nbroad HF staff commited on
Commit
ebbba25
1 Parent(s): d6004d7

Model save

Browse files
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/deberta-v3-base
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ - precision
10
+ - recall
11
+ model-index:
12
+ - name: deberta-v3-base-orgs-v2
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # deberta-v3-base-orgs-v2
20
+
21
+ This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the None dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Accuracy: 0.9632
24
+ - F1: 0.7927
25
+ - Loss: 0.1186
26
+ - Precision: 0.8127
27
+ - Recall: 0.7735
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 0.0003
47
+ - train_batch_size: 256
48
+ - eval_batch_size: 256
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - lr_scheduler_warmup_steps: 20
53
+ - num_epochs: 3.0
54
+ - mixed_precision_training: Native AMP
55
+
56
+ ### Training results
57
+
58
+ | Training Loss | Epoch | Step | Accuracy | F1 | Validation Loss | Precision | Recall |
59
+ |:-------------:|:-----:|:----:|:--------:|:------:|:---------------:|:---------:|:------:|
60
+ | 0.0706 | 0.7 | 600 | 0.9602 | 0.7690 | 0.1138 | 0.7590 | 0.7793 |
61
+ | 0.0526 | 1.4 | 1200 | 0.9617 | 0.7870 | 0.1113 | 0.7942 | 0.7799 |
62
+ | 0.0409 | 2.11 | 1800 | 0.9627 | 0.7875 | 0.1125 | 0.7911 | 0.7839 |
63
+ | 0.0376 | 2.81 | 2400 | 0.9632 | 0.7927 | 0.1186 | 0.8127 | 0.7735 |
64
+
65
+
66
+ ### Framework versions
67
+
68
+ - Transformers 4.35.2
69
+ - Pytorch 2.1.0a0+32f93b1
70
+ - Datasets 2.15.0
71
+ - Tokenizers 0.15.0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
all_results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9627981870229008,
4
+ "eval_f1": 0.7875191815856777,
5
+ "eval_loss": 0.12025153636932373,
6
+ "eval_precision": 0.8050617025726835,
7
+ "eval_recall": 0.7707248698438126,
8
+ "eval_runtime": 3.4859,
9
+ "eval_samples": 3000,
10
+ "eval_samples_per_second": 860.608,
11
+ "eval_steps_per_second": 3.442,
12
+ "train_loss": 0.056466960860507065,
13
+ "train_runtime": 473.6102,
14
+ "train_samples": 109424,
15
+ "train_samples_per_second": 693.127,
16
+ "train_steps_per_second": 5.416
17
+ }
config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "finetuning_task": "ner",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-ORG",
14
+ "2": "I-ORG"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "B-ORG": 1,
20
+ "I-ORG": 2,
21
+ "O": 0
22
+ },
23
+ "layer_norm_eps": 1e-07,
24
+ "max_position_embeddings": 512,
25
+ "max_relative_positions": -1,
26
+ "model_type": "deberta-v2",
27
+ "norm_rel_ebd": "layer_norm",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 0,
31
+ "pooler_dropout": 0,
32
+ "pooler_hidden_act": "gelu",
33
+ "pooler_hidden_size": 768,
34
+ "pos_att_type": [
35
+ "p2c",
36
+ "c2p"
37
+ ],
38
+ "position_biased_input": false,
39
+ "position_buckets": 256,
40
+ "relative_attention": true,
41
+ "share_att_key": true,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.35.2",
44
+ "type_vocab_size": 0,
45
+ "vocab_size": 128100
46
+ }
eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9627981870229008,
4
+ "eval_f1": 0.7875191815856777,
5
+ "eval_loss": 0.12025153636932373,
6
+ "eval_precision": 0.8050617025726835,
7
+ "eval_recall": 0.7707248698438126,
8
+ "eval_runtime": 3.4859,
9
+ "eval_samples": 3000,
10
+ "eval_samples_per_second": 860.608,
11
+ "eval_steps_per_second": 3.442
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33e3414be3d3106da0080167cdaba17c9bef17ad636ab5438c5ce8d273428f07
3
+ size 735359804
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[CLS]",
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": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
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_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.056466960860507065,
4
+ "train_runtime": 473.6102,
5
+ "train_samples": 109424,
6
+ "train_samples_per_second": 693.127,
7
+ "train_steps_per_second": 5.416
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,382 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 600,
6
+ "global_step": 2565,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.06,
13
+ "learning_rate": 9.820662768031189e-05,
14
+ "loss": 0.2265,
15
+ "step": 50
16
+ },
17
+ {
18
+ "epoch": 0.12,
19
+ "learning_rate": 9.625730994152047e-05,
20
+ "loss": 0.0839,
21
+ "step": 100
22
+ },
23
+ {
24
+ "epoch": 0.18,
25
+ "learning_rate": 9.430799220272904e-05,
26
+ "loss": 0.0794,
27
+ "step": 150
28
+ },
29
+ {
30
+ "epoch": 0.23,
31
+ "learning_rate": 9.235867446393762e-05,
32
+ "loss": 0.0751,
33
+ "step": 200
34
+ },
35
+ {
36
+ "epoch": 0.29,
37
+ "learning_rate": 9.04093567251462e-05,
38
+ "loss": 0.0733,
39
+ "step": 250
40
+ },
41
+ {
42
+ "epoch": 0.35,
43
+ "learning_rate": 8.846003898635477e-05,
44
+ "loss": 0.0706,
45
+ "step": 300
46
+ },
47
+ {
48
+ "epoch": 0.41,
49
+ "learning_rate": 8.651072124756335e-05,
50
+ "loss": 0.0695,
51
+ "step": 350
52
+ },
53
+ {
54
+ "epoch": 0.47,
55
+ "learning_rate": 8.456140350877193e-05,
56
+ "loss": 0.071,
57
+ "step": 400
58
+ },
59
+ {
60
+ "epoch": 0.53,
61
+ "learning_rate": 8.26120857699805e-05,
62
+ "loss": 0.0691,
63
+ "step": 450
64
+ },
65
+ {
66
+ "epoch": 0.58,
67
+ "learning_rate": 8.066276803118908e-05,
68
+ "loss": 0.0668,
69
+ "step": 500
70
+ },
71
+ {
72
+ "epoch": 0.64,
73
+ "learning_rate": 7.871345029239767e-05,
74
+ "loss": 0.0659,
75
+ "step": 550
76
+ },
77
+ {
78
+ "epoch": 0.7,
79
+ "learning_rate": 7.676413255360623e-05,
80
+ "loss": 0.0706,
81
+ "step": 600
82
+ },
83
+ {
84
+ "epoch": 0.7,
85
+ "eval_accuracy": 0.9601979961832061,
86
+ "eval_f1": 0.769017980636238,
87
+ "eval_loss": 0.11379604041576385,
88
+ "eval_precision": 0.7589703588143526,
89
+ "eval_recall": 0.7793352022426913,
90
+ "eval_runtime": 3.4889,
91
+ "eval_samples_per_second": 859.867,
92
+ "eval_steps_per_second": 3.439,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.76,
97
+ "learning_rate": 7.481481481481481e-05,
98
+ "loss": 0.0689,
99
+ "step": 650
100
+ },
101
+ {
102
+ "epoch": 0.82,
103
+ "learning_rate": 7.28654970760234e-05,
104
+ "loss": 0.0658,
105
+ "step": 700
106
+ },
107
+ {
108
+ "epoch": 0.88,
109
+ "learning_rate": 7.091617933723196e-05,
110
+ "loss": 0.0645,
111
+ "step": 750
112
+ },
113
+ {
114
+ "epoch": 0.94,
115
+ "learning_rate": 6.896686159844055e-05,
116
+ "loss": 0.0663,
117
+ "step": 800
118
+ },
119
+ {
120
+ "epoch": 0.99,
121
+ "learning_rate": 6.701754385964913e-05,
122
+ "loss": 0.063,
123
+ "step": 850
124
+ },
125
+ {
126
+ "epoch": 1.05,
127
+ "learning_rate": 6.50682261208577e-05,
128
+ "loss": 0.0537,
129
+ "step": 900
130
+ },
131
+ {
132
+ "epoch": 1.11,
133
+ "learning_rate": 6.311890838206628e-05,
134
+ "loss": 0.055,
135
+ "step": 950
136
+ },
137
+ {
138
+ "epoch": 1.17,
139
+ "learning_rate": 6.116959064327486e-05,
140
+ "loss": 0.054,
141
+ "step": 1000
142
+ },
143
+ {
144
+ "epoch": 1.23,
145
+ "learning_rate": 5.9220272904483434e-05,
146
+ "loss": 0.0532,
147
+ "step": 1050
148
+ },
149
+ {
150
+ "epoch": 1.29,
151
+ "learning_rate": 5.727095516569201e-05,
152
+ "loss": 0.0534,
153
+ "step": 1100
154
+ },
155
+ {
156
+ "epoch": 1.35,
157
+ "learning_rate": 5.5321637426900584e-05,
158
+ "loss": 0.0516,
159
+ "step": 1150
160
+ },
161
+ {
162
+ "epoch": 1.4,
163
+ "learning_rate": 5.3372319688109166e-05,
164
+ "loss": 0.0526,
165
+ "step": 1200
166
+ },
167
+ {
168
+ "epoch": 1.4,
169
+ "eval_accuracy": 0.9617127862595419,
170
+ "eval_f1": 0.7870276823600727,
171
+ "eval_loss": 0.11129256337881088,
172
+ "eval_precision": 0.7942495921696574,
173
+ "eval_recall": 0.7799359231077293,
174
+ "eval_runtime": 3.4578,
175
+ "eval_samples_per_second": 867.603,
176
+ "eval_steps_per_second": 3.47,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 1.46,
181
+ "learning_rate": 5.142300194931774e-05,
182
+ "loss": 0.0512,
183
+ "step": 1250
184
+ },
185
+ {
186
+ "epoch": 1.52,
187
+ "learning_rate": 4.9473684210526315e-05,
188
+ "loss": 0.0515,
189
+ "step": 1300
190
+ },
191
+ {
192
+ "epoch": 1.58,
193
+ "learning_rate": 4.752436647173489e-05,
194
+ "loss": 0.048,
195
+ "step": 1350
196
+ },
197
+ {
198
+ "epoch": 1.64,
199
+ "learning_rate": 4.557504873294347e-05,
200
+ "loss": 0.0509,
201
+ "step": 1400
202
+ },
203
+ {
204
+ "epoch": 1.7,
205
+ "learning_rate": 4.362573099415205e-05,
206
+ "loss": 0.0495,
207
+ "step": 1450
208
+ },
209
+ {
210
+ "epoch": 1.75,
211
+ "learning_rate": 4.167641325536062e-05,
212
+ "loss": 0.0531,
213
+ "step": 1500
214
+ },
215
+ {
216
+ "epoch": 1.81,
217
+ "learning_rate": 3.97270955165692e-05,
218
+ "loss": 0.0524,
219
+ "step": 1550
220
+ },
221
+ {
222
+ "epoch": 1.87,
223
+ "learning_rate": 3.777777777777778e-05,
224
+ "loss": 0.0496,
225
+ "step": 1600
226
+ },
227
+ {
228
+ "epoch": 1.93,
229
+ "learning_rate": 3.582846003898635e-05,
230
+ "loss": 0.0487,
231
+ "step": 1650
232
+ },
233
+ {
234
+ "epoch": 1.99,
235
+ "learning_rate": 3.3879142300194935e-05,
236
+ "loss": 0.0514,
237
+ "step": 1700
238
+ },
239
+ {
240
+ "epoch": 2.05,
241
+ "learning_rate": 3.192982456140351e-05,
242
+ "loss": 0.0406,
243
+ "step": 1750
244
+ },
245
+ {
246
+ "epoch": 2.11,
247
+ "learning_rate": 2.9980506822612088e-05,
248
+ "loss": 0.0409,
249
+ "step": 1800
250
+ },
251
+ {
252
+ "epoch": 2.11,
253
+ "eval_accuracy": 0.9626550572519084,
254
+ "eval_f1": 0.7874886855073921,
255
+ "eval_loss": 0.1125219315290451,
256
+ "eval_precision": 0.7910689028086482,
257
+ "eval_recall": 0.7839407288746496,
258
+ "eval_runtime": 3.4674,
259
+ "eval_samples_per_second": 865.198,
260
+ "eval_steps_per_second": 3.461,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 2.16,
265
+ "learning_rate": 2.8031189083820663e-05,
266
+ "loss": 0.0386,
267
+ "step": 1850
268
+ },
269
+ {
270
+ "epoch": 2.22,
271
+ "learning_rate": 2.608187134502924e-05,
272
+ "loss": 0.0387,
273
+ "step": 1900
274
+ },
275
+ {
276
+ "epoch": 2.28,
277
+ "learning_rate": 2.413255360623782e-05,
278
+ "loss": 0.0399,
279
+ "step": 1950
280
+ },
281
+ {
282
+ "epoch": 2.34,
283
+ "learning_rate": 2.2183235867446394e-05,
284
+ "loss": 0.0379,
285
+ "step": 2000
286
+ },
287
+ {
288
+ "epoch": 2.4,
289
+ "learning_rate": 2.0233918128654973e-05,
290
+ "loss": 0.038,
291
+ "step": 2050
292
+ },
293
+ {
294
+ "epoch": 2.46,
295
+ "learning_rate": 1.8284600389863547e-05,
296
+ "loss": 0.04,
297
+ "step": 2100
298
+ },
299
+ {
300
+ "epoch": 2.51,
301
+ "learning_rate": 1.6335282651072126e-05,
302
+ "loss": 0.0382,
303
+ "step": 2150
304
+ },
305
+ {
306
+ "epoch": 2.57,
307
+ "learning_rate": 1.4385964912280702e-05,
308
+ "loss": 0.0384,
309
+ "step": 2200
310
+ },
311
+ {
312
+ "epoch": 2.63,
313
+ "learning_rate": 1.243664717348928e-05,
314
+ "loss": 0.038,
315
+ "step": 2250
316
+ },
317
+ {
318
+ "epoch": 2.69,
319
+ "learning_rate": 1.0487329434697857e-05,
320
+ "loss": 0.0399,
321
+ "step": 2300
322
+ },
323
+ {
324
+ "epoch": 2.75,
325
+ "learning_rate": 8.538011695906434e-06,
326
+ "loss": 0.0379,
327
+ "step": 2350
328
+ },
329
+ {
330
+ "epoch": 2.81,
331
+ "learning_rate": 6.588693957115009e-06,
332
+ "loss": 0.0376,
333
+ "step": 2400
334
+ },
335
+ {
336
+ "epoch": 2.81,
337
+ "eval_accuracy": 0.9631560114503817,
338
+ "eval_f1": 0.7926541499948702,
339
+ "eval_loss": 0.11860690265893936,
340
+ "eval_precision": 0.8127498422049232,
341
+ "eval_recall": 0.7735282338806568,
342
+ "eval_runtime": 3.4445,
343
+ "eval_samples_per_second": 870.961,
344
+ "eval_steps_per_second": 3.484,
345
+ "step": 2400
346
+ },
347
+ {
348
+ "epoch": 2.87,
349
+ "learning_rate": 4.639376218323587e-06,
350
+ "loss": 0.036,
351
+ "step": 2450
352
+ },
353
+ {
354
+ "epoch": 2.92,
355
+ "learning_rate": 2.690058479532164e-06,
356
+ "loss": 0.0366,
357
+ "step": 2500
358
+ },
359
+ {
360
+ "epoch": 2.98,
361
+ "learning_rate": 7.407407407407408e-07,
362
+ "loss": 0.0375,
363
+ "step": 2550
364
+ },
365
+ {
366
+ "epoch": 3.0,
367
+ "step": 2565,
368
+ "total_flos": 1.7165637031885056e+16,
369
+ "train_loss": 0.056466960860507065,
370
+ "train_runtime": 473.6102,
371
+ "train_samples_per_second": 693.127,
372
+ "train_steps_per_second": 5.416
373
+ }
374
+ ],
375
+ "logging_steps": 50,
376
+ "max_steps": 2565,
377
+ "num_train_epochs": 3,
378
+ "save_steps": 500,
379
+ "total_flos": 1.7165637031885056e+16,
380
+ "trial_name": null,
381
+ "trial_params": null
382
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8477dc023ec1022bcc64d9971312e6e9e0f93be242ffa235784eb729a3626e4
3
+ size 4600