Hugging Face's logo

bradmin
/
reward-bert-duplicate-answer

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Model card Files
xet
Metrics Community
bradmin commited on
Commit
88b7027
·
1 Parent(s): 1b0fd19

Training in progress, step 300, checkpoint

Browse files
Files changed (11) hide show
  1. checkpoint-300/config.json +35 -0
  2. checkpoint-300/model.safetensors +3 -0
  3. checkpoint-300/optimizer.pt +3 -0
  4. checkpoint-300/rng_state.pth +3 -0
  5. checkpoint-300/scheduler.pt +3 -0
  6. checkpoint-300/special_tokens_map.json +9 -0
  7. checkpoint-300/tokenizer.json +0 -0
  8. checkpoint-300/tokenizer_config.json +59 -0
  9. checkpoint-300/trainer_state.json +226 -0
  10. checkpoint-300/training_args.bin +3 -0
  11. checkpoint-300/vocab.txt +0 -0
checkpoint-300/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "klue/roberta-large",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "LABEL_0"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
+ "label2id": {
20
+ "LABEL_0": 0
21
+ },
22
+ "layer_norm_eps": 1e-05,
23
+ "max_position_embeddings": 514,
24
+ "model_type": "roberta",
25
+ "num_attention_heads": 16,
26
+ "num_hidden_layers": 24,
27
+ "pad_token_id": 2,
28
+ "position_embedding_type": "absolute",
29
+ "tokenizer_class": "BertTokenizer",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.35.0",
32
+ "type_vocab_size": 1,
33
+ "use_cache": true,
34
+ "vocab_size": 32000
35
+ }
checkpoint-300/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e31712b1c54a718173a5ed61b32b09cc853bc61eee3d3e1b31a7738cb28f282
3
+ size 1346677820
checkpoint-300/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12d6faafd1c10cc8cc919937cdc671bddba652e4a66d1f82424dac05b1a71b4b
3
+ size 2693490618
checkpoint-300/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bfb5872f84290c6b6451ddacb28d1e7d7d25078655e75a83c0afe24368b67f5
3
+ size 14308
checkpoint-300/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:410162674ab7be8a31275c0f76cbc619dd0acfb78777223591ea9a86942204df
3
+ size 1064
checkpoint-300/special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
checkpoint-300/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-300/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[CLS]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[PAD]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": false,
49
+ "eos_token": "[SEP]",
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
checkpoint-300/trainer_state.json ADDED
@@ -0,0 +1,226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.3771805752003772,
5
+ "eval_steps": 100,
6
+ "global_step": 300,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.01,
13
+ "learning_rate": 8.996486892091073e-06,
14
+ "loss": 0.6543,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.03,
19
+ "learning_rate": 8.985953053665263e-06,
20
+ "loss": 0.469,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.04,
25
+ "learning_rate": 8.968414932060827e-06,
26
+ "loss": 0.2958,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.05,
31
+ "learning_rate": 8.94389991097275e-06,
32
+ "loss": 0.2424,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.06,
37
+ "learning_rate": 8.912446267696357e-06,
38
+ "loss": 0.2481,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.08,
43
+ "learning_rate": 8.874103113361848e-06,
44
+ "loss": 0.251,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.09,
49
+ "learning_rate": 8.828930316253112e-06,
50
+ "loss": 0.1803,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.1,
55
+ "learning_rate": 8.7769984083305e-06,
56
+ "loss": 0.2148,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.11,
61
+ "learning_rate": 8.718388475103545e-06,
62
+ "loss": 0.1926,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.13,
67
+ "learning_rate": 8.653192029025561e-06,
68
+ "loss": 0.2202,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.13,
73
+ "eval_accuracy": 0.0,
74
+ "eval_loss": 0.07498380541801453,
75
+ "eval_runtime": 28.9719,
76
+ "eval_samples_per_second": 97.612,
77
+ "eval_steps_per_second": 24.403,
78
+ "step": 100
79
+ },
80
+ {
81
+ "epoch": 0.14,
82
+ "learning_rate": 8.581510866607817e-06,
83
+ "loss": 0.1805,
84
+ "step": 110
85
+ },
86
+ {
87
+ "epoch": 0.15,
88
+ "learning_rate": 8.503456909476364e-06,
89
+ "loss": 0.2322,
90
+ "step": 120
91
+ },
92
+ {
93
+ "epoch": 0.16,
94
+ "learning_rate": 8.419152029619696e-06,
95
+ "loss": 0.1636,
96
+ "step": 130
97
+ },
98
+ {
99
+ "epoch": 0.18,
100
+ "learning_rate": 8.32872785910012e-06,
101
+ "loss": 0.1689,
102
+ "step": 140
103
+ },
104
+ {
105
+ "epoch": 0.19,
106
+ "learning_rate": 8.232325584525908e-06,
107
+ "loss": 0.1738,
108
+ "step": 150
109
+ },
110
+ {
111
+ "epoch": 0.2,
112
+ "learning_rate": 8.130095726605169e-06,
113
+ "loss": 0.1509,
114
+ "step": 160
115
+ },
116
+ {
117
+ "epoch": 0.21,
118
+ "learning_rate": 8.022197905125629e-06,
119
+ "loss": 0.1821,
120
+ "step": 170
121
+ },
122
+ {
123
+ "epoch": 0.23,
124
+ "learning_rate": 7.90880058972729e-06,
125
+ "loss": 0.1435,
126
+ "step": 180
127
+ },
128
+ {
129
+ "epoch": 0.24,
130
+ "learning_rate": 7.790080836857073e-06,
131
+ "loss": 0.1621,
132
+ "step": 190
133
+ },
134
+ {
135
+ "epoch": 0.25,
136
+ "learning_rate": 7.666224013316203e-06,
137
+ "loss": 0.1527,
138
+ "step": 200
139
+ },
140
+ {
141
+ "epoch": 0.25,
142
+ "eval_accuracy": 0.0,
143
+ "eval_loss": 0.03772040829062462,
144
+ "eval_runtime": 29.7593,
145
+ "eval_samples_per_second": 95.029,
146
+ "eval_steps_per_second": 23.757,
147
+ "step": 200
148
+ },
149
+ {
150
+ "epoch": 0.26,
151
+ "learning_rate": 7.537423506831948e-06,
152
+ "loss": 0.1684,
153
+ "step": 210
154
+ },
155
+ {
156
+ "epoch": 0.28,
157
+ "learning_rate": 7.403880424105644e-06,
158
+ "loss": 0.2118,
159
+ "step": 220
160
+ },
161
+ {
162
+ "epoch": 0.29,
163
+ "learning_rate": 7.2658032768084485e-06,
164
+ "loss": 0.1381,
165
+ "step": 230
166
+ },
167
+ {
168
+ "epoch": 0.3,
169
+ "learning_rate": 7.123407656015124e-06,
170
+ "loss": 0.1364,
171
+ "step": 240
172
+ },
173
+ {
174
+ "epoch": 0.31,
175
+ "learning_rate": 6.976915895584163e-06,
176
+ "loss": 0.1147,
177
+ "step": 250
178
+ },
179
+ {
180
+ "epoch": 0.33,
181
+ "learning_rate": 6.826556725009857e-06,
182
+ "loss": 0.1129,
183
+ "step": 260
184
+ },
185
+ {
186
+ "epoch": 0.34,
187
+ "learning_rate": 6.672564912288353e-06,
188
+ "loss": 0.1357,
189
+ "step": 270
190
+ },
191
+ {
192
+ "epoch": 0.35,
193
+ "learning_rate": 6.515180897355285e-06,
194
+ "loss": 0.1285,
195
+ "step": 280
196
+ },
197
+ {
198
+ "epoch": 0.36,
199
+ "learning_rate": 6.354650416667365e-06,
200
+ "loss": 0.1013,
201
+ "step": 290
202
+ },
203
+ {
204
+ "epoch": 0.38,
205
+ "learning_rate": 6.191224119514071e-06,
206
+ "loss": 0.1483,
207
+ "step": 300
208
+ },
209
+ {
210
+ "epoch": 0.38,
211
+ "eval_accuracy": 0.0,
212
+ "eval_loss": 0.07286300510168076,
213
+ "eval_runtime": 29.1592,
214
+ "eval_samples_per_second": 96.985,
215
+ "eval_steps_per_second": 24.246,
216
+ "step": 300
217
+ }
218
+ ],
219
+ "logging_steps": 10,
220
+ "max_steps": 795,
221
+ "num_train_epochs": 1,
222
+ "save_steps": 100,
223
+ "total_flos": 0.0,
224
+ "trial_name": null,
225
+ "trial_params": null
226
+ }
checkpoint-300/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97515eaa596c1259df8da372577f8444c126856d2334b3f90d539244c52eb51c
3
+ size 4664
checkpoint-300/vocab.txt ADDED
The diff for this file is too large to render. See raw diff