Poodja commited on
Commit
e88fcd4
·
verified ·
1 Parent(s): 1cae09d

Training in progress, epoch 1

Browse files
Files changed (47) hide show
  1. model.safetensors +1 -1
  2. run-3/checkpoint-108/config.json +25 -0
  3. run-3/checkpoint-108/model.safetensors +3 -0
  4. run-3/checkpoint-108/optimizer.pt +3 -0
  5. run-3/checkpoint-108/rng_state.pth +3 -0
  6. run-3/checkpoint-108/scheduler.pt +3 -0
  7. run-3/checkpoint-108/special_tokens_map.json +7 -0
  8. run-3/checkpoint-108/tokenizer.json +0 -0
  9. run-3/checkpoint-108/tokenizer_config.json +55 -0
  10. run-3/checkpoint-108/trainer_state.json +62 -0
  11. run-3/checkpoint-108/training_args.bin +3 -0
  12. run-3/checkpoint-108/vocab.txt +0 -0
  13. run-3/checkpoint-54/config.json +25 -0
  14. run-3/checkpoint-54/model.safetensors +3 -0
  15. run-3/checkpoint-54/optimizer.pt +3 -0
  16. run-3/checkpoint-54/rng_state.pth +3 -0
  17. run-3/checkpoint-54/scheduler.pt +3 -0
  18. run-3/checkpoint-54/special_tokens_map.json +7 -0
  19. run-3/checkpoint-54/tokenizer.json +0 -0
  20. run-3/checkpoint-54/tokenizer_config.json +55 -0
  21. run-3/checkpoint-54/trainer_state.json +44 -0
  22. run-3/checkpoint-54/training_args.bin +3 -0
  23. run-3/checkpoint-54/vocab.txt +0 -0
  24. run-3/checkpoint-81/config.json +25 -0
  25. run-3/checkpoint-81/model.safetensors +3 -0
  26. run-3/checkpoint-81/optimizer.pt +3 -0
  27. run-3/checkpoint-81/rng_state.pth +3 -0
  28. run-3/checkpoint-81/scheduler.pt +3 -0
  29. run-3/checkpoint-81/special_tokens_map.json +7 -0
  30. run-3/checkpoint-81/tokenizer.json +0 -0
  31. run-3/checkpoint-81/tokenizer_config.json +55 -0
  32. run-3/checkpoint-81/trainer_state.json +53 -0
  33. run-3/checkpoint-81/training_args.bin +3 -0
  34. run-3/checkpoint-81/vocab.txt +0 -0
  35. run-4/checkpoint-54/config.json +25 -0
  36. run-4/checkpoint-54/model.safetensors +3 -0
  37. run-4/checkpoint-54/optimizer.pt +3 -0
  38. run-4/checkpoint-54/rng_state.pth +3 -0
  39. run-4/checkpoint-54/scheduler.pt +3 -0
  40. run-4/checkpoint-54/special_tokens_map.json +7 -0
  41. run-4/checkpoint-54/tokenizer.json +0 -0
  42. run-4/checkpoint-54/tokenizer_config.json +55 -0
  43. run-4/checkpoint-54/trainer_state.json +35 -0
  44. run-4/checkpoint-54/training_args.bin +3 -0
  45. run-4/checkpoint-54/vocab.txt +0 -0
  46. runs/Feb27_13-20-57_4ffe06e164fd/events.out.tfevents.1709042221.4ffe06e164fd.373.6 +3 -0
  47. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69ffb22f37430603cdbc9fcc14ddf2c6acc136c9d72c65654154e3b0137be539
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc16e65209478886081b742b22316812399606054dd93aa03530a3c88f496fc5
3
  size 267832560
run-3/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-3/checkpoint-108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe1f9c51775094081042c3c700d2258bb67266866b1fb5bf395320e0c2fe8352
3
+ size 267832560
run-3/checkpoint-108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea929e22c24e7b603ae94b867490ac2ce70a17cc5d07d81f6faf5b115022fbe0
3
+ size 535727290
run-3/checkpoint-108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6d08e5e7cc27f099578a87aafdab211980ce65d5543db099a078fad53510271
3
+ size 14244
run-3/checkpoint-108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a2881c7196ec845c9ec5b13f65afe8b2b3093eb665071df72278b8d7ef5c8ba
3
+ size 1064
run-3/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-3/checkpoint-108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-108/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-27",
4
+ "epoch": 4.0,
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": 0.6507918238639832,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7137,
16
+ "eval_samples_per_second": 1461.439,
17
+ "eval_steps_per_second": 92.478,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6393526792526245,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 1.2472,
25
+ "eval_samples_per_second": 836.28,
26
+ "eval_steps_per_second": 52.919,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6333318948745728,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.8155,
34
+ "eval_samples_per_second": 1278.909,
35
+ "eval_steps_per_second": 80.928,
36
+ "step": 81
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.6314817070960999,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 0.77,
43
+ "eval_samples_per_second": 1354.558,
44
+ "eval_steps_per_second": 85.715,
45
+ "step": 108
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 108,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 4,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 32,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 1.3701497217179056e-06,
58
+ "num_train_epochs": 4,
59
+ "per_device_train_batch_size": 32,
60
+ "seed": 11
61
+ }
62
+ }
run-3/checkpoint-108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a0332785fee37f34fdfc4524e8ec12492e948a3ebdef9e0f44312d346fcd90
3
+ size 4984
run-3/checkpoint-108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf6a323a10b01daae2b82074815f24c01756314407b1a069abe9e6f2e2240b1a
3
+ size 267832560
run-3/checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bf73e1bb553efde90c57047384e0b8c21047aaa3de1a582dce397cb6bd8f21f
3
+ size 535727290
run-3/checkpoint-54/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e42e2747302ca66575567cd2ad92e4c499840df43d7c74871abe2a004c812c2b
3
+ size 14244
run-3/checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5c69221615632746d03603a3fea2c3d0b58f88e73117dc76cf4a7e42e427d06
3
+ size 1064
run-3/checkpoint-54/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-54/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-54/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-54/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-27",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 54,
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": 0.6507918238639832,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7137,
16
+ "eval_samples_per_second": 1461.439,
17
+ "eval_steps_per_second": 92.478,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6393526792526245,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 1.2472,
25
+ "eval_samples_per_second": 836.28,
26
+ "eval_steps_per_second": 52.919,
27
+ "step": 54
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 108,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 32,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 1.3701497217179056e-06,
40
+ "num_train_epochs": 4,
41
+ "per_device_train_batch_size": 32,
42
+ "seed": 11
43
+ }
44
+ }
run-3/checkpoint-54/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a0332785fee37f34fdfc4524e8ec12492e948a3ebdef9e0f44312d346fcd90
3
+ size 4984
run-3/checkpoint-54/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-81/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-81/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb578ef3b1bfb1d4cab53f8baaeb3eab8cea8a6153515fdf4034bba313a9e9e5
3
+ size 267832560
run-3/checkpoint-81/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f017316cfc7d2db2c368541167cc5f12bf307250dcdb43f98a4783d7242c0a
3
+ size 535727290
run-3/checkpoint-81/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dae41a659a7e169ccb25d03d75764e0a3e0b457ebd805deda168932be6a6d48
3
+ size 14244
run-3/checkpoint-81/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b6142d6587975eb958ba747b0322e02947b2b751645adefe71e8e02d01d697b
3
+ size 1064
run-3/checkpoint-81/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-81/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-81/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-81/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-27",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 81,
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": 0.6507918238639832,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7137,
16
+ "eval_samples_per_second": 1461.439,
17
+ "eval_steps_per_second": 92.478,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6393526792526245,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 1.2472,
25
+ "eval_samples_per_second": 836.28,
26
+ "eval_steps_per_second": 52.919,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6333318948745728,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.8155,
34
+ "eval_samples_per_second": 1278.909,
35
+ "eval_steps_per_second": 80.928,
36
+ "step": 81
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 108,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 4,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 32,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 1.3701497217179056e-06,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 32,
51
+ "seed": 11
52
+ }
53
+ }
run-3/checkpoint-81/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a0332785fee37f34fdfc4524e8ec12492e948a3ebdef9e0f44312d346fcd90
3
+ size 4984
run-3/checkpoint-81/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/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-4/checkpoint-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc16e65209478886081b742b22316812399606054dd93aa03530a3c88f496fc5
3
+ size 267832560
run-4/checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68f0c3e8191603c1e40b30da8f00e50bbfafc0c3f1276dcd3440c0acf455c984
3
+ size 535727290
run-4/checkpoint-54/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9db3ea772ae1ff4ff44b0aaa292584c5ca9795073bc425eedbfea08a319e7e71
3
+ size 14308
run-4/checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cb2eafea1afab298e67cbf889edbe8da0739693111fe295b25ff3888f939d79
3
+ size 1064
run-4/checkpoint-54/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-54/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-54/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-54/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-54",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 54,
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": 0.6084455251693726,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7112,
16
+ "eval_samples_per_second": 1466.533,
17
+ "eval_steps_per_second": 92.801,
18
+ "step": 54
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 270,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 16,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 7.670979185958202e-06,
31
+ "num_train_epochs": 5,
32
+ "per_device_train_batch_size": 16,
33
+ "seed": 32
34
+ }
35
+ }
run-4/checkpoint-54/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d01cc994ba3d9d3ab321de5dd591365526c0475b39b130e8cca28028d8b400
3
+ size 4984
run-4/checkpoint-54/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb27_13-20-57_4ffe06e164fd/events.out.tfevents.1709042221.4ffe06e164fd.373.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a909dcbc108fa687137a34b8e593822353f929f083858a3b1516679b01acde11
3
+ size 6559
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4a0332785fee37f34fdfc4524e8ec12492e948a3ebdef9e0f44312d346fcd90
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5d01cc994ba3d9d3ab321de5dd591365526c0475b39b130e8cca28028d8b400
3
  size 4984