mrm8488 commited on
Commit
8e52830
1 Parent(s): 9a291d9

Initial commit from mrm8488

Browse files

Files changed (5) hide show
  1. config.json +164 -0
  2. pytorch_model.bin +3 -0
  3. scheduler.pt +0 -0
  4. trainer_state.json +442 -0
  5. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,164 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "EncoderDecoderModel"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "bert-base-multilingual-cased",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "BertForMaskedLM"
10
+ ],
11
+ "attention_probs_dropout_prob": 0.1,
12
+ "bad_words_ids": null,
13
+ "bos_token_id": null,
14
+ "chunk_size_feed_forward": 0,
15
+ "decoder_start_token_id": null,
16
+ "directionality": "bidi",
17
+ "diversity_penalty": 0.0,
18
+ "do_sample": false,
19
+ "early_stopping": false,
20
+ "eos_token_id": null,
21
+ "finetuning_task": null,
22
+ "gradient_checkpointing": false,
23
+ "hidden_act": "gelu",
24
+ "hidden_dropout_prob": 0.1,
25
+ "hidden_size": 768,
26
+ "id2label": {
27
+ "0": "LABEL_0",
28
+ "1": "LABEL_1"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 3072,
32
+ "is_decoder": true,
33
+ "is_encoder_decoder": false,
34
+ "label2id": {
35
+ "LABEL_0": 0,
36
+ "LABEL_1": 1
37
+ },
38
+ "layer_norm_eps": 1e-12,
39
+ "length_penalty": 1.0,
40
+ "max_length": 20,
41
+ "max_position_embeddings": 512,
42
+ "min_length": 0,
43
+ "model_type": "bert",
44
+ "no_repeat_ngram_size": 0,
45
+ "num_attention_heads": 12,
46
+ "num_beam_groups": 1,
47
+ "num_beams": 1,
48
+ "num_hidden_layers": 12,
49
+ "num_return_sequences": 1,
50
+ "output_attentions": false,
51
+ "output_hidden_states": false,
52
+ "pad_token_id": 0,
53
+ "pooler_fc_size": 768,
54
+ "pooler_num_attention_heads": 12,
55
+ "pooler_num_fc_layers": 3,
56
+ "pooler_size_per_head": 128,
57
+ "pooler_type": "first_token_transform",
58
+ "position_embedding_type": "absolute",
59
+ "prefix": null,
60
+ "pruned_heads": {},
61
+ "repetition_penalty": 1.0,
62
+ "return_dict": true,
63
+ "sep_token_id": null,
64
+ "task_specific_params": null,
65
+ "temperature": 1.0,
66
+ "tie_encoder_decoder": false,
67
+ "tie_word_embeddings": true,
68
+ "tokenizer_class": null,
69
+ "top_k": 50,
70
+ "top_p": 1.0,
71
+ "torchscript": false,
72
+ "type_vocab_size": 2,
73
+ "use_bfloat16": false,
74
+ "use_cache": true,
75
+ "vocab_size": 119547,
76
+ "xla_device": null
77
+ },
78
+ "decoder_start_token_id": 101,
79
+ "early_stopping": true,
80
+ "encoder": {
81
+ "_name_or_path": "bert-base-multilingual-cased",
82
+ "add_cross_attention": false,
83
+ "architectures": [
84
+ "BertForMaskedLM"
85
+ ],
86
+ "attention_probs_dropout_prob": 0.1,
87
+ "bad_words_ids": null,
88
+ "bos_token_id": null,
89
+ "chunk_size_feed_forward": 0,
90
+ "decoder_start_token_id": null,
91
+ "directionality": "bidi",
92
+ "diversity_penalty": 0.0,
93
+ "do_sample": false,
94
+ "early_stopping": false,
95
+ "eos_token_id": null,
96
+ "finetuning_task": null,
97
+ "gradient_checkpointing": false,
98
+ "hidden_act": "gelu",
99
+ "hidden_dropout_prob": 0.1,
100
+ "hidden_size": 768,
101
+ "id2label": {
102
+ "0": "LABEL_0",
103
+ "1": "LABEL_1"
104
+ },
105
+ "initializer_range": 0.02,
106
+ "intermediate_size": 3072,
107
+ "is_decoder": false,
108
+ "is_encoder_decoder": false,
109
+ "label2id": {
110
+ "LABEL_0": 0,
111
+ "LABEL_1": 1
112
+ },
113
+ "layer_norm_eps": 1e-12,
114
+ "length_penalty": 1.0,
115
+ "max_length": 20,
116
+ "max_position_embeddings": 512,
117
+ "min_length": 0,
118
+ "model_type": "bert",
119
+ "no_repeat_ngram_size": 0,
120
+ "num_attention_heads": 12,
121
+ "num_beam_groups": 1,
122
+ "num_beams": 1,
123
+ "num_hidden_layers": 12,
124
+ "num_return_sequences": 1,
125
+ "output_attentions": false,
126
+ "output_hidden_states": false,
127
+ "pad_token_id": 0,
128
+ "pooler_fc_size": 768,
129
+ "pooler_num_attention_heads": 12,
130
+ "pooler_num_fc_layers": 3,
131
+ "pooler_size_per_head": 128,
132
+ "pooler_type": "first_token_transform",
133
+ "position_embedding_type": "absolute",
134
+ "prefix": null,
135
+ "pruned_heads": {},
136
+ "repetition_penalty": 1.0,
137
+ "return_dict": true,
138
+ "sep_token_id": null,
139
+ "task_specific_params": null,
140
+ "temperature": 1.0,
141
+ "tie_encoder_decoder": false,
142
+ "tie_word_embeddings": true,
143
+ "tokenizer_class": null,
144
+ "top_k": 50,
145
+ "top_p": 1.0,
146
+ "torchscript": false,
147
+ "type_vocab_size": 2,
148
+ "use_bfloat16": false,
149
+ "use_cache": true,
150
+ "vocab_size": 119547,
151
+ "xla_device": null
152
+ },
153
+ "eos_token_id": 102,
154
+ "is_encoder_decoder": true,
155
+ "length_penalty": 2.0,
156
+ "max_length": 128,
157
+ "min_length": 6,
158
+ "model_type": "encoder-decoder",
159
+ "no_repeat_ngram_size": 3,
160
+ "num_beams": 4,
161
+ "pad_token_id": 0,
162
+ "tie_encoder_decoder": true,
163
+ "vocab_size": 119547
164
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:954e37bc127eb634e282294c32bee44655e69be9c5137abb4b4d5cc8e2c4e127
3
+ size 827921799
scheduler.pt ADDED
Binary file
trainer_state.json ADDED
@@ -0,0 +1,442 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 11.465683130211675,
5
+ "global_step": 71500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.1603592046183451,
12
+ "learning_rate": 4.942728855493449e-05,
13
+ "loss": 3.79368212890625,
14
+ "step": 1000
15
+ },
16
+ {
17
+ "epoch": 0.3207184092366902,
18
+ "learning_rate": 4.8854577109868964e-05,
19
+ "loss": 2.90124365234375,
20
+ "step": 2000
21
+ },
22
+ {
23
+ "epoch": 0.4810776138550353,
24
+ "learning_rate": 4.828186566480345e-05,
25
+ "loss": 2.601152587890625,
26
+ "step": 3000
27
+ },
28
+ {
29
+ "epoch": 0.6414368184733804,
30
+ "learning_rate": 4.7709154219737926e-05,
31
+ "loss": 2.300880615234375,
32
+ "step": 4000
33
+ },
34
+ {
35
+ "epoch": 0.8017960230917255,
36
+ "learning_rate": 4.713644277467241e-05,
37
+ "loss": 2.096479736328125,
38
+ "step": 5000
39
+ },
40
+ {
41
+ "epoch": 0.9621552277100706,
42
+ "learning_rate": 4.6563731329606894e-05,
43
+ "loss": 1.9469154052734374,
44
+ "step": 6000
45
+ },
46
+ {
47
+ "epoch": 1.1225144323284157,
48
+ "learning_rate": 4.5991019884541375e-05,
49
+ "loss": 1.593583740234375,
50
+ "step": 7000
51
+ },
52
+ {
53
+ "epoch": 1.2828736369467608,
54
+ "learning_rate": 4.5418308439475855e-05,
55
+ "loss": 1.4818087158203126,
56
+ "step": 8000
57
+ },
58
+ {
59
+ "epoch": 1.443232841565106,
60
+ "learning_rate": 4.4845596994410336e-05,
61
+ "loss": 1.446810791015625,
62
+ "step": 9000
63
+ },
64
+ {
65
+ "epoch": 1.603592046183451,
66
+ "learning_rate": 4.4272885549344824e-05,
67
+ "loss": 1.425852783203125,
68
+ "step": 10000
69
+ },
70
+ {
71
+ "epoch": 1.763951250801796,
72
+ "learning_rate": 4.37001741042793e-05,
73
+ "loss": 1.4071231689453125,
74
+ "step": 11000
75
+ },
76
+ {
77
+ "epoch": 1.9243104554201411,
78
+ "learning_rate": 4.3127462659213785e-05,
79
+ "loss": 1.3911290283203126,
80
+ "step": 12000
81
+ },
82
+ {
83
+ "epoch": 2.0846696600384864,
84
+ "learning_rate": 4.2554751214148266e-05,
85
+ "loss": 1.1586458740234375,
86
+ "step": 13000
87
+ },
88
+ {
89
+ "epoch": 2.2450288646568315,
90
+ "learning_rate": 4.198203976908275e-05,
91
+ "loss": 1.0172818603515625,
92
+ "step": 14000
93
+ },
94
+ {
95
+ "epoch": 2.4053880692751766,
96
+ "learning_rate": 4.140932832401723e-05,
97
+ "loss": 1.037733154296875,
98
+ "step": 15000
99
+ },
100
+ {
101
+ "epoch": 2.5657472738935216,
102
+ "learning_rate": 4.083661687895171e-05,
103
+ "loss": 1.0479439697265625,
104
+ "step": 16000
105
+ },
106
+ {
107
+ "epoch": 2.7261064785118667,
108
+ "learning_rate": 4.0263905433886196e-05,
109
+ "loss": 1.0455704345703125,
110
+ "step": 17000
111
+ },
112
+ {
113
+ "epoch": 2.886465683130212,
114
+ "learning_rate": 3.969119398882068e-05,
115
+ "loss": 1.047005859375,
116
+ "step": 18000
117
+ },
118
+ {
119
+ "epoch": 3.046824887748557,
120
+ "learning_rate": 3.911848254375516e-05,
121
+ "loss": 0.9432368774414063,
122
+ "step": 19000
123
+ },
124
+ {
125
+ "epoch": 3.207184092366902,
126
+ "learning_rate": 3.854577109868964e-05,
127
+ "loss": 0.7485797119140625,
128
+ "step": 20000
129
+ },
130
+ {
131
+ "epoch": 3.367543296985247,
132
+ "learning_rate": 3.797305965362412e-05,
133
+ "loss": 0.7684258422851562,
134
+ "step": 21000
135
+ },
136
+ {
137
+ "epoch": 3.527902501603592,
138
+ "learning_rate": 3.74003482085586e-05,
139
+ "loss": 0.7839947509765625,
140
+ "step": 22000
141
+ },
142
+ {
143
+ "epoch": 3.688261706221937,
144
+ "learning_rate": 3.682763676349308e-05,
145
+ "loss": 0.7889647216796875,
146
+ "step": 23000
147
+ },
148
+ {
149
+ "epoch": 3.8486209108402822,
150
+ "learning_rate": 3.625492531842756e-05,
151
+ "loss": 0.808726806640625,
152
+ "step": 24000
153
+ },
154
+ {
155
+ "epoch": 4.008980115458628,
156
+ "learning_rate": 3.568221387336205e-05,
157
+ "loss": 0.8007049560546875,
158
+ "step": 25000
159
+ },
160
+ {
161
+ "epoch": 4.169339320076973,
162
+ "learning_rate": 3.510950242829653e-05,
163
+ "loss": 0.5585819091796875,
164
+ "step": 26000
165
+ },
166
+ {
167
+ "epoch": 4.329698524695318,
168
+ "learning_rate": 3.453679098323101e-05,
169
+ "loss": 0.5828939819335938,
170
+ "step": 27000
171
+ },
172
+ {
173
+ "epoch": 4.490057729313663,
174
+ "learning_rate": 3.396407953816549e-05,
175
+ "loss": 0.5914722900390625,
176
+ "step": 28000
177
+ },
178
+ {
179
+ "epoch": 4.650416933932008,
180
+ "learning_rate": 3.339136809309997e-05,
181
+ "loss": 0.6112024536132813,
182
+ "step": 29000
183
+ },
184
+ {
185
+ "epoch": 4.810776138550353,
186
+ "learning_rate": 3.281865664803446e-05,
187
+ "loss": 0.6254320678710937,
188
+ "step": 30000
189
+ },
190
+ {
191
+ "epoch": 4.971135343168698,
192
+ "learning_rate": 3.2245945202968934e-05,
193
+ "loss": 0.6254859619140625,
194
+ "step": 31000
195
+ },
196
+ {
197
+ "epoch": 5.131494547787043,
198
+ "learning_rate": 3.167323375790342e-05,
199
+ "loss": 0.4557585144042969,
200
+ "step": 32000
201
+ },
202
+ {
203
+ "epoch": 5.291853752405388,
204
+ "learning_rate": 3.1100522312837895e-05,
205
+ "loss": 0.43634527587890626,
206
+ "step": 33000
207
+ },
208
+ {
209
+ "epoch": 5.452212957023733,
210
+ "learning_rate": 3.052781086777238e-05,
211
+ "loss": 0.46431121826171873,
212
+ "step": 34000
213
+ },
214
+ {
215
+ "epoch": 5.6125721616420785,
216
+ "learning_rate": 2.9955099422706867e-05,
217
+ "loss": 0.46590155029296876,
218
+ "step": 35000
219
+ },
220
+ {
221
+ "epoch": 5.772931366260424,
222
+ "learning_rate": 2.9382387977641345e-05,
223
+ "loss": 0.47823056030273436,
224
+ "step": 36000
225
+ },
226
+ {
227
+ "epoch": 5.933290570878769,
228
+ "learning_rate": 2.880967653257583e-05,
229
+ "loss": 0.4822598571777344,
230
+ "step": 37000
231
+ },
232
+ {
233
+ "epoch": 6.093649775497114,
234
+ "learning_rate": 2.823696508751031e-05,
235
+ "loss": 0.38333685302734377,
236
+ "step": 38000
237
+ },
238
+ {
239
+ "epoch": 6.254008980115459,
240
+ "learning_rate": 2.7664253642444794e-05,
241
+ "loss": 0.3381705017089844,
242
+ "step": 39000
243
+ },
244
+ {
245
+ "epoch": 6.414368184733804,
246
+ "learning_rate": 2.709154219737927e-05,
247
+ "loss": 0.3528754272460938,
248
+ "step": 40000
249
+ },
250
+ {
251
+ "epoch": 6.574727389352149,
252
+ "learning_rate": 2.6518830752313755e-05,
253
+ "loss": 0.358309326171875,
254
+ "step": 41000
255
+ },
256
+ {
257
+ "epoch": 6.735086593970494,
258
+ "learning_rate": 2.594611930724824e-05,
259
+ "loss": 0.36756768798828127,
260
+ "step": 42000
261
+ },
262
+ {
263
+ "epoch": 6.895445798588839,
264
+ "learning_rate": 2.537340786218272e-05,
265
+ "loss": 0.3713406677246094,
266
+ "step": 43000
267
+ },
268
+ {
269
+ "epoch": 7.055805003207184,
270
+ "learning_rate": 2.48006964171172e-05,
271
+ "loss": 0.330199462890625,
272
+ "step": 44000
273
+ },
274
+ {
275
+ "epoch": 7.216164207825529,
276
+ "learning_rate": 2.4227984972051682e-05,
277
+ "loss": 0.25607583618164065,
278
+ "step": 45000
279
+ },
280
+ {
281
+ "epoch": 7.376523412443874,
282
+ "learning_rate": 2.3655273526986163e-05,
283
+ "loss": 0.2684461975097656,
284
+ "step": 46000
285
+ },
286
+ {
287
+ "epoch": 7.536882617062219,
288
+ "learning_rate": 2.3082562081920647e-05,
289
+ "loss": 0.27459906005859375,
290
+ "step": 47000
291
+ },
292
+ {
293
+ "epoch": 7.6972418216805645,
294
+ "learning_rate": 2.2509850636855128e-05,
295
+ "loss": 0.2851370239257813,
296
+ "step": 48000
297
+ },
298
+ {
299
+ "epoch": 7.8576010262989096,
300
+ "learning_rate": 2.1937139191789612e-05,
301
+ "loss": 0.2865502624511719,
302
+ "step": 49000
303
+ },
304
+ {
305
+ "epoch": 8.017960230917256,
306
+ "learning_rate": 2.1364427746724092e-05,
307
+ "loss": 0.2776366882324219,
308
+ "step": 50000
309
+ },
310
+ {
311
+ "epoch": 8.1783194355356,
312
+ "learning_rate": 2.0791716301658573e-05,
313
+ "loss": 0.1949043884277344,
314
+ "step": 51000
315
+ },
316
+ {
317
+ "epoch": 8.338678640153946,
318
+ "learning_rate": 2.0219004856593054e-05,
319
+ "loss": 0.20391067504882812,
320
+ "step": 52000
321
+ },
322
+ {
323
+ "epoch": 8.49903784477229,
324
+ "learning_rate": 1.9646293411527535e-05,
325
+ "loss": 0.21169953918457032,
326
+ "step": 53000
327
+ },
328
+ {
329
+ "epoch": 8.659397049390636,
330
+ "learning_rate": 1.907358196646202e-05,
331
+ "loss": 0.21576847839355467,
332
+ "step": 54000
333
+ },
334
+ {
335
+ "epoch": 8.819756254008981,
336
+ "learning_rate": 1.8500870521396503e-05,
337
+ "loss": 0.21953797912597656,
338
+ "step": 55000
339
+ },
340
+ {
341
+ "epoch": 8.980115458627326,
342
+ "learning_rate": 1.7928159076330984e-05,
343
+ "loss": 0.22510685729980467,
344
+ "step": 56000
345
+ },
346
+ {
347
+ "epoch": 9.140474663245671,
348
+ "learning_rate": 1.7355447631265465e-05,
349
+ "loss": 0.15727980041503906,
350
+ "step": 57000
351
+ },
352
+ {
353
+ "epoch": 9.300833867864016,
354
+ "learning_rate": 1.6782736186199946e-05,
355
+ "loss": 0.15759164428710937,
356
+ "step": 58000
357
+ },
358
+ {
359
+ "epoch": 9.461193072482361,
360
+ "learning_rate": 1.6210024741134426e-05,
361
+ "loss": 0.16151931762695312,
362
+ "step": 59000
363
+ },
364
+ {
365
+ "epoch": 9.621552277100706,
366
+ "learning_rate": 1.563731329606891e-05,
367
+ "loss": 0.16533021545410156,
368
+ "step": 60000
369
+ },
370
+ {
371
+ "epoch": 9.781911481719051,
372
+ "learning_rate": 1.506460185100339e-05,
373
+ "loss": 0.16902993774414063,
374
+ "step": 61000
375
+ },
376
+ {
377
+ "epoch": 9.942270686337396,
378
+ "learning_rate": 1.4491890405937872e-05,
379
+ "loss": 0.16983213806152345,
380
+ "step": 62000
381
+ },
382
+ {
383
+ "epoch": 10.102629890955741,
384
+ "learning_rate": 1.3919178960872356e-05,
385
+ "loss": 0.1350119171142578,
386
+ "step": 63000
387
+ },
388
+ {
389
+ "epoch": 10.262989095574087,
390
+ "learning_rate": 1.3346467515806837e-05,
391
+ "loss": 0.1185531997680664,
392
+ "step": 64000
393
+ },
394
+ {
395
+ "epoch": 10.423348300192432,
396
+ "learning_rate": 1.277375607074132e-05,
397
+ "loss": 0.12531481170654296,
398
+ "step": 65000
399
+ },
400
+ {
401
+ "epoch": 10.583707504810777,
402
+ "learning_rate": 1.22010446256758e-05,
403
+ "loss": 0.1266140365600586,
404
+ "step": 66000
405
+ },
406
+ {
407
+ "epoch": 10.744066709429122,
408
+ "learning_rate": 1.1628333180610281e-05,
409
+ "loss": 0.12920794677734376,
410
+ "step": 67000
411
+ },
412
+ {
413
+ "epoch": 10.904425914047467,
414
+ "learning_rate": 1.1055621735544764e-05,
415
+ "loss": 0.1271785125732422,
416
+ "step": 68000
417
+ },
418
+ {
419
+ "epoch": 11.064785118665812,
420
+ "learning_rate": 1.0482910290479244e-05,
421
+ "loss": 0.11574956512451172,
422
+ "step": 69000
423
+ },
424
+ {
425
+ "epoch": 11.225144323284157,
426
+ "learning_rate": 9.910198845413727e-06,
427
+ "loss": 0.09364027404785157,
428
+ "step": 70000
429
+ },
430
+ {
431
+ "epoch": 11.385503527902502,
432
+ "learning_rate": 9.33748740034821e-06,
433
+ "loss": 0.09231264495849609,
434
+ "step": 71000
435
+ }
436
+ ],
437
+ "max_steps": 87304,
438
+ "num_train_epochs": 14,
439
+ "total_flos": 409014659202678144,
440
+ "trial_name": null,
441
+ "trial_params": null
442
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83900cd7c9eee7567e626c4bf4bbdf558cc6fc0dfb3fb5f84079ac68cc4f8a06
3
+ size 2223