jjkozlow commited on
Commit
a4644a4
1 Parent(s): 18339c7

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-5/checkpoint-28/config.json +25 -0
  3. run-5/checkpoint-28/model.safetensors +3 -0
  4. run-5/checkpoint-28/optimizer.pt +3 -0
  5. run-5/checkpoint-28/rng_state.pth +3 -0
  6. run-5/checkpoint-28/scheduler.pt +3 -0
  7. run-5/checkpoint-28/special_tokens_map.json +7 -0
  8. run-5/checkpoint-28/tokenizer.json +0 -0
  9. run-5/checkpoint-28/tokenizer_config.json +55 -0
  10. run-5/checkpoint-28/trainer_state.json +44 -0
  11. run-5/checkpoint-28/training_args.bin +3 -0
  12. run-5/checkpoint-28/vocab.txt +0 -0
  13. run-5/checkpoint-42/config.json +25 -0
  14. run-5/checkpoint-42/model.safetensors +3 -0
  15. run-5/checkpoint-42/optimizer.pt +3 -0
  16. run-5/checkpoint-42/rng_state.pth +3 -0
  17. run-5/checkpoint-42/scheduler.pt +3 -0
  18. run-5/checkpoint-42/special_tokens_map.json +7 -0
  19. run-5/checkpoint-42/tokenizer.json +0 -0
  20. run-5/checkpoint-42/tokenizer_config.json +55 -0
  21. run-5/checkpoint-42/trainer_state.json +53 -0
  22. run-5/checkpoint-42/training_args.bin +3 -0
  23. run-5/checkpoint-42/vocab.txt +0 -0
  24. run-5/checkpoint-56/config.json +25 -0
  25. run-5/checkpoint-56/model.safetensors +3 -0
  26. run-5/checkpoint-56/optimizer.pt +3 -0
  27. run-5/checkpoint-56/rng_state.pth +3 -0
  28. run-5/checkpoint-56/scheduler.pt +3 -0
  29. run-5/checkpoint-56/special_tokens_map.json +7 -0
  30. run-5/checkpoint-56/tokenizer.json +0 -0
  31. run-5/checkpoint-56/tokenizer_config.json +55 -0
  32. run-5/checkpoint-56/trainer_state.json +62 -0
  33. run-5/checkpoint-56/training_args.bin +3 -0
  34. run-5/checkpoint-56/vocab.txt +0 -0
  35. run-5/checkpoint-70/config.json +25 -0
  36. run-5/checkpoint-70/model.safetensors +3 -0
  37. run-5/checkpoint-70/optimizer.pt +3 -0
  38. run-5/checkpoint-70/rng_state.pth +3 -0
  39. run-5/checkpoint-70/scheduler.pt +3 -0
  40. run-5/checkpoint-70/special_tokens_map.json +7 -0
  41. run-5/checkpoint-70/tokenizer.json +0 -0
  42. run-5/checkpoint-70/tokenizer_config.json +55 -0
  43. run-5/checkpoint-70/trainer_state.json +71 -0
  44. run-5/checkpoint-70/training_args.bin +3 -0
  45. run-5/checkpoint-70/vocab.txt +0 -0
  46. run-6/checkpoint-27/config.json +25 -0
  47. run-6/checkpoint-27/model.safetensors +3 -0
  48. run-6/checkpoint-27/optimizer.pt +3 -0
  49. run-6/checkpoint-27/rng_state.pth +3 -0
  50. run-6/checkpoint-27/scheduler.pt +3 -0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09c399d5c6d274b5d5cc7cb7fda95ecfef67cd76674fe54860120bfb1c6a843c
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a344b57655b8bca213d5cfa687cecdb5897e4a015cb742dd436cd70abb4c5b09
3
  size 267832560
run-5/checkpoint-28/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": "4.40.1",
24
+ "vocab_size": 30522
25
+ }
run-5/checkpoint-28/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74562e82d9f3a469ac0f5c561335cad2151bb29e58d92bf59f1318f05568e7bb
3
+ size 267832560
run-5/checkpoint-28/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5248c7021a5ff5ee95375605569770edb6897c538964308051883720eef4818
3
+ size 535727290
run-5/checkpoint-28/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc68be50d2b80353ed69065c005c6ee6ffa54cfe45dbefe3f83c70a727f53bef
3
+ size 14308
run-5/checkpoint-28/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eefd32eccb7e1b336d9419a7783f93b226b7f9039ba31a37fd7739885e63882
3
+ size 1064
run-5/checkpoint-28/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-5/checkpoint-28/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-28/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": 1000000000000000019884624838656,
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-5/checkpoint-28/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-14",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 28,
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": 0.6652335524559021,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7146,
16
+ "eval_samples_per_second": 1459.613,
17
+ "eval_steps_per_second": 92.363,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6462804079055786,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7964,
25
+ "eval_samples_per_second": 1309.62,
26
+ "eval_steps_per_second": 82.871,
27
+ "step": 28
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 70,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 5,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 3.860924155455462e-06,
40
+ "num_train_epochs": 5,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 8
43
+ }
44
+ }
run-5/checkpoint-28/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0bea53eaf520e20e0203095307f0258657ec6af89d1c1cafc64a01bf35c1887
3
+ size 5048
run-5/checkpoint-28/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-42/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": "4.40.1",
24
+ "vocab_size": 30522
25
+ }
run-5/checkpoint-42/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f69f82bb1efa457cacff756305bc585db7eb75a4f962ba5883941fb2b230eab7
3
+ size 267832560
run-5/checkpoint-42/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07213e1b355c05bc6b9ac400472a82f9a969b6be329acc67b355d899430b8178
3
+ size 535727290
run-5/checkpoint-42/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e91222f21cbb790436f77ccee75959e0946846cc86ae464d1deb197c6029abce
3
+ size 14308
run-5/checkpoint-42/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b407531ede59f4a7a64fcd56767038199c6124d30a67456fd1d2d9175318d47
3
+ size 1064
run-5/checkpoint-42/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-5/checkpoint-42/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-42/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": 1000000000000000019884624838656,
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-5/checkpoint-42/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-14",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 42,
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": 0.6652335524559021,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7146,
16
+ "eval_samples_per_second": 1459.613,
17
+ "eval_steps_per_second": 92.363,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6462804079055786,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7964,
25
+ "eval_samples_per_second": 1309.62,
26
+ "eval_steps_per_second": 82.871,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6326283812522888,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.7981,
34
+ "eval_samples_per_second": 1306.904,
35
+ "eval_steps_per_second": 82.7,
36
+ "step": 42
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 70,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 5,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 64,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 3.860924155455462e-06,
49
+ "num_train_epochs": 5,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 8
52
+ }
53
+ }
run-5/checkpoint-42/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0bea53eaf520e20e0203095307f0258657ec6af89d1c1cafc64a01bf35c1887
3
+ size 5048
run-5/checkpoint-42/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-56/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.40.1",
24
+ "vocab_size": 30522
25
+ }
run-5/checkpoint-56/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e31529e7ac6f14f047e4a3f2036649165ea605a5c18574766ec135f36abaa4f2
3
+ size 267832560
run-5/checkpoint-56/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6244c8ec3c607c0a5264155cb826858eeb5bdf3c8d8c0d516aef862e651b7e0f
3
+ size 535727290
run-5/checkpoint-56/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea765a50dfc49023807bbc7748445b75b950e783dee9b315d99b031f4dcf1227
3
+ size 14308
run-5/checkpoint-56/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40fcd33b2b4dacb9641a1000b4579a3e17636c284ced2fddea85aee96e812cbd
3
+ size 1064
run-5/checkpoint-56/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-5/checkpoint-56/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-56/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 1000000000000000019884624838656,
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-5/checkpoint-56/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-14",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 56,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_loss": 0.6652335524559021,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7146,
16
+ "eval_samples_per_second": 1459.613,
17
+ "eval_steps_per_second": 92.363,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6462804079055786,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7964,
25
+ "eval_samples_per_second": 1309.62,
26
+ "eval_steps_per_second": 82.871,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6326283812522888,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.7981,
34
+ "eval_samples_per_second": 1306.904,
35
+ "eval_steps_per_second": 82.7,
36
+ "step": 42
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.6263242959976196,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 0.7465,
43
+ "eval_samples_per_second": 1397.225,
44
+ "eval_steps_per_second": 88.415,
45
+ "step": 56
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 70,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 5,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 64,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 3.860924155455462e-06,
58
+ "num_train_epochs": 5,
59
+ "per_device_train_batch_size": 64,
60
+ "seed": 8
61
+ }
62
+ }
run-5/checkpoint-56/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0bea53eaf520e20e0203095307f0258657ec6af89d1c1cafc64a01bf35c1887
3
+ size 5048
run-5/checkpoint-56/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-70/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": "4.40.1",
24
+ "vocab_size": 30522
25
+ }
run-5/checkpoint-70/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5df307d3b88bf07e6fe97b80e20726ea436e2e94ed56cb25e7f6dea399b384de
3
+ size 267832560
run-5/checkpoint-70/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf82ef1b52530a042b1a9442e8bdee5385c01257218617071dc50e67f60dc0c
3
+ size 535727290
run-5/checkpoint-70/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75e38fa484b525b8954613616eccfe0e6896b9373f5507f53313ef9f0452e658
3
+ size 14308
run-5/checkpoint-70/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a208eb73b27e72356cb76658840a9a9c4bed1b1f3e4c721850541e4be930aa3b
3
+ size 1064
run-5/checkpoint-70/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-5/checkpoint-70/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-70/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": 1000000000000000019884624838656,
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-5/checkpoint-70/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-5/checkpoint-14",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 70,
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": 0.6652335524559021,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7146,
16
+ "eval_samples_per_second": 1459.613,
17
+ "eval_steps_per_second": 92.363,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6462804079055786,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7964,
25
+ "eval_samples_per_second": 1309.62,
26
+ "eval_steps_per_second": 82.871,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6326283812522888,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.7981,
34
+ "eval_samples_per_second": 1306.904,
35
+ "eval_steps_per_second": 82.7,
36
+ "step": 42
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.6263242959976196,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 0.7465,
43
+ "eval_samples_per_second": 1397.225,
44
+ "eval_steps_per_second": 88.415,
45
+ "step": 56
46
+ },
47
+ {
48
+ "epoch": 5.0,
49
+ "eval_loss": 0.6247925758361816,
50
+ "eval_matthews_correlation": 0.0,
51
+ "eval_runtime": 1.3716,
52
+ "eval_samples_per_second": 760.451,
53
+ "eval_steps_per_second": 48.121,
54
+ "step": 70
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 70,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 5,
61
+ "save_steps": 500,
62
+ "total_flos": 0,
63
+ "train_batch_size": 64,
64
+ "trial_name": null,
65
+ "trial_params": {
66
+ "learning_rate": 3.860924155455462e-06,
67
+ "num_train_epochs": 5,
68
+ "per_device_train_batch_size": 64,
69
+ "seed": 8
70
+ }
71
+ }
run-5/checkpoint-70/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0bea53eaf520e20e0203095307f0258657ec6af89d1c1cafc64a01bf35c1887
3
+ size 5048
run-5/checkpoint-70/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-6/checkpoint-27/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": "4.40.1",
24
+ "vocab_size": 30522
25
+ }
run-6/checkpoint-27/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a344b57655b8bca213d5cfa687cecdb5897e4a015cb742dd436cd70abb4c5b09
3
+ size 267832560
run-6/checkpoint-27/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ed8edc0b4938e6f1733136d72124b4afca3c812b2c34d26f5e9727206e82514
3
+ size 535727290
run-6/checkpoint-27/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b90ebca1050e423c024178d467898876cda7a2ec8e72b57011a5e92de0de867d
3
+ size 14308
run-6/checkpoint-27/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffc452b08d8fcfc79c8349559c5ce856f3bcd153fae294f8ed1a3016eac28b0e
3
+ size 1064