karunac commited on
Commit
4b10c0c
·
verified ·
1 Parent(s): cddc72e

Training in progress, epoch 1

Browse files
Files changed (47) hide show
  1. model.safetensors +1 -1
  2. run-9/checkpoint-14/config.json +25 -0
  3. run-9/checkpoint-14/model.safetensors +3 -0
  4. run-9/checkpoint-14/optimizer.pt +3 -0
  5. run-9/checkpoint-14/rng_state.pth +3 -0
  6. run-9/checkpoint-14/scheduler.pt +3 -0
  7. run-9/checkpoint-14/special_tokens_map.json +7 -0
  8. run-9/checkpoint-14/tokenizer.json +0 -0
  9. run-9/checkpoint-14/tokenizer_config.json +55 -0
  10. run-9/checkpoint-14/trainer_state.json +44 -0
  11. run-9/checkpoint-14/training_args.bin +3 -0
  12. run-9/checkpoint-14/vocab.txt +0 -0
  13. run-9/checkpoint-21/config.json +25 -0
  14. run-9/checkpoint-21/model.safetensors +3 -0
  15. run-9/checkpoint-21/optimizer.pt +3 -0
  16. run-9/checkpoint-21/rng_state.pth +3 -0
  17. run-9/checkpoint-21/scheduler.pt +3 -0
  18. run-9/checkpoint-21/special_tokens_map.json +7 -0
  19. run-9/checkpoint-21/tokenizer.json +0 -0
  20. run-9/checkpoint-21/tokenizer_config.json +55 -0
  21. run-9/checkpoint-21/trainer_state.json +53 -0
  22. run-9/checkpoint-21/training_args.bin +3 -0
  23. run-9/checkpoint-21/vocab.txt +0 -0
  24. run-9/checkpoint-28/config.json +25 -0
  25. run-9/checkpoint-28/model.safetensors +3 -0
  26. run-9/checkpoint-28/optimizer.pt +3 -0
  27. run-9/checkpoint-28/rng_state.pth +3 -0
  28. run-9/checkpoint-28/scheduler.pt +3 -0
  29. run-9/checkpoint-28/special_tokens_map.json +7 -0
  30. run-9/checkpoint-28/tokenizer.json +0 -0
  31. run-9/checkpoint-28/tokenizer_config.json +55 -0
  32. run-9/checkpoint-28/trainer_state.json +62 -0
  33. run-9/checkpoint-28/training_args.bin +3 -0
  34. run-9/checkpoint-28/vocab.txt +0 -0
  35. run-9/checkpoint-35/config.json +25 -0
  36. run-9/checkpoint-35/model.safetensors +3 -0
  37. run-9/checkpoint-35/optimizer.pt +3 -0
  38. run-9/checkpoint-35/rng_state.pth +3 -0
  39. run-9/checkpoint-35/scheduler.pt +3 -0
  40. run-9/checkpoint-35/special_tokens_map.json +7 -0
  41. run-9/checkpoint-35/tokenizer.json +0 -0
  42. run-9/checkpoint-35/tokenizer_config.json +55 -0
  43. run-9/checkpoint-35/trainer_state.json +71 -0
  44. run-9/checkpoint-35/training_args.bin +3 -0
  45. run-9/checkpoint-35/vocab.txt +0 -0
  46. runs/Mar05_15-34-07_d253bcf50e04/events.out.tfevents.1709655147.d253bcf50e04.1525.13 +3 -0
  47. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caec63192e29947701432ef3df04ccf6146e588c613f76d086776be073df0124
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f60fd24bca88e4c6dc9c059bdff977f562836103dd535460d081164ba75573bb
3
  size 267832560
run-9/checkpoint-14/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-9/checkpoint-14/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:337a47d9c36125176e17e60a21d918c5b005a7ec89efe74ff46197b1361331bc
3
+ size 267832560
run-9/checkpoint-14/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2757981053e620ff74e305da8c98c0c226085badf9e40ce1935733adbcb0bc7c
3
+ size 535724410
run-9/checkpoint-14/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c9c28382a79b8625cf88b59966d56273f992421ef47f251ebf101f3fcae6bc4
3
+ size 13990
run-9/checkpoint-14/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d575429d873f18283718537aa8e207d5c4af13bbfeb8cba4ecbc41c19f90fa2
3
+ size 1064
run-9/checkpoint-14/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-14/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-14/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-14/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-7",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 14,
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": 0.6760221123695374,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 3.3857,
16
+ "eval_samples_per_second": 29.536,
17
+ "eval_steps_per_second": 2.068,
18
+ "step": 7
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6726043820381165,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 6.7172,
25
+ "eval_samples_per_second": 14.887,
26
+ "eval_steps_per_second": 1.042,
27
+ "step": 14
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 35,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 5,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 32,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 1.8071792757343938e-06,
40
+ "num_train_epochs": 5,
41
+ "per_device_train_batch_size": 32,
42
+ "seed": 10
43
+ }
44
+ }
run-9/checkpoint-14/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af94058e72f387c0df78403dd98e2cb7618eece96024a04aa046348c0b89ddf0
3
+ size 4984
run-9/checkpoint-14/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-21/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-9/checkpoint-21/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aa88b9532873f92136d32425901e16e67e330c3e3ae9fb10f7a32bcbfb3e4f8
3
+ size 267832560
run-9/checkpoint-21/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0249e5086858d4d9e7d7a5e6e83cf5f5ddd4f3d49730581f61d7b525339432e1
3
+ size 535724410
run-9/checkpoint-21/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1fe3d199e29fac82705fa07ccbf988ef9815bed0c0610306d60cda77fe5a4bc
3
+ size 13990
run-9/checkpoint-21/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a444b1c472be786fd0726d47c3c463b1077e00196b43a971af5f80bea2faf41e
3
+ size 1064
run-9/checkpoint-21/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-21/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-21/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-21/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-7",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 21,
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": 0.6760221123695374,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 3.3857,
16
+ "eval_samples_per_second": 29.536,
17
+ "eval_steps_per_second": 2.068,
18
+ "step": 7
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6726043820381165,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 6.7172,
25
+ "eval_samples_per_second": 14.887,
26
+ "eval_steps_per_second": 1.042,
27
+ "step": 14
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6705675721168518,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 6.0494,
34
+ "eval_samples_per_second": 16.53,
35
+ "eval_steps_per_second": 1.157,
36
+ "step": 21
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 35,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 5,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 32,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 1.8071792757343938e-06,
49
+ "num_train_epochs": 5,
50
+ "per_device_train_batch_size": 32,
51
+ "seed": 10
52
+ }
53
+ }
run-9/checkpoint-21/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af94058e72f387c0df78403dd98e2cb7618eece96024a04aa046348c0b89ddf0
3
+ size 4984
run-9/checkpoint-21/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/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-9/checkpoint-28/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae131a1afd797e81ce301db6b6bae6bafc3b0f4d261f85b68bf0ed012f399cab
3
+ size 267832560
run-9/checkpoint-28/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071a3d3fa417c4fa1b0620e11322bfb36a8f731256011a6972f3b1a51f309c39
3
+ size 535724410
run-9/checkpoint-28/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d899a008237fa7fd4dc1f9a412f417a1b6fab13cd2abe5a02953529b11d43677
3
+ size 13990
run-9/checkpoint-28/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea6c34e97e944f58910637611993266bfce8d878601aa764f94ad9f31eca203a
3
+ size 1064
run-9/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-9/checkpoint-28/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/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-9/checkpoint-28/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-7",
4
+ "epoch": 4.0,
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": 0.6760221123695374,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 3.3857,
16
+ "eval_samples_per_second": 29.536,
17
+ "eval_steps_per_second": 2.068,
18
+ "step": 7
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6726043820381165,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 6.7172,
25
+ "eval_samples_per_second": 14.887,
26
+ "eval_steps_per_second": 1.042,
27
+ "step": 14
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6705675721168518,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 6.0494,
34
+ "eval_samples_per_second": 16.53,
35
+ "eval_steps_per_second": 1.157,
36
+ "step": 21
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.669508159160614,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 5.5552,
43
+ "eval_samples_per_second": 18.001,
44
+ "eval_steps_per_second": 1.26,
45
+ "step": 28
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 35,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 5,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 32,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 1.8071792757343938e-06,
58
+ "num_train_epochs": 5,
59
+ "per_device_train_batch_size": 32,
60
+ "seed": 10
61
+ }
62
+ }
run-9/checkpoint-28/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af94058e72f387c0df78403dd98e2cb7618eece96024a04aa046348c0b89ddf0
3
+ size 4984
run-9/checkpoint-28/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-35/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-9/checkpoint-35/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:232ff1c6241589da2372f216926f4cbd34055ea3ab9644e4c40020c4a5a1d95e
3
+ size 267832560
run-9/checkpoint-35/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c774a202a5c95e52218bcb75e3c0b05fa162bbf2f83257fde17517d2da7fe8e1
3
+ size 535724410
run-9/checkpoint-35/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:017402b81e5261c53ef70be696779a988d56eb8aad82092ff6715bf8c6fc58ca
3
+ size 13990
run-9/checkpoint-35/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de8cd4b1d67626429547c4446e61e8a51b2141d59491be4d2c3f2af70651280a
3
+ size 1064
run-9/checkpoint-35/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-35/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-9/checkpoint-35/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-35/trainer_state.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-9/checkpoint-7",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 35,
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": 0.6760221123695374,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 3.3857,
16
+ "eval_samples_per_second": 29.536,
17
+ "eval_steps_per_second": 2.068,
18
+ "step": 7
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6726043820381165,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 6.7172,
25
+ "eval_samples_per_second": 14.887,
26
+ "eval_steps_per_second": 1.042,
27
+ "step": 14
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6705675721168518,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 6.0494,
34
+ "eval_samples_per_second": 16.53,
35
+ "eval_steps_per_second": 1.157,
36
+ "step": 21
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.669508159160614,
41
+ "eval_matthews_correlation": 0.0,
42
+ "eval_runtime": 5.5552,
43
+ "eval_samples_per_second": 18.001,
44
+ "eval_steps_per_second": 1.26,
45
+ "step": 28
46
+ },
47
+ {
48
+ "epoch": 5.0,
49
+ "eval_loss": 0.669070839881897,
50
+ "eval_matthews_correlation": 0.0,
51
+ "eval_runtime": 5.7869,
52
+ "eval_samples_per_second": 17.28,
53
+ "eval_steps_per_second": 1.21,
54
+ "step": 35
55
+ }
56
+ ],
57
+ "logging_steps": 500,
58
+ "max_steps": 35,
59
+ "num_input_tokens_seen": 0,
60
+ "num_train_epochs": 5,
61
+ "save_steps": 500,
62
+ "total_flos": 0,
63
+ "train_batch_size": 32,
64
+ "trial_name": null,
65
+ "trial_params": {
66
+ "learning_rate": 1.8071792757343938e-06,
67
+ "num_train_epochs": 5,
68
+ "per_device_train_batch_size": 32,
69
+ "seed": 10
70
+ }
71
+ }
run-9/checkpoint-35/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af94058e72f387c0df78403dd98e2cb7618eece96024a04aa046348c0b89ddf0
3
+ size 4984
run-9/checkpoint-35/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar05_15-34-07_d253bcf50e04/events.out.tfevents.1709655147.d253bcf50e04.1525.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62f73c4b39da512533dbea699a12b511d816587be63a2ffa0a9351a7d25e56cb
3
+ size 5549
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af94058e72f387c0df78403dd98e2cb7618eece96024a04aa046348c0b89ddf0
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48e8f93936b56d4497b52c2e09a31abe44e6174d766f7ddfba45dcda5565ac1
3
  size 4984