Hugging Face's logo

worldboss
/
falcon-7b-worldboss-ft

PEFT
llama
Model card Files Community
4

Upload folder using huggingface_hub

#2
by worldboss - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+130806
-0
Files changed (11) hide show
  1. README.md +32 -0
  2. adapter_config.json +23 -0
  3. adapter_model.bin +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +17 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +7 -0
  10. trainer_state.json +736 -0
  11. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
+ - llm_int8_threshold: 6.0
22
+ - llm_int8_skip_modules: None
23
+ - llm_int8_enable_fp32_cpu_offload: False
24
+ - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
+ - bnb_4bit_use_double_quant: False
27
+ - bnb_4bit_compute_dtype: float16
28
+ ### Framework versions
29
+
30
+ - PEFT 0.5.0.dev0
31
+
32
+ - PEFT 0.5.0.dev0
adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "ybelkada/falcon-7b-sharded-bf16",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "query_key_value",
18
+ "dense",
19
+ "dense_h_to_4h",
20
+ "dense_4h_to_h"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d7b785c5898635bf81d340ce11d1b475c27cede41abc141b8809f3313f70893
3
+ size 522284877
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71b98472c7a174766e790c7c8716d81b298dac0735ad3a90c502a33dbc4583bb
3
+ size 1044539653
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01a42de28d0225cbeb5044d25abea7fe423b23d9a0394f696544cfc3b8dc5699
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2a25f133d8edd724f544d8f0f5d6f5fc7c5822269fb2ddbe4f1912a4b23a53a
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "eos_token": "<|endoftext|>",
16
+ "pad_token": "<|endoftext|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "<|endoftext|>",
5
+ "model_max_length": 2048,
6
+ "tokenizer_class": "PreTrainedTokenizerFast"
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,736 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.0482994566311129,
5
+ "global_step": 120,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 0.0002,
13
+ "loss": 3.9383,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 0.0002,
19
+ "loss": 4.297,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.0,
24
+ "learning_rate": 0.0002,
25
+ "loss": 4.4497,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.0,
30
+ "learning_rate": 0.0002,
31
+ "loss": 4.1237,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.0,
36
+ "learning_rate": 0.0002,
37
+ "loss": 3.9559,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.0,
42
+ "learning_rate": 0.0002,
43
+ "loss": 3.437,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.0,
48
+ "learning_rate": 0.0002,
49
+ "loss": 2.5411,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.0,
54
+ "learning_rate": 0.0002,
55
+ "loss": 2.796,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.0,
60
+ "learning_rate": 0.0002,
61
+ "loss": 2.3798,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.0,
66
+ "learning_rate": 0.0002,
67
+ "loss": 2.3777,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.0,
72
+ "learning_rate": 0.0002,
73
+ "loss": 3.0632,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.0,
78
+ "learning_rate": 0.0002,
79
+ "loss": 2.553,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.01,
84
+ "learning_rate": 0.0002,
85
+ "loss": 2.6332,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.01,
90
+ "learning_rate": 0.0002,
91
+ "loss": 2.2341,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.01,
96
+ "learning_rate": 0.0002,
97
+ "loss": 2.4234,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.01,
102
+ "learning_rate": 0.0002,
103
+ "loss": 2.1505,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.01,
108
+ "learning_rate": 0.0002,
109
+ "loss": 2.6074,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.01,
114
+ "learning_rate": 0.0002,
115
+ "loss": 2.1098,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.01,
120
+ "learning_rate": 0.0002,
121
+ "loss": 2.4064,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.01,
126
+ "learning_rate": 0.0002,
127
+ "loss": 2.0261,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.01,
132
+ "learning_rate": 0.0002,
133
+ "loss": 2.3355,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.01,
138
+ "learning_rate": 0.0002,
139
+ "loss": 2.2424,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.01,
144
+ "learning_rate": 0.0002,
145
+ "loss": 1.9745,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.01,
150
+ "learning_rate": 0.0002,
151
+ "loss": 2.1781,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.01,
156
+ "learning_rate": 0.0002,
157
+ "loss": 1.9489,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.01,
162
+ "learning_rate": 0.0002,
163
+ "loss": 2.0495,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.01,
168
+ "learning_rate": 0.0002,
169
+ "loss": 2.13,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.01,
174
+ "learning_rate": 0.0002,
175
+ "loss": 1.7854,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.01,
180
+ "learning_rate": 0.0002,
181
+ "loss": 2.2759,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.01,
186
+ "learning_rate": 0.0002,
187
+ "loss": 1.8816,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.01,
192
+ "learning_rate": 0.0002,
193
+ "loss": 1.9239,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.01,
198
+ "learning_rate": 0.0002,
199
+ "loss": 1.963,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.01,
204
+ "learning_rate": 0.0002,
205
+ "loss": 1.9837,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.01,
210
+ "learning_rate": 0.0002,
211
+ "loss": 2.2882,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.01,
216
+ "learning_rate": 0.0002,
217
+ "loss": 2.501,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.01,
222
+ "learning_rate": 0.0002,
223
+ "loss": 2.2086,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.01,
228
+ "learning_rate": 0.0002,
229
+ "loss": 1.8153,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.02,
234
+ "learning_rate": 0.0002,
235
+ "loss": 1.906,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.02,
240
+ "learning_rate": 0.0002,
241
+ "loss": 2.2252,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.02,
246
+ "learning_rate": 0.0002,
247
+ "loss": 2.1101,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.02,
252
+ "learning_rate": 0.0002,
253
+ "loss": 1.9331,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.02,
258
+ "learning_rate": 0.0002,
259
+ "loss": 2.2006,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.02,
264
+ "learning_rate": 0.0002,
265
+ "loss": 2.0551,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.02,
270
+ "learning_rate": 0.0002,
271
+ "loss": 1.8635,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.02,
276
+ "learning_rate": 0.0002,
277
+ "loss": 1.7884,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.02,
282
+ "learning_rate": 0.0002,
283
+ "loss": 1.8641,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.02,
288
+ "learning_rate": 0.0002,
289
+ "loss": 1.9707,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.02,
294
+ "learning_rate": 0.0002,
295
+ "loss": 1.638,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.02,
300
+ "learning_rate": 0.0002,
301
+ "loss": 1.6951,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.02,
306
+ "learning_rate": 0.0002,
307
+ "loss": 1.6499,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.02,
312
+ "learning_rate": 0.0002,
313
+ "loss": 4.0906,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.02,
318
+ "learning_rate": 0.0002,
319
+ "loss": 3.8166,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.02,
324
+ "learning_rate": 0.0002,
325
+ "loss": 3.2648,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.02,
330
+ "learning_rate": 0.0002,
331
+ "loss": 2.8758,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.02,
336
+ "learning_rate": 0.0002,
337
+ "loss": 2.4187,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.02,
342
+ "learning_rate": 0.0002,
343
+ "loss": 2.366,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.02,
348
+ "learning_rate": 0.0002,
349
+ "loss": 2.9111,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.02,
354
+ "learning_rate": 0.0002,
355
+ "loss": 2.1172,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.02,
360
+ "learning_rate": 0.0002,
361
+ "loss": 2.2097,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.02,
366
+ "learning_rate": 0.0002,
367
+ "loss": 2.214,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.02,
372
+ "learning_rate": 0.0002,
373
+ "loss": 2.2931,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.02,
378
+ "learning_rate": 0.0002,
379
+ "loss": 2.3941,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.03,
384
+ "learning_rate": 0.0002,
385
+ "loss": 2.0872,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.03,
390
+ "learning_rate": 0.0002,
391
+ "loss": 1.9758,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.03,
396
+ "learning_rate": 0.0002,
397
+ "loss": 2.1443,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 0.03,
402
+ "learning_rate": 0.0002,
403
+ "loss": 1.8564,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 0.03,
408
+ "learning_rate": 0.0002,
409
+ "loss": 2.2959,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 0.03,
414
+ "learning_rate": 0.0002,
415
+ "loss": 2.111,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 0.03,
420
+ "learning_rate": 0.0002,
421
+ "loss": 2.3046,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 0.03,
426
+ "learning_rate": 0.0002,
427
+ "loss": 1.7973,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 0.03,
432
+ "learning_rate": 0.0002,
433
+ "loss": 2.2716,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 0.03,
438
+ "learning_rate": 0.0002,
439
+ "loss": 2.0394,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 0.03,
444
+ "learning_rate": 0.0002,
445
+ "loss": 2.3104,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 0.03,
450
+ "learning_rate": 0.0002,
451
+ "loss": 2.2478,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 0.03,
456
+ "learning_rate": 0.0002,
457
+ "loss": 1.9765,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 0.03,
462
+ "learning_rate": 0.0002,
463
+ "loss": 2.3162,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 0.03,
468
+ "learning_rate": 0.0002,
469
+ "loss": 2.1498,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 0.03,
474
+ "learning_rate": 0.0002,
475
+ "loss": 1.9034,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 0.03,
480
+ "learning_rate": 0.0002,
481
+ "loss": 2.1262,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 0.03,
486
+ "learning_rate": 0.0002,
487
+ "loss": 2.1205,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 0.03,
492
+ "learning_rate": 0.0002,
493
+ "loss": 1.7249,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 0.03,
498
+ "learning_rate": 0.0002,
499
+ "loss": 2.0516,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 0.03,
504
+ "learning_rate": 0.0002,
505
+ "loss": 1.6536,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 0.03,
510
+ "learning_rate": 0.0002,
511
+ "loss": 2.1003,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 0.03,
516
+ "learning_rate": 0.0002,
517
+ "loss": 1.9858,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 0.03,
522
+ "learning_rate": 0.0002,
523
+ "loss": 1.9845,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 0.04,
528
+ "learning_rate": 0.0002,
529
+ "loss": 2.1915,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 0.04,
534
+ "learning_rate": 0.0002,
535
+ "loss": 1.9285,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 0.04,
540
+ "learning_rate": 0.0002,
541
+ "loss": 1.7922,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 0.04,
546
+ "learning_rate": 0.0002,
547
+ "loss": 2.0,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 0.04,
552
+ "learning_rate": 0.0002,
553
+ "loss": 2.0684,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 0.04,
558
+ "learning_rate": 0.0002,
559
+ "loss": 1.5623,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 0.04,
564
+ "learning_rate": 0.0002,
565
+ "loss": 1.6741,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 0.04,
570
+ "learning_rate": 0.0002,
571
+ "loss": 1.9877,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 0.04,
576
+ "learning_rate": 0.0002,
577
+ "loss": 1.8461,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 0.04,
582
+ "learning_rate": 0.0002,
583
+ "loss": 1.7781,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 0.04,
588
+ "learning_rate": 0.0002,
589
+ "loss": 1.6342,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 0.04,
594
+ "learning_rate": 0.0002,
595
+ "loss": 1.5765,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 0.04,
600
+ "learning_rate": 0.0002,
601
+ "loss": 1.7775,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 0.04,
606
+ "learning_rate": 0.0002,
607
+ "loss": 1.7932,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 0.04,
612
+ "learning_rate": 0.0002,
613
+ "loss": 3.0298,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 0.04,
618
+ "learning_rate": 0.0002,
619
+ "loss": 2.9655,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 0.04,
624
+ "learning_rate": 0.0002,
625
+ "loss": 2.8451,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 0.04,
630
+ "learning_rate": 0.0002,
631
+ "loss": 2.5459,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 0.04,
636
+ "learning_rate": 0.0002,
637
+ "loss": 2.3641,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 0.04,
642
+ "learning_rate": 0.0002,
643
+ "loss": 2.1216,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 0.04,
648
+ "learning_rate": 0.0002,
649
+ "loss": 2.1987,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 0.04,
654
+ "learning_rate": 0.0002,
655
+ "loss": 1.9505,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 0.04,
660
+ "learning_rate": 0.0002,
661
+ "loss": 1.6535,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 0.04,
666
+ "learning_rate": 0.0002,
667
+ "loss": 2.2628,
668
+ "step": 110
669
+ },
670
+ {
671
+ "epoch": 0.04,
672
+ "learning_rate": 0.0002,
673
+ "loss": 2.0268,
674
+ "step": 111
675
+ },
676
+ {
677
+ "epoch": 0.05,
678
+ "learning_rate": 0.0002,
679
+ "loss": 2.0586,
680
+ "step": 112
681
+ },
682
+ {
683
+ "epoch": 0.05,
684
+ "learning_rate": 0.0002,
685
+ "loss": 2.1307,
686
+ "step": 113
687
+ },
688
+ {
689
+ "epoch": 0.05,
690
+ "learning_rate": 0.0002,
691
+ "loss": 1.9611,
692
+ "step": 114
693
+ },
694
+ {
695
+ "epoch": 0.05,
696
+ "learning_rate": 0.0002,
697
+ "loss": 2.3489,
698
+ "step": 115
699
+ },
700
+ {
701
+ "epoch": 0.05,
702
+ "learning_rate": 0.0002,
703
+ "loss": 1.73,
704
+ "step": 116
705
+ },
706
+ {
707
+ "epoch": 0.05,
708
+ "learning_rate": 0.0002,
709
+ "loss": 2.1855,
710
+ "step": 117
711
+ },
712
+ {
713
+ "epoch": 0.05,
714
+ "learning_rate": 0.0002,
715
+ "loss": 2.138,
716
+ "step": 118
717
+ },
718
+ {
719
+ "epoch": 0.05,
720
+ "learning_rate": 0.0002,
721
+ "loss": 2.0705,
722
+ "step": 119
723
+ },
724
+ {
725
+ "epoch": 0.05,
726
+ "learning_rate": 0.0002,
727
+ "loss": 1.8792,
728
+ "step": 120
729
+ }
730
+ ],
731
+ "max_steps": 120,
732
+ "num_train_epochs": 1,
733
+ "total_flos": 479793488348160.0,
734
+ "trial_name": null,
735
+ "trial_params": null
736
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec2f57455273768b10622efa0b25e9698936e8c841f33c11a9b608f699f813c
3
+ size 3963