VeipsF commited on
Commit
d38cf45
1 Parent(s): 206e96a

Training in progress, epoch 1

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. model.safetensors +1 -1
  2. run-3/checkpoint-107/config.json +25 -0
  3. run-3/checkpoint-107/model.safetensors +3 -0
  4. run-3/checkpoint-107/optimizer.pt +3 -0
  5. run-3/checkpoint-107/rng_state.pth +3 -0
  6. run-3/checkpoint-107/scheduler.pt +3 -0
  7. run-3/checkpoint-107/special_tokens_map.json +7 -0
  8. run-3/checkpoint-107/tokenizer.json +0 -0
  9. run-3/checkpoint-107/tokenizer_config.json +55 -0
  10. run-3/checkpoint-107/trainer_state.json +35 -0
  11. run-3/checkpoint-107/training_args.bin +3 -0
  12. run-3/checkpoint-107/vocab.txt +0 -0
  13. run-3/checkpoint-214/config.json +25 -0
  14. run-3/checkpoint-214/model.safetensors +3 -0
  15. run-3/checkpoint-214/optimizer.pt +3 -0
  16. run-3/checkpoint-214/rng_state.pth +3 -0
  17. run-3/checkpoint-214/scheduler.pt +3 -0
  18. run-3/checkpoint-214/special_tokens_map.json +7 -0
  19. run-3/checkpoint-214/tokenizer.json +0 -0
  20. run-3/checkpoint-214/tokenizer_config.json +55 -0
  21. run-3/checkpoint-214/trainer_state.json +44 -0
  22. run-3/checkpoint-214/training_args.bin +3 -0
  23. run-3/checkpoint-214/vocab.txt +0 -0
  24. run-4/checkpoint-214/config.json +25 -0
  25. run-4/checkpoint-214/model.safetensors +3 -0
  26. run-4/checkpoint-214/optimizer.pt +3 -0
  27. run-4/checkpoint-214/rng_state.pth +3 -0
  28. run-4/checkpoint-214/scheduler.pt +3 -0
  29. run-4/checkpoint-214/special_tokens_map.json +7 -0
  30. run-4/checkpoint-214/tokenizer.json +0 -0
  31. run-4/checkpoint-214/tokenizer_config.json +55 -0
  32. run-4/checkpoint-214/trainer_state.json +35 -0
  33. run-4/checkpoint-214/training_args.bin +3 -0
  34. run-4/checkpoint-214/vocab.txt +0 -0
  35. run-4/checkpoint-428/config.json +25 -0
  36. run-4/checkpoint-428/model.safetensors +3 -0
  37. run-4/checkpoint-428/optimizer.pt +3 -0
  38. run-4/checkpoint-428/rng_state.pth +3 -0
  39. run-4/checkpoint-428/scheduler.pt +3 -0
  40. run-4/checkpoint-428/special_tokens_map.json +7 -0
  41. run-4/checkpoint-428/tokenizer.json +0 -0
  42. run-4/checkpoint-428/tokenizer_config.json +55 -0
  43. run-4/checkpoint-428/trainer_state.json +44 -0
  44. run-4/checkpoint-428/training_args.bin +3 -0
  45. run-4/checkpoint-428/vocab.txt +0 -0
  46. run-5/checkpoint-54/config.json +25 -0
  47. run-5/checkpoint-54/model.safetensors +3 -0
  48. run-5/checkpoint-54/optimizer.pt +3 -0
  49. run-5/checkpoint-54/rng_state.pth +3 -0
  50. run-5/checkpoint-54/scheduler.pt +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b762acdb0832bf34ce17635f8fbe9bc15d4f9c7dab6083a49a6b77b362dee28
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fa0198d1d8cb8b95f8e378ff78e1fe169ae40ea2fa6c2d7da9bf5ef5385aa48
3
  size 267832560
run-3/checkpoint-107/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-3/checkpoint-107/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b762acdb0832bf34ce17635f8fbe9bc15d4f9c7dab6083a49a6b77b362dee28
3
+ size 267832560
run-3/checkpoint-107/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af6904224fd6478dd438074aef35fd0d5fe48e702486648ab47858ab1ca51903
3
+ size 535727290
run-3/checkpoint-107/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dca705bb0efb42a3936aff8c677f0d4fe2183af835290a8dd4f5120e52522df3
3
+ size 14308
run-3/checkpoint-107/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:811ce8661160081734d170d827480590eae7278182aa5bece442b733ef4f6038
3
+ size 1064
run-3/checkpoint-107/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-3/checkpoint-107/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-107/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-3/checkpoint-107/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-107",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 107,
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": 0.5585448145866394,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7404,
16
+ "eval_samples_per_second": 1408.698,
17
+ "eval_steps_per_second": 89.141,
18
+ "step": 107
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 214,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 2,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 8,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 7.014969669852374e-05,
31
+ "num_train_epochs": 2,
32
+ "per_device_train_batch_size": 8,
33
+ "seed": 17
34
+ }
35
+ }
run-3/checkpoint-107/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b5c2c13e96c8ba8b989d0434d4c36aa3f323797ab19f623b3d48953a4303d7
3
+ size 4984
run-3/checkpoint-107/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-214/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-3/checkpoint-214/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:811b286d01ebcaea4bb2ea5e51897802f3e2d7fe788aebea584bef81dc5439df
3
+ size 267832560
run-3/checkpoint-214/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc1b6a7a7fc1ae2a31efa8304ce42002981cbe124932685bd89685982b2e1a2c
3
+ size 535727290
run-3/checkpoint-214/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6694467851aa60239814a037b9815306f53e6e2db4fa1b5d2796d16885547f32
3
+ size 14308
run-3/checkpoint-214/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25015917a4402f7a283eb4afdf82d9601d31e6a0c9d02a52279029e28ccf75ad
3
+ size 1064
run-3/checkpoint-214/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-3/checkpoint-214/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-214/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-3/checkpoint-214/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.29230910937537136,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-214",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 214,
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": 0.5585448145866394,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7404,
16
+ "eval_samples_per_second": 1408.698,
17
+ "eval_steps_per_second": 89.141,
18
+ "step": 107
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.8820879459381104,
23
+ "eval_matthews_correlation": 0.29230910937537136,
24
+ "eval_runtime": 0.7969,
25
+ "eval_samples_per_second": 1308.816,
26
+ "eval_steps_per_second": 82.821,
27
+ "step": 214
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 214,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 8,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 7.014969669852374e-05,
40
+ "num_train_epochs": 2,
41
+ "per_device_train_batch_size": 8,
42
+ "seed": 17
43
+ }
44
+ }
run-3/checkpoint-214/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b5c2c13e96c8ba8b989d0434d4c36aa3f323797ab19f623b3d48953a4303d7
3
+ size 4984
run-3/checkpoint-214/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-214/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-214/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a94bd5f6760ca1517812ddbf907ea7e739fc44bfdcd126cc489c42e3781f6b61
3
+ size 267832560
run-4/checkpoint-214/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e238192c9a51f983a0b56182db252192c8cd29df9031ecc85beac23d7e1d717
3
+ size 535727290
run-4/checkpoint-214/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52ee81ef94ef0da90cebede3c25a13206fe50ed5fecf1ece78d7b57f26f80c9e
3
+ size 14244
run-4/checkpoint-214/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46fe0632b69814242aa8a0da472797fafd4064dcba7f2e8c5ae28f185214226d
3
+ size 1064
run-4/checkpoint-214/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-214/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-214/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-214/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-214",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 214,
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": 0.6662102341651917,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7618,
16
+ "eval_samples_per_second": 1369.104,
17
+ "eval_steps_per_second": 86.636,
18
+ "step": 214
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 428,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 2,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 4,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 1.5553250937719495e-05,
31
+ "num_train_epochs": 2,
32
+ "per_device_train_batch_size": 4,
33
+ "seed": 23
34
+ }
35
+ }
run-4/checkpoint-214/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6915e56e0701694be660f8f5c87ccaa9a6d3ffa889bd7bf0a6bea6f8f7dced02
3
+ size 4984
run-4/checkpoint-214/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-428/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-428/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:571e8d5907b56773c6de9a4a5b9e0bf9d31db6e6fa710784b3ac57e28477bbec
3
+ size 267832560
run-4/checkpoint-428/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e7bead3e035ba502d6c857cfda3098b7f98b8369020c1e8a16ab89c8260931d
3
+ size 535727290
run-4/checkpoint-428/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbc01c9b8decaf847b109439d81f8e5f5f4066578b72138082925f7895910683
3
+ size 14244
run-4/checkpoint-428/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:577c707a0b82cb688fcd086126a918755c1d046f457c1b91d883141f372548a2
3
+ size 1064
run-4/checkpoint-428/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-428/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-428/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-428/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.227078643624653,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-428",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 428,
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": 0.6662102341651917,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7618,
16
+ "eval_samples_per_second": 1369.104,
17
+ "eval_steps_per_second": 86.636,
18
+ "step": 214
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6536537408828735,
23
+ "eval_matthews_correlation": 0.227078643624653,
24
+ "eval_runtime": 1.2359,
25
+ "eval_samples_per_second": 843.936,
26
+ "eval_steps_per_second": 53.403,
27
+ "step": 428
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 428,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 2,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 4,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 1.5553250937719495e-05,
40
+ "num_train_epochs": 2,
41
+ "per_device_train_batch_size": 4,
42
+ "seed": 23
43
+ }
44
+ }
run-4/checkpoint-428/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6915e56e0701694be660f8f5c87ccaa9a6d3ffa889bd7bf0a6bea6f8f7dced02
3
+ size 4984
run-4/checkpoint-428/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-54/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-5/checkpoint-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fa0198d1d8cb8b95f8e378ff78e1fe169ae40ea2fa6c2d7da9bf5ef5385aa48
3
+ size 267832560
run-5/checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf75816ea22037d1688abd615c88b38dd9378ed786240eee52812fdebc101b1
3
+ size 535727290
run-5/checkpoint-54/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:369d7b80e9e7cb856d382ef6a50ec190c9ca9a8950f95fb694f8f1fdbb7c9fee
3
+ size 14244
run-5/checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:878f6f0925f866e2179648e9d5f9abc87cadf506c4d37ac0bb8448f0660826f1
3
+ size 1064