ArtoriasXV commited on
Commit
b4e7718
·
verified ·
1 Parent(s): 1c2db32

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-0/checkpoint-56/config.json +25 -0
  3. run-0/checkpoint-56/model.safetensors +3 -0
  4. run-0/checkpoint-56/optimizer.pt +3 -0
  5. run-0/checkpoint-56/rng_state.pth +3 -0
  6. run-0/checkpoint-56/scheduler.pt +3 -0
  7. run-0/checkpoint-56/special_tokens_map.json +7 -0
  8. run-0/checkpoint-56/tokenizer.json +0 -0
  9. run-0/checkpoint-56/tokenizer_config.json +55 -0
  10. run-0/checkpoint-56/trainer_state.json +62 -0
  11. run-0/checkpoint-56/training_args.bin +3 -0
  12. run-0/checkpoint-56/vocab.txt +0 -0
  13. run-1/checkpoint-108/config.json +25 -0
  14. run-1/checkpoint-108/model.safetensors +3 -0
  15. run-1/checkpoint-108/optimizer.pt +3 -0
  16. run-1/checkpoint-108/rng_state.pth +3 -0
  17. run-1/checkpoint-108/scheduler.pt +3 -0
  18. run-1/checkpoint-108/special_tokens_map.json +7 -0
  19. run-1/checkpoint-108/tokenizer.json +0 -0
  20. run-1/checkpoint-108/tokenizer_config.json +55 -0
  21. run-1/checkpoint-108/trainer_state.json +44 -0
  22. run-1/checkpoint-108/training_args.bin +3 -0
  23. run-1/checkpoint-108/vocab.txt +0 -0
  24. run-1/checkpoint-162/config.json +25 -0
  25. run-1/checkpoint-162/model.safetensors +3 -0
  26. run-1/checkpoint-162/optimizer.pt +3 -0
  27. run-1/checkpoint-162/rng_state.pth +3 -0
  28. run-1/checkpoint-162/scheduler.pt +3 -0
  29. run-1/checkpoint-162/special_tokens_map.json +7 -0
  30. run-1/checkpoint-162/tokenizer.json +0 -0
  31. run-1/checkpoint-162/tokenizer_config.json +55 -0
  32. run-1/checkpoint-162/trainer_state.json +53 -0
  33. run-1/checkpoint-162/training_args.bin +3 -0
  34. run-1/checkpoint-162/vocab.txt +0 -0
  35. run-1/checkpoint-216/config.json +25 -0
  36. run-1/checkpoint-216/model.safetensors +3 -0
  37. run-1/checkpoint-216/optimizer.pt +3 -0
  38. run-1/checkpoint-216/rng_state.pth +3 -0
  39. run-1/checkpoint-216/scheduler.pt +3 -0
  40. run-1/checkpoint-216/special_tokens_map.json +7 -0
  41. run-1/checkpoint-216/tokenizer.json +0 -0
  42. run-1/checkpoint-216/tokenizer_config.json +55 -0
  43. run-1/checkpoint-216/trainer_state.json +62 -0
  44. run-1/checkpoint-216/training_args.bin +3 -0
  45. run-1/checkpoint-216/vocab.txt +0 -0
  46. run-1/checkpoint-270/config.json +25 -0
  47. run-1/checkpoint-270/model.safetensors +3 -0
  48. run-1/checkpoint-270/optimizer.pt +3 -0
  49. run-1/checkpoint-270/rng_state.pth +3 -0
  50. run-1/checkpoint-270/scheduler.pt +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:545b6a713c6506dd2198745a6eb79045153309a67ec1fcae0279a5765e5c7cae
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca695362ee6b22cb7b6e9f819725f63ad1ec2693e5a34a78ab2c3becc56cc066
3
  size 267832560
run-0/checkpoint-56/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-0/checkpoint-56/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:545b6a713c6506dd2198745a6eb79045153309a67ec1fcae0279a5765e5c7cae
3
+ size 267832560
run-0/checkpoint-56/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5883f555da3bbd7f6c6cda28d277924dc40bb9d86f0bd0ab9f49b496d319b3c
3
+ size 535727290
run-0/checkpoint-56/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65e4492e3f27619401192d125a149b39d48b4ab3e263956db240341bf5323451
3
+ size 14244
run-0/checkpoint-56/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8431f71a0f6cc21b01bc55e5fe3bb87a949608ea0d3a8fce96465049865aa6ce
3
+ size 1064
run-0/checkpoint-56/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-0/checkpoint-56/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/checkpoint-56/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-0/checkpoint-56/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-0/checkpoint-14",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 56,
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": 0.6275959014892578,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.8308,
16
+ "eval_samples_per_second": 1255.449,
17
+ "eval_steps_per_second": 79.444,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6147311925888062,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.6967,
25
+ "eval_samples_per_second": 1497.063,
26
+ "eval_steps_per_second": 94.733,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6137582659721375,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.7586,
34
+ "eval_samples_per_second": 1374.866,
35
+ "eval_steps_per_second": 87.0,
36
+ "step": 42
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.6106928586959839,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 0.6886,
43
+ "eval_samples_per_second": 1514.709,
44
+ "eval_steps_per_second": 95.849,
45
+ "step": 56
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 56,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 4,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 64,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 8.219212725200357e-06,
58
+ "num_train_epochs": 4,
59
+ "per_device_train_batch_size": 64,
60
+ "seed": 15
61
+ }
62
+ }
run-0/checkpoint-56/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52ed7b2111aadd145363f970443f5758354e03e46557384b6001a048998cb254
3
+ size 4984
run-0/checkpoint-56/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-108/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:956221cbe845b519d581db6ff4678b590a6eece35c812bcacb586e429d75076c
3
+ size 267832560
run-1/checkpoint-108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31134d15f7ba350f2f45018c5fca64d94630787f87641a95afe4d976a485f97c
3
+ size 535727290
run-1/checkpoint-108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d2ce677d59bd42c4069fde1f4e20262cfffbc9034e60063a7cb86b37e99e902
3
+ size 14244
run-1/checkpoint-108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c8251d96a636289cdea64fa21b3c0d1a8a9c513771742eddfe37c3f25fea6df
3
+ size 1064
run-1/checkpoint-108/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-108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-108/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-108/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.2555516815486373,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-108",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 108,
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": 0.5905566215515137,
14
+ "eval_matthews_correlation": 0.0928457264044978,
15
+ "eval_runtime": 0.6953,
16
+ "eval_samples_per_second": 1500.167,
17
+ "eval_steps_per_second": 94.929,
18
+ "step": 54
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.7765615582466125,
23
+ "eval_matthews_correlation": 0.2555516815486373,
24
+ "eval_runtime": 1.3105,
25
+ "eval_samples_per_second": 795.885,
26
+ "eval_steps_per_second": 50.363,
27
+ "step": 108
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 270,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 5,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 16,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 8.062343844760649e-05,
40
+ "num_train_epochs": 5,
41
+ "per_device_train_batch_size": 16,
42
+ "seed": 22
43
+ }
44
+ }
run-1/checkpoint-108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2a285bd5d1ba7ccfe930c23cedf60174cf9292ccd17171c6cbf5354a51e2946
3
+ size 4984
run-1/checkpoint-108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-162/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-162/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae09d92dceec3922101ef24e1bc1efd3d7e037b1e9d69e34c44bb374ba01c00f
3
+ size 267832560
run-1/checkpoint-162/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:503db2bcc09b65376c06a7cbd95cd00a1d98de1605db1a78bfe7c3304eb48172
3
+ size 535727290
run-1/checkpoint-162/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05cf25a8aac0197f9dd0fc73950ab5ebf0b0120b5a26a3fbb66223702c12946d
3
+ size 14244
run-1/checkpoint-162/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6a36b6cdaf28c70eb84437a2f24980006c3a05981a9de85b15c595542973b88
3
+ size 1064
run-1/checkpoint-162/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-162/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-162/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-162/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3052591174566493,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-162",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 162,
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": 0.5905566215515137,
14
+ "eval_matthews_correlation": 0.0928457264044978,
15
+ "eval_runtime": 0.6953,
16
+ "eval_samples_per_second": 1500.167,
17
+ "eval_steps_per_second": 94.929,
18
+ "step": 54
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.7765615582466125,
23
+ "eval_matthews_correlation": 0.2555516815486373,
24
+ "eval_runtime": 1.3105,
25
+ "eval_samples_per_second": 795.885,
26
+ "eval_steps_per_second": 50.363,
27
+ "step": 108
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 1.1682683229446411,
32
+ "eval_matthews_correlation": 0.3052591174566493,
33
+ "eval_runtime": 1.411,
34
+ "eval_samples_per_second": 739.172,
35
+ "eval_steps_per_second": 46.774,
36
+ "step": 162
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 270,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 5,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 16,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 8.062343844760649e-05,
49
+ "num_train_epochs": 5,
50
+ "per_device_train_batch_size": 16,
51
+ "seed": 22
52
+ }
53
+ }
run-1/checkpoint-162/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2a285bd5d1ba7ccfe930c23cedf60174cf9292ccd17171c6cbf5354a51e2946
3
+ size 4984
run-1/checkpoint-162/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-216/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-216/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5390e2c4c3d568fc71afe1987e968724b12ebb0ff1fb2952ffdaef05ea1632e9
3
+ size 267832560
run-1/checkpoint-216/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53add8627aa0a30967afd48e973232ce59599a9edf12c32787d8bfef5c09612d
3
+ size 535727290
run-1/checkpoint-216/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b99bd1a1dde66fbd9bfaac8ed2c34fb9bdde5bc7e9c66485be72a23c4b855e0
3
+ size 14244
run-1/checkpoint-216/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a75b5a41ffe790fd9e286de60053f89c56d9ef6562a6877d0348d10932146bdb
3
+ size 1064
run-1/checkpoint-216/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-216/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-216/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-216/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3052591174566493,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-162",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 216,
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": 0.5905566215515137,
14
+ "eval_matthews_correlation": 0.0928457264044978,
15
+ "eval_runtime": 0.6953,
16
+ "eval_samples_per_second": 1500.167,
17
+ "eval_steps_per_second": 94.929,
18
+ "step": 54
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.7765615582466125,
23
+ "eval_matthews_correlation": 0.2555516815486373,
24
+ "eval_runtime": 1.3105,
25
+ "eval_samples_per_second": 795.885,
26
+ "eval_steps_per_second": 50.363,
27
+ "step": 108
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 1.1682683229446411,
32
+ "eval_matthews_correlation": 0.3052591174566493,
33
+ "eval_runtime": 1.411,
34
+ "eval_samples_per_second": 739.172,
35
+ "eval_steps_per_second": 46.774,
36
+ "step": 162
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 1.3417069911956787,
41
+ "eval_matthews_correlation": 0.2801337199061549,
42
+ "eval_runtime": 0.7621,
43
+ "eval_samples_per_second": 1368.598,
44
+ "eval_steps_per_second": 86.604,
45
+ "step": 216
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 270,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 5,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 16,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 8.062343844760649e-05,
58
+ "num_train_epochs": 5,
59
+ "per_device_train_batch_size": 16,
60
+ "seed": 22
61
+ }
62
+ }
run-1/checkpoint-216/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2a285bd5d1ba7ccfe930c23cedf60174cf9292ccd17171c6cbf5354a51e2946
3
+ size 4984
run-1/checkpoint-216/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-270/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-1/checkpoint-270/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc22c8758aab5162b56a8466a09c3e12ae13635fe6c1692baf879ee681245f15
3
+ size 267832560
run-1/checkpoint-270/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14a56d4c35eac2325246795501c7605efe7388c0124debdb51480dee627b8425
3
+ size 535727290
run-1/checkpoint-270/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c19d11d585344ba606d8a3f52d2542cc2301bcb4dd63a6336369906566d51e5c
3
+ size 14244
run-1/checkpoint-270/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d59507f3811c0ebd36f20c9d38253a9e91020beaf273945c8ad380f107bdeaa
3
+ size 1064