kbberendsen commited on
Commit
d4f7847
·
verified ·
1 Parent(s): d05ba30

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-107/config.json +25 -0
  3. run-0/checkpoint-107/model.safetensors +3 -0
  4. run-0/checkpoint-107/optimizer.pt +3 -0
  5. run-0/checkpoint-107/rng_state.pth +3 -0
  6. run-0/checkpoint-107/scheduler.pt +3 -0
  7. run-0/checkpoint-107/special_tokens_map.json +7 -0
  8. run-0/checkpoint-107/tokenizer.json +0 -0
  9. run-0/checkpoint-107/tokenizer_config.json +55 -0
  10. run-0/checkpoint-107/trainer_state.json +35 -0
  11. run-0/checkpoint-107/training_args.bin +3 -0
  12. run-0/checkpoint-107/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 sha256:5e1c3da3a591a75b5098686af3e33bb6d5dbde8de64f9a250c5785b8b676e0e1
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f355ff596fc9a81f9d48fca17727279c1b8e426ea17d864e94ad0fad9e40bae7
3
  size 267832560
run-0/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-0/checkpoint-107/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ed21a9b7cf2a1849ecfe79885181e7767655ddeaa05e6abe4341e9b056dba8
3
+ size 267832560
run-0/checkpoint-107/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b99e5b177f8e929c01316f911337489bd6f6c6aad00cd7e839311e305f3b84c
3
+ size 535727290
run-0/checkpoint-107/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae60ce2da9ba95e755793c0257c4f16dc182d10c2ea798817ac92d796dbfa806
3
+ size 14308
run-0/checkpoint-107/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88927de3756c5716c3890de82ceb0288144c073606e412421fbf9e21f57cf796
3
+ size 1064
run-0/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-0/checkpoint-107/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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-0/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-0/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": 0.6291466355323792,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.955,
16
+ "eval_samples_per_second": 1092.188,
17
+ "eval_steps_per_second": 69.113,
18
+ "step": 107
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 107,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 1,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 8,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 3.448385897205627e-06,
31
+ "num_train_epochs": 1,
32
+ "per_device_train_batch_size": 8,
33
+ "seed": 31
34
+ }
35
+ }
run-0/checkpoint-107/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81bd41e7d6266d202b2106105d36818a4d95755e2e776c9fbfaffaf77da124ad
3
+ size 4984
run-0/checkpoint-107/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": "4.38.1",
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:bb6055d3fc8ec4f98259c860039d249358d0ce55d76a356257f96bc1f7419990
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 sha256:83fc4756e451ebc73cdfca26dc21b7c04e2f6d87846151f52ce08b4ea15d191f
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:d8dd6c246cf2378133e9a0612f058a3b88aefcccc84f7bae72b9c5e5ee21483e
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": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-54",
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": 0.6076961159706116,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.914,
16
+ "eval_samples_per_second": 1141.177,
17
+ "eval_steps_per_second": 72.213,
18
+ "step": 54
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5892916321754456,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 1.1202,
25
+ "eval_samples_per_second": 931.043,
26
+ "eval_steps_per_second": 58.915,
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": 9.09529636397016e-06,
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 sha256:29713d6be431df230f39d5c57e20e237737020640e0fc942f5f07ce3fac1960b
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": "4.38.1",
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:ce98dbf4dd6997fdb248433d847e33f25ae599bd82067d2d53c2065e98c1cb21
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:af6dff06fc37e7e8d0552936e2595c3ac98abbb71738dfa3ca573170028633b2
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:c76a75841f906b92463c679ecefeed0663aafcde16398dffc514b15b668b1927
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": 0.166651669293941,
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": 0.6076961159706116,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.914,
16
+ "eval_samples_per_second": 1141.177,
17
+ "eval_steps_per_second": 72.213,
18
+ "step": 54
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5892916321754456,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 1.1202,
25
+ "eval_samples_per_second": 931.043,
26
+ "eval_steps_per_second": 58.915,
27
+ "step": 108
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5696114301681519,
32
+ "eval_matthews_correlation": 0.166651669293941,
33
+ "eval_runtime": 1.0426,
34
+ "eval_samples_per_second": 1000.412,
35
+ "eval_steps_per_second": 63.305,
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": 9.09529636397016e-06,
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 sha256:29713d6be431df230f39d5c57e20e237737020640e0fc942f5f07ce3fac1960b
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": "4.38.1",
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 sha256:98cea7607ccfa88208fcbd7b91cc2f37bcb8d1fc3032b0c4260a80c1dc4703c4
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 sha256:3ed9f56e9b1873a6285bdbef325a16dc325ac5ebe9506ef78a037544fd833728
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:b499f5dc423f5a42a59b3da27c9751587620e9743426630b9cf152fd59292d3f
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": 0.2526248957927519,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-216",
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": 0.6076961159706116,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.914,
16
+ "eval_samples_per_second": 1141.177,
17
+ "eval_steps_per_second": 72.213,
18
+ "step": 54
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5892916321754456,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 1.1202,
25
+ "eval_samples_per_second": 931.043,
26
+ "eval_steps_per_second": 58.915,
27
+ "step": 108
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5696114301681519,
32
+ "eval_matthews_correlation": 0.166651669293941,
33
+ "eval_runtime": 1.0426,
34
+ "eval_samples_per_second": 1000.412,
35
+ "eval_steps_per_second": 63.305,
36
+ "step": 162
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.560063898563385,
41
+ "eval_matthews_correlation": 0.2526248957927519,
42
+ "eval_runtime": 1.4859,
43
+ "eval_samples_per_second": 701.918,
44
+ "eval_steps_per_second": 44.417,
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": 9.09529636397016e-06,
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 sha256:29713d6be431df230f39d5c57e20e237737020640e0fc942f5f07ce3fac1960b
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": "4.38.1",
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 sha256:643ee05081060a7035cff7c67706cd1d4d9e8e96bb138364f28d5af1ee3262bd
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:cc6c9fa382d301bc30025d4feb4bd1ee745bda42dc36d2321ef304e8c47c2aed
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 sha256:3a383de2f751c3be5860ae338eda4849f1505fae0a579c80bb4182ca31d3ecb5
3
+ size 1064