Giuggiola01 commited on
Commit
35ae64e
·
verified ·
1 Parent(s): 9ae084c

Training in progress, epoch 1

Browse files
Files changed (48) hide show
  1. model.safetensors +1 -1
  2. run-1/checkpoint-428/config.json +25 -0
  3. run-1/checkpoint-428/model.safetensors +3 -0
  4. run-1/checkpoint-428/optimizer.pt +3 -0
  5. run-1/checkpoint-428/rng_state.pth +3 -0
  6. run-1/checkpoint-428/scheduler.pt +3 -0
  7. run-1/checkpoint-428/special_tokens_map.json +7 -0
  8. run-1/checkpoint-428/tokenizer.json +0 -0
  9. run-1/checkpoint-428/tokenizer_config.json +55 -0
  10. run-1/checkpoint-428/trainer_state.json +44 -0
  11. run-1/checkpoint-428/training_args.bin +3 -0
  12. run-1/checkpoint-428/vocab.txt +0 -0
  13. run-1/checkpoint-642/config.json +25 -0
  14. run-1/checkpoint-642/model.safetensors +3 -0
  15. run-1/checkpoint-642/optimizer.pt +3 -0
  16. run-1/checkpoint-642/rng_state.pth +3 -0
  17. run-1/checkpoint-642/scheduler.pt +3 -0
  18. run-1/checkpoint-642/special_tokens_map.json +7 -0
  19. run-1/checkpoint-642/tokenizer.json +0 -0
  20. run-1/checkpoint-642/tokenizer_config.json +55 -0
  21. run-1/checkpoint-642/trainer_state.json +60 -0
  22. run-1/checkpoint-642/training_args.bin +3 -0
  23. run-1/checkpoint-642/vocab.txt +0 -0
  24. run-1/checkpoint-856/config.json +25 -0
  25. run-1/checkpoint-856/model.safetensors +3 -0
  26. run-1/checkpoint-856/optimizer.pt +3 -0
  27. run-1/checkpoint-856/rng_state.pth +3 -0
  28. run-1/checkpoint-856/scheduler.pt +3 -0
  29. run-1/checkpoint-856/special_tokens_map.json +7 -0
  30. run-1/checkpoint-856/tokenizer.json +0 -0
  31. run-1/checkpoint-856/tokenizer_config.json +55 -0
  32. run-1/checkpoint-856/trainer_state.json +69 -0
  33. run-1/checkpoint-856/training_args.bin +3 -0
  34. run-1/checkpoint-856/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_12-32-24_dc4ea0da08d6/events.out.tfevents.1709039478.dc4ea0da08d6.176.3 +2 -2
  47. runs/Feb27_12-32-24_dc4ea0da08d6/events.out.tfevents.1709039564.dc4ea0da08d6.176.4 +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 sha256:69a5b49e354618c7472b677e5eafedef3d735cbf11e2a8a1f7b232618ccf5747
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:381cb647ef8dadaf274186a4b1150150019bf4448b65ce08a309ed951bec1b86
3
  size 267832560
run-1/checkpoint-428/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-428/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b0a94471ff0e5fb79a887e6467df0871697af667de6a40d0c63ead40e23fe0f
3
+ size 267832560
run-1/checkpoint-428/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25579796c7f569ef23cd23c8487ef8d1dc9be91e125918ea9253fb657d1a8d88
3
+ size 535727290
run-1/checkpoint-428/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f4cea2ee955619386e87d1101293dcc33776b3bfa9431398682c432a8cb919
3
+ size 14244
run-1/checkpoint-428/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba39d8015d120b10d80912569bc9423bd0215f29cddafc2b92449fcbdf1de81a
3
+ size 1064
run-1/checkpoint-428/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-428/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-428/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-428/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0463559874942472,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-428",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 428,
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": 0.6059978604316711,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.8427,
16
+ "eval_samples_per_second": 1237.647,
17
+ "eval_steps_per_second": 78.317,
18
+ "step": 214
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6243721842765808,
23
+ "eval_matthews_correlation": 0.0463559874942472,
24
+ "eval_runtime": 0.7667,
25
+ "eval_samples_per_second": 1360.34,
26
+ "eval_steps_per_second": 86.081,
27
+ "step": 428
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 856,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 4,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 5.197631194907433e-06,
40
+ "num_train_epochs": 4,
41
+ "per_device_train_batch_size": 4,
42
+ "seed": 22
43
+ }
44
+ }
run-1/checkpoint-428/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00aad8bf64b0fdf0d8f8d5afc23c306106d82e3ecc925c87e056001a15d8866c
3
+ size 4984
run-1/checkpoint-428/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-642/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-642/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e42a335a333f310344b44c027a0e8244a24781fe3ac20748b572e68cf52175c
3
+ size 267832560
run-1/checkpoint-642/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c049796891b1406aee03878acb82a7ac9d67623c9ea7aac867268d766747ad5b
3
+ size 535727290
run-1/checkpoint-642/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ec9265b75286abf3d2ceb4874ce2d3cb99a15cfe998e20d9b987ed976a37e7d
3
+ size 14244
run-1/checkpoint-642/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79451fe523e626ec20d1472517e8fe629ca7c6168a967eb59ea4c130f9a7d1e1
3
+ size 1064
run-1/checkpoint-642/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-642/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-642/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-642/trainer_state.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.18197557342971335,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-642",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 642,
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": 0.6059978604316711,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.8427,
16
+ "eval_samples_per_second": 1237.647,
17
+ "eval_steps_per_second": 78.317,
18
+ "step": 214
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6243721842765808,
23
+ "eval_matthews_correlation": 0.0463559874942472,
24
+ "eval_runtime": 0.7667,
25
+ "eval_samples_per_second": 1360.34,
26
+ "eval_steps_per_second": 86.081,
27
+ "step": 428
28
+ },
29
+ {
30
+ "epoch": 2.34,
31
+ "grad_norm": 4.93717098236084,
32
+ "learning_rate": 2.1616316651717827e-06,
33
+ "loss": 0.5871,
34
+ "step": 500
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_loss": 0.5885143280029297,
39
+ "eval_matthews_correlation": 0.18197557342971335,
40
+ "eval_runtime": 0.7645,
41
+ "eval_samples_per_second": 1364.229,
42
+ "eval_steps_per_second": 86.327,
43
+ "step": 642
44
+ }
45
+ ],
46
+ "logging_steps": 500,
47
+ "max_steps": 856,
48
+ "num_input_tokens_seen": 0,
49
+ "num_train_epochs": 4,
50
+ "save_steps": 500,
51
+ "total_flos": 8278177514448.0,
52
+ "train_batch_size": 4,
53
+ "trial_name": null,
54
+ "trial_params": {
55
+ "learning_rate": 5.197631194907433e-06,
56
+ "num_train_epochs": 4,
57
+ "per_device_train_batch_size": 4,
58
+ "seed": 22
59
+ }
60
+ }
run-1/checkpoint-642/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00aad8bf64b0fdf0d8f8d5afc23c306106d82e3ecc925c87e056001a15d8866c
3
+ size 4984
run-1/checkpoint-642/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-856/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-856/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1b72c69a8791eee9d6c60c70ca9be3eff2286b94685b766a140405f5ba2efce
3
+ size 267832560
run-1/checkpoint-856/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c472c3b0e448d1877505997ed1ca22f34da28bd55a0467cba458ca40732eb31
3
+ size 535727290
run-1/checkpoint-856/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c36b07af6f385afe1e30deda996eec260214f5bbacc0638c16e3be43cf8ef20
3
+ size 14244
run-1/checkpoint-856/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:634f04ff21e38fad76f252cde08a32f58484411e8ab3499fdd4d73e78c2e15b5
3
+ size 1064
run-1/checkpoint-856/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-856/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-856/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-856/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.2445258947660564,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-856",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 856,
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": 0.6059978604316711,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.8427,
16
+ "eval_samples_per_second": 1237.647,
17
+ "eval_steps_per_second": 78.317,
18
+ "step": 214
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6243721842765808,
23
+ "eval_matthews_correlation": 0.0463559874942472,
24
+ "eval_runtime": 0.7667,
25
+ "eval_samples_per_second": 1360.34,
26
+ "eval_steps_per_second": 86.081,
27
+ "step": 428
28
+ },
29
+ {
30
+ "epoch": 2.34,
31
+ "grad_norm": 4.93717098236084,
32
+ "learning_rate": 2.1616316651717827e-06,
33
+ "loss": 0.5871,
34
+ "step": 500
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_loss": 0.5885143280029297,
39
+ "eval_matthews_correlation": 0.18197557342971335,
40
+ "eval_runtime": 0.7645,
41
+ "eval_samples_per_second": 1364.229,
42
+ "eval_steps_per_second": 86.327,
43
+ "step": 642
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_loss": 0.5947996973991394,
48
+ "eval_matthews_correlation": 0.2445258947660564,
49
+ "eval_runtime": 1.3384,
50
+ "eval_samples_per_second": 779.315,
51
+ "eval_steps_per_second": 49.314,
52
+ "step": 856
53
+ }
54
+ ],
55
+ "logging_steps": 500,
56
+ "max_steps": 856,
57
+ "num_input_tokens_seen": 0,
58
+ "num_train_epochs": 4,
59
+ "save_steps": 500,
60
+ "total_flos": 8278177514448.0,
61
+ "train_batch_size": 4,
62
+ "trial_name": null,
63
+ "trial_params": {
64
+ "learning_rate": 5.197631194907433e-06,
65
+ "num_train_epochs": 4,
66
+ "per_device_train_batch_size": 4,
67
+ "seed": 22
68
+ }
69
+ }
run-1/checkpoint-856/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00aad8bf64b0fdf0d8f8d5afc23c306106d82e3ecc925c87e056001a15d8866c
3
+ size 4984
run-1/checkpoint-856/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 sha256:381cb647ef8dadaf274186a4b1150150019bf4448b65ce08a309ed951bec1b86
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 sha256:90d9d73fbe71c39e143f09fae0deb802a48af4083c0db6b17a67b53b68838f4e
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 sha256:0a74ac3e4252a439bb91fbfbcf6b2c0960fb674021010d4ffa5db1893512fd83
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 sha256:60fa2cf7bef815364a476e6ca62406f14aa8b0c01de28c7cf7e9b084153c6f58
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": 0.5795422792434692,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.6891,
16
+ "eval_samples_per_second": 1513.519,
17
+ "eval_steps_per_second": 95.774,
18
+ "step": 54
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 216,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 16,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 3.925782760210966e-05,
31
+ "num_train_epochs": 4,
32
+ "per_device_train_batch_size": 16,
33
+ "seed": 38
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:a3f8086ee62144e63e320118ca61e3aefafa0f68734de134db0bd4f27cff0598
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_12-32-24_dc4ea0da08d6/events.out.tfevents.1709039478.dc4ea0da08d6.176.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4d20187723ccf2360aa976d66416a1d24e2fffab12b602c640b79960f44797d
3
- size 5757
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2cb40b3bf4182320950db34456c0723f5067e589bd017fb47bb7bb89074677a
3
+ size 6446
runs/Feb27_12-32-24_dc4ea0da08d6/events.out.tfevents.1709039564.dc4ea0da08d6.176.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c1526b25d730c15d32dec1fb9ba9ffec6fd9c988e0ed0a2c053707b0a7b4b99
3
+ size 6224
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00aad8bf64b0fdf0d8f8d5afc23c306106d82e3ecc925c87e056001a15d8866c
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3f8086ee62144e63e320118ca61e3aefafa0f68734de134db0bd4f27cff0598
3
  size 4984