bobox commited on
Commit
0929227
1 Parent(s): 0ad2630

Training in progress, epoch 1, checkpoint

Browse files
last-checkpoint/1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
last-checkpoint/README.md ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-small",
3
+ "architectures": [
4
+ "DebertaV2Model"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 3072,
12
+ "layer_norm_eps": 1e-07,
13
+ "max_position_embeddings": 512,
14
+ "max_relative_positions": -1,
15
+ "model_type": "deberta-v2",
16
+ "norm_rel_ebd": "layer_norm",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 6,
19
+ "pad_token_id": 0,
20
+ "pooler_dropout": 0,
21
+ "pooler_hidden_act": "gelu",
22
+ "pooler_hidden_size": 768,
23
+ "pos_att_type": [
24
+ "p2c",
25
+ "c2p"
26
+ ],
27
+ "position_biased_input": false,
28
+ "position_buckets": 256,
29
+ "relative_attention": true,
30
+ "share_att_key": true,
31
+ "torch_dtype": "float32",
32
+ "transformers_version": "4.41.2",
33
+ "type_vocab_size": 0,
34
+ "vocab_size": 128100
35
+ }
last-checkpoint/config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.1",
4
+ "transformers": "4.41.2",
5
+ "pytorch": "2.1.2"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
last-checkpoint/modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ }
14
+ ]
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24a991a022791dbad68bcccfc1a822f0a523b0d0033cb55ebbbb7278fa749813
3
+ size 1130520122
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2ad0a254872f555e16b4825539b2ed51a358095478594397a27f095a144279b
3
+ size 565251810
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c341d87b21e7e32706eb595f0f035e1e0247fe56c8c298f72c6e286fd8ab0e20
3
+ size 14244
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:072f295cd9400d44a23f01cc82ad8c9b8b89be4ef3aba1d3b8e750e9883aec90
3
+ size 1064
last-checkpoint/sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
last-checkpoint/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
+ }
last-checkpoint/spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/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
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,343 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 471,
6
+ "global_step": 4710,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1,
13
+ "grad_norm": 23.178159713745117,
14
+ "learning_rate": 3.004181408813123e-06,
15
+ "loss": 3.3296,
16
+ "step": 471
17
+ },
18
+ {
19
+ "epoch": 0.1,
20
+ "eval_nli-pairs_loss": 1.8879033327102661,
21
+ "eval_nli-pairs_runtime": 14.5841,
22
+ "eval_nli-pairs_samples_per_second": 466.81,
23
+ "eval_nli-pairs_steps_per_second": 29.21,
24
+ "step": 471
25
+ },
26
+ {
27
+ "epoch": 0.1,
28
+ "eval_scitail-pairs-pos_loss": 1.3438984155654907,
29
+ "eval_scitail-pairs-pos_runtime": 3.3055,
30
+ "eval_scitail-pairs-pos_samples_per_second": 394.499,
31
+ "eval_scitail-pairs-pos_steps_per_second": 24.807,
32
+ "step": 471
33
+ },
34
+ {
35
+ "epoch": 0.1,
36
+ "eval_qnli-contrastive_loss": 2.2597947120666504,
37
+ "eval_qnli-contrastive_runtime": 15.4075,
38
+ "eval_qnli-contrastive_samples_per_second": 354.567,
39
+ "eval_qnli-contrastive_steps_per_second": 22.197,
40
+ "step": 471
41
+ },
42
+ {
43
+ "epoch": 0.2,
44
+ "grad_norm": 20.00649070739746,
45
+ "learning_rate": 6.021228690897395e-06,
46
+ "loss": 1.8704,
47
+ "step": 942
48
+ },
49
+ {
50
+ "epoch": 0.2,
51
+ "eval_nli-pairs_loss": 0.9545981884002686,
52
+ "eval_nli-pairs_runtime": 14.5243,
53
+ "eval_nli-pairs_samples_per_second": 468.731,
54
+ "eval_nli-pairs_steps_per_second": 29.33,
55
+ "step": 942
56
+ },
57
+ {
58
+ "epoch": 0.2,
59
+ "eval_scitail-pairs-pos_loss": 0.5628724098205566,
60
+ "eval_scitail-pairs-pos_runtime": 3.3029,
61
+ "eval_scitail-pairs-pos_samples_per_second": 394.801,
62
+ "eval_scitail-pairs-pos_steps_per_second": 24.826,
63
+ "step": 942
64
+ },
65
+ {
66
+ "epoch": 0.2,
67
+ "eval_qnli-contrastive_loss": 1.840173602104187,
68
+ "eval_qnli-contrastive_runtime": 15.4134,
69
+ "eval_qnli-contrastive_samples_per_second": 354.433,
70
+ "eval_qnli-contrastive_steps_per_second": 22.189,
71
+ "step": 942
72
+ },
73
+ {
74
+ "epoch": 0.3,
75
+ "grad_norm": 14.465508460998535,
76
+ "learning_rate": 9.051141846252816e-06,
77
+ "loss": 1.2621,
78
+ "step": 1413
79
+ },
80
+ {
81
+ "epoch": 0.3,
82
+ "eval_nli-pairs_loss": 0.715168297290802,
83
+ "eval_nli-pairs_runtime": 14.4626,
84
+ "eval_nli-pairs_samples_per_second": 470.731,
85
+ "eval_nli-pairs_steps_per_second": 29.455,
86
+ "step": 1413
87
+ },
88
+ {
89
+ "epoch": 0.3,
90
+ "eval_scitail-pairs-pos_loss": 0.45529162883758545,
91
+ "eval_scitail-pairs-pos_runtime": 3.3513,
92
+ "eval_scitail-pairs-pos_samples_per_second": 389.098,
93
+ "eval_scitail-pairs-pos_steps_per_second": 24.468,
94
+ "step": 1413
95
+ },
96
+ {
97
+ "epoch": 0.3,
98
+ "eval_qnli-contrastive_loss": 1.388743281364441,
99
+ "eval_qnli-contrastive_runtime": 15.4261,
100
+ "eval_qnli-contrastive_samples_per_second": 354.139,
101
+ "eval_qnli-contrastive_steps_per_second": 22.17,
102
+ "step": 1413
103
+ },
104
+ {
105
+ "epoch": 0.4,
106
+ "grad_norm": 164.2409210205078,
107
+ "learning_rate": 1.2081055001608235e-05,
108
+ "loss": 1.2512,
109
+ "step": 1884
110
+ },
111
+ {
112
+ "epoch": 0.4,
113
+ "eval_nli-pairs_loss": 0.5274420976638794,
114
+ "eval_nli-pairs_runtime": 14.4658,
115
+ "eval_nli-pairs_samples_per_second": 470.628,
116
+ "eval_nli-pairs_steps_per_second": 29.449,
117
+ "step": 1884
118
+ },
119
+ {
120
+ "epoch": 0.4,
121
+ "eval_scitail-pairs-pos_loss": 0.3621281683444977,
122
+ "eval_scitail-pairs-pos_runtime": 3.3054,
123
+ "eval_scitail-pairs-pos_samples_per_second": 394.502,
124
+ "eval_scitail-pairs-pos_steps_per_second": 24.808,
125
+ "step": 1884
126
+ },
127
+ {
128
+ "epoch": 0.4,
129
+ "eval_qnli-contrastive_loss": 0.8418154120445251,
130
+ "eval_qnli-contrastive_runtime": 15.4336,
131
+ "eval_qnli-contrastive_samples_per_second": 353.967,
132
+ "eval_qnli-contrastive_steps_per_second": 22.159,
133
+ "step": 1884
134
+ },
135
+ {
136
+ "epoch": 0.5,
137
+ "grad_norm": 1.1174694299697876,
138
+ "learning_rate": 1.5110968156963654e-05,
139
+ "loss": 1.1724,
140
+ "step": 2355
141
+ },
142
+ {
143
+ "epoch": 0.5,
144
+ "eval_nli-pairs_loss": 0.49269717931747437,
145
+ "eval_nli-pairs_runtime": 14.6969,
146
+ "eval_nli-pairs_samples_per_second": 463.228,
147
+ "eval_nli-pairs_steps_per_second": 28.986,
148
+ "step": 2355
149
+ },
150
+ {
151
+ "epoch": 0.5,
152
+ "eval_scitail-pairs-pos_loss": 0.39243820309638977,
153
+ "eval_scitail-pairs-pos_runtime": 3.3462,
154
+ "eval_scitail-pairs-pos_samples_per_second": 389.699,
155
+ "eval_scitail-pairs-pos_steps_per_second": 24.506,
156
+ "step": 2355
157
+ },
158
+ {
159
+ "epoch": 0.5,
160
+ "eval_qnli-contrastive_loss": 0.14236953854560852,
161
+ "eval_qnli-contrastive_runtime": 15.7375,
162
+ "eval_qnli-contrastive_samples_per_second": 347.133,
163
+ "eval_qnli-contrastive_steps_per_second": 21.732,
164
+ "step": 2355
165
+ },
166
+ {
167
+ "epoch": 0.6,
168
+ "grad_norm": 8.20367431640625,
169
+ "learning_rate": 1.8140881312319075e-05,
170
+ "loss": 0.9036,
171
+ "step": 2826
172
+ },
173
+ {
174
+ "epoch": 0.6,
175
+ "eval_nli-pairs_loss": 0.46205422282218933,
176
+ "eval_nli-pairs_runtime": 14.6645,
177
+ "eval_nli-pairs_samples_per_second": 464.249,
178
+ "eval_nli-pairs_steps_per_second": 29.05,
179
+ "step": 2826
180
+ },
181
+ {
182
+ "epoch": 0.6,
183
+ "eval_scitail-pairs-pos_loss": 0.37769660353660583,
184
+ "eval_scitail-pairs-pos_runtime": 3.3324,
185
+ "eval_scitail-pairs-pos_samples_per_second": 391.314,
186
+ "eval_scitail-pairs-pos_steps_per_second": 24.607,
187
+ "step": 2826
188
+ },
189
+ {
190
+ "epoch": 0.6,
191
+ "eval_qnli-contrastive_loss": 0.3408704996109009,
192
+ "eval_qnli-contrastive_runtime": 15.4886,
193
+ "eval_qnli-contrastive_samples_per_second": 352.711,
194
+ "eval_qnli-contrastive_steps_per_second": 22.081,
195
+ "step": 2826
196
+ },
197
+ {
198
+ "epoch": 0.7,
199
+ "grad_norm": 13.231554985046387,
200
+ "learning_rate": 1.995898723197675e-05,
201
+ "loss": 1.0374,
202
+ "step": 3297
203
+ },
204
+ {
205
+ "epoch": 0.7,
206
+ "eval_nli-pairs_loss": 0.41105732321739197,
207
+ "eval_nli-pairs_runtime": 14.6153,
208
+ "eval_nli-pairs_samples_per_second": 465.813,
209
+ "eval_nli-pairs_steps_per_second": 29.148,
210
+ "step": 3297
211
+ },
212
+ {
213
+ "epoch": 0.7,
214
+ "eval_scitail-pairs-pos_loss": 0.3417491614818573,
215
+ "eval_scitail-pairs-pos_runtime": 3.3206,
216
+ "eval_scitail-pairs-pos_samples_per_second": 392.697,
217
+ "eval_scitail-pairs-pos_steps_per_second": 24.694,
218
+ "step": 3297
219
+ },
220
+ {
221
+ "epoch": 0.7,
222
+ "eval_qnli-contrastive_loss": 0.21254216134548187,
223
+ "eval_qnli-contrastive_runtime": 15.5347,
224
+ "eval_qnli-contrastive_samples_per_second": 351.664,
225
+ "eval_qnli-contrastive_steps_per_second": 22.015,
226
+ "step": 3297
227
+ },
228
+ {
229
+ "epoch": 0.8,
230
+ "grad_norm": 23.010765075683594,
231
+ "learning_rate": 1.9476312452068522e-05,
232
+ "loss": 0.9259,
233
+ "step": 3768
234
+ },
235
+ {
236
+ "epoch": 0.8,
237
+ "eval_nli-pairs_loss": 0.3852880597114563,
238
+ "eval_nli-pairs_runtime": 14.5431,
239
+ "eval_nli-pairs_samples_per_second": 468.125,
240
+ "eval_nli-pairs_steps_per_second": 29.292,
241
+ "step": 3768
242
+ },
243
+ {
244
+ "epoch": 0.8,
245
+ "eval_scitail-pairs-pos_loss": 0.2818955183029175,
246
+ "eval_scitail-pairs-pos_runtime": 3.3663,
247
+ "eval_scitail-pairs-pos_samples_per_second": 387.364,
248
+ "eval_scitail-pairs-pos_steps_per_second": 24.359,
249
+ "step": 3768
250
+ },
251
+ {
252
+ "epoch": 0.8,
253
+ "eval_qnli-contrastive_loss": 0.16461187601089478,
254
+ "eval_qnli-contrastive_runtime": 15.6023,
255
+ "eval_qnli-contrastive_samples_per_second": 350.141,
256
+ "eval_qnli-contrastive_steps_per_second": 21.92,
257
+ "step": 3768
258
+ },
259
+ {
260
+ "epoch": 0.9,
261
+ "grad_norm": 4.332469940185547,
262
+ "learning_rate": 1.8475083492522773e-05,
263
+ "loss": 0.8709,
264
+ "step": 4239
265
+ },
266
+ {
267
+ "epoch": 0.9,
268
+ "eval_nli-pairs_loss": 0.37486234307289124,
269
+ "eval_nli-pairs_runtime": 14.7406,
270
+ "eval_nli-pairs_samples_per_second": 461.852,
271
+ "eval_nli-pairs_steps_per_second": 28.9,
272
+ "step": 4239
273
+ },
274
+ {
275
+ "epoch": 0.9,
276
+ "eval_scitail-pairs-pos_loss": 0.29122474789619446,
277
+ "eval_scitail-pairs-pos_runtime": 3.5504,
278
+ "eval_scitail-pairs-pos_samples_per_second": 367.283,
279
+ "eval_scitail-pairs-pos_steps_per_second": 23.096,
280
+ "step": 4239
281
+ },
282
+ {
283
+ "epoch": 0.9,
284
+ "eval_qnli-contrastive_loss": 0.11566311866044998,
285
+ "eval_qnli-contrastive_runtime": 15.6925,
286
+ "eval_qnli-contrastive_samples_per_second": 348.129,
287
+ "eval_qnli-contrastive_steps_per_second": 21.794,
288
+ "step": 4239
289
+ },
290
+ {
291
+ "epoch": 1.0,
292
+ "grad_norm": 26.054088592529297,
293
+ "learning_rate": 1.701008869684049e-05,
294
+ "loss": 0.8686,
295
+ "step": 4710
296
+ },
297
+ {
298
+ "epoch": 1.0,
299
+ "eval_nli-pairs_loss": 0.36355406045913696,
300
+ "eval_nli-pairs_runtime": 14.5214,
301
+ "eval_nli-pairs_samples_per_second": 468.824,
302
+ "eval_nli-pairs_steps_per_second": 29.336,
303
+ "step": 4710
304
+ },
305
+ {
306
+ "epoch": 1.0,
307
+ "eval_scitail-pairs-pos_loss": 0.3108903765678406,
308
+ "eval_scitail-pairs-pos_runtime": 3.3842,
309
+ "eval_scitail-pairs-pos_samples_per_second": 385.319,
310
+ "eval_scitail-pairs-pos_steps_per_second": 24.23,
311
+ "step": 4710
312
+ },
313
+ {
314
+ "epoch": 1.0,
315
+ "eval_qnli-contrastive_loss": 0.09614822268486023,
316
+ "eval_qnli-contrastive_runtime": 15.7192,
317
+ "eval_qnli-contrastive_samples_per_second": 347.537,
318
+ "eval_qnli-contrastive_steps_per_second": 21.757,
319
+ "step": 4710
320
+ }
321
+ ],
322
+ "logging_steps": 471,
323
+ "max_steps": 9420,
324
+ "num_input_tokens_seen": 0,
325
+ "num_train_epochs": 2,
326
+ "save_steps": 4710,
327
+ "stateful_callbacks": {
328
+ "TrainerControl": {
329
+ "args": {
330
+ "should_epoch_stop": false,
331
+ "should_evaluate": false,
332
+ "should_log": false,
333
+ "should_save": true,
334
+ "should_training_stop": false
335
+ },
336
+ "attributes": {}
337
+ }
338
+ },
339
+ "total_flos": 0.0,
340
+ "train_batch_size": 28,
341
+ "trial_name": null,
342
+ "trial_params": null
343
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:560933d9c6eb8f6d338a68068ece75f7a5e1161e1e11dd62ae04fb4abb096493
3
+ size 5624