Hugging Face's logo

chtsai2104
/
llmhw01

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
chtsai2104 commited on
Commit
4e04749
·
1 Parent(s): 6601d96

Training in progress, epoch 1

Browse files
Files changed (48) hide show
  1. model.safetensors +1 -1
  2. run-1/checkpoint-1070/config.json +25 -0
  3. run-1/checkpoint-1070/model.safetensors +3 -0
  4. run-1/checkpoint-1070/optimizer.pt +3 -0
  5. run-1/checkpoint-1070/rng_state.pth +3 -0
  6. run-1/checkpoint-1070/scheduler.pt +3 -0
  7. run-1/checkpoint-1070/special_tokens_map.json +7 -0
  8. run-1/checkpoint-1070/tokenizer.json +0 -0
  9. run-1/checkpoint-1070/tokenizer_config.json +55 -0
  10. run-1/checkpoint-1070/trainer_state.json +56 -0
  11. run-1/checkpoint-1070/training_args.bin +3 -0
  12. run-1/checkpoint-1070/vocab.txt +0 -0
  13. run-1/checkpoint-1605/config.json +25 -0
  14. run-1/checkpoint-1605/model.safetensors +3 -0
  15. run-1/checkpoint-1605/optimizer.pt +3 -0
  16. run-1/checkpoint-1605/rng_state.pth +3 -0
  17. run-1/checkpoint-1605/scheduler.pt +3 -0
  18. run-1/checkpoint-1605/special_tokens_map.json +7 -0
  19. run-1/checkpoint-1605/tokenizer.json +0 -0
  20. run-1/checkpoint-1605/tokenizer_config.json +55 -0
  21. run-1/checkpoint-1605/trainer_state.json +71 -0
  22. run-1/checkpoint-1605/training_args.bin +3 -0
  23. run-1/checkpoint-1605/vocab.txt +0 -0
  24. run-1/checkpoint-2140/config.json +25 -0
  25. run-1/checkpoint-2140/model.safetensors +3 -0
  26. run-1/checkpoint-2140/optimizer.pt +3 -0
  27. run-1/checkpoint-2140/rng_state.pth +3 -0
  28. run-1/checkpoint-2140/scheduler.pt +3 -0
  29. run-1/checkpoint-2140/special_tokens_map.json +7 -0
  30. run-1/checkpoint-2140/tokenizer.json +0 -0
  31. run-1/checkpoint-2140/tokenizer_config.json +55 -0
  32. run-1/checkpoint-2140/trainer_state.json +86 -0
  33. run-1/checkpoint-2140/training_args.bin +3 -0
  34. run-1/checkpoint-2140/vocab.txt +0 -0
  35. run-2/checkpoint-134/config.json +25 -0
  36. run-2/checkpoint-134/model.safetensors +3 -0
  37. run-2/checkpoint-134/optimizer.pt +3 -0
  38. run-2/checkpoint-134/rng_state.pth +3 -0
  39. run-2/checkpoint-134/scheduler.pt +3 -0
  40. run-2/checkpoint-134/special_tokens_map.json +7 -0
  41. run-2/checkpoint-134/tokenizer.json +0 -0
  42. run-2/checkpoint-134/tokenizer_config.json +55 -0
  43. run-2/checkpoint-134/trainer_state.json +35 -0
  44. run-2/checkpoint-134/training_args.bin +3 -0
  45. run-2/checkpoint-134/vocab.txt +0 -0
  46. runs/Dec23_02-12-15_e683d65323e5/events.out.tfevents.1703298029.e683d65323e5.236.3 +2 -2
  47. runs/Dec23_02-12-15_e683d65323e5/events.out.tfevents.1703298175.e683d65323e5.236.4 +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 sha256:415625783743e920c820b8cdcdc0468095fe7c15af0e6b50a45354d7d0972b7b
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1efa5249c09de3318da8a60a90f547c5ca4582a0c7d27e0d264ac047de3dbc91
3
  size 267832560
run-1/checkpoint-1070/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-1070/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ef64a3551c02c8fd1ee3a4fcd85f751a2a1354b4313b77c99929165c1aede75
3
+ size 267832560
run-1/checkpoint-1070/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dabea70866d550b53c6538bcaf7d267e1b40f1aa2dd3b5af2aa7411d4c1ba75
3
+ size 535727290
run-1/checkpoint-1070/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:090bc05676d452dc8567b51156bbbe934e1cc2b82eb2e62c3ebbf0479fc862a1
3
+ size 14244
run-1/checkpoint-1070/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9462c69125251a4a52ba89f96e4cc009aa250339eb4603c8d7d8c6e0a3742e28
3
+ size 1064
run-1/checkpoint-1070/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-1/checkpoint-1070/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1070/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-1/checkpoint-1070/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5040599209761474,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1070",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1070,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "learning_rate": 3.9225534251659633e-05,
14
+ "loss": 0.5417,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.49440810084342957,
20
+ "eval_matthews_correlation": 0.4269251310554325,
21
+ "eval_runtime": 0.754,
22
+ "eval_samples_per_second": 1383.379,
23
+ "eval_steps_per_second": 87.539,
24
+ "step": 535
25
+ },
26
+ {
27
+ "epoch": 1.87,
28
+ "learning_rate": 2.7266529906641447e-05,
29
+ "loss": 0.339,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_loss": 0.5495947003364563,
35
+ "eval_matthews_correlation": 0.5040599209761474,
36
+ "eval_runtime": 0.8175,
37
+ "eval_samples_per_second": 1275.811,
38
+ "eval_steps_per_second": 80.732,
39
+ "step": 1070
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 2140,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 4,
46
+ "save_steps": 500,
47
+ "total_flos": 85332548744772.0,
48
+ "train_batch_size": 16,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 5.118453859667781e-05,
52
+ "num_train_epochs": 4,
53
+ "per_device_train_batch_size": 16,
54
+ "seed": 5
55
+ }
56
+ }
run-1/checkpoint-1070/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8fc4986476e31f56c4c4f17f60b246ee9e2627392135b005bccdd6794390e92
3
+ size 4792
run-1/checkpoint-1070/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1605/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-1605/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b683931ea336363acbd3dc246b39770a2db503c0bcfc43446d997a3bd1be40ea
3
+ size 267832560
run-1/checkpoint-1605/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10f0f37c15fa81b2ecee5816b95577f64bd0cba3e77df068054ed34e04914e7f
3
+ size 535727290
run-1/checkpoint-1605/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fccee8f6e8f02f990cea2d4ceafa31cc8ec85a8e208d060f905adba2e3c9b85
3
+ size 14244
run-1/checkpoint-1605/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fef24bc8b9a07e18422cf6b0e26c991f0bd448de7d95aa24b42efb12e0447fbf
3
+ size 1064
run-1/checkpoint-1605/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-1/checkpoint-1605/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-1605/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-1/checkpoint-1605/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5040599209761474,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1070",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1605,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "learning_rate": 3.9225534251659633e-05,
14
+ "loss": 0.5417,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.49440810084342957,
20
+ "eval_matthews_correlation": 0.4269251310554325,
21
+ "eval_runtime": 0.754,
22
+ "eval_samples_per_second": 1383.379,
23
+ "eval_steps_per_second": 87.539,
24
+ "step": 535
25
+ },
26
+ {
27
+ "epoch": 1.87,
28
+ "learning_rate": 2.7266529906641447e-05,
29
+ "loss": 0.339,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_loss": 0.5495947003364563,
35
+ "eval_matthews_correlation": 0.5040599209761474,
36
+ "eval_runtime": 0.8175,
37
+ "eval_samples_per_second": 1275.811,
38
+ "eval_steps_per_second": 80.732,
39
+ "step": 1070
40
+ },
41
+ {
42
+ "epoch": 2.8,
43
+ "learning_rate": 1.5307525561623268e-05,
44
+ "loss": 0.2022,
45
+ "step": 1500
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_loss": 0.7561798095703125,
50
+ "eval_matthews_correlation": 0.4855357738917488,
51
+ "eval_runtime": 0.7911,
52
+ "eval_samples_per_second": 1318.416,
53
+ "eval_steps_per_second": 83.428,
54
+ "step": 1605
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 2140,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 4,
61
+ "save_steps": 500,
62
+ "total_flos": 128317702157868.0,
63
+ "train_batch_size": 16,
64
+ "trial_name": null,
65
+ "trial_params": {
66
+ "learning_rate": 5.118453859667781e-05,
67
+ "num_train_epochs": 4,
68
+ "per_device_train_batch_size": 16,
69
+ "seed": 5
70
+ }
71
+ }
run-1/checkpoint-1605/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8fc4986476e31f56c4c4f17f60b246ee9e2627392135b005bccdd6794390e92
3
+ size 4792
run-1/checkpoint-1605/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-2140/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-2140/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71da945589ae8439007fac375ff722114836dd72e5224c715078384433823607
3
+ size 267832560
run-1/checkpoint-2140/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6284000b6d45bdbebae02e7fd1433a54964e942ec053b45511d0ea48e33e6e27
3
+ size 535727290
run-1/checkpoint-2140/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77f86e538f61359ca64b470ac70153dbcd28262ad9c8fff94239d29212c1ee6f
3
+ size 14244
run-1/checkpoint-2140/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e305c627a6a9590ce763f17e16f361a725f822ad97bff6d32c79ce83bf11a0f
3
+ size 1064
run-1/checkpoint-2140/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-1/checkpoint-2140/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-2140/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-1/checkpoint-2140/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5040599209761474,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1070",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2140,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.93,
13
+ "learning_rate": 3.9225534251659633e-05,
14
+ "loss": 0.5417,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.49440810084342957,
20
+ "eval_matthews_correlation": 0.4269251310554325,
21
+ "eval_runtime": 0.754,
22
+ "eval_samples_per_second": 1383.379,
23
+ "eval_steps_per_second": 87.539,
24
+ "step": 535
25
+ },
26
+ {
27
+ "epoch": 1.87,
28
+ "learning_rate": 2.7266529906641447e-05,
29
+ "loss": 0.339,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_loss": 0.5495947003364563,
35
+ "eval_matthews_correlation": 0.5040599209761474,
36
+ "eval_runtime": 0.8175,
37
+ "eval_samples_per_second": 1275.811,
38
+ "eval_steps_per_second": 80.732,
39
+ "step": 1070
40
+ },
41
+ {
42
+ "epoch": 2.8,
43
+ "learning_rate": 1.5307525561623268e-05,
44
+ "loss": 0.2022,
45
+ "step": 1500
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_loss": 0.7561798095703125,
50
+ "eval_matthews_correlation": 0.4855357738917488,
51
+ "eval_runtime": 0.7911,
52
+ "eval_samples_per_second": 1318.416,
53
+ "eval_steps_per_second": 83.428,
54
+ "step": 1605
55
+ },
56
+ {
57
+ "epoch": 3.74,
58
+ "learning_rate": 3.3485212166050904e-06,
59
+ "loss": 0.1348,
60
+ "step": 2000
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_loss": 0.9071329832077026,
65
+ "eval_matthews_correlation": 0.4815411884536147,
66
+ "eval_runtime": 0.7894,
67
+ "eval_samples_per_second": 1321.237,
68
+ "eval_steps_per_second": 83.607,
69
+ "step": 2140
70
+ }
71
+ ],
72
+ "logging_steps": 500,
73
+ "max_steps": 2140,
74
+ "num_input_tokens_seen": 0,
75
+ "num_train_epochs": 4,
76
+ "save_steps": 500,
77
+ "total_flos": 171343734182268.0,
78
+ "train_batch_size": 16,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "learning_rate": 5.118453859667781e-05,
82
+ "num_train_epochs": 4,
83
+ "per_device_train_batch_size": 16,
84
+ "seed": 5
85
+ }
86
+ }
run-1/checkpoint-2140/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8fc4986476e31f56c4c4f17f60b246ee9e2627392135b005bccdd6794390e92
3
+ size 4792
run-1/checkpoint-2140/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-134/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1efa5249c09de3318da8a60a90f547c5ca4582a0c7d27e0d264ac047de3dbc91
3
+ size 267832560
run-2/checkpoint-134/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ae2af01646fc96ba78625e118624e7e153dbfa171b9eda61d01d7862aced4f3
3
+ size 535727290
run-2/checkpoint-134/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d541a2d8175d2c782e56e40a78b96145ebea1680c52e64a135d7bea6dcc603c2
3
+ size 14244
run-2/checkpoint-134/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fb0dcb05d626d90075925f079248e7c6909fe257c6de581f395cd16358c7f29
3
+ size 1064
run-2/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-2/checkpoint-134/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-134/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.35716279157209735,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/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": 0.5236373543739319,
14
+ "eval_matthews_correlation": 0.35716279157209735,
15
+ "eval_runtime": 0.8011,
16
+ "eval_samples_per_second": 1301.97,
17
+ "eval_steps_per_second": 82.387,
18
+ "step": 134
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 134,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 1,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 64,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 2.212457653938768e-05,
31
+ "num_train_epochs": 1,
32
+ "per_device_train_batch_size": 64,
33
+ "seed": 9
34
+ }
35
+ }
run-2/checkpoint-134/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e12a9e203ab30850475d9d0a21702718391cd4c7d7bdf472950a5780b01e0835
3
+ size 4792
run-2/checkpoint-134/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-12-15_e683d65323e5/events.out.tfevents.1703298029.e683d65323e5.236.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54110b82fae09dc88d88281d4a5aa6087597abf165523c3d21a197b82ab57a29
3
- size 4838
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da290f145514e087a8b53688c53883479e52366f199b927ca15a214bc29b0705
3
+ size 6668
runs/Dec23_02-12-15_e683d65323e5/events.out.tfevents.1703298175.e683d65323e5.236.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9e4c71d3a1b21af97f887ba1ea0d6f898f334d92b37ed63ba7e40d472d80f73
3
+ size 5035
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8fc4986476e31f56c4c4f17f60b246ee9e2627392135b005bccdd6794390e92
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e12a9e203ab30850475d9d0a21702718391cd4c7d7bdf472950a5780b01e0835
3
  size 4792