Hugging Face's logo

AilingDAI
/
HM_1

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Metrics Community
AilingDAI commited on
Commit
27d3d6f
·
verified ·
1 Parent(s): 70aa73b

Training in progress, epoch 1

Browse files
Files changed (37) hide show
  1. model.safetensors +1 -1
  2. run-3/checkpoint-536/config.json +25 -0
  3. run-3/checkpoint-536/model.safetensors +3 -0
  4. run-3/checkpoint-536/optimizer.pt +3 -0
  5. run-3/checkpoint-536/rng_state.pth +3 -0
  6. run-3/checkpoint-536/scheduler.pt +3 -0
  7. run-3/checkpoint-536/special_tokens_map.json +7 -0
  8. run-3/checkpoint-536/tokenizer.json +0 -0
  9. run-3/checkpoint-536/tokenizer_config.json +55 -0
  10. run-3/checkpoint-536/trainer_state.json +51 -0
  11. run-3/checkpoint-536/training_args.bin +3 -0
  12. run-3/checkpoint-536/vocab.txt +0 -0
  13. run-3/checkpoint-804/config.json +25 -0
  14. run-3/checkpoint-804/model.safetensors +3 -0
  15. run-3/checkpoint-804/optimizer.pt +3 -0
  16. run-3/checkpoint-804/rng_state.pth +3 -0
  17. run-3/checkpoint-804/scheduler.pt +3 -0
  18. run-3/checkpoint-804/special_tokens_map.json +7 -0
  19. run-3/checkpoint-804/tokenizer.json +0 -0
  20. run-3/checkpoint-804/tokenizer_config.json +55 -0
  21. run-3/checkpoint-804/trainer_state.json +60 -0
  22. run-3/checkpoint-804/training_args.bin +3 -0
  23. run-3/checkpoint-804/vocab.txt +0 -0
  24. run-4/checkpoint-134/config.json +25 -0
  25. run-4/checkpoint-134/model.safetensors +3 -0
  26. run-4/checkpoint-134/optimizer.pt +3 -0
  27. run-4/checkpoint-134/rng_state.pth +3 -0
  28. run-4/checkpoint-134/scheduler.pt +3 -0
  29. run-4/checkpoint-134/special_tokens_map.json +7 -0
  30. run-4/checkpoint-134/tokenizer.json +0 -0
  31. run-4/checkpoint-134/tokenizer_config.json +55 -0
  32. run-4/checkpoint-134/trainer_state.json +35 -0
  33. run-4/checkpoint-134/training_args.bin +3 -0
  34. run-4/checkpoint-134/vocab.txt +0 -0
  35. runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711160674.52e0cb6c1736.459.5 +2 -2
  36. runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711160778.52e0cb6c1736.459.6 +3 -0
  37. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:726756e6aaf8542a88d22eac44451c6a7c584ddeb956346d43e9bf36b2e8c311
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9113d76ba545fb086fb6a5e9e3fc213529275493d8432e21f9e80dab7fab4bca
3
  size 267832560
run-3/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": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-3/checkpoint-536/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec86e47b9208e0271d72aac635c2553d0a69623bcae3c419cc9d9e070530ec7
3
+ size 267832560
run-3/checkpoint-536/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:986f7d97757f9b537d44386b83f77f9fe3b8e1ae218c66f72c18bcd57f5186ea
3
+ size 535727290
run-3/checkpoint-536/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:177c3e13ba89dd3c772846b45ea81c44af694521955ca0ef000c19bacf8bc619
3
+ size 14244
run-3/checkpoint-536/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f27f2cfb1a916fc142d060affb292f12f715f22cc95760fab1ec78531b28e56
3
+ size 1064
run-3/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-3/checkpoint-536/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-536/trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.3636302567913777,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-536",
4
+ "epoch": 2.0,
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": 0.5497495532035828,
14
+ "eval_matthews_correlation": 0.0928457264044978,
15
+ "eval_runtime": 0.7621,
16
+ "eval_samples_per_second": 1368.64,
17
+ "eval_steps_per_second": 86.606,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "grad_norm": 3.906301498413086,
23
+ "learning_rate": 1.5090673992837595e-06,
24
+ "loss": 0.5538,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_loss": 0.5196466445922852,
30
+ "eval_matthews_correlation": 0.3636302567913777,
31
+ "eval_runtime": 1.0628,
32
+ "eval_samples_per_second": 981.371,
33
+ "eval_steps_per_second": 62.1,
34
+ "step": 536
35
+ }
36
+ ],
37
+ "logging_steps": 500,
38
+ "max_steps": 804,
39
+ "num_input_tokens_seen": 0,
40
+ "num_train_epochs": 3,
41
+ "save_steps": 500,
42
+ "total_flos": 96158136429468.0,
43
+ "train_batch_size": 32,
44
+ "trial_name": null,
45
+ "trial_params": {
46
+ "learning_rate": 3.9910861481057325e-06,
47
+ "num_train_epochs": 3,
48
+ "per_device_train_batch_size": 32,
49
+ "seed": 19
50
+ }
51
+ }
run-3/checkpoint-536/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd40e13ada81b097b394cc550acc79b74483a245c86a38ab12015892bd5ce555
3
+ size 4984
run-3/checkpoint-536/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-804/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": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-3/checkpoint-804/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a97a41001ef6e895b020a2a12ec2f2cefd7fe8aedb18e81e17f08dccf20c3eb7
3
+ size 267832560
run-3/checkpoint-804/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ad581c724102953af4dcdfd78cec5fb6556db19c0a8a90d2ddd8560efc80e64
3
+ size 535727290
run-3/checkpoint-804/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:043d33b191b85d29becc8fc90cd248cf23846723a95a87c12bd765c7348a4904
3
+ size 14244
run-3/checkpoint-804/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e608cf97231afcef17a07f83244ca9a201a8612a018b106874405cb95a982767
3
+ size 1064
run-3/checkpoint-804/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-3/checkpoint-804/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-804/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-3/checkpoint-804/trainer_state.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4033324209850535,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-804",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 804,
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": 0.5497495532035828,
14
+ "eval_matthews_correlation": 0.0928457264044978,
15
+ "eval_runtime": 0.7621,
16
+ "eval_samples_per_second": 1368.64,
17
+ "eval_steps_per_second": 86.606,
18
+ "step": 268
19
+ },
20
+ {
21
+ "epoch": 1.87,
22
+ "grad_norm": 3.906301498413086,
23
+ "learning_rate": 1.5090673992837595e-06,
24
+ "loss": 0.5538,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_loss": 0.5196466445922852,
30
+ "eval_matthews_correlation": 0.3636302567913777,
31
+ "eval_runtime": 1.0628,
32
+ "eval_samples_per_second": 981.371,
33
+ "eval_steps_per_second": 62.1,
34
+ "step": 536
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_loss": 0.5164278745651245,
39
+ "eval_matthews_correlation": 0.4033324209850535,
40
+ "eval_runtime": 0.8583,
41
+ "eval_samples_per_second": 1215.213,
42
+ "eval_steps_per_second": 76.897,
43
+ "step": 804
44
+ }
45
+ ],
46
+ "logging_steps": 500,
47
+ "max_steps": 804,
48
+ "num_input_tokens_seen": 0,
49
+ "num_train_epochs": 3,
50
+ "save_steps": 500,
51
+ "total_flos": 96158136429468.0,
52
+ "train_batch_size": 32,
53
+ "trial_name": null,
54
+ "trial_params": {
55
+ "learning_rate": 3.9910861481057325e-06,
56
+ "num_train_epochs": 3,
57
+ "per_device_train_batch_size": 32,
58
+ "seed": 19
59
+ }
60
+ }
run-3/checkpoint-804/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd40e13ada81b097b394cc550acc79b74483a245c86a38ab12015892bd5ce555
3
+ size 4984
run-3/checkpoint-804/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-134/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": "4.39.1",
24
+ "vocab_size": 30522
25
+ }
run-4/checkpoint-134/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9113d76ba545fb086fb6a5e9e3fc213529275493d8432e21f9e80dab7fab4bca
3
+ size 267832560
run-4/checkpoint-134/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b0106ff33b59455777abc2985d6ec13b640c6c055e4b7864d7fd5bbc451f140
3
+ size 535727290
run-4/checkpoint-134/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a208b40e2f0aa886fa15a4a55da06d4448874802d6825c61697aad10fba501f
3
+ size 14244
run-4/checkpoint-134/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25e9ff4ba45e6cdf15ab862ba9ffc5d5aba0cbfe1a4fe2f92274174a2fa1c312
3
+ size 1064
run-4/checkpoint-134/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-4/checkpoint-134/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-4/checkpoint-134/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-4/checkpoint-134/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.46741180953359257,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-4/checkpoint-134",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 134,
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": 0.46314120292663574,
14
+ "eval_matthews_correlation": 0.46741180953359257,
15
+ "eval_runtime": 0.803,
16
+ "eval_samples_per_second": 1298.905,
17
+ "eval_steps_per_second": 82.193,
18
+ "step": 134
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 536,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 4,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 64,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 3.0100334336501613e-05,
31
+ "num_train_epochs": 4,
32
+ "per_device_train_batch_size": 64,
33
+ "seed": 15
34
+ }
35
+ }
run-4/checkpoint-134/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:151c174a2ffa585401c97ac1e4a204237f812a0791c32e61c4a49909b4de743c
3
+ size 4984
run-4/checkpoint-134/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711160674.52e0cb6c1736.459.5 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98dc32f1d21d64e305220d1f19bbf48e78925b3924e07befcaa6dc93ec8555f5
3
- size 5468
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:221b7f8b1ab52ae3502aade6819ee253fba3e44c2dd768925bfb9e3cd02ce721
3
+ size 6157
runs/Mar23_02-10-25_52e0cb6c1736/events.out.tfevents.1711160778.52e0cb6c1736.459.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1bfa42faf095e3a82012afdd6ffa95f28ab919fa083b87ca26775225fc933e1
3
+ size 6492
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd40e13ada81b097b394cc550acc79b74483a245c86a38ab12015892bd5ce555
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:151c174a2ffa585401c97ac1e4a204237f812a0791c32e61c4a49909b4de743c
3
  size 4984