foolstar41 commited on
Commit
e89b10c
·
1 Parent(s): 4d5e0a7

Training in progress, epoch 1

Browse files
Files changed (48) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-1070/config.json +25 -0
  3. run-2/checkpoint-1070/model.safetensors +3 -0
  4. run-2/checkpoint-1070/optimizer.pt +3 -0
  5. run-2/checkpoint-1070/rng_state.pth +3 -0
  6. run-2/checkpoint-1070/scheduler.pt +3 -0
  7. run-2/checkpoint-1070/special_tokens_map.json +7 -0
  8. run-2/checkpoint-1070/tokenizer.json +0 -0
  9. run-2/checkpoint-1070/tokenizer_config.json +55 -0
  10. run-2/checkpoint-1070/trainer_state.json +56 -0
  11. run-2/checkpoint-1070/training_args.bin +3 -0
  12. run-2/checkpoint-1070/vocab.txt +0 -0
  13. run-2/checkpoint-1605/config.json +25 -0
  14. run-2/checkpoint-1605/model.safetensors +3 -0
  15. run-2/checkpoint-1605/optimizer.pt +3 -0
  16. run-2/checkpoint-1605/rng_state.pth +3 -0
  17. run-2/checkpoint-1605/scheduler.pt +3 -0
  18. run-2/checkpoint-1605/special_tokens_map.json +7 -0
  19. run-2/checkpoint-1605/tokenizer.json +0 -0
  20. run-2/checkpoint-1605/tokenizer_config.json +55 -0
  21. run-2/checkpoint-1605/trainer_state.json +71 -0
  22. run-2/checkpoint-1605/training_args.bin +3 -0
  23. run-2/checkpoint-1605/vocab.txt +0 -0
  24. run-2/checkpoint-2140/config.json +25 -0
  25. run-2/checkpoint-2140/model.safetensors +3 -0
  26. run-2/checkpoint-2140/optimizer.pt +3 -0
  27. run-2/checkpoint-2140/rng_state.pth +3 -0
  28. run-2/checkpoint-2140/scheduler.pt +3 -0
  29. run-2/checkpoint-2140/special_tokens_map.json +7 -0
  30. run-2/checkpoint-2140/tokenizer.json +0 -0
  31. run-2/checkpoint-2140/tokenizer_config.json +55 -0
  32. run-2/checkpoint-2140/trainer_state.json +86 -0
  33. run-2/checkpoint-2140/training_args.bin +3 -0
  34. run-2/checkpoint-2140/vocab.txt +0 -0
  35. run-3/checkpoint-1069/config.json +25 -0
  36. run-3/checkpoint-1069/model.safetensors +3 -0
  37. run-3/checkpoint-1069/optimizer.pt +3 -0
  38. run-3/checkpoint-1069/rng_state.pth +3 -0
  39. run-3/checkpoint-1069/scheduler.pt +3 -0
  40. run-3/checkpoint-1069/special_tokens_map.json +7 -0
  41. run-3/checkpoint-1069/tokenizer.json +0 -0
  42. run-3/checkpoint-1069/tokenizer_config.json +55 -0
  43. run-3/checkpoint-1069/trainer_state.json +47 -0
  44. run-3/checkpoint-1069/training_args.bin +3 -0
  45. run-3/checkpoint-1069/vocab.txt +0 -0
  46. runs/Dec23_02-07-52_773b0b4b06bc/events.out.tfevents.1703298258.773b0b4b06bc.493.4 +2 -2
  47. runs/Dec23_02-07-52_773b0b4b06bc/events.out.tfevents.1703298415.773b0b4b06bc.493.5 +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 sha256:9c605558fb4679495f2033d1404356d51f142cd8af744ebcf9c7977a6ae09bc8
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:604dafc6720048b897c01028f12fdf776cd8c0621457c3ffc5d896a215031869
3
  size 267832560
run-2/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-2/checkpoint-1070/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55b4bb7446a810b7da0ff0e709a8f32e09b29bfa9d3dc94c88cfac5e5f8b89d8
3
+ size 267832560
run-2/checkpoint-1070/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a573ac367686ea275c17b957e2f3095f8171656ec99f35dbd54940c4d69e50a
3
+ size 535727290
run-2/checkpoint-1070/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1cdefaa1e2bd723286fc009dcf16a060253d8179c850b70782edba370ef01e2
3
+ size 14244
run-2/checkpoint-1070/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ad391175ed1411901ccde74f636d5258df810e6dd7a3ec05e38fc2d08b2addb
3
+ size 1064
run-2/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-2/checkpoint-1070/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-1070/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4584020596329,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/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": 3.854935106207992e-05,
14
+ "loss": 0.529,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.4637433886528015,
20
+ "eval_matthews_correlation": 0.42825981555844306,
21
+ "eval_runtime": 0.7351,
22
+ "eval_samples_per_second": 1418.842,
23
+ "eval_steps_per_second": 89.783,
24
+ "step": 535
25
+ },
26
+ {
27
+ "epoch": 1.87,
28
+ "learning_rate": 2.6796500128518964e-05,
29
+ "loss": 0.327,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_loss": 0.5142660737037659,
35
+ "eval_matthews_correlation": 0.4584020596329,
36
+ "eval_runtime": 0.7637,
37
+ "eval_samples_per_second": 1365.788,
38
+ "eval_steps_per_second": 86.426,
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": 85088053253112.0,
48
+ "train_batch_size": 16,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 5.030220199564087e-05,
52
+ "num_train_epochs": 4,
53
+ "per_device_train_batch_size": 16,
54
+ "seed": 27
55
+ }
56
+ }
run-2/checkpoint-1070/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaf5433238535e3a9051fa91efd995dc6d4ed3adae963af5d669ca9f9d094baa
3
+ size 4792
run-2/checkpoint-1070/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-1605/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:476195028d3b2da2e4d6d15c798bde9964aa9b1b5bcfff8fec3b1c1f86ef2607
3
+ size 267832560
run-2/checkpoint-1605/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:609030efa853633e0b3885e896c8c818e11ce204ae26bdc762f0d97e40a5d6f4
3
+ size 535727290
run-2/checkpoint-1605/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcab5315ffdddce50b8e2944aa184bbf66f00c8352ed1fbbc651362b9832d3fc
3
+ size 14244
run-2/checkpoint-1605/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef473577c87aedfdadfe1cef43f21a6d0b05ab0f4272b2d550ca3cccfbb522f6
3
+ size 1064
run-2/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-2/checkpoint-1605/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-1605/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.507910414966408,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-1605",
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": 3.854935106207992e-05,
14
+ "loss": 0.529,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.4637433886528015,
20
+ "eval_matthews_correlation": 0.42825981555844306,
21
+ "eval_runtime": 0.7351,
22
+ "eval_samples_per_second": 1418.842,
23
+ "eval_steps_per_second": 89.783,
24
+ "step": 535
25
+ },
26
+ {
27
+ "epoch": 1.87,
28
+ "learning_rate": 2.6796500128518964e-05,
29
+ "loss": 0.327,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_loss": 0.5142660737037659,
35
+ "eval_matthews_correlation": 0.4584020596329,
36
+ "eval_runtime": 0.7637,
37
+ "eval_samples_per_second": 1365.788,
38
+ "eval_steps_per_second": 86.426,
39
+ "step": 1070
40
+ },
41
+ {
42
+ "epoch": 2.8,
43
+ "learning_rate": 1.5043649194958016e-05,
44
+ "loss": 0.1912,
45
+ "step": 1500
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_loss": 0.7642378807067871,
50
+ "eval_matthews_correlation": 0.507910414966408,
51
+ "eval_runtime": 0.7199,
52
+ "eval_samples_per_second": 1448.91,
53
+ "eval_steps_per_second": 91.686,
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": 127289010015180.0,
63
+ "train_batch_size": 16,
64
+ "trial_name": null,
65
+ "trial_params": {
66
+ "learning_rate": 5.030220199564087e-05,
67
+ "num_train_epochs": 4,
68
+ "per_device_train_batch_size": 16,
69
+ "seed": 27
70
+ }
71
+ }
run-2/checkpoint-1605/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaf5433238535e3a9051fa91efd995dc6d4ed3adae963af5d669ca9f9d094baa
3
+ size 4792
run-2/checkpoint-1605/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-2140/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a391606c00f60d6af6f30363a22dc346fa6c18c1ebc7a5f34d12945ecdd319b5
3
+ size 267832560
run-2/checkpoint-2140/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd63fd3a7c9fb05e0d09ad7c496fd41be1e4624156b7e5ca906d5e89ef020021
3
+ size 535727290
run-2/checkpoint-2140/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c814120057184dafddb86724d94ca5be1cf82057428330436240a4693f258c80
3
+ size 14244
run-2/checkpoint-2140/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:399e917a21f1a0301575a3298d7be21cd8d3f82babc36553ebae421fd3db8e47
3
+ size 1064
run-2/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-2/checkpoint-2140/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-2140/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.507910414966408,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-1605",
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": 3.854935106207992e-05,
14
+ "loss": 0.529,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_loss": 0.4637433886528015,
20
+ "eval_matthews_correlation": 0.42825981555844306,
21
+ "eval_runtime": 0.7351,
22
+ "eval_samples_per_second": 1418.842,
23
+ "eval_steps_per_second": 89.783,
24
+ "step": 535
25
+ },
26
+ {
27
+ "epoch": 1.87,
28
+ "learning_rate": 2.6796500128518964e-05,
29
+ "loss": 0.327,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 2.0,
34
+ "eval_loss": 0.5142660737037659,
35
+ "eval_matthews_correlation": 0.4584020596329,
36
+ "eval_runtime": 0.7637,
37
+ "eval_samples_per_second": 1365.788,
38
+ "eval_steps_per_second": 86.426,
39
+ "step": 1070
40
+ },
41
+ {
42
+ "epoch": 2.8,
43
+ "learning_rate": 1.5043649194958016e-05,
44
+ "loss": 0.1912,
45
+ "step": 1500
46
+ },
47
+ {
48
+ "epoch": 3.0,
49
+ "eval_loss": 0.7642378807067871,
50
+ "eval_matthews_correlation": 0.507910414966408,
51
+ "eval_runtime": 0.7199,
52
+ "eval_samples_per_second": 1448.91,
53
+ "eval_steps_per_second": 91.686,
54
+ "step": 1605
55
+ },
56
+ {
57
+ "epoch": 3.74,
58
+ "learning_rate": 3.290798261397066e-06,
59
+ "loss": 0.1201,
60
+ "step": 2000
61
+ },
62
+ {
63
+ "epoch": 4.0,
64
+ "eval_loss": 0.9557287096977234,
65
+ "eval_matthews_correlation": 0.49787102363508634,
66
+ "eval_runtime": 1.0346,
67
+ "eval_samples_per_second": 1008.128,
68
+ "eval_steps_per_second": 63.793,
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": 170405595925380.0,
78
+ "train_batch_size": 16,
79
+ "trial_name": null,
80
+ "trial_params": {
81
+ "learning_rate": 5.030220199564087e-05,
82
+ "num_train_epochs": 4,
83
+ "per_device_train_batch_size": 16,
84
+ "seed": 27
85
+ }
86
+ }
run-2/checkpoint-2140/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaf5433238535e3a9051fa91efd995dc6d4ed3adae963af5d669ca9f9d094baa
3
+ size 4792
run-2/checkpoint-2140/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-1069/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.36.2",
24
+ "vocab_size": 30522
25
+ }
run-3/checkpoint-1069/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:604dafc6720048b897c01028f12fdf776cd8c0621457c3ffc5d896a215031869
3
+ size 267832560
run-3/checkpoint-1069/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01a6468bc8ebd0404709628469436e2049e184b6f3586ee3289e0387a6a73496
3
+ size 535727290
run-3/checkpoint-1069/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfdfabb6c5fe1c92db76035f9980a0c2272c0b5ef1bdd093af8ac52086434f02
3
+ size 14244
run-3/checkpoint-1069/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83b2afb6c14a6a18e0702b97d37b2f587736fddb8f22e80e86a43bbb5b160102
3
+ size 1064
run-3/checkpoint-1069/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-3/checkpoint-1069/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-1069/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-3/checkpoint-1069/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4153896652547264,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-1069",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1069,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.47,
13
+ "learning_rate": 2.0073962409744884e-05,
14
+ "loss": 0.5491,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.94,
19
+ "learning_rate": 1.6366174746326915e-05,
20
+ "loss": 0.4981,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.0,
25
+ "eval_loss": 0.4900423288345337,
26
+ "eval_matthews_correlation": 0.4153896652547264,
27
+ "eval_runtime": 0.7314,
28
+ "eval_samples_per_second": 1425.957,
29
+ "eval_steps_per_second": 90.233,
30
+ "step": 1069
31
+ }
32
+ ],
33
+ "logging_steps": 500,
34
+ "max_steps": 3207,
35
+ "num_input_tokens_seen": 0,
36
+ "num_train_epochs": 3,
37
+ "save_steps": 500,
38
+ "total_flos": 37577275353120.0,
39
+ "train_batch_size": 8,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "learning_rate": 2.3781750073162853e-05,
43
+ "num_train_epochs": 3,
44
+ "per_device_train_batch_size": 8,
45
+ "seed": 4
46
+ }
47
+ }
run-3/checkpoint-1069/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afcad0aa7e2ccb8e2de574c0db08353470aae4815118a27ef0f48d3f85331771
3
+ size 4792
run-3/checkpoint-1069/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-07-52_773b0b4b06bc/events.out.tfevents.1703298258.773b0b4b06bc.493.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09236e96810c0573bd6d0fe415d67c8907d9d216953753c2942873c6ab58edc5
3
- size 4836
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d3314bccee4f682523ad0e625ee6d8e1822b8b95343c90b991806a7d985d07d
3
+ size 6666
runs/Dec23_02-07-52_773b0b4b06bc/events.out.tfevents.1703298415.773b0b4b06bc.493.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c77a52861a2a68f58ad1f712805a70de62eac48aeab1039495ca86d145bf7f38
3
+ size 5149
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eaf5433238535e3a9051fa91efd995dc6d4ed3adae963af5d669ca9f9d094baa
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afcad0aa7e2ccb8e2de574c0db08353470aae4815118a27ef0f48d3f85331771
3
  size 4792