Hugging Face's logo

xuancoblab2023
/
tiny-bert-sst2-distilled

Text Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
xuancoblab2023 commited on
Commit
9fbd17f
·
verified ·
1 Parent(s): efa8a26

Training in progress, epoch 5

Browse files
Files changed (24) hide show
  1. logs/events.out.tfevents.1713588876.1376c752d37a.9760.23 +2 -2
  2. model.safetensors +1 -1
  3. run-23/checkpoint-1070/config.json +34 -0
  4. run-23/checkpoint-1070/model.safetensors +3 -0
  5. run-23/checkpoint-1070/optimizer.pt +3 -0
  6. run-23/checkpoint-1070/rng_state.pth +3 -0
  7. run-23/checkpoint-1070/scheduler.pt +3 -0
  8. run-23/checkpoint-1070/special_tokens_map.json +7 -0
  9. run-23/checkpoint-1070/tokenizer.json +0 -0
  10. run-23/checkpoint-1070/tokenizer_config.json +57 -0
  11. run-23/checkpoint-1070/trainer_state.json +126 -0
  12. run-23/checkpoint-1070/training_args.bin +3 -0
  13. run-23/checkpoint-1070/vocab.txt +0 -0
  14. run-23/checkpoint-856/config.json +34 -0
  15. run-23/checkpoint-856/model.safetensors +3 -0
  16. run-23/checkpoint-856/optimizer.pt +3 -0
  17. run-23/checkpoint-856/rng_state.pth +3 -0
  18. run-23/checkpoint-856/scheduler.pt +3 -0
  19. run-23/checkpoint-856/special_tokens_map.json +7 -0
  20. run-23/checkpoint-856/tokenizer.json +0 -0
  21. run-23/checkpoint-856/tokenizer_config.json +57 -0
  22. run-23/checkpoint-856/trainer_state.json +106 -0
  23. run-23/checkpoint-856/training_args.bin +3 -0
  24. run-23/checkpoint-856/vocab.txt +0 -0
logs/events.out.tfevents.1713588876.1376c752d37a.9760.23 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e38b8219746b73ddd01523b96d9f4d888824690862dc4fb917609153c7b6c961
3
- size 6943
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe2ed7ce4758323f07306e47164bc372324952fa3436d404e0fddaf3dad88854
3
+ size 8403
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d87aa5bd2d38323542976390fdbd8e21079024a98dc1fe0724542cafe53f4c2b
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:129e10e846884d805ecee0d99421bd9f8630a9f4dcf2e51ee8a454b2e4264c45
3
  size 17549312
run-23/checkpoint-1070/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-23/checkpoint-1070/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:129e10e846884d805ecee0d99421bd9f8630a9f4dcf2e51ee8a454b2e4264c45
3
+ size 17549312
run-23/checkpoint-1070/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37472cab00846405391bb2f1c983b34395b51d90ff5c2c0ba32f02386cd21acd
3
+ size 35123898
run-23/checkpoint-1070/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8889b20d89ae20d68b3b1e02c508fe878c92c2f33b24682cc4f66bd3af9eea6
3
+ size 14308
run-23/checkpoint-1070/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:662499231a6f82af34cb783e4be910c494a0aef8796cb8ced1f44fa0f64321f2
3
+ size 1064
run-23/checkpoint-1070/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-23/checkpoint-1070/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-23/checkpoint-1070/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-23/checkpoint-1070/trainer_state.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7492677211482133,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-23/checkpoint-1070",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1070,
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
+ "grad_norm": 8.174213409423828,
14
+ "learning_rate": 0.00021193737357349756,
15
+ "loss": 0.6053,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7041593438781488,
21
+ "eval_f1": 0.4107351225204201,
22
+ "eval_loss": 0.5531450510025024,
23
+ "eval_mcc": 0.2654659366009494,
24
+ "eval_precision": 0.6111111111111112,
25
+ "eval_recall": 0.3093145869947276,
26
+ "eval_runtime": 3.1397,
27
+ "eval_samples_per_second": 543.682,
28
+ "eval_steps_per_second": 17.199,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.549020290374756,
34
+ "learning_rate": 0.00018544520187681036,
35
+ "loss": 0.5455,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7229056824838899,
41
+ "eval_f1": 0.4569460390355913,
42
+ "eval_loss": 0.5337331295013428,
43
+ "eval_mcc": 0.32023248430720136,
44
+ "eval_precision": 0.6589403973509934,
45
+ "eval_recall": 0.34973637961335674,
46
+ "eval_runtime": 3.1777,
47
+ "eval_samples_per_second": 537.185,
48
+ "eval_steps_per_second": 16.994,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 3.2418973445892334,
54
+ "learning_rate": 0.00015895303018012317,
55
+ "loss": 0.514,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7311072056239016,
61
+ "eval_f1": 0.43122676579925656,
62
+ "eval_loss": 0.5188717246055603,
63
+ "eval_mcc": 0.3396283739174578,
64
+ "eval_precision": 0.7310924369747899,
65
+ "eval_recall": 0.30579964850615116,
66
+ "eval_runtime": 3.1525,
67
+ "eval_samples_per_second": 541.47,
68
+ "eval_steps_per_second": 17.129,
69
+ "step": 642
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 4.082540988922119,
74
+ "learning_rate": 0.000132460858483436,
75
+ "loss": 0.5028,
76
+ "step": 856
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7281780902167545,
81
+ "eval_f1": 0.3796791443850267,
82
+ "eval_loss": 0.521298348903656,
83
+ "eval_mcc": 0.33395946974565643,
84
+ "eval_precision": 0.7932960893854749,
85
+ "eval_recall": 0.24956063268892795,
86
+ "eval_runtime": 3.1071,
87
+ "eval_samples_per_second": 549.395,
88
+ "eval_steps_per_second": 17.38,
89
+ "step": 856
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 5.98746919631958,
94
+ "learning_rate": 0.00010596868678674878,
95
+ "loss": 0.4947,
96
+ "step": 1070
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.7492677211482133,
101
+ "eval_f1": 0.5668016194331983,
102
+ "eval_loss": 0.49519282579421997,
103
+ "eval_mcc": 0.4052305275875567,
104
+ "eval_precision": 0.6682577565632458,
105
+ "eval_recall": 0.492091388400703,
106
+ "eval_runtime": 3.1175,
107
+ "eval_samples_per_second": 547.552,
108
+ "eval_steps_per_second": 17.321,
109
+ "step": 1070
110
+ }
111
+ ],
112
+ "logging_steps": 500,
113
+ "max_steps": 1926,
114
+ "num_input_tokens_seen": 0,
115
+ "num_train_epochs": 9,
116
+ "save_steps": 500,
117
+ "total_flos": 2623878322200.0,
118
+ "train_batch_size": 32,
119
+ "trial_name": null,
120
+ "trial_params": {
121
+ "alpha": 0.9926400370862213,
122
+ "learning_rate": 0.00023842954527018476,
123
+ "num_train_epochs": 9,
124
+ "temperature": 23
125
+ }
126
+ }
run-23/checkpoint-1070/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af146dad23da6bdb3233b97634c1ec6cd3215ed9e511d41e8ad3a40f344164c7
3
+ size 5048
run-23/checkpoint-1070/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-23/checkpoint-856/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 128,
11
+ "id2label": {
12
+ "0": "negative",
13
+ "1": "positive"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 512,
17
+ "label2id": {
18
+ "negative": "0",
19
+ "positive": "1"
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 2,
25
+ "num_hidden_layers": 2,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.40.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 30522
34
+ }
run-23/checkpoint-856/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd076b61f5fff2393f3650da87ee5f98a0f9eb1ee864c530fb09537a6cd84ad4
3
+ size 17549312
run-23/checkpoint-856/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d35a13d28a2dcdcabc8e070acdc49f171abe60278502c2a673cc09e660085d0
3
+ size 35123898
run-23/checkpoint-856/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057111bfbb4d541cc190a3ed4fcfe228e7425a50e4a06afd33224d43272b1a59
3
+ size 14308
run-23/checkpoint-856/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9caa510e34021cbb70c3308a09ee2d627bd656110f27e8e3e29412133357ec10
3
+ size 1064
run-23/checkpoint-856/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-23/checkpoint-856/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-23/checkpoint-856/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
run-23/checkpoint-856/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7311072056239016,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-23/checkpoint-642",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 856,
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
+ "grad_norm": 8.174213409423828,
14
+ "learning_rate": 0.00021193737357349756,
15
+ "loss": 0.6053,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7041593438781488,
21
+ "eval_f1": 0.4107351225204201,
22
+ "eval_loss": 0.5531450510025024,
23
+ "eval_mcc": 0.2654659366009494,
24
+ "eval_precision": 0.6111111111111112,
25
+ "eval_recall": 0.3093145869947276,
26
+ "eval_runtime": 3.1397,
27
+ "eval_samples_per_second": 543.682,
28
+ "eval_steps_per_second": 17.199,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.549020290374756,
34
+ "learning_rate": 0.00018544520187681036,
35
+ "loss": 0.5455,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7229056824838899,
41
+ "eval_f1": 0.4569460390355913,
42
+ "eval_loss": 0.5337331295013428,
43
+ "eval_mcc": 0.32023248430720136,
44
+ "eval_precision": 0.6589403973509934,
45
+ "eval_recall": 0.34973637961335674,
46
+ "eval_runtime": 3.1777,
47
+ "eval_samples_per_second": 537.185,
48
+ "eval_steps_per_second": 16.994,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 3.2418973445892334,
54
+ "learning_rate": 0.00015895303018012317,
55
+ "loss": 0.514,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7311072056239016,
61
+ "eval_f1": 0.43122676579925656,
62
+ "eval_loss": 0.5188717246055603,
63
+ "eval_mcc": 0.3396283739174578,
64
+ "eval_precision": 0.7310924369747899,
65
+ "eval_recall": 0.30579964850615116,
66
+ "eval_runtime": 3.1525,
67
+ "eval_samples_per_second": 541.47,
68
+ "eval_steps_per_second": 17.129,
69
+ "step": 642
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 4.082540988922119,
74
+ "learning_rate": 0.000132460858483436,
75
+ "loss": 0.5028,
76
+ "step": 856
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7281780902167545,
81
+ "eval_f1": 0.3796791443850267,
82
+ "eval_loss": 0.521298348903656,
83
+ "eval_mcc": 0.33395946974565643,
84
+ "eval_precision": 0.7932960893854749,
85
+ "eval_recall": 0.24956063268892795,
86
+ "eval_runtime": 3.1071,
87
+ "eval_samples_per_second": 549.395,
88
+ "eval_steps_per_second": 17.38,
89
+ "step": 856
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 1926,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 9,
96
+ "save_steps": 500,
97
+ "total_flos": 2099102657760.0,
98
+ "train_batch_size": 32,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.9926400370862213,
102
+ "learning_rate": 0.00023842954527018476,
103
+ "num_train_epochs": 9,
104
+ "temperature": 23
105
+ }
106
+ }
run-23/checkpoint-856/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af146dad23da6bdb3233b97634c1ec6cd3215ed9e511d41e8ad3a40f344164c7
3
+ size 5048
run-23/checkpoint-856/vocab.txt ADDED
The diff for this file is too large to render. See raw diff