Hugging Face's logo

ZeroUniqueness
/
qlora-llama2-13b

PEFT
TensorBoard
Model card Files Metrics Community
ZeroUniqueness commited on
Commit
e7d1793
•
1 Parent(s): 21a1113

Training in progress, step 8000

Browse files
Files changed (9) hide show
  1. adapter_model.bin +1 -1
  2. checkpoint-8000/README.md +20 -0
  3. checkpoint-8000/adapter_config.json +26 -0
  4. checkpoint-8000/adapter_model.bin +3 -0
  5. checkpoint-8000/optimizer.pt +3 -0
  6. checkpoint-8000/rng_state.pth +3 -0
  7. checkpoint-8000/scheduler.pt +3 -0
  8. checkpoint-8000/trainer_state.json +560 -0
  9. checkpoint-8000/training_args.bin +3 -0
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:157f6b6252bea0a483afac1b940a1e1d1fef2b0645bc8ee85e303857453144a6
3
  size 500897101
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4391c3f67be599ec6891113b7074b9b9ecd890ea222792b2e018423f592bd1f
3
  size 500897101
checkpoint-8000/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: True
16
+ - bnb_4bit_compute_dtype: bfloat16
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.5.0.dev0
checkpoint-8000/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
4
+ "bias": "none",
5
+ "fan_in_fan_out": null,
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": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 32,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "v_proj",
18
+ "k_proj",
19
+ "up_proj",
20
+ "down_proj",
21
+ "gate_proj",
22
+ "o_proj",
23
+ "q_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
checkpoint-8000/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4391c3f67be599ec6891113b7074b9b9ecd890ea222792b2e018423f592bd1f
3
+ size 500897101
checkpoint-8000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fa222fc1c73aa91ebc8aabc3b2605cd943a439e6a71affa7f44e89b5f3be90c
3
+ size 1001723453
checkpoint-8000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3138ce747168baeb9a5b79edadd642d8b6308e2b4f29f3c24604bc8092aca021
3
+ size 14575
checkpoint-8000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d0708b67737e3740635d2f95d2a98504e4a39f2dbf75dc26041c92384992a5a
3
+ size 627
checkpoint-8000/trainer_state.json ADDED
@@ -0,0 +1,560 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6973471641540527,
3
+ "best_model_checkpoint": "./qlora-out/checkpoint-8000",
4
+ "epoch": 0.29827374072555085,
5
+ "global_step": 8000,
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": 0.00019999938245325715,
13
+ "loss": 0.9023,
14
+ "step": 100
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 0.00019999724773356797,
19
+ "loss": 0.8027,
20
+ "step": 200
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 0.0001999935882494411,
25
+ "loss": 0.8041,
26
+ "step": 300
27
+ },
28
+ {
29
+ "epoch": 0.01,
30
+ "learning_rate": 0.00019998840405667672,
31
+ "loss": 0.7944,
32
+ "step": 400
33
+ },
34
+ {
35
+ "epoch": 0.02,
36
+ "learning_rate": 0.00019998169523432365,
37
+ "loss": 0.81,
38
+ "step": 500
39
+ },
40
+ {
41
+ "epoch": 0.02,
42
+ "learning_rate": 0.0001999734618846785,
43
+ "loss": 0.7855,
44
+ "step": 600
45
+ },
46
+ {
47
+ "epoch": 0.03,
48
+ "learning_rate": 0.00019996370413328385,
49
+ "loss": 0.7849,
50
+ "step": 700
51
+ },
52
+ {
53
+ "epoch": 0.03,
54
+ "learning_rate": 0.00019995242212892653,
55
+ "loss": 0.7564,
56
+ "step": 800
57
+ },
58
+ {
59
+ "epoch": 0.03,
60
+ "learning_rate": 0.00019993961604363532,
61
+ "loss": 0.7724,
62
+ "step": 900
63
+ },
64
+ {
65
+ "epoch": 0.04,
66
+ "learning_rate": 0.00019992528607267815,
67
+ "loss": 0.7308,
68
+ "step": 1000
69
+ },
70
+ {
71
+ "epoch": 0.04,
72
+ "eval_loss": 0.7677998542785645,
73
+ "eval_runtime": 1774.3517,
74
+ "eval_samples_per_second": 0.305,
75
+ "eval_steps_per_second": 0.305,
76
+ "step": 1000
77
+ },
78
+ {
79
+ "epoch": 0.04,
80
+ "learning_rate": 0.0001999094324345594,
81
+ "loss": 0.7844,
82
+ "step": 1100
83
+ },
84
+ {
85
+ "epoch": 0.04,
86
+ "learning_rate": 0.00019989205537101633,
87
+ "loss": 0.7668,
88
+ "step": 1200
89
+ },
90
+ {
91
+ "epoch": 0.05,
92
+ "learning_rate": 0.00019987315514701553,
93
+ "loss": 0.7727,
94
+ "step": 1300
95
+ },
96
+ {
97
+ "epoch": 0.05,
98
+ "learning_rate": 0.00019985273205074878,
99
+ "loss": 0.7467,
100
+ "step": 1400
101
+ },
102
+ {
103
+ "epoch": 0.06,
104
+ "learning_rate": 0.00019983078639362883,
105
+ "loss": 0.7516,
106
+ "step": 1500
107
+ },
108
+ {
109
+ "epoch": 0.06,
110
+ "learning_rate": 0.00019980731851028445,
111
+ "loss": 0.7267,
112
+ "step": 1600
113
+ },
114
+ {
115
+ "epoch": 0.06,
116
+ "learning_rate": 0.0001997823287585554,
117
+ "loss": 0.7632,
118
+ "step": 1700
119
+ },
120
+ {
121
+ "epoch": 0.07,
122
+ "learning_rate": 0.000199755817519487,
123
+ "loss": 0.7392,
124
+ "step": 1800
125
+ },
126
+ {
127
+ "epoch": 0.07,
128
+ "learning_rate": 0.00019972778519732436,
129
+ "loss": 0.7528,
130
+ "step": 1900
131
+ },
132
+ {
133
+ "epoch": 0.07,
134
+ "learning_rate": 0.0001996982322195061,
135
+ "loss": 0.725,
136
+ "step": 2000
137
+ },
138
+ {
139
+ "epoch": 0.07,
140
+ "eval_loss": 0.7452704310417175,
141
+ "eval_runtime": 1787.7554,
142
+ "eval_samples_per_second": 0.303,
143
+ "eval_steps_per_second": 0.303,
144
+ "step": 2000
145
+ },
146
+ {
147
+ "epoch": 0.08,
148
+ "learning_rate": 0.00019966715903665795,
149
+ "loss": 0.7234,
150
+ "step": 2100
151
+ },
152
+ {
153
+ "epoch": 0.08,
154
+ "learning_rate": 0.00019963456612258576,
155
+ "loss": 0.754,
156
+ "step": 2200
157
+ },
158
+ {
159
+ "epoch": 0.09,
160
+ "learning_rate": 0.00019960045397426841,
161
+ "loss": 0.7856,
162
+ "step": 2300
163
+ },
164
+ {
165
+ "epoch": 0.09,
166
+ "learning_rate": 0.00019956482311185006,
167
+ "loss": 0.7387,
168
+ "step": 2400
169
+ },
170
+ {
171
+ "epoch": 0.09,
172
+ "learning_rate": 0.00019952767407863245,
173
+ "loss": 0.7309,
174
+ "step": 2500
175
+ },
176
+ {
177
+ "epoch": 0.1,
178
+ "learning_rate": 0.00019948900744106633,
179
+ "loss": 0.7232,
180
+ "step": 2600
181
+ },
182
+ {
183
+ "epoch": 0.1,
184
+ "learning_rate": 0.00019944882378874316,
185
+ "loss": 0.7406,
186
+ "step": 2700
187
+ },
188
+ {
189
+ "epoch": 0.1,
190
+ "learning_rate": 0.0001994071237343858,
191
+ "loss": 0.7166,
192
+ "step": 2800
193
+ },
194
+ {
195
+ "epoch": 0.11,
196
+ "learning_rate": 0.00019936390791383936,
197
+ "loss": 0.7308,
198
+ "step": 2900
199
+ },
200
+ {
201
+ "epoch": 0.11,
202
+ "learning_rate": 0.00019931917698606143,
203
+ "loss": 0.7288,
204
+ "step": 3000
205
+ },
206
+ {
207
+ "epoch": 0.11,
208
+ "eval_loss": 0.7343490123748779,
209
+ "eval_runtime": 1770.9966,
210
+ "eval_samples_per_second": 0.306,
211
+ "eval_steps_per_second": 0.306,
212
+ "step": 3000
213
+ },
214
+ {
215
+ "epoch": 0.12,
216
+ "learning_rate": 0.00019927293163311206,
217
+ "loss": 0.7236,
218
+ "step": 3100
219
+ },
220
+ {
221
+ "epoch": 0.12,
222
+ "learning_rate": 0.00019922517256014337,
223
+ "loss": 0.716,
224
+ "step": 3200
225
+ },
226
+ {
227
+ "epoch": 0.12,
228
+ "learning_rate": 0.00019917590049538874,
229
+ "loss": 0.7564,
230
+ "step": 3300
231
+ },
232
+ {
233
+ "epoch": 0.13,
234
+ "learning_rate": 0.00019912511619015177,
235
+ "loss": 0.7082,
236
+ "step": 3400
237
+ },
238
+ {
239
+ "epoch": 0.13,
240
+ "learning_rate": 0.00019907282041879484,
241
+ "loss": 0.7103,
242
+ "step": 3500
243
+ },
244
+ {
245
+ "epoch": 0.13,
246
+ "learning_rate": 0.00019901901397872715,
247
+ "loss": 0.7457,
248
+ "step": 3600
249
+ },
250
+ {
251
+ "epoch": 0.14,
252
+ "learning_rate": 0.0001989636976903928,
253
+ "loss": 0.7076,
254
+ "step": 3700
255
+ },
256
+ {
257
+ "epoch": 0.14,
258
+ "learning_rate": 0.0001989068723972581,
259
+ "loss": 0.7217,
260
+ "step": 3800
261
+ },
262
+ {
263
+ "epoch": 0.15,
264
+ "learning_rate": 0.00019884853896579873,
265
+ "loss": 0.7175,
266
+ "step": 3900
267
+ },
268
+ {
269
+ "epoch": 0.15,
270
+ "learning_rate": 0.0001987886982854866,
271
+ "loss": 0.7083,
272
+ "step": 4000
273
+ },
274
+ {
275
+ "epoch": 0.15,
276
+ "eval_loss": 0.726176917552948,
277
+ "eval_runtime": 1765.3933,
278
+ "eval_samples_per_second": 0.307,
279
+ "eval_steps_per_second": 0.307,
280
+ "step": 4000
281
+ },
282
+ {
283
+ "epoch": 0.15,
284
+ "learning_rate": 0.00019872735126877622,
285
+ "loss": 0.7228,
286
+ "step": 4100
287
+ },
288
+ {
289
+ "epoch": 0.16,
290
+ "learning_rate": 0.0001986644988510909,
291
+ "loss": 0.7133,
292
+ "step": 4200
293
+ },
294
+ {
295
+ "epoch": 0.16,
296
+ "learning_rate": 0.00019860014199080822,
297
+ "loss": 0.7243,
298
+ "step": 4300
299
+ },
300
+ {
301
+ "epoch": 0.16,
302
+ "learning_rate": 0.00019853428166924576,
303
+ "loss": 0.6929,
304
+ "step": 4400
305
+ },
306
+ {
307
+ "epoch": 0.17,
308
+ "learning_rate": 0.00019846691889064593,
309
+ "loss": 0.7392,
310
+ "step": 4500
311
+ },
312
+ {
313
+ "epoch": 0.17,
314
+ "learning_rate": 0.0001983980546821607,
315
+ "loss": 0.7247,
316
+ "step": 4600
317
+ },
318
+ {
319
+ "epoch": 0.18,
320
+ "learning_rate": 0.0001983276900938359,
321
+ "loss": 0.7258,
322
+ "step": 4700
323
+ },
324
+ {
325
+ "epoch": 0.18,
326
+ "learning_rate": 0.00019825582619859532,
327
+ "loss": 0.7197,
328
+ "step": 4800
329
+ },
330
+ {
331
+ "epoch": 0.18,
332
+ "learning_rate": 0.0001981824640922242,
333
+ "loss": 0.6906,
334
+ "step": 4900
335
+ },
336
+ {
337
+ "epoch": 0.19,
338
+ "learning_rate": 0.00019810760489335266,
339
+ "loss": 0.7274,
340
+ "step": 5000
341
+ },
342
+ {
343
+ "epoch": 0.19,
344
+ "eval_loss": 0.7171670794487,
345
+ "eval_runtime": 1812.7597,
346
+ "eval_samples_per_second": 0.299,
347
+ "eval_steps_per_second": 0.299,
348
+ "step": 5000
349
+ },
350
+ {
351
+ "epoch": 0.19,
352
+ "learning_rate": 0.0001980312497434385,
353
+ "loss": 0.7105,
354
+ "step": 5100
355
+ },
356
+ {
357
+ "epoch": 0.19,
358
+ "learning_rate": 0.00019795339980675002,
359
+ "loss": 0.7091,
360
+ "step": 5200
361
+ },
362
+ {
363
+ "epoch": 0.2,
364
+ "learning_rate": 0.00019787405627034804,
365
+ "loss": 0.7102,
366
+ "step": 5300
367
+ },
368
+ {
369
+ "epoch": 0.2,
370
+ "learning_rate": 0.0001977932203440678,
371
+ "loss": 0.7314,
372
+ "step": 5400
373
+ },
374
+ {
375
+ "epoch": 0.21,
376
+ "learning_rate": 0.00019771089326050075,
377
+ "loss": 0.6945,
378
+ "step": 5500
379
+ },
380
+ {
381
+ "epoch": 0.21,
382
+ "learning_rate": 0.0001976270762749755,
383
+ "loss": 0.7048,
384
+ "step": 5600
385
+ },
386
+ {
387
+ "epoch": 0.21,
388
+ "learning_rate": 0.00019754177066553882,
389
+ "loss": 0.6963,
390
+ "step": 5700
391
+ },
392
+ {
393
+ "epoch": 0.22,
394
+ "learning_rate": 0.00019745497773293613,
395
+ "loss": 0.711,
396
+ "step": 5800
397
+ },
398
+ {
399
+ "epoch": 0.22,
400
+ "learning_rate": 0.0001973666988005916,
401
+ "loss": 0.7017,
402
+ "step": 5900
403
+ },
404
+ {
405
+ "epoch": 0.22,
406
+ "learning_rate": 0.00019727693521458806,
407
+ "loss": 0.7287,
408
+ "step": 6000
409
+ },
410
+ {
411
+ "epoch": 0.22,
412
+ "eval_loss": 0.710155725479126,
413
+ "eval_runtime": 1786.7467,
414
+ "eval_samples_per_second": 0.303,
415
+ "eval_steps_per_second": 0.303,
416
+ "step": 6000
417
+ },
418
+ {
419
+ "epoch": 0.23,
420
+ "learning_rate": 0.00019718568834364638,
421
+ "loss": 0.6894,
422
+ "step": 6100
423
+ },
424
+ {
425
+ "epoch": 0.23,
426
+ "learning_rate": 0.00019709295957910476,
427
+ "loss": 0.7061,
428
+ "step": 6200
429
+ },
430
+ {
431
+ "epoch": 0.23,
432
+ "learning_rate": 0.00019699875033489728,
433
+ "loss": 0.7063,
434
+ "step": 6300
435
+ },
436
+ {
437
+ "epoch": 0.24,
438
+ "learning_rate": 0.00019690306204753254,
439
+ "loss": 0.6872,
440
+ "step": 6400
441
+ },
442
+ {
443
+ "epoch": 0.24,
444
+ "learning_rate": 0.0001968058961760717,
445
+ "loss": 0.7095,
446
+ "step": 6500
447
+ },
448
+ {
449
+ "epoch": 0.25,
450
+ "learning_rate": 0.00019670725420210618,
451
+ "loss": 0.695,
452
+ "step": 6600
453
+ },
454
+ {
455
+ "epoch": 0.25,
456
+ "learning_rate": 0.0001966071376297351,
457
+ "loss": 0.674,
458
+ "step": 6700
459
+ },
460
+ {
461
+ "epoch": 0.25,
462
+ "learning_rate": 0.00019650554798554236,
463
+ "loss": 0.7225,
464
+ "step": 6800
465
+ },
466
+ {
467
+ "epoch": 0.26,
468
+ "learning_rate": 0.00019640248681857342,
469
+ "loss": 0.6845,
470
+ "step": 6900
471
+ },
472
+ {
473
+ "epoch": 0.26,
474
+ "learning_rate": 0.00019629795570031149,
475
+ "loss": 0.6891,
476
+ "step": 7000
477
+ },
478
+ {
479
+ "epoch": 0.26,
480
+ "eval_loss": 0.703677773475647,
481
+ "eval_runtime": 1767.3593,
482
+ "eval_samples_per_second": 0.307,
483
+ "eval_steps_per_second": 0.307,
484
+ "step": 7000
485
+ },
486
+ {
487
+ "epoch": 0.26,
488
+ "learning_rate": 0.00019619195622465379,
489
+ "loss": 0.6962,
490
+ "step": 7100
491
+ },
492
+ {
493
+ "epoch": 0.27,
494
+ "learning_rate": 0.0001960844900078871,
495
+ "loss": 0.6779,
496
+ "step": 7200
497
+ },
498
+ {
499
+ "epoch": 0.27,
500
+ "learning_rate": 0.00019597555868866318,
501
+ "loss": 0.7354,
502
+ "step": 7300
503
+ },
504
+ {
505
+ "epoch": 0.28,
506
+ "learning_rate": 0.00019586516392797374,
507
+ "loss": 0.7196,
508
+ "step": 7400
509
+ },
510
+ {
511
+ "epoch": 0.28,
512
+ "learning_rate": 0.0001957533074091252,
513
+ "loss": 0.682,
514
+ "step": 7500
515
+ },
516
+ {
517
+ "epoch": 0.28,
518
+ "learning_rate": 0.0001956399908377129,
519
+ "loss": 0.6938,
520
+ "step": 7600
521
+ },
522
+ {
523
+ "epoch": 0.29,
524
+ "learning_rate": 0.0001955252159415952,
525
+ "loss": 0.6912,
526
+ "step": 7700
527
+ },
528
+ {
529
+ "epoch": 0.29,
530
+ "learning_rate": 0.00019540898447086705,
531
+ "loss": 0.7048,
532
+ "step": 7800
533
+ },
534
+ {
535
+ "epoch": 0.29,
536
+ "learning_rate": 0.00019529129819783334,
537
+ "loss": 0.7007,
538
+ "step": 7900
539
+ },
540
+ {
541
+ "epoch": 0.3,
542
+ "learning_rate": 0.00019517215891698192,
543
+ "loss": 0.6969,
544
+ "step": 8000
545
+ },
546
+ {
547
+ "epoch": 0.3,
548
+ "eval_loss": 0.6973471641540527,
549
+ "eval_runtime": 1793.2355,
550
+ "eval_samples_per_second": 0.302,
551
+ "eval_steps_per_second": 0.302,
552
+ "step": 8000
553
+ }
554
+ ],
555
+ "max_steps": 80463,
556
+ "num_train_epochs": 3,
557
+ "total_flos": 2.2424408000217907e+18,
558
+ "trial_name": null,
559
+ "trial_params": null
560
+ }
checkpoint-8000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a281372a257be5e7ebbea8ac16ec51e707b224a5ed57c48e2f69549c5a031d8
3
+ size 4027