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
5d0a65f
·
verified ·
1 Parent(s): b184ecf

Training in progress, epoch 5

Browse files
Files changed (24) hide show
  1. logs/events.out.tfevents.1713589458.1376c752d37a.9760.31 +2 -2
  2. model.safetensors +1 -1
  3. run-31/checkpoint-1070/config.json +34 -0
  4. run-31/checkpoint-1070/model.safetensors +3 -0
  5. run-31/checkpoint-1070/optimizer.pt +3 -0
  6. run-31/checkpoint-1070/rng_state.pth +3 -0
  7. run-31/checkpoint-1070/scheduler.pt +3 -0
  8. run-31/checkpoint-1070/special_tokens_map.json +7 -0
  9. run-31/checkpoint-1070/tokenizer.json +0 -0
  10. run-31/checkpoint-1070/tokenizer_config.json +57 -0
  11. run-31/checkpoint-1070/trainer_state.json +126 -0
  12. run-31/checkpoint-1070/training_args.bin +3 -0
  13. run-31/checkpoint-1070/vocab.txt +0 -0
  14. run-31/checkpoint-856/config.json +34 -0
  15. run-31/checkpoint-856/model.safetensors +3 -0
  16. run-31/checkpoint-856/optimizer.pt +3 -0
  17. run-31/checkpoint-856/rng_state.pth +3 -0
  18. run-31/checkpoint-856/scheduler.pt +3 -0
  19. run-31/checkpoint-856/special_tokens_map.json +7 -0
  20. run-31/checkpoint-856/tokenizer.json +0 -0
  21. run-31/checkpoint-856/tokenizer_config.json +57 -0
  22. run-31/checkpoint-856/trainer_state.json +106 -0
  23. run-31/checkpoint-856/training_args.bin +3 -0
  24. run-31/checkpoint-856/vocab.txt +0 -0
logs/events.out.tfevents.1713589458.1376c752d37a.9760.31 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:176e8a1a8440eee913536fae4cd4fa555d911f378ccb0dc7211be5f46eac882f
3
- size 6943
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd9781ca1f12fb1cfc15b1ec282fcf4419c2f2ca64f90b473d6874016b2dbdcb
3
+ size 8403
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17fe435897935f2e9ed769aca474a86bc0c58d882a630c354c06d91c27a595fe
3
  size 17549312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3f3c7145d999191e55428e78e8d873a4dd6f45553ce46ced20b424df1b4aec5
3
  size 17549312
run-31/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-31/checkpoint-1070/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3f3c7145d999191e55428e78e8d873a4dd6f45553ce46ced20b424df1b4aec5
3
+ size 17549312
run-31/checkpoint-1070/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f37bc22489f3a78f81fc58cd63ce4d64533b677e771b186e342ed87170c5a0ab
3
+ size 35123898
run-31/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-31/checkpoint-1070/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00db144f94c61037de129f799c9350219a8ad616e05754ae9dcbade454e8f715
3
+ size 1064
run-31/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-31/checkpoint-1070/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-31/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-31/checkpoint-1070/trainer_state.json ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7521968365553603,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-31/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": 8.190187454223633,
14
+ "learning_rate": 0.00012111783530103911,
15
+ "loss": 0.6036,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7106033977738723,
21
+ "eval_f1": 0.46304347826086956,
22
+ "eval_loss": 0.5476045608520508,
23
+ "eval_mcc": 0.2951848655219638,
24
+ "eval_precision": 0.6068376068376068,
25
+ "eval_recall": 0.37434094903339193,
26
+ "eval_runtime": 3.1382,
27
+ "eval_samples_per_second": 543.94,
28
+ "eval_steps_per_second": 17.207,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.7711777687072754,
34
+ "learning_rate": 0.0001009315294175326,
35
+ "loss": 0.5367,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7305213825424721,
41
+ "eval_f1": 0.5168067226890756,
42
+ "eval_loss": 0.5195680260658264,
43
+ "eval_mcc": 0.35250881017307234,
44
+ "eval_precision": 0.6422976501305483,
45
+ "eval_recall": 0.43233743409490333,
46
+ "eval_runtime": 3.1515,
47
+ "eval_samples_per_second": 541.653,
48
+ "eval_steps_per_second": 17.135,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.508857488632202,
54
+ "learning_rate": 8.074522353402607e-05,
55
+ "loss": 0.5095,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7428236672524897,
61
+ "eval_f1": 0.5284640171858218,
62
+ "eval_loss": 0.5116792321205139,
63
+ "eval_mcc": 0.38102846368132237,
64
+ "eval_precision": 0.6795580110497238,
65
+ "eval_recall": 0.43233743409490333,
66
+ "eval_runtime": 3.1425,
67
+ "eval_samples_per_second": 543.207,
68
+ "eval_steps_per_second": 17.184,
69
+ "step": 642
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 4.153243064880371,
74
+ "learning_rate": 6.0558917650519556e-05,
75
+ "loss": 0.5003,
76
+ "step": 856
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7469244288224957,
81
+ "eval_f1": 0.5364806866952789,
82
+ "eval_loss": 0.5013575553894043,
83
+ "eval_mcc": 0.3917806841670766,
84
+ "eval_precision": 0.6887052341597796,
85
+ "eval_recall": 0.43936731107205623,
86
+ "eval_runtime": 3.159,
87
+ "eval_samples_per_second": 540.365,
88
+ "eval_steps_per_second": 17.094,
89
+ "step": 856
90
+ },
91
+ {
92
+ "epoch": 5.0,
93
+ "grad_norm": 6.839134693145752,
94
+ "learning_rate": 4.037261176701304e-05,
95
+ "loss": 0.4897,
96
+ "step": 1070
97
+ },
98
+ {
99
+ "epoch": 5.0,
100
+ "eval_accuracy": 0.7521968365553603,
101
+ "eval_f1": 0.5952153110047848,
102
+ "eval_loss": 0.49949556589126587,
103
+ "eval_mcc": 0.42215185251347925,
104
+ "eval_precision": 0.6533613445378151,
105
+ "eval_recall": 0.546572934973638,
106
+ "eval_runtime": 3.1467,
107
+ "eval_samples_per_second": 542.465,
108
+ "eval_steps_per_second": 17.161,
109
+ "step": 1070
110
+ }
111
+ ],
112
+ "logging_steps": 500,
113
+ "max_steps": 1498,
114
+ "num_input_tokens_seen": 0,
115
+ "num_train_epochs": 7,
116
+ "save_steps": 500,
117
+ "total_flos": 2623878322200.0,
118
+ "train_batch_size": 32,
119
+ "trial_name": null,
120
+ "trial_params": {
121
+ "alpha": 0.9889630226398882,
122
+ "learning_rate": 0.00014130414118454564,
123
+ "num_train_epochs": 7,
124
+ "temperature": 15
125
+ }
126
+ }
run-31/checkpoint-1070/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c981cf0a286d911e6656921fe8054df3cc858ad8c45c649b452912044449904c
3
+ size 5048
run-31/checkpoint-1070/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-31/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-31/checkpoint-856/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c5ae419834af7a940786b421b9113f59019c89f96d1c92581e696c72c276faa
3
+ size 17549312
run-31/checkpoint-856/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2626622f9062d6629788d13245ee1e60c37e14d75349288c597b9454e30b129d
3
+ size 35123898
run-31/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-31/checkpoint-856/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2445c9edf854e641ed79ccf1388a92abf2b131b68495cb9b040dedc40e14ace
3
+ size 1064
run-31/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-31/checkpoint-856/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-31/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-31/checkpoint-856/trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7469244288224957,
3
+ "best_model_checkpoint": "tiny-bert-sst2-distilled/run-31/checkpoint-856",
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": 8.190187454223633,
14
+ "learning_rate": 0.00012111783530103911,
15
+ "loss": 0.6036,
16
+ "step": 214
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7106033977738723,
21
+ "eval_f1": 0.46304347826086956,
22
+ "eval_loss": 0.5476045608520508,
23
+ "eval_mcc": 0.2951848655219638,
24
+ "eval_precision": 0.6068376068376068,
25
+ "eval_recall": 0.37434094903339193,
26
+ "eval_runtime": 3.1382,
27
+ "eval_samples_per_second": 543.94,
28
+ "eval_steps_per_second": 17.207,
29
+ "step": 214
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "grad_norm": 2.7711777687072754,
34
+ "learning_rate": 0.0001009315294175326,
35
+ "loss": 0.5367,
36
+ "step": 428
37
+ },
38
+ {
39
+ "epoch": 2.0,
40
+ "eval_accuracy": 0.7305213825424721,
41
+ "eval_f1": 0.5168067226890756,
42
+ "eval_loss": 0.5195680260658264,
43
+ "eval_mcc": 0.35250881017307234,
44
+ "eval_precision": 0.6422976501305483,
45
+ "eval_recall": 0.43233743409490333,
46
+ "eval_runtime": 3.1515,
47
+ "eval_samples_per_second": 541.653,
48
+ "eval_steps_per_second": 17.135,
49
+ "step": 428
50
+ },
51
+ {
52
+ "epoch": 3.0,
53
+ "grad_norm": 2.508857488632202,
54
+ "learning_rate": 8.074522353402607e-05,
55
+ "loss": 0.5095,
56
+ "step": 642
57
+ },
58
+ {
59
+ "epoch": 3.0,
60
+ "eval_accuracy": 0.7428236672524897,
61
+ "eval_f1": 0.5284640171858218,
62
+ "eval_loss": 0.5116792321205139,
63
+ "eval_mcc": 0.38102846368132237,
64
+ "eval_precision": 0.6795580110497238,
65
+ "eval_recall": 0.43233743409490333,
66
+ "eval_runtime": 3.1425,
67
+ "eval_samples_per_second": 543.207,
68
+ "eval_steps_per_second": 17.184,
69
+ "step": 642
70
+ },
71
+ {
72
+ "epoch": 4.0,
73
+ "grad_norm": 4.153243064880371,
74
+ "learning_rate": 6.0558917650519556e-05,
75
+ "loss": 0.5003,
76
+ "step": 856
77
+ },
78
+ {
79
+ "epoch": 4.0,
80
+ "eval_accuracy": 0.7469244288224957,
81
+ "eval_f1": 0.5364806866952789,
82
+ "eval_loss": 0.5013575553894043,
83
+ "eval_mcc": 0.3917806841670766,
84
+ "eval_precision": 0.6887052341597796,
85
+ "eval_recall": 0.43936731107205623,
86
+ "eval_runtime": 3.159,
87
+ "eval_samples_per_second": 540.365,
88
+ "eval_steps_per_second": 17.094,
89
+ "step": 856
90
+ }
91
+ ],
92
+ "logging_steps": 500,
93
+ "max_steps": 1498,
94
+ "num_input_tokens_seen": 0,
95
+ "num_train_epochs": 7,
96
+ "save_steps": 500,
97
+ "total_flos": 2099102657760.0,
98
+ "train_batch_size": 32,
99
+ "trial_name": null,
100
+ "trial_params": {
101
+ "alpha": 0.9889630226398882,
102
+ "learning_rate": 0.00014130414118454564,
103
+ "num_train_epochs": 7,
104
+ "temperature": 15
105
+ }
106
+ }
run-31/checkpoint-856/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c981cf0a286d911e6656921fe8054df3cc858ad8c45c649b452912044449904c
3
+ size 5048
run-31/checkpoint-856/vocab.txt ADDED
The diff for this file is too large to render. See raw diff