obudzecie commited on
Commit
9d163bf
·
verified ·
1 Parent(s): 8ce86af

Training in progress, epoch 1

Browse files
Files changed (49) hide show
  1. model.safetensors +1 -1
  2. run-0/checkpoint-28/config.json +25 -0
  3. run-0/checkpoint-28/model.safetensors +3 -0
  4. run-0/checkpoint-28/optimizer.pt +3 -0
  5. run-0/checkpoint-28/rng_state.pth +3 -0
  6. run-0/checkpoint-28/scheduler.pt +3 -0
  7. run-0/checkpoint-28/special_tokens_map.json +7 -0
  8. run-0/checkpoint-28/tokenizer.json +0 -0
  9. run-0/checkpoint-28/tokenizer_config.json +55 -0
  10. run-0/checkpoint-28/trainer_state.json +44 -0
  11. run-0/checkpoint-28/training_args.bin +3 -0
  12. run-0/checkpoint-28/vocab.txt +0 -0
  13. run-0/checkpoint-42/config.json +25 -0
  14. run-0/checkpoint-42/model.safetensors +3 -0
  15. run-0/checkpoint-42/optimizer.pt +3 -0
  16. run-0/checkpoint-42/rng_state.pth +3 -0
  17. run-0/checkpoint-42/scheduler.pt +3 -0
  18. run-0/checkpoint-42/special_tokens_map.json +7 -0
  19. run-0/checkpoint-42/tokenizer.json +0 -0
  20. run-0/checkpoint-42/tokenizer_config.json +55 -0
  21. run-0/checkpoint-42/trainer_state.json +53 -0
  22. run-0/checkpoint-42/training_args.bin +3 -0
  23. run-0/checkpoint-42/vocab.txt +0 -0
  24. run-1/checkpoint-54/config.json +25 -0
  25. run-1/checkpoint-54/model.safetensors +3 -0
  26. run-1/checkpoint-54/optimizer.pt +3 -0
  27. run-1/checkpoint-54/rng_state.pth +3 -0
  28. run-1/checkpoint-54/scheduler.pt +3 -0
  29. run-1/checkpoint-54/special_tokens_map.json +7 -0
  30. run-1/checkpoint-54/tokenizer.json +0 -0
  31. run-1/checkpoint-54/tokenizer_config.json +55 -0
  32. run-1/checkpoint-54/trainer_state.json +35 -0
  33. run-1/checkpoint-54/training_args.bin +3 -0
  34. run-1/checkpoint-54/vocab.txt +0 -0
  35. run-2/checkpoint-54/config.json +25 -0
  36. run-2/checkpoint-54/model.safetensors +3 -0
  37. run-2/checkpoint-54/optimizer.pt +3 -0
  38. run-2/checkpoint-54/rng_state.pth +3 -0
  39. run-2/checkpoint-54/scheduler.pt +3 -0
  40. run-2/checkpoint-54/special_tokens_map.json +7 -0
  41. run-2/checkpoint-54/tokenizer.json +0 -0
  42. run-2/checkpoint-54/tokenizer_config.json +55 -0
  43. run-2/checkpoint-54/trainer_state.json +35 -0
  44. run-2/checkpoint-54/training_args.bin +3 -0
  45. run-2/checkpoint-54/vocab.txt +0 -0
  46. runs/Feb27_12-55-59_86e2730489af/events.out.tfevents.1709039850.86e2730489af.508.2 +2 -2
  47. runs/Feb27_12-55-59_86e2730489af/events.out.tfevents.1709039934.86e2730489af.508.3 +3 -0
  48. runs/Feb27_12-55-59_86e2730489af/events.out.tfevents.1709039961.86e2730489af.508.4 +3 -0
  49. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e18d66452db55d99e35342177e49d6e4d7903a06fcc4061f0f8211e24dfea29
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14425fcaecc2d46a7e64c553c7c0e03a8b0b899a83ea0d3963fb80be859c7eb1
3
  size 267832560
run-0/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-0/checkpoint-28/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6ce764070444d43068b553396eb365995d77cbcbd1914c72aa9a6c97850709b
3
+ size 267832560
run-0/checkpoint-28/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc2ebe14313b9e6c3947fd1d953eeda5d13b11ff870720b9710937950626a362
3
+ size 535727290
run-0/checkpoint-28/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c33e0c0fc4377f79ddd532f22fabff059620d2e02ddbf80b3af980df5f7875f1
3
+ size 14308
run-0/checkpoint-28/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39b41d01198466edea710d83579bcbe9782f3537fd512c2b54f81697b76e4f30
3
+ size 1064
run-0/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-0/checkpoint-28/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-0/checkpoint-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-0/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": 0.6425530314445496,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.6667,
16
+ "eval_samples_per_second": 1564.434,
17
+ "eval_steps_per_second": 98.996,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6215561628341675,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7349,
25
+ "eval_samples_per_second": 1419.255,
26
+ "eval_steps_per_second": 89.809,
27
+ "step": 28
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 42,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 64,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 5.9402286931455415e-06,
40
+ "num_train_epochs": 3,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 33
43
+ }
44
+ }
run-0/checkpoint-28/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3890eb403da684d0292db5dfdfff23f4d1c6bfee6a85697d4ee366d75565506
3
+ size 4984
run-0/checkpoint-28/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-0/checkpoint-42/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97ffbe361e628c035a5dc0d9b6ff0da9663779ef6c33d32548093321d557d4c5
3
+ size 267832560
run-0/checkpoint-42/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a092b9b657055e02cc1b3c9d67839aa5a26c67d271854d32a337c82981b392d
3
+ size 535727290
run-0/checkpoint-42/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eb54a559e9f7a15741425be982f035337cb287ddc27004001ffee7ef33aea90
3
+ size 14308
run-0/checkpoint-42/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dc713509705d8be350fc088c8f0b4ea97577a90703dee54859ed00a44aec89c
3
+ size 1064
run-0/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-0/checkpoint-42/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-0/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": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-0/checkpoint-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-0/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": 0.6425530314445496,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.6667,
16
+ "eval_samples_per_second": 1564.434,
17
+ "eval_steps_per_second": 98.996,
18
+ "step": 14
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6215561628341675,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7349,
25
+ "eval_samples_per_second": 1419.255,
26
+ "eval_steps_per_second": 89.809,
27
+ "step": 28
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6188336610794067,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.8898,
34
+ "eval_samples_per_second": 1172.174,
35
+ "eval_steps_per_second": 74.174,
36
+ "step": 42
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 42,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 3,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 64,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 5.9402286931455415e-06,
49
+ "num_train_epochs": 3,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 33
52
+ }
53
+ }
run-0/checkpoint-42/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3890eb403da684d0292db5dfdfff23f4d1c6bfee6a85697d4ee366d75565506
3
+ size 4984
run-0/checkpoint-42/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/checkpoint-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33679f62cde9c80bda0fa96f5b3301caa1d7f1d2e18a9696e715fc024c60e548
3
+ size 267832560
run-1/checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b3798e4eda2034d4177133ca6f2e516817f4c882c6eb0ffbdcd988bdda97519
3
+ size 535727290
run-1/checkpoint-54/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:156dca70f156dd4e17a1e78e5ba6c0e3ab4d562ab9db28a63fdbcdc968ddbcf4
3
+ size 14244
run-1/checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e402f08d469b0a4383f742e4a667e93cdbee1a5f97700a18999d30b6d69c7cac
3
+ size 1064
run-1/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-1/checkpoint-54/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/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-1/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-1/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": 0.6343640685081482,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.8541,
16
+ "eval_samples_per_second": 1221.137,
17
+ "eval_steps_per_second": 77.272,
18
+ "step": 54
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 54,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 1,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 16,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 5.55238341580637e-06,
31
+ "num_train_epochs": 1,
32
+ "per_device_train_batch_size": 16,
33
+ "seed": 34
34
+ }
35
+ }
run-1/checkpoint-54/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eed53a79aaf87d8828c834cf09964b5833fd0c0b84709c49a3b6f49a04be2f1
3
+ size 4984
run-1/checkpoint-54/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14425fcaecc2d46a7e64c553c7c0e03a8b0b899a83ea0d3963fb80be859c7eb1
3
+ size 267832560
run-2/checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07ae695ffdfeaac72f872617409a19fb5058475afe9daf1b332404d000ec6f69
3
+ size 535727290
run-2/checkpoint-54/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b572b27b244cd3dd989c9481fc02ee379dcdbaed97fcf14e8931c8b2ae832eb0
3
+ size 14244
run-2/checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:700c9106ecf3f8f32a5908730c0dcfadc0f2a4bcfa5fc4122d6a9f505e0c9f25
3
+ size 1064
run-2/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-2/checkpoint-54/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/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-2/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": 0.5949434041976929,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.6642,
16
+ "eval_samples_per_second": 1570.266,
17
+ "eval_steps_per_second": 99.365,
18
+ "step": 54
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 162,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 16,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 1.8548433860537384e-05,
31
+ "num_train_epochs": 3,
32
+ "per_device_train_batch_size": 16,
33
+ "seed": 19
34
+ }
35
+ }
run-2/checkpoint-54/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f43db310149dc85ff8b52f32f702ad0e0fc7c0abc14ab704372d592275b95932
3
+ size 4984
run-2/checkpoint-54/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb27_12-55-59_86e2730489af/events.out.tfevents.1709039850.86e2730489af.508.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62a6ca9aff3d0c35b1c0cb07046c037ff72a60c59ad44df3a9573e781daabe61
3
- size 5201
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:002278485c0813f7be8bc2039a5f9f1eb88e63a744c592c9d56745064cccb366
3
+ size 5878
runs/Feb27_12-55-59_86e2730489af/events.out.tfevents.1709039934.86e2730489af.508.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a521d5baa06fd6270432697322354ec5e97f724e81df9cacb1623602af2ab32
3
+ size 5218
runs/Feb27_12-55-59_86e2730489af/events.out.tfevents.1709039961.86e2730489af.508.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98cb53bc1663023c50ea8928aa925e2515ec107f298add4d2e24bbf8be8c20ac
3
+ size 5890
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f3890eb403da684d0292db5dfdfff23f4d1c6bfee6a85697d4ee366d75565506
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f43db310149dc85ff8b52f32f702ad0e0fc7c0abc14ab704372d592275b95932
3
  size 4984