Hugging Face's logo

kbberendsen
/
distilbert-base-uncased-finetuned-cola

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Model card Files Metrics Community
kbberendsen commited on
Commit
5a5c673
·
verified ·
1 Parent(s): af2ab9b

Training in progress, epoch 1

Browse files
Files changed (36) hide show
  1. model.safetensors +1 -1
  2. run-5/checkpoint-27/config.json +25 -0
  3. run-5/checkpoint-27/model.safetensors +3 -0
  4. run-5/checkpoint-27/optimizer.pt +3 -0
  5. run-5/checkpoint-27/rng_state.pth +3 -0
  6. run-5/checkpoint-27/scheduler.pt +3 -0
  7. run-5/checkpoint-27/special_tokens_map.json +7 -0
  8. run-5/checkpoint-27/tokenizer.json +0 -0
  9. run-5/checkpoint-27/tokenizer_config.json +55 -0
  10. run-5/checkpoint-27/trainer_state.json +35 -0
  11. run-5/checkpoint-27/training_args.bin +3 -0
  12. run-5/checkpoint-27/vocab.txt +0 -0
  13. run-5/checkpoint-54/config.json +25 -0
  14. run-5/checkpoint-54/model.safetensors +3 -0
  15. run-5/checkpoint-54/optimizer.pt +3 -0
  16. run-5/checkpoint-54/rng_state.pth +3 -0
  17. run-5/checkpoint-54/scheduler.pt +3 -0
  18. run-5/checkpoint-54/special_tokens_map.json +7 -0
  19. run-5/checkpoint-54/tokenizer.json +0 -0
  20. run-5/checkpoint-54/tokenizer_config.json +55 -0
  21. run-5/checkpoint-54/trainer_state.json +44 -0
  22. run-5/checkpoint-54/training_args.bin +3 -0
  23. run-5/checkpoint-54/vocab.txt +0 -0
  24. run-5/checkpoint-81/config.json +25 -0
  25. run-5/checkpoint-81/model.safetensors +3 -0
  26. run-5/checkpoint-81/optimizer.pt +3 -0
  27. run-5/checkpoint-81/rng_state.pth +3 -0
  28. run-5/checkpoint-81/scheduler.pt +3 -0
  29. run-5/checkpoint-81/special_tokens_map.json +7 -0
  30. run-5/checkpoint-81/tokenizer.json +0 -0
  31. run-5/checkpoint-81/tokenizer_config.json +55 -0
  32. run-5/checkpoint-81/trainer_state.json +53 -0
  33. run-5/checkpoint-81/training_args.bin +3 -0
  34. run-5/checkpoint-81/vocab.txt +0 -0
  35. runs/Feb27_12-50-31_a10b095f85e3/events.out.tfevents.1709040522.a10b095f85e3.329.8 +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 sha256:872d481f05dd0fefb060273bdd748c6647f0bc036adfdd1f3e0bd2d0c3c2cd98
3
  size 267832560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f19fdfd0493a182edb5fa666ac51bd975bd01f8af00e04463c041880bc34da
3
  size 267832560
run-5/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-5/checkpoint-27/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:872d481f05dd0fefb060273bdd748c6647f0bc036adfdd1f3e0bd2d0c3c2cd98
3
+ size 267832560
run-5/checkpoint-27/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cba0e540f2e3e9266d3f5f07c4aa01f77ce80679fe52ab60184b05f066a6330
3
+ size 535727290
run-5/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-5/checkpoint-27/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a705a97aaecdc21103505d03fbb2747df369475898d049cb463ad4cba6132d99
3
+ size 1064
run-5/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-5/checkpoint-27/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/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-5/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-5/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": 0.6419833302497864,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.8978,
16
+ "eval_samples_per_second": 1161.719,
17
+ "eval_steps_per_second": 73.512,
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": 2.2137358701553763e-06,
31
+ "num_train_epochs": 3,
32
+ "per_device_train_batch_size": 32,
33
+ "seed": 11
34
+ }
35
+ }
run-5/checkpoint-27/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d0fa30219cd780fa15bb36c41b552337e69f4b8abe90ea1feffc93833591be
3
+ size 4984
run-5/checkpoint-27/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/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-5/checkpoint-54/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef8e094b67327e2df694cc6bfa18daddb4b063fcc412c8f1f3bee1a2166db21e
3
+ size 267832560
run-5/checkpoint-54/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f12faf965dff58f40b9355809e8adbe3d9a43764797300f88ddf3b1cb062ac0
3
+ size 535727290
run-5/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-5/checkpoint-54/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:748021ffaf65c340e0b18eeeb8068b046adf5b1571541c4525464f22568aed7b
3
+ size 1064
run-5/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-5/checkpoint-54/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/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-5/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-5/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": 0.6419833302497864,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.8978,
16
+ "eval_samples_per_second": 1161.719,
17
+ "eval_steps_per_second": 73.512,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6295746564865112,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.8402,
25
+ "eval_samples_per_second": 1241.318,
26
+ "eval_steps_per_second": 78.549,
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": 2.2137358701553763e-06,
40
+ "num_train_epochs": 3,
41
+ "per_device_train_batch_size": 32,
42
+ "seed": 11
43
+ }
44
+ }
run-5/checkpoint-54/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d0fa30219cd780fa15bb36c41b552337e69f4b8abe90ea1feffc93833591be
3
+ size 4984
run-5/checkpoint-54/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/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-5/checkpoint-81/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7959fcb43fa7cfb56684f53331c92c4455aeafbe7f38362e1d5b41818464d928
3
+ size 267832560
run-5/checkpoint-81/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddd4cf0b41882ec36719acdba055472605f0c676f3588ce2700fdbdd1d657066
3
+ size 535727290
run-5/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-5/checkpoint-81/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf9228e2628549d6f938f221dde27f8c79155bcbd3e4cbd19307fd6d8523a8d
3
+ size 1064
run-5/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-5/checkpoint-81/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/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-5/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-5/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": 0.6419833302497864,
14
+ "eval_matthews_correlation": 0.0,
15
+ "eval_runtime": 0.8978,
16
+ "eval_samples_per_second": 1161.719,
17
+ "eval_steps_per_second": 73.512,
18
+ "step": 27
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.6295746564865112,
23
+ "eval_matthews_correlation": 0.0,
24
+ "eval_runtime": 0.8402,
25
+ "eval_samples_per_second": 1241.318,
26
+ "eval_steps_per_second": 78.549,
27
+ "step": 54
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_loss": 0.6265798211097717,
32
+ "eval_matthews_correlation": 0.0,
33
+ "eval_runtime": 1.2439,
34
+ "eval_samples_per_second": 838.519,
35
+ "eval_steps_per_second": 53.061,
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": 2.2137358701553763e-06,
49
+ "num_train_epochs": 3,
50
+ "per_device_train_batch_size": 32,
51
+ "seed": 11
52
+ }
53
+ }
run-5/checkpoint-81/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d0fa30219cd780fa15bb36c41b552337e69f4b8abe90ea1feffc93833591be
3
+ size 4984
run-5/checkpoint-81/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Feb27_12-50-31_a10b095f85e3/events.out.tfevents.1709040522.a10b095f85e3.329.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a49ad78cfaf18af55516aab6d440bf3257a736b8cdb0cbf9f6b7c5bda5a3e0ca
3
+ size 5875
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38d0fa30219cd780fa15bb36c41b552337e69f4b8abe90ea1feffc93833591be
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76371698f5e5e033ea9e0985edf1634d0e473bb92c31fdb1f3c784d2a40e74a9
3
  size 4984