Hugging Face's logo

anamelchor
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
anamelchor commited on
Commit
ba02dc9
·
verified ·
1 Parent(s): 4940d35

Training in progress, epoch 1

Browse files
Files changed (36) hide show
  1. model.safetensors +1 -1
  2. run-3/checkpoint-27/config.json +25 -0
  3. run-3/checkpoint-27/model.safetensors +3 -0
  4. run-3/checkpoint-27/optimizer.pt +3 -0
  5. run-3/checkpoint-27/rng_state.pth +3 -0
  6. run-3/checkpoint-27/scheduler.pt +3 -0
  7. run-3/checkpoint-27/special_tokens_map.json +7 -0
  8. run-3/checkpoint-27/tokenizer.json +0 -0
  9. run-3/checkpoint-27/tokenizer_config.json +55 -0
  10. run-3/checkpoint-27/trainer_state.json +35 -0
  11. run-3/checkpoint-27/training_args.bin +3 -0
  12. run-3/checkpoint-27/vocab.txt +0 -0
  13. run-3/checkpoint-54/config.json +25 -0
  14. run-3/checkpoint-54/model.safetensors +3 -0
  15. run-3/checkpoint-54/optimizer.pt +3 -0
  16. run-3/checkpoint-54/rng_state.pth +3 -0
  17. run-3/checkpoint-54/scheduler.pt +3 -0
  18. run-3/checkpoint-54/special_tokens_map.json +7 -0
  19. run-3/checkpoint-54/tokenizer.json +0 -0
  20. run-3/checkpoint-54/tokenizer_config.json +55 -0
  21. run-3/checkpoint-54/trainer_state.json +44 -0
  22. run-3/checkpoint-54/training_args.bin +3 -0
  23. run-3/checkpoint-54/vocab.txt +0 -0
  24. run-3/checkpoint-81/config.json +25 -0
  25. run-3/checkpoint-81/model.safetensors +3 -0
  26. run-3/checkpoint-81/optimizer.pt +3 -0
  27. run-3/checkpoint-81/rng_state.pth +3 -0
  28. run-3/checkpoint-81/scheduler.pt +3 -0
  29. run-3/checkpoint-81/special_tokens_map.json +7 -0
  30. run-3/checkpoint-81/tokenizer.json +0 -0
  31. run-3/checkpoint-81/tokenizer_config.json +55 -0
  32. run-3/checkpoint-81/trainer_state.json +53 -0
  33. run-3/checkpoint-81/training_args.bin +3 -0
  34. run-3/checkpoint-81/vocab.txt +0 -0
  35. runs/Feb27_12-48-22_1e7c639bcfdf/events.out.tfevents.1709039335.1e7c639bcfdf.1356.6 +3 -0
  36. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d9e7cc5f9dfa56a62a4d0b840f756a573005cff8e9051460fbbdd072356e604
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb261ee18f81041ba8cec98c84be936a1ec23b01180cf95bd3d1190a82549429
3
  size 267832560
run-3/checkpoint-27/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-3/checkpoint-27/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d9e7cc5f9dfa56a62a4d0b840f756a573005cff8e9051460fbbdd072356e604
3
+ size 267832560
run-3/checkpoint-27/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3996dbcf5b4c2938cfc063398e7cae366335c4a71675d01a4e7172a96323ff3e
3
+ size 535727290
run-3/checkpoint-27/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09277ee62e69c41b5a1294ae25ca6ea35a705b91436a421b631d6d8b8116f5c9
3
+ size 14244
run-3/checkpoint-27/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da714f90710adfc3865b742b76805ba5d5e3deb9e467aecbd2a0556eff74a54b
3
+ size 1064
run-3/checkpoint-27/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-27/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-27/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-27/trainer_state.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-27",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 27,
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": 0.6133037209510803,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7211,
16
+ "eval_samples_per_second": 1446.303,
17
+ "eval_steps_per_second": 91.521,
18
+ "step": 27
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 81,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
25
+ "save_steps": 500,
26
+ "total_flos": 0,
27
+ "train_batch_size": 32,
28
+ "trial_name": null,
29
+ "trial_params": {
30
+ "learning_rate": 1.3154436092520629e-05,
31
+ "num_train_epochs": 3,
32
+ "per_device_train_batch_size": 32,
33
+ "seed": 11
34
+ }
35
+ }
run-3/checkpoint-27/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a928816deab35d3e8df523de63ad52240403194afbbbb5f72cce080ba7e882de
3
+ size 4984
run-3/checkpoint-27/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2bcff6431b5a1424138e9ff3d040a3b74c504b79cd3a808e107025b288b0655
3
+ size 267832560
run-3/checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71f6f4639283c8ecac90f5551a900fddb0102cffd939c42368afefd68ce6acd1
3
+ size 535727290
run-3/checkpoint-54/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e42e2747302ca66575567cd2ad92e4c499840df43d7c74871abe2a004c812c2b
3
+ size 14244
run-3/checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1fa4a9cd65cb4e5d0cd19a4551bc3f87cf14bf8cf2b1acc18298cabdc78b3b2
3
+ size 1064
run-3/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-3/checkpoint-54/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-54/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-27",
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": 0.6133037209510803,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7211,
16
+ "eval_samples_per_second": 1446.303,
17
+ "eval_steps_per_second": 91.521,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6006867289543152,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7678,
25
+ "eval_samples_per_second": 1358.5,
26
+ "eval_steps_per_second": 85.965,
27
+ "step": 54
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 81,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 3,
34
+ "save_steps": 500,
35
+ "total_flos": 0,
36
+ "train_batch_size": 32,
37
+ "trial_name": null,
38
+ "trial_params": {
39
+ "learning_rate": 1.3154436092520629e-05,
40
+ "num_train_epochs": 3,
41
+ "per_device_train_batch_size": 32,
42
+ "seed": 11
43
+ }
44
+ }
run-3/checkpoint-54/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a928816deab35d3e8df523de63ad52240403194afbbbb5f72cce080ba7e882de
3
+ size 4984
run-3/checkpoint-54/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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": "4.38.1",
24
+ "vocab_size": 30522
25
+ }
run-3/checkpoint-81/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d116274c28f1c38ce1e8490f31c7dfd5f3e4343e69ef43a748d30354afc1993e
3
+ size 267832560
run-3/checkpoint-81/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8170bf3b182d666cca0f095471fa9c1b2f34b7caf6da84f176726a09a0b0372
3
+ size 535727290
run-3/checkpoint-81/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dae41a659a7e169ccb25d03d75764e0a3e0b457ebd805deda168932be6a6d48
3
+ size 14244
run-3/checkpoint-81/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffda6f9e9a1c6a030a83ddc787bfb11783d101449108ae8da4be4983d4b42589
3
+ size 1064
run-3/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-3/checkpoint-81/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/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-3/checkpoint-81/trainer_state.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.0,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-27",
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": 0.6133037209510803,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.7211,
16
+ "eval_samples_per_second": 1446.303,
17
+ "eval_steps_per_second": 91.521,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6006867289543152,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.7678,
25
+ "eval_samples_per_second": 1358.5,
26
+ "eval_steps_per_second": 85.965,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.5950407981872559,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 0.7626,
34
+ "eval_samples_per_second": 1367.606,
35
+ "eval_steps_per_second": 86.541,
36
+ "step": 81
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 81,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 3,
43
+ "save_steps": 500,
44
+ "total_flos": 0,
45
+ "train_batch_size": 32,
46
+ "trial_name": null,
47
+ "trial_params": {
48
+ "learning_rate": 1.3154436092520629e-05,
49
+ "num_train_epochs": 3,
50
+ "per_device_train_batch_size": 32,
51
+ "seed": 11
52
+ }
53
+ }
run-3/checkpoint-81/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a928816deab35d3e8df523de63ad52240403194afbbbb5f72cce080ba7e882de
3
+ size 4984
run-3/checkpoint-81/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb27_12-48-22_1e7c639bcfdf/events.out.tfevents.1709039335.1e7c639bcfdf.1356.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b31e09a33e4da1f0ba1fb2be4ede783f92cf18f50ca7480b44b3a3857b54417
3
+ size 5219
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a928816deab35d3e8df523de63ad52240403194afbbbb5f72cce080ba7e882de
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f522a57ff45b04702d23b1a21b6a560b003d1565d8bb0047401bc05c8c441902
3
  size 4984