LastSmile commited on
Commit
f2c4402
·
1 Parent(s): b51a709

Training in progress, epoch 2

Browse files
Files changed (48) hide show
  1. model.safetensors +1 -1
  2. run-8/checkpoint-536/config.json +25 -0
  3. run-8/checkpoint-536/model.safetensors +3 -0
  4. run-8/checkpoint-536/optimizer.pt +3 -0
  5. run-8/checkpoint-536/rng_state.pth +3 -0
  6. run-8/checkpoint-536/scheduler.pt +3 -0
  7. run-8/checkpoint-536/special_tokens_map.json +7 -0
  8. run-8/checkpoint-536/tokenizer.json +0 -0
  9. run-8/checkpoint-536/tokenizer_config.json +55 -0
  10. run-8/checkpoint-536/trainer_state.json +50 -0
  11. run-8/checkpoint-536/training_args.bin +3 -0
  12. run-8/checkpoint-536/vocab.txt +0 -0
  13. run-8/checkpoint-804/config.json +25 -0
  14. run-8/checkpoint-804/model.safetensors +3 -0
  15. run-8/checkpoint-804/optimizer.pt +3 -0
  16. run-8/checkpoint-804/rng_state.pth +3 -0
  17. run-8/checkpoint-804/scheduler.pt +3 -0
  18. run-8/checkpoint-804/special_tokens_map.json +7 -0
  19. run-8/checkpoint-804/tokenizer.json +0 -0
  20. run-8/checkpoint-804/tokenizer_config.json +55 -0
  21. run-8/checkpoint-804/trainer_state.json +59 -0
  22. run-8/checkpoint-804/training_args.bin +3 -0
  23. run-8/checkpoint-804/vocab.txt +0 -0
  24. run-9/checkpoint-2138/config.json +25 -0
  25. run-9/checkpoint-2138/model.safetensors +3 -0
  26. run-9/checkpoint-2138/optimizer.pt +3 -0
  27. run-9/checkpoint-2138/rng_state.pth +3 -0
  28. run-9/checkpoint-2138/scheduler.pt +3 -0
  29. run-9/checkpoint-2138/special_tokens_map.json +7 -0
  30. run-9/checkpoint-2138/tokenizer.json +0 -0
  31. run-9/checkpoint-2138/tokenizer_config.json +55 -0
  32. run-9/checkpoint-2138/trainer_state.json +59 -0
  33. run-9/checkpoint-2138/training_args.bin +3 -0
  34. run-9/checkpoint-2138/vocab.txt +0 -0
  35. run-9/checkpoint-4276/config.json +25 -0
  36. run-9/checkpoint-4276/model.safetensors +3 -0
  37. run-9/checkpoint-4276/optimizer.pt +3 -0
  38. run-9/checkpoint-4276/rng_state.pth +3 -0
  39. run-9/checkpoint-4276/scheduler.pt +3 -0
  40. run-9/checkpoint-4276/special_tokens_map.json +7 -0
  41. run-9/checkpoint-4276/tokenizer.json +0 -0
  42. run-9/checkpoint-4276/tokenizer_config.json +55 -0
  43. run-9/checkpoint-4276/trainer_state.json +92 -0
  44. run-9/checkpoint-4276/training_args.bin +3 -0
  45. run-9/checkpoint-4276/vocab.txt +0 -0
  46. runs/Dec23_02-11-14_9e1ba8448b92/events.out.tfevents.1703298636.9e1ba8448b92.4051.10 +2 -2
  47. runs/Dec23_02-11-14_9e1ba8448b92/events.out.tfevents.1703298721.9e1ba8448b92.4051.11 +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 sha256:043ae018c8ef6d941948135daf64ce17122ca3cf864e998c72301d8d2d8ee911
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3929f906e9450e7447f207d88ebc993fab5e67f25beada1793a7c22d576bd78
3
  size 267832560
run-8/checkpoint-536/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-8/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52bc02c37834f7e013f91aa91585cb687721fcc7ff27ab46c17804ebd373b0a4
3
+ size 267832560
run-8/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4109bc572b557c5d78a31b970872539f8edb13143c4a32462ad61445d8dd0e85
3
+ size 535727290
run-8/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d2fc113ee7360d3244b8c4f5edf43d5f8deabd99f4b106b2de0784f23acc6fa
3
+ size 14308
run-8/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46d1af402782ec6509ab195fc97a1b6abfe45023aeab6b3e2a1581d8c0baa4f3
3
+ size 1064
run-8/checkpoint-536/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-8/checkpoint-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-536/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-8/checkpoint-536/trainer_state.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.42727410372514657,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-268",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 536,
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": 0.5017905235290527,
14
+ "eval_matthews_correlation": 0.42727410372514657,
15
+ "eval_runtime": 0.7287,
16
+ "eval_samples_per_second": 1431.32,
17
+ "eval_steps_per_second": 90.572,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 3.185722189196676e-05,
23
+ "loss": 0.4295,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.5037716627120972,
29
+ "eval_matthews_correlation": 0.42699958677022615,
30
+ "eval_runtime": 0.7359,
31
+ "eval_samples_per_second": 1417.405,
32
+ "eval_steps_per_second": 89.692,
33
+ "step": 536
34
+ }
35
+ ],
36
+ "logging_steps": 500,
37
+ "max_steps": 804,
38
+ "num_input_tokens_seen": 0,
39
+ "num_train_epochs": 3,
40
+ "save_steps": 500,
41
+ "total_flos": 97452798271020.0,
42
+ "train_batch_size": 32,
43
+ "trial_name": null,
44
+ "trial_params": {
45
+ "learning_rate": 8.425396842480683e-05,
46
+ "num_train_epochs": 3,
47
+ "per_device_train_batch_size": 32,
48
+ "seed": 33
49
+ }
50
+ }
run-8/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4655682e2fb07f788b39f5acf250a4612106fee5bd19f53c29712145e8484df2
3
+ size 4792
run-8/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-804/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-8/checkpoint-804/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23632e418fe4a7a72c28be626596968f9954e1ca3736ddd13824d098dc4e530f
3
+ size 267832560
run-8/checkpoint-804/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f4eb370fcb04dbeb1648315d975ae625b6ec375c27c3b24816e8a91223550de
3
+ size 535727290
run-8/checkpoint-804/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13960e747bdd61dc2f6c7e4f79e99fcd3d4fac9e6964c851120b6f9d2bf744b5
3
+ size 14308
run-8/checkpoint-804/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32674a7f085fbd3c9e4cdc811b974b7341bb80380f5db77dc2856aa1cd3f4ff1
3
+ size 1064
run-8/checkpoint-804/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-8/checkpoint-804/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-804/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-8/checkpoint-804/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.44491715698475054,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-8/checkpoint-804",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 804,
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": 0.5017905235290527,
14
+ "eval_matthews_correlation": 0.42727410372514657,
15
+ "eval_runtime": 0.7287,
16
+ "eval_samples_per_second": 1431.32,
17
+ "eval_steps_per_second": 90.572,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "learning_rate": 3.185722189196676e-05,
23
+ "loss": 0.4295,
24
+ "step": 500
25
+ },
26
+ {
27
+ "epoch": 2.0,
28
+ "eval_loss": 0.5037716627120972,
29
+ "eval_matthews_correlation": 0.42699958677022615,
30
+ "eval_runtime": 0.7359,
31
+ "eval_samples_per_second": 1417.405,
32
+ "eval_steps_per_second": 89.692,
33
+ "step": 536
34
+ },
35
+ {
36
+ "epoch": 3.0,
37
+ "eval_loss": 0.6981148719787598,
38
+ "eval_matthews_correlation": 0.44491715698475054,
39
+ "eval_runtime": 0.8461,
40
+ "eval_samples_per_second": 1232.787,
41
+ "eval_steps_per_second": 78.01,
42
+ "step": 804
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 804,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 3,
49
+ "save_steps": 500,
50
+ "total_flos": 97452798271020.0,
51
+ "train_batch_size": 32,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 8.425396842480683e-05,
55
+ "num_train_epochs": 3,
56
+ "per_device_train_batch_size": 32,
57
+ "seed": 33
58
+ }
59
+ }
run-8/checkpoint-804/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4655682e2fb07f788b39f5acf250a4612106fee5bd19f53c29712145e8484df2
3
+ size 4792
run-8/checkpoint-804/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-2138/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-9/checkpoint-2138/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49817f626da76e78139ec03de4519cc6531e863bc8cca61d06b1ff151960fa9b
3
+ size 267832560
run-9/checkpoint-2138/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f56b93364018b6f70e00b638ea7fef6269a0dc5dd69e30023e11b89d371c30b7
3
+ size 535727290
run-9/checkpoint-2138/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5008a6b97f7f941a202ea9000ec91099bbc523c9bc2122970f9599146b56306f
3
+ size 14308
run-9/checkpoint-2138/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0942c558005b186b85d8f150cdb735f95196864d54bd1bbeb3fabeb88c406b0
3
+ size 1064
run-9/checkpoint-2138/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-9/checkpoint-2138/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-2138/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-9/checkpoint-2138/trainer_state.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4227320658781353,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-2138",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2138,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23,
13
+ "learning_rate": 2.4756314159255174e-05,
14
+ "loss": 0.6193,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 2.3219036826961632e-05,
20
+ "loss": 0.5585,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 2.1681759494668092e-05,
26
+ "loss": 0.5666,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 2.0144482162374553e-05,
32
+ "loss": 0.5675,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.6569426655769348,
38
+ "eval_matthews_correlation": 0.4227320658781353,
39
+ "eval_runtime": 0.7268,
40
+ "eval_samples_per_second": 1435.065,
41
+ "eval_steps_per_second": 90.81,
42
+ "step": 2138
43
+ }
44
+ ],
45
+ "logging_steps": 500,
46
+ "max_steps": 8552,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 4,
49
+ "save_steps": 500,
50
+ "total_flos": 32693574929232.0,
51
+ "train_batch_size": 4,
52
+ "trial_name": null,
53
+ "trial_params": {
54
+ "learning_rate": 2.6293591491548714e-05,
55
+ "num_train_epochs": 4,
56
+ "per_device_train_batch_size": 4,
57
+ "seed": 37
58
+ }
59
+ }
run-9/checkpoint-2138/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d7f90b376166285bdadbbcc6bcdd97137714d15514517ba081d36c394405082
3
+ size 4792
run-9/checkpoint-2138/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-4276/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-9/checkpoint-4276/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3929f906e9450e7447f207d88ebc993fab5e67f25beada1793a7c22d576bd78
3
+ size 267832560
run-9/checkpoint-4276/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8bbb72b2b177fe48604c1fe6628118fc6a7fd3119774dcb0ecc5534e633301d
3
+ size 535727290
run-9/checkpoint-4276/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c76a9e2c882102b6bc05501887118bd602c4d5a830017585573b0bed099579e3
3
+ size 14308
run-9/checkpoint-4276/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72808d389218fbec4c65fecc5a71d900ed9032b1ac089edf4e76e37d72992195
3
+ size 1064
run-9/checkpoint-4276/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-9/checkpoint-4276/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-4276/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-9/checkpoint-4276/trainer_state.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.47958645804826155,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-4276",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4276,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.23,
13
+ "learning_rate": 2.4756314159255174e-05,
14
+ "loss": 0.6193,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.47,
19
+ "learning_rate": 2.3219036826961632e-05,
20
+ "loss": 0.5585,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.7,
25
+ "learning_rate": 2.1681759494668092e-05,
26
+ "loss": 0.5666,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.94,
31
+ "learning_rate": 2.0144482162374553e-05,
32
+ "loss": 0.5675,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.0,
37
+ "eval_loss": 0.6569426655769348,
38
+ "eval_matthews_correlation": 0.4227320658781353,
39
+ "eval_runtime": 0.7268,
40
+ "eval_samples_per_second": 1435.065,
41
+ "eval_steps_per_second": 90.81,
42
+ "step": 2138
43
+ },
44
+ {
45
+ "epoch": 1.17,
46
+ "learning_rate": 1.8607204830081014e-05,
47
+ "loss": 0.4882,
48
+ "step": 2500
49
+ },
50
+ {
51
+ "epoch": 1.4,
52
+ "learning_rate": 1.706992749778747e-05,
53
+ "loss": 0.4369,
54
+ "step": 3000
55
+ },
56
+ {
57
+ "epoch": 1.64,
58
+ "learning_rate": 1.5532650165493932e-05,
59
+ "loss": 0.4617,
60
+ "step": 3500
61
+ },
62
+ {
63
+ "epoch": 1.87,
64
+ "learning_rate": 1.399537283320039e-05,
65
+ "loss": 0.4431,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 2.0,
70
+ "eval_loss": 0.8103704452514648,
71
+ "eval_matthews_correlation": 0.47958645804826155,
72
+ "eval_runtime": 0.7309,
73
+ "eval_samples_per_second": 1427.024,
74
+ "eval_steps_per_second": 90.301,
75
+ "step": 4276
76
+ }
77
+ ],
78
+ "logging_steps": 500,
79
+ "max_steps": 8552,
80
+ "num_input_tokens_seen": 0,
81
+ "num_train_epochs": 4,
82
+ "save_steps": 500,
83
+ "total_flos": 65437860034512.0,
84
+ "train_batch_size": 4,
85
+ "trial_name": null,
86
+ "trial_params": {
87
+ "learning_rate": 2.6293591491548714e-05,
88
+ "num_train_epochs": 4,
89
+ "per_device_train_batch_size": 4,
90
+ "seed": 37
91
+ }
92
+ }
run-9/checkpoint-4276/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d7f90b376166285bdadbbcc6bcdd97137714d15514517ba081d36c394405082
3
+ size 4792
run-9/checkpoint-4276/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec23_02-11-14_9e1ba8448b92/events.out.tfevents.1703298636.9e1ba8448b92.4051.10 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48821f2b06df1750620297ce9471b01982c6c5983e15ed47da969c82c4addbb1
3
- size 5171
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bfd468fa63bb4f9126030e33f3beab623c75ad1d9ebe12e857aacf542aa8a99
3
+ size 5860
runs/Dec23_02-11-14_9e1ba8448b92/events.out.tfevents.1703298721.9e1ba8448b92.4051.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18806da157f4bd30b8a728ce3f2d44266e7444eda0dd9c2bf1532db4b107391f
3
+ size 6584
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4655682e2fb07f788b39f5acf250a4612106fee5bd19f53c29712145e8484df2
3
  size 4792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d7f90b376166285bdadbbcc6bcdd97137714d15514517ba081d36c394405082
3
  size 4792