +7 -0
  41. run-6/checkpoint-1069/tokenizer.json +0 -0
  42. run-6/checkpoint-1069/tokenizer_config.json +55 -0
  43. run-6/checkpoint-1069/trainer_state.json +47 -0
  44. run-6/checkpoint-1069/training_args.bin +3 -0
  45. run-6/checkpoint-1069/vocab.txt +0 -0
  46. runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703299699.04248f4b0c3a.492.6 +3 -0
  47. runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703299800.04248f4b0c3a.492.7 +3 -0
  48. runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703299823.04248f4b0c3a.492.8 +3 -0
  49. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3842cbeb9c80ecc10d415d7fc4b0e674dad4c34a5fa0afc3d7d516aff9af1669
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8915dda6d92bf3398fe024e98d750561c54a54989ef0c77890ebd461e6099b69
3
  size 267832560
run-4/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": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-134/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:949408d61d5ac6b2653a74d309ab26cdd3be09b79060ae6c3894e67ad1e97068
3
+ size 267832560
run-4/checkpoint-134/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8df5c326146b9f46ec0c075009734a7fdcc33e443f607ffa52d3473271f54437
3
+ size 535727290
run-4/checkpoint-134/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7d58e82f2ee7a032b0b5398225e6e82ec00cc018b7d78794d6e570470038097
3
+ size 14308
run-4/checkpoint-134/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77136fe6a7094a4cb5cc83cb5201f3ba4a89761186c3850a980cc44fa8495c96
3
+ size 1064
run-4/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-4/checkpoint-134/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-134/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4130889956247439,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/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": 0.4921027719974518,
14
+ "eval_matthews_correlation": 0.4130889956247439,
15
+ "eval_runtime": 0.7437,
16
+ "eval_samples_per_second": 1402.413,
17
+ "eval_steps_per_second": 88.743,
18
+ "step": 134
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 402,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 64,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 2.3070930848457665e-05,
31
+ "num_train_epochs": 3,
32
+ "per_device_train_batch_size": 64,
33
+ "seed": 17
34
+ }
35
+ }
run-4/checkpoint-134/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36bde66e6449e9c1f7e73eb4952b2d02cf91a055154e256af6d28a1a6c8f7d0c
3
+ size 4792
run-4/checkpoint-134/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
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": "4.36.2",
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 sha256:23e834589b1a2f28c299ce7cb5cf5e0891ab445f649e9ce25a76b9177a2af4c7
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 sha256:96c92d9a743ba47444ecb0b53cd98bf744571370c379ecb80cc95b0d3715ee38
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 sha256:67c7825404bfca8251e3494c1620a72bb2e77173338c20795f9bf4ce6c487968
3
+ size 14308
run-4/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d2e29bb1379012fb8bed39a76bc69a742722634ce80c9419ba02eec2e0f5258
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": 0.472806497515492,
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": 0.4921027719974518,
14
+ "eval_matthews_correlation": 0.4130889956247439,
15
+ "eval_runtime": 0.7437,
16
+ "eval_samples_per_second": 1402.413,
17
+ "eval_steps_per_second": 88.743,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.47313278913497925,
23
+ "eval_matthews_correlation": 0.472806497515492,
24
+ "eval_runtime": 0.7764,
25
+ "eval_samples_per_second": 1343.447,
26
+ "eval_steps_per_second": 85.012,
27
+ "step": 268
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 402,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 2.3070930848457665e-05,
40
+ "num_train_epochs": 3,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 17
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 sha256:36bde66e6449e9c1f7e73eb4952b2d02cf91a055154e256af6d28a1a6c8f7d0c
3
+ size 4792
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": "4.36.2",
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:c3354d90441ef340b351648cbeb0c1e14a51ab8932d3d41f68defa20f99a945e
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 sha256:8073458bb1aafd1fd2cebe487dc9455267493831c494bd3da84de4d76b9d105b
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 sha256:7e94700464065d7210e304995f87e6c38cd10867184f842b51244323518b2bcc
3
+ size 14308
run-4/checkpoint-402/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdb419fbf518150296b1645004333563adb6aaf70cbc153884850dc62f63d2e7
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": 0.4738935490751179,
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": 0.4921027719974518,
14
+ "eval_matthews_correlation": 0.4130889956247439,
15
+ "eval_runtime": 0.7437,
16
+ "eval_samples_per_second": 1402.413,
17
+ "eval_steps_per_second": 88.743,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.47313278913497925,
23
+ "eval_matthews_correlation": 0.472806497515492,
24
+ "eval_runtime": 0.7764,
25
+ "eval_samples_per_second": 1343.447,
26
+ "eval_steps_per_second": 85.012,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.514751672744751,
32
+ "eval_matthews_correlation": 0.4738935490751179,
33
+ "eval_runtime": 0.7708,
34
+ "eval_samples_per_second": 1353.057,
35
+ "eval_steps_per_second": 85.62,
36
+ "step": 402
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 402,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 3,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 64,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 2.3070930848457665e-05,
49
+ "num_train_epochs": 3,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 17
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 sha256:36bde66e6449e9c1f7e73eb4952b2d02cf91a055154e256af6d28a1a6c8f7d0c
3
+ size 4792
run-4/checkpoint-402/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/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-6/checkpoint-1069/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8915dda6d92bf3398fe024e98d750561c54a54989ef0c77890ebd461e6099b69
3
+ size 267832560
run-6/checkpoint-1069/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:704600c97ef21000a64d8007ccec3042f7a3f259aa911627d51ad02478193652
3
+ size 535727290
run-6/checkpoint-1069/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2485b8add507e78fc24054d9539cf6391c5d2a94a4f6671e88414003788f5300
3
+ size 14244
run-6/checkpoint-1069/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c2ca8f117f99978e6a19645929df9bd33b315be54b19b9f2344060d0f94d77c
3
+ size 1064
run-6/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-6/checkpoint-1069/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-6/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-6/checkpoint-1069/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0463559874942472,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-6/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": 1.262825365991774e-06,
14
+ "loss": 0.6149,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.94,
19
+ "learning_rate": 8.773475375449563e-07,
20
+ "loss": 0.5808,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 0.5693468451499939,
26
+ "eval_matthews_correlation": 0.0463559874942472,
27
+ "eval_runtime": 0.7153,
28
+ "eval_samples_per_second": 1458.129,
29
+ "eval_steps_per_second": 92.269,
30
+ "step": 1069
31
+ }
32
+ ],
33
+ "logging_steps": 500,
34
+ "max_steps": 2138,
35
+ "num_input_tokens_seen": 0,
36
+ "num_train_epochs": 2,
37
+ "save_steps": 500,
38
+ "total_flos": 89089500103920.0,
39
+ "train_batch_size": 8,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "learning_rate": 1.6483031944385912e-06,
43
+ "num_train_epochs": 2,
44
+ "per_device_train_batch_size": 8,
45
+ "seed": 30
46
+ }
47
+ }
run-6/checkpoint-1069/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73b7838d90f9933ce298b9953ccb17bc30f24792210f4086fe838cd67602ec0d
3
+ size 4792
run-6/checkpoint-1069/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703299699.04248f4b0c3a.492.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5bfd44698d5d2163c6970dc64821094ef4e1851d286af2d01b7f3fe09f6f60
3
+ size 5711
runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703299800.04248f4b0c3a.492.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e01cf73da524098031deb491f0488aa7431511aaadafa97215eb9bcfa5488cf3
3
+ size 4685
runs/Dec23_02-22-21_04248f4b0c3a/events.out.tfevents.1703299823.04248f4b0c3a.492.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eb46e5a539feb35e636e9cb3c54050758f0ebcdef7bc13aa218b653f65d8ac8
3
+ size 5649
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b91e4836dde5a11432215e79bbc165d4ffa71f41124bd5e3404c89fe5fe37126
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73b7838d90f9933ce298b9953ccb17bc30f24792210f4086fe838cd67602ec0d
3
  size 4792