Hugging Face's logo

SjardiWillems
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
SjardiWillems commited on
Commit
ced918e
·
verified ·
1 Parent(s): d6e7670

Training in progress, epoch 1

Browse files
Files changed (38) hide show
  1. model.safetensors +1 -1
  2. run-7/checkpoint-108/config.json +25 -0
  3. run-7/checkpoint-108/model.safetensors +3 -0
  4. run-7/checkpoint-108/optimizer.pt +3 -0
  5. run-7/checkpoint-108/rng_state.pth +3 -0
  6. run-7/checkpoint-108/scheduler.pt +3 -0
  7. run-7/checkpoint-108/special_tokens_map.json +7 -0
  8. run-7/checkpoint-108/tokenizer.json +0 -0
  9. run-7/checkpoint-108/tokenizer_config.json +55 -0
  10. run-7/checkpoint-108/trainer_state.json +62 -0
  11. run-7/checkpoint-108/training_args.bin +3 -0
  12. run-7/checkpoint-108/vocab.txt +0 -0
  13. run-7/checkpoint-54/config.json +25 -0
  14. run-7/checkpoint-54/model.safetensors +3 -0
  15. run-7/checkpoint-54/optimizer.pt +3 -0
  16. run-7/checkpoint-54/rng_state.pth +3 -0
  17. run-7/checkpoint-54/scheduler.pt +3 -0
  18. run-7/checkpoint-54/special_tokens_map.json +7 -0
  19. run-7/checkpoint-54/tokenizer.json +0 -0
  20. run-7/checkpoint-54/tokenizer_config.json +55 -0
  21. run-7/checkpoint-54/trainer_state.json +44 -0
  22. run-7/checkpoint-54/training_args.bin +3 -0
  23. run-7/checkpoint-54/vocab.txt +0 -0
  24. run-7/checkpoint-81/config.json +25 -0
  25. run-7/checkpoint-81/model.safetensors +3 -0
  26. run-7/checkpoint-81/optimizer.pt +3 -0
  27. run-7/checkpoint-81/rng_state.pth +3 -0
  28. run-7/checkpoint-81/scheduler.pt +3 -0
  29. run-7/checkpoint-81/special_tokens_map.json +7 -0
  30. run-7/checkpoint-81/tokenizer.json +0 -0
  31. run-7/checkpoint-81/tokenizer_config.json +55 -0
  32. run-7/checkpoint-81/trainer_state.json +53 -0
  33. run-7/checkpoint-81/training_args.bin +3 -0
  34. run-7/checkpoint-81/vocab.txt +0 -0
  35. runs/Mar05_22-12-34_418b5b5ae03a/events.out.tfevents.1709677399.418b5b5ae03a.490.10 +3 -0
  36. runs/Mar05_22-12-34_418b5b5ae03a/events.out.tfevents.1709677401.418b5b5ae03a.490.11 +3 -0
  37. runs/Mar05_22-12-34_418b5b5ae03a/events.out.tfevents.1709677408.418b5b5ae03a.490.12 +3 -0
  38. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da6945b97547fcd1347d0eb086fa772fc867596fbaa4aee1a56dea9ebf3c3c9d
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef7da22ad4eab57d7f75f227a7e86180d679df13dd0f44ce401b24a90efb8d2b
3
  size 267832560
run-7/checkpoint-108/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-108/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb7dced76209c7fd8e64df47e7b6535bf4f6eebb9f53d564fd951c6189c20363
3
+ size 267832560
run-7/checkpoint-108/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:557e43eaea6ccf06cf189f81ebf51f592df20ac3c4a38e274e780a12581f0ef3
3
+ size 535727290
run-7/checkpoint-108/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5913789817ad972a59be2182e896406d1a892ff08eea01ac43e452983e1835a7
3
+ size 14244
run-7/checkpoint-108/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d421237077ba0b32a576d3a917574a8633b7d176e12d6d51236c317d27d73c3
3
+ size 1064
run-7/checkpoint-108/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-7/checkpoint-108/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-108/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-7/checkpoint-108/trainer_state.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.2854756779127197,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-108",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 108,
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": 0.5998417735099792,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.5239,
16
+ "eval_samples_per_second": 1990.765,
17
+ "eval_steps_per_second": 125.974,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5701206922531128,
23
+ "eval_matthews_correlation": 0.13611320682675296,
24
+ "eval_runtime": 0.5141,
25
+ "eval_samples_per_second": 2028.622,
26
+ "eval_steps_per_second": 128.369,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5535181760787964,
32
+ "eval_matthews_correlation": 0.26333420373394023,
33
+ "eval_runtime": 0.5162,
34
+ "eval_samples_per_second": 2020.378,
35
+ "eval_steps_per_second": 127.847,
36
+ "step": 81
37
+ },
38
+ {
39
+ "epoch": 4.0,
40
+ "eval_loss": 0.566290020942688,
41
+ "eval_matthews_correlation": 0.2854756779127197,
42
+ "eval_runtime": 0.499,
43
+ "eval_samples_per_second": 2090.137,
44
+ "eval_steps_per_second": 132.262,
45
+ "step": 108
46
+ }
47
+ ],
48
+ "logging_steps": 500,
49
+ "max_steps": 108,
50
+ "num_input_tokens_seen": 0,
51
+ "num_train_epochs": 4,
52
+ "save_steps": 500,
53
+ "total_flos": 0,
54
+ "train_batch_size": 32,
55
+ "trial_name": null,
56
+ "trial_params": {
57
+ "learning_rate": 2.2209965791334402e-05,
58
+ "num_train_epochs": 4,
59
+ "per_device_train_batch_size": 32,
60
+ "seed": 28
61
+ }
62
+ }
run-7/checkpoint-108/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94b0d56488edd3793a16ad0562738b1de6b57022238c542f89f0c5ecb6516f1d
3
+ size 4984
run-7/checkpoint-108/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab28e803d6d4a2459fb67c72a593fd49b1c52b7daec62b328d7ea0f1832d54f9
3
+ size 267832560
run-7/checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d90072578c5f9c8f8cba19bd78a9283e00a9d579705892558984ae173d8fe11
3
+ size 535727290
run-7/checkpoint-54/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:178e84e398f82183f8cd1e07af160e81bcfe39fa9928e132642e187467f60d90
3
+ size 14244
run-7/checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61624bc40dca92f569bd6a2a8d5babe47bc7e73f499a9c3986c9045d661f34da
3
+ size 1064
run-7/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-7/checkpoint-54/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/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-7/checkpoint-54/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.13611320682675296,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-54",
4
+ "epoch": 2.0,
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": 0.5998417735099792,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.5239,
16
+ "eval_samples_per_second": 1990.765,
17
+ "eval_steps_per_second": 125.974,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5701206922531128,
23
+ "eval_matthews_correlation": 0.13611320682675296,
24
+ "eval_runtime": 0.5141,
25
+ "eval_samples_per_second": 2028.622,
26
+ "eval_steps_per_second": 128.369,
27
+ "step": 54
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 108,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 4,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 32,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 2.2209965791334402e-05,
40
+ "num_train_epochs": 4,
41
+ "per_device_train_batch_size": 32,
42
+ "seed": 28
43
+ }
44
+ }
run-7/checkpoint-54/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94b0d56488edd3793a16ad0562738b1de6b57022238c542f89f0c5ecb6516f1d
3
+ size 4984
run-7/checkpoint-54/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-81/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": "4.38.2",
24
+ "vocab_size": 30522
25
+ }
run-7/checkpoint-81/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:857e5a8a1293779baa6721bf6f1ffe4293728bfe92b322f25ba58c96b3a91b27
3
+ size 267832560
run-7/checkpoint-81/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa7c1c8b1fe07d90034884ab0529215450303a8c1e5e9f9f3af094f39a96f77b
3
+ size 535727290
run-7/checkpoint-81/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:860bba221025f276e3f7e8ddf27c5de6dc3879f8685d54fbe9399e136ff00d9e
3
+ size 14244
run-7/checkpoint-81/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dae5e112fb84a786567546bb73606115c5f645145fdb141fa45a53c6e68e45ac
3
+ size 1064
run-7/checkpoint-81/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-7/checkpoint-81/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-7/checkpoint-81/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-7/checkpoint-81/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.26333420373394023,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-7/checkpoint-81",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 81,
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": 0.5998417735099792,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.5239,
16
+ "eval_samples_per_second": 1990.765,
17
+ "eval_steps_per_second": 125.974,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.5701206922531128,
23
+ "eval_matthews_correlation": 0.13611320682675296,
24
+ "eval_runtime": 0.5141,
25
+ "eval_samples_per_second": 2028.622,
26
+ "eval_steps_per_second": 128.369,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5535181760787964,
32
+ "eval_matthews_correlation": 0.26333420373394023,
33
+ "eval_runtime": 0.5162,
34
+ "eval_samples_per_second": 2020.378,
35
+ "eval_steps_per_second": 127.847,
36
+ "step": 81
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 108,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 4,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 32,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 2.2209965791334402e-05,
49
+ "num_train_epochs": 4,
50
+ "per_device_train_batch_size": 32,
51
+ "seed": 28
52
+ }
53
+ }
run-7/checkpoint-81/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94b0d56488edd3793a16ad0562738b1de6b57022238c542f89f0c5ecb6516f1d
3
+ size 4984
run-7/checkpoint-81/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar05_22-12-34_418b5b5ae03a/events.out.tfevents.1709677399.418b5b5ae03a.490.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ae874b924352a52a07e5089a85cfbe6be435400ef5ac967cdb690d37621a2e9
3
+ size 4871
runs/Mar05_22-12-34_418b5b5ae03a/events.out.tfevents.1709677401.418b5b5ae03a.490.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a398324b2aabd661651ee6d9e6bf43595d6749413286049ccefd7ca0cf788b7a
3
+ size 4875
runs/Mar05_22-12-34_418b5b5ae03a/events.out.tfevents.1709677408.418b5b5ae03a.490.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a48bd0fdf091d6287d2849eaa2a0c5dcde17f9787f14eec47a450c96044eba4
3
+ size 6205
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94b0d56488edd3793a16ad0562738b1de6b57022238c542f89f0c5ecb6516f1d
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0528b625bd56c5f820c6a81109a84f0cb3b06c0ef021c43787878a2c5d2ba02
3
  size 4984