BENBENBENb commited on
Commit
0b8df04
1 Parent(s): ae7e378

End of training

Browse files
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama2
3
+ base_model: lmsys/vicuna-7b-v1.5
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: finetune_arc_1_cot
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # finetune_arc_1_cot
15
+
16
+ This model is a fine-tuned version of [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 1.2197
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0001
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 8
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - lr_scheduler_warmup_steps: 5
44
+ - num_epochs: 1
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 1.2522 | 1.0 | 150 | 1.2197 |
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 4.35.2
57
+ - Pytorch 2.1.0+cu121
58
+ - Datasets 2.15.0
59
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "lmsys/vicuna-7b-v1.5",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layers_pattern": null,
10
+ "layers_to_transform": null,
11
+ "lora_alpha": 64,
12
+ "lora_dropout": 0.1,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 16,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "gate_proj",
20
+ "q_proj",
21
+ "up_proj",
22
+ "v_proj",
23
+ "down_proj",
24
+ "o_proj",
25
+ "k_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM"
28
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71abeb44c21cccca9e876254bdf78370d1962ba40687714d22f6f9c68ebc368e
3
+ size 160069834
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36cf62dc07145e503a951e36bb6e6fa1e29a0d36300ee074c22a997c77c6eb7f
3
+ size 159967880
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 1.2855440950393677,
4
+ "train_runtime": 278.1355,
5
+ "train_samples_per_second": 2.157,
6
+ "train_steps_per_second": 0.539
7
+ }
args.txt ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ base_model_name: lmsys/vicuna-7b-v1.5
2
+ batch_size: 4
3
+ cot: true
4
+ dataset_name: BENBENBENb/ARC1000COT
5
+ epochs: 1
6
+ eval_strategy: epoch
7
+ learning_rate: 0.0001
8
+ logging_steps: 1
9
+ output_dir: BENBENBENb/finetune_arc_1_cot
10
+ seed: 42
11
+ warmup_steps: 5
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 1.2855440950393677,
4
+ "train_runtime": 278.1355,
5
+ "train_samples_per_second": 2.157,
6
+ "train_steps_per_second": 0.539
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,936 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 150,
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": 2e-05,
14
+ "loss": 2.2293,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 4e-05,
20
+ "loss": 2.007,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.02,
25
+ "learning_rate": 6e-05,
26
+ "loss": 2.1479,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.03,
31
+ "learning_rate": 8e-05,
32
+ "loss": 1.9411,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.03,
37
+ "learning_rate": 0.0001,
38
+ "loss": 1.9661,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.04,
43
+ "learning_rate": 9.931034482758621e-05,
44
+ "loss": 1.8085,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.05,
49
+ "learning_rate": 9.862068965517242e-05,
50
+ "loss": 2.0453,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.05,
55
+ "learning_rate": 9.793103448275862e-05,
56
+ "loss": 1.7957,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.06,
61
+ "learning_rate": 9.724137931034482e-05,
62
+ "loss": 1.7825,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.07,
67
+ "learning_rate": 9.655172413793105e-05,
68
+ "loss": 1.4005,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.07,
73
+ "learning_rate": 9.586206896551725e-05,
74
+ "loss": 1.2935,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.08,
79
+ "learning_rate": 9.517241379310345e-05,
80
+ "loss": 1.508,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.09,
85
+ "learning_rate": 9.448275862068966e-05,
86
+ "loss": 1.7479,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.09,
91
+ "learning_rate": 9.379310344827587e-05,
92
+ "loss": 1.5322,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.1,
97
+ "learning_rate": 9.310344827586207e-05,
98
+ "loss": 1.6156,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.11,
103
+ "learning_rate": 9.241379310344827e-05,
104
+ "loss": 1.5161,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.11,
109
+ "learning_rate": 9.172413793103448e-05,
110
+ "loss": 1.3889,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.12,
115
+ "learning_rate": 9.10344827586207e-05,
116
+ "loss": 1.3077,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.13,
121
+ "learning_rate": 9.034482758620691e-05,
122
+ "loss": 1.2614,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.13,
127
+ "learning_rate": 8.96551724137931e-05,
128
+ "loss": 1.4132,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.14,
133
+ "learning_rate": 8.896551724137931e-05,
134
+ "loss": 1.3799,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.15,
139
+ "learning_rate": 8.827586206896552e-05,
140
+ "loss": 1.3482,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.15,
145
+ "learning_rate": 8.758620689655173e-05,
146
+ "loss": 1.3903,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.16,
151
+ "learning_rate": 8.689655172413794e-05,
152
+ "loss": 1.3016,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.17,
157
+ "learning_rate": 8.620689655172413e-05,
158
+ "loss": 1.3541,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.17,
163
+ "learning_rate": 8.551724137931035e-05,
164
+ "loss": 1.1017,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.18,
169
+ "learning_rate": 8.482758620689656e-05,
170
+ "loss": 1.3111,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.19,
175
+ "learning_rate": 8.413793103448277e-05,
176
+ "loss": 1.1006,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.19,
181
+ "learning_rate": 8.344827586206896e-05,
182
+ "loss": 1.3251,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.2,
187
+ "learning_rate": 8.275862068965517e-05,
188
+ "loss": 1.2726,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.21,
193
+ "learning_rate": 8.206896551724138e-05,
194
+ "loss": 1.3384,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.21,
199
+ "learning_rate": 8.137931034482759e-05,
200
+ "loss": 1.162,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.22,
205
+ "learning_rate": 8.06896551724138e-05,
206
+ "loss": 1.3263,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.23,
211
+ "learning_rate": 8e-05,
212
+ "loss": 1.3329,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.23,
217
+ "learning_rate": 7.931034482758621e-05,
218
+ "loss": 1.1882,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.24,
223
+ "learning_rate": 7.862068965517242e-05,
224
+ "loss": 1.1654,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.25,
229
+ "learning_rate": 7.793103448275862e-05,
230
+ "loss": 1.2161,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.25,
235
+ "learning_rate": 7.724137931034483e-05,
236
+ "loss": 1.258,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.26,
241
+ "learning_rate": 7.655172413793103e-05,
242
+ "loss": 1.1031,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.27,
247
+ "learning_rate": 7.586206896551724e-05,
248
+ "loss": 1.1444,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.27,
253
+ "learning_rate": 7.517241379310345e-05,
254
+ "loss": 1.088,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.28,
259
+ "learning_rate": 7.448275862068966e-05,
260
+ "loss": 1.1113,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.29,
265
+ "learning_rate": 7.379310344827587e-05,
266
+ "loss": 1.2534,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.29,
271
+ "learning_rate": 7.310344827586208e-05,
272
+ "loss": 1.1533,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.3,
277
+ "learning_rate": 7.241379310344828e-05,
278
+ "loss": 1.323,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.31,
283
+ "learning_rate": 7.172413793103448e-05,
284
+ "loss": 1.2384,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.31,
289
+ "learning_rate": 7.103448275862069e-05,
290
+ "loss": 1.3594,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.32,
295
+ "learning_rate": 7.03448275862069e-05,
296
+ "loss": 1.114,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.33,
301
+ "learning_rate": 6.96551724137931e-05,
302
+ "loss": 1.1204,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.33,
307
+ "learning_rate": 6.896551724137931e-05,
308
+ "loss": 1.0803,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.34,
313
+ "learning_rate": 6.827586206896552e-05,
314
+ "loss": 1.2556,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.35,
319
+ "learning_rate": 6.758620689655173e-05,
320
+ "loss": 1.1148,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.35,
325
+ "learning_rate": 6.689655172413794e-05,
326
+ "loss": 1.2603,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.36,
331
+ "learning_rate": 6.620689655172415e-05,
332
+ "loss": 1.442,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.37,
337
+ "learning_rate": 6.551724137931034e-05,
338
+ "loss": 1.1207,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.37,
343
+ "learning_rate": 6.482758620689655e-05,
344
+ "loss": 1.4429,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.38,
349
+ "learning_rate": 6.482758620689655e-05,
350
+ "loss": 1.1722,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.39,
355
+ "learning_rate": 6.413793103448276e-05,
356
+ "loss": 1.3962,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.39,
361
+ "learning_rate": 6.344827586206897e-05,
362
+ "loss": 1.2407,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.4,
367
+ "learning_rate": 6.275862068965517e-05,
368
+ "loss": 1.0778,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.41,
373
+ "learning_rate": 6.206896551724138e-05,
374
+ "loss": 1.2103,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.41,
379
+ "learning_rate": 6.137931034482759e-05,
380
+ "loss": 1.1721,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.42,
385
+ "learning_rate": 6.068965517241379e-05,
386
+ "loss": 1.0806,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.43,
391
+ "learning_rate": 6e-05,
392
+ "loss": 1.276,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.43,
397
+ "learning_rate": 5.93103448275862e-05,
398
+ "loss": 1.3421,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.44,
403
+ "learning_rate": 5.862068965517241e-05,
404
+ "loss": 1.2496,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.45,
409
+ "learning_rate": 5.7931034482758627e-05,
410
+ "loss": 0.9466,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.45,
415
+ "learning_rate": 5.7241379310344835e-05,
416
+ "loss": 1.3298,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.46,
421
+ "learning_rate": 5.6551724137931037e-05,
422
+ "loss": 1.1273,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.47,
427
+ "learning_rate": 5.5862068965517245e-05,
428
+ "loss": 1.3189,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.47,
433
+ "learning_rate": 5.517241379310345e-05,
434
+ "loss": 1.1226,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.48,
439
+ "learning_rate": 5.4482758620689655e-05,
440
+ "loss": 1.1242,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.49,
445
+ "learning_rate": 5.379310344827586e-05,
446
+ "loss": 1.2395,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.49,
451
+ "learning_rate": 5.3103448275862065e-05,
452
+ "loss": 1.1385,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.5,
457
+ "learning_rate": 5.241379310344828e-05,
458
+ "loss": 1.4045,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.51,
463
+ "learning_rate": 5.172413793103449e-05,
464
+ "loss": 1.2756,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.51,
469
+ "learning_rate": 5.10344827586207e-05,
470
+ "loss": 1.3189,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.52,
475
+ "learning_rate": 5.03448275862069e-05,
476
+ "loss": 1.2318,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.53,
481
+ "learning_rate": 4.9655172413793107e-05,
482
+ "loss": 1.0645,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.53,
487
+ "learning_rate": 4.896551724137931e-05,
488
+ "loss": 1.2349,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.54,
493
+ "learning_rate": 4.827586206896552e-05,
494
+ "loss": 1.1248,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.55,
499
+ "learning_rate": 4.7586206896551725e-05,
500
+ "loss": 1.5145,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.55,
505
+ "learning_rate": 4.689655172413793e-05,
506
+ "loss": 1.138,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.56,
511
+ "learning_rate": 4.6206896551724135e-05,
512
+ "loss": 1.0639,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.57,
517
+ "learning_rate": 4.551724137931035e-05,
518
+ "loss": 1.357,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.57,
523
+ "learning_rate": 4.482758620689655e-05,
524
+ "loss": 1.1459,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.58,
529
+ "learning_rate": 4.413793103448276e-05,
530
+ "loss": 1.0465,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.59,
535
+ "learning_rate": 4.344827586206897e-05,
536
+ "loss": 1.2478,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.59,
541
+ "learning_rate": 4.275862068965518e-05,
542
+ "loss": 1.0688,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.6,
547
+ "learning_rate": 4.2068965517241385e-05,
548
+ "loss": 1.2847,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.61,
553
+ "learning_rate": 4.1379310344827587e-05,
554
+ "loss": 1.2504,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.61,
559
+ "learning_rate": 4.0689655172413795e-05,
560
+ "loss": 1.1649,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.62,
565
+ "learning_rate": 4e-05,
566
+ "loss": 1.2221,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.63,
571
+ "learning_rate": 3.931034482758621e-05,
572
+ "loss": 1.024,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.63,
577
+ "learning_rate": 3.862068965517241e-05,
578
+ "loss": 1.262,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.64,
583
+ "learning_rate": 3.793103448275862e-05,
584
+ "loss": 1.3909,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.65,
589
+ "learning_rate": 3.724137931034483e-05,
590
+ "loss": 1.2316,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.65,
595
+ "learning_rate": 3.655172413793104e-05,
596
+ "loss": 1.1374,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.66,
601
+ "learning_rate": 3.586206896551724e-05,
602
+ "loss": 1.4087,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.67,
607
+ "learning_rate": 3.517241379310345e-05,
608
+ "loss": 1.4166,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.67,
613
+ "learning_rate": 3.4482758620689657e-05,
614
+ "loss": 1.2136,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.68,
619
+ "learning_rate": 3.3793103448275865e-05,
620
+ "loss": 1.2016,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.69,
625
+ "learning_rate": 3.310344827586207e-05,
626
+ "loss": 1.2509,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.69,
631
+ "learning_rate": 3.2413793103448275e-05,
632
+ "loss": 1.189,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.7,
637
+ "learning_rate": 3.172413793103448e-05,
638
+ "loss": 1.3552,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.71,
643
+ "learning_rate": 3.103448275862069e-05,
644
+ "loss": 1.1281,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.71,
649
+ "learning_rate": 3.0344827586206897e-05,
650
+ "loss": 1.3008,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.72,
655
+ "learning_rate": 2.96551724137931e-05,
656
+ "loss": 1.249,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.73,
661
+ "learning_rate": 2.8965517241379313e-05,
662
+ "loss": 0.994,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.73,
667
+ "learning_rate": 2.8275862068965518e-05,
668
+ "loss": 1.2791,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.74,
673
+ "learning_rate": 2.7586206896551727e-05,
674
+ "loss": 1.2621,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.75,
679
+ "learning_rate": 2.689655172413793e-05,
680
+ "loss": 1.3775,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.75,
685
+ "learning_rate": 2.620689655172414e-05,
686
+ "loss": 0.8981,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.76,
691
+ "learning_rate": 2.551724137931035e-05,
692
+ "loss": 1.3001,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.77,
697
+ "learning_rate": 2.4827586206896553e-05,
698
+ "loss": 1.3469,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.77,
703
+ "learning_rate": 2.413793103448276e-05,
704
+ "loss": 1.3073,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.78,
709
+ "learning_rate": 2.3448275862068967e-05,
710
+ "loss": 1.3737,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.79,
715
+ "learning_rate": 2.2758620689655175e-05,
716
+ "loss": 1.1672,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.79,
721
+ "learning_rate": 2.206896551724138e-05,
722
+ "loss": 1.1311,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.8,
727
+ "learning_rate": 2.137931034482759e-05,
728
+ "loss": 1.1298,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.81,
733
+ "learning_rate": 2.0689655172413793e-05,
734
+ "loss": 1.1022,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.81,
739
+ "learning_rate": 2e-05,
740
+ "loss": 1.1768,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.82,
745
+ "learning_rate": 1.9310344827586207e-05,
746
+ "loss": 1.127,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.83,
751
+ "learning_rate": 1.8620689655172415e-05,
752
+ "loss": 1.427,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.83,
757
+ "learning_rate": 1.793103448275862e-05,
758
+ "loss": 1.1697,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.84,
763
+ "learning_rate": 1.7241379310344828e-05,
764
+ "loss": 1.0438,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.85,
769
+ "learning_rate": 1.6551724137931037e-05,
770
+ "loss": 1.0684,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.85,
775
+ "learning_rate": 1.586206896551724e-05,
776
+ "loss": 1.174,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.86,
781
+ "learning_rate": 1.5172413793103448e-05,
782
+ "loss": 1.2778,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.87,
787
+ "learning_rate": 1.4482758620689657e-05,
788
+ "loss": 1.4606,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.87,
793
+ "learning_rate": 1.3793103448275863e-05,
794
+ "loss": 1.2492,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.88,
799
+ "learning_rate": 1.310344827586207e-05,
800
+ "loss": 1.0584,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.89,
805
+ "learning_rate": 1.2413793103448277e-05,
806
+ "loss": 1.2099,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.89,
811
+ "learning_rate": 1.1724137931034483e-05,
812
+ "loss": 1.0901,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.9,
817
+ "learning_rate": 1.103448275862069e-05,
818
+ "loss": 1.1183,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.91,
823
+ "learning_rate": 1.0344827586206897e-05,
824
+ "loss": 0.9985,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.91,
829
+ "learning_rate": 9.655172413793103e-06,
830
+ "loss": 1.2695,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.92,
835
+ "learning_rate": 8.96551724137931e-06,
836
+ "loss": 1.3367,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.93,
841
+ "learning_rate": 8.275862068965518e-06,
842
+ "loss": 1.2725,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.93,
847
+ "learning_rate": 7.586206896551724e-06,
848
+ "loss": 1.3437,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.94,
853
+ "learning_rate": 6.896551724137932e-06,
854
+ "loss": 1.314,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.95,
859
+ "learning_rate": 6.206896551724138e-06,
860
+ "loss": 1.2984,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.95,
865
+ "learning_rate": 5.517241379310345e-06,
866
+ "loss": 1.0817,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.96,
871
+ "learning_rate": 4.827586206896552e-06,
872
+ "loss": 1.2493,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.97,
877
+ "learning_rate": 4.137931034482759e-06,
878
+ "loss": 1.2914,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.97,
883
+ "learning_rate": 3.448275862068966e-06,
884
+ "loss": 1.3364,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.98,
889
+ "learning_rate": 2.7586206896551725e-06,
890
+ "loss": 1.2835,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.99,
895
+ "learning_rate": 2.0689655172413796e-06,
896
+ "loss": 1.1986,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.99,
901
+ "learning_rate": 1.3793103448275862e-06,
902
+ "loss": 1.1952,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 1.0,
907
+ "learning_rate": 6.896551724137931e-07,
908
+ "loss": 1.2522,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 1.0,
913
+ "eval_loss": 1.2197036743164062,
914
+ "eval_runtime": 24.7422,
915
+ "eval_samples_per_second": 8.083,
916
+ "eval_steps_per_second": 1.01,
917
+ "step": 150
918
+ },
919
+ {
920
+ "epoch": 1.0,
921
+ "step": 150,
922
+ "total_flos": 7657713303552000.0,
923
+ "train_loss": 1.2855440950393677,
924
+ "train_runtime": 278.1355,
925
+ "train_samples_per_second": 2.157,
926
+ "train_steps_per_second": 0.539
927
+ }
928
+ ],
929
+ "logging_steps": 1,
930
+ "max_steps": 150,
931
+ "num_train_epochs": 1,
932
+ "save_steps": 500,
933
+ "total_flos": 7657713303552000.0,
934
+ "trial_name": null,
935
+ "trial_params": null
936
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45aecd25bf3a9caeeeccc18bb10a2cd5148a1aa5f428f58c892c802811ba765e
3
+ size 4600