Ethan615 commited on
Commit
81372bf
1 Parent(s): dc58b31

Training in progress, epoch 4

Browse files
Files changed (35) hide show
  1. model.safetensors +1 -1
  2. run-2/checkpoint-268/config.json +25 -0
  3. run-2/checkpoint-268/model.safetensors +3 -0
  4. run-2/checkpoint-268/optimizer.pt +3 -0
  5. run-2/checkpoint-268/rng_state.pth +3 -0
  6. run-2/checkpoint-268/scheduler.pt +3 -0
  7. run-2/checkpoint-268/special_tokens_map.json +7 -0
  8. run-2/checkpoint-268/tokenizer.json +0 -0
  9. run-2/checkpoint-268/tokenizer_config.json +55 -0
  10. run-2/checkpoint-268/trainer_state.json +44 -0
  11. run-2/checkpoint-268/training_args.bin +3 -0
  12. run-2/checkpoint-268/vocab.txt +0 -0
  13. run-2/checkpoint-402/config.json +25 -0
  14. run-2/checkpoint-402/model.safetensors +3 -0
  15. run-2/checkpoint-402/optimizer.pt +3 -0
  16. run-2/checkpoint-402/rng_state.pth +3 -0
  17. run-2/checkpoint-402/scheduler.pt +3 -0
  18. run-2/checkpoint-402/special_tokens_map.json +7 -0
  19. run-2/checkpoint-402/tokenizer.json +0 -0
  20. run-2/checkpoint-402/tokenizer_config.json +55 -0
  21. run-2/checkpoint-402/trainer_state.json +53 -0
  22. run-2/checkpoint-402/training_args.bin +3 -0
  23. run-2/checkpoint-402/vocab.txt +0 -0
  24. run-2/checkpoint-536/config.json +25 -0
  25. run-2/checkpoint-536/model.safetensors +3 -0
  26. run-2/checkpoint-536/optimizer.pt +3 -0
  27. run-2/checkpoint-536/rng_state.pth +3 -0
  28. run-2/checkpoint-536/scheduler.pt +3 -0
  29. run-2/checkpoint-536/special_tokens_map.json +7 -0
  30. run-2/checkpoint-536/tokenizer.json +0 -0
  31. run-2/checkpoint-536/tokenizer_config.json +55 -0
  32. run-2/checkpoint-536/trainer_state.json +69 -0
  33. run-2/checkpoint-536/training_args.bin +3 -0
  34. run-2/checkpoint-536/vocab.txt +0 -0
  35. runs/Apr05_13-35-05_48c5213de69d/events.out.tfevents.1712325354.48c5213de69d.790.4 +2 -2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70d9a7725f53d0ca883e7a5e2b9ea616e1226fe7197a8eac920a11635f181740
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac2b2c1a145f24819a84e968cce494decebe3f341e3aca22cd8aacdb7bda79a5
3
  size 267832560
run-2/checkpoint-268/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": "4.39.3",
24
+ "vocab_size": 30522
25
+ }
run-2/checkpoint-268/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f13a7f961564b7eff49d1c9bfffcd34201316e49e23aa346d2642c637532b86
3
+ size 267832560
run-2/checkpoint-268/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1bb5c61ff06709b73091430fc5de9c4d8491c5d56edaf92c78ee3383264641e
3
+ size 535727290
run-2/checkpoint-268/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efc4abb53cd320a4d5c0600074dbbd855bfb5f4dbd08bf03d9d4c7e64a9b9b0f
3
+ size 14244
run-2/checkpoint-268/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04aa76f4ea786876f22a648535ac11b72ff3e5687df4ad6b88baa9ec6ee430ca
3
+ size 1064
run-2/checkpoint-268/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-268/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-268/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-268/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-134",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 268,
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": 0.6129281520843506,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7848,
16
+ "eval_samples_per_second": 1329.021,
17
+ "eval_steps_per_second": 84.099,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5989838242530823,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.815,
25
+ "eval_samples_per_second": 1279.741,
26
+ "eval_steps_per_second": 80.981,
27
+ "step": 268
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 670,
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": 1.3930988519295147e-06,
40
+ "num_train_epochs": 5,
41
+ "per_device_train_batch_size": 64,
42
+ "seed": 39
43
+ }
44
+ }
run-2/checkpoint-268/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d32d1c75dfe216a11588ced994610f6025781f4b30aa859e060a5e0ac253b3f2
3
+ size 4984
run-2/checkpoint-268/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-402/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": "4.39.3",
24
+ "vocab_size": 30522
25
+ }
run-2/checkpoint-402/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:428283dbd55d6dca3262fa4f24adb028b89d1c884fe897e9f936e055b806ebde
3
+ size 267832560
run-2/checkpoint-402/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:377045ef3494aafdeaf68734fb4de11aaa71c8491f62ee92b2d7853fb811419a
3
+ size 535727290
run-2/checkpoint-402/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcb74ecc9f51c18d74ab6a9cc0f77d0b9f5230d27eb10037a7b6ef42aaa3608d
3
+ size 14244
run-2/checkpoint-402/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8277bf9b61a431e0ffb650fe380264fcd571e4abd660ba97ee2dcf1c45b48d83
3
+ size 1064
run-2/checkpoint-402/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-402/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-402/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-402/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-134",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 402,
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": 0.6129281520843506,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7848,
16
+ "eval_samples_per_second": 1329.021,
17
+ "eval_steps_per_second": 84.099,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5989838242530823,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.815,
25
+ "eval_samples_per_second": 1279.741,
26
+ "eval_steps_per_second": 80.981,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5856398344039917,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 1.2157,
34
+ "eval_samples_per_second": 857.939,
35
+ "eval_steps_per_second": 54.29,
36
+ "step": 402
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 670,
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": 1.3930988519295147e-06,
49
+ "num_train_epochs": 5,
50
+ "per_device_train_batch_size": 64,
51
+ "seed": 39
52
+ }
53
+ }
run-2/checkpoint-402/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d32d1c75dfe216a11588ced994610f6025781f4b30aa859e060a5e0ac253b3f2
3
+ size 4984
run-2/checkpoint-402/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-536/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "pad_token_id": 0,
17
+ "problem_type": "single_label_classification",
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": false,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.39.3",
24
+ "vocab_size": 30522
25
+ }
run-2/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac2b2c1a145f24819a84e968cce494decebe3f341e3aca22cd8aacdb7bda79a5
3
+ size 267832560
run-2/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5fe2db289dbd8f6c812f57fb8e8d04d7d05dc9d0958c015757d24c9af8fb6e
3
+ size 535727290
run-2/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d517de88a01b96ddbfa1773e2f5c2f0503365519d4e696a4a2f3e16723931886
3
+ size 14244
run-2/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baadeeaed0a84b880c7bd4ce915abbec5809946ee5e262c2d9dd0945ecb049c5
3
+ size 1064
run-2/checkpoint-536/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-2/checkpoint-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-536/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-2/checkpoint-536/trainer_state.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-134",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 536,
7
+ "is_hyper_param_search": true,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_loss": 0.6129281520843506,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7848,
16
+ "eval_samples_per_second": 1329.021,
17
+ "eval_steps_per_second": 84.099,
18
+ "step": 134
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5989838242530823,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.815,
25
+ "eval_samples_per_second": 1279.741,
26
+ "eval_steps_per_second": 80.981,
27
+ "step": 268
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5856398344039917,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 1.2157,
34
+ "eval_samples_per_second": 857.939,
35
+ "eval_steps_per_second": 54.29,
36
+ "step": 402
37
+ },
38
+ {
39
+ "epoch": 3.73,
40
+ "grad_norm": 1.4250954389572144,
41
+ "learning_rate": 3.534728430268918e-07,
42
+ "loss": 0.5971,
43
+ "step": 500
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_loss": 0.5745069980621338,
48
+ "eval_matthews_correlation": 0.0,
49
+ "eval_runtime": 0.7598,
50
+ "eval_samples_per_second": 1372.813,
51
+ "eval_steps_per_second": 86.87,
52
+ "step": 536
53
+ }
54
+ ],
55
+ "logging_steps": 500,
56
+ "max_steps": 670,
57
+ "num_input_tokens_seen": 0,
58
+ "num_train_epochs": 5,
59
+ "save_steps": 500,
60
+ "total_flos": 209241052840344.0,
61
+ "train_batch_size": 64,
62
+ "trial_name": null,
63
+ "trial_params": {
64
+ "learning_rate": 1.3930988519295147e-06,
65
+ "num_train_epochs": 5,
66
+ "per_device_train_batch_size": 64,
67
+ "seed": 39
68
+ }
69
+ }
run-2/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d32d1c75dfe216a11588ced994610f6025781f4b30aa859e060a5e0ac253b3f2
3
+ size 4984
run-2/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Apr05_13-35-05_48c5213de69d/events.out.tfevents.1712325354.48c5213de69d.790.4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1405d3e3ec0996221661787e87884562db4df170fc77bf20795c888334cbd36a
3
- size 5264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c58e51005ced90dae48d3288a442fea0319141306194f28b30fa97234bb527a
3
+ size 6834