CreatorPhan commited on
Commit
5a71f02
1 Parent(s): e7d5a02

Upload folder using huggingface_hub

Browse files
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ee3b3a42cb5ab5d4324b43b03c14e5347da2d1931f2318489d2d9cacbcf44c0
3
  size 39409357
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9965124964cb337825ddfaf69b302836615f6c9078be280e07c56ca53a3dee2
3
  size 39409357
checkpoint-100/README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: True
10
+ - load_in_4bit: False
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: fp4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float32
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: True
22
+ - load_in_4bit: False
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: fp4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float32
30
+ ### Framework versions
31
+
32
+ - PEFT 0.6.0.dev0
33
+
34
+ - PEFT 0.6.0.dev0
checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "vilm/vietcuna-3b",
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": 0.0,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "dense_4h_to_h",
18
+ "dense",
19
+ "dense_h_to_4h",
20
+ "query_key_value"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
checkpoint-100/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7162cb89a36eade56456564472b7286d9710cbd215038fb634105d465db2572a
3
+ size 39409357
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b21aaf3d05278b35d430ba855cffc90597c9a169b3ca6c2bddee123f1ec461a8
3
+ size 78844421
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:972139d83957a9cf2600cb6eeca17287d7a5377c33a53500ae7e13fe830ad36b
3
+ size 14575
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3adb9ae90f42b2bc990d25a964a915b32fecbfb6d0d4a4db300c3b7b07de568
3
+ size 627
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-100/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
3
+ size 14500471
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "tokenizer_class": "BloomTokenizer",
9
+ "unk_token": "<unk>"
10
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,619 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.244167962674961,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
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": 0.00099375,
14
+ "loss": 2.9311,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.02,
19
+ "learning_rate": 0.0009875,
20
+ "loss": 2.9309,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.04,
25
+ "learning_rate": 0.00098125,
26
+ "loss": 2.8566,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.05,
31
+ "learning_rate": 0.000975,
32
+ "loss": 2.773,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.06,
37
+ "learning_rate": 0.00096875,
38
+ "loss": 2.7367,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.07,
43
+ "learning_rate": 0.0009625,
44
+ "loss": 2.7924,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.09,
49
+ "learning_rate": 0.0009562500000000001,
50
+ "loss": 2.7099,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.1,
55
+ "learning_rate": 0.00095,
56
+ "loss": 2.7658,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.11,
61
+ "learning_rate": 0.00094375,
62
+ "loss": 2.7514,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.12,
67
+ "learning_rate": 0.0009375,
68
+ "loss": 2.6899,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.14,
73
+ "learning_rate": 0.00093125,
74
+ "loss": 2.7072,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.15,
79
+ "learning_rate": 0.000925,
80
+ "loss": 2.7687,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.16,
85
+ "learning_rate": 0.00091875,
86
+ "loss": 2.652,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.17,
91
+ "learning_rate": 0.0009125,
92
+ "loss": 2.6991,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.19,
97
+ "learning_rate": 0.00090625,
98
+ "loss": 2.6259,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.2,
103
+ "learning_rate": 0.0009000000000000001,
104
+ "loss": 2.5914,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.21,
109
+ "learning_rate": 0.00089375,
110
+ "loss": 2.7453,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.22,
115
+ "learning_rate": 0.0008874999999999999,
116
+ "loss": 2.6502,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.24,
121
+ "learning_rate": 0.00088125,
122
+ "loss": 2.6558,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.25,
127
+ "learning_rate": 0.000875,
128
+ "loss": 2.6839,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.26,
133
+ "learning_rate": 0.0008687500000000001,
134
+ "loss": 2.5649,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.27,
139
+ "learning_rate": 0.0008625000000000001,
140
+ "loss": 2.724,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.29,
145
+ "learning_rate": 0.00085625,
146
+ "loss": 2.6601,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.3,
151
+ "learning_rate": 0.00085,
152
+ "loss": 2.573,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.31,
157
+ "learning_rate": 0.00084375,
158
+ "loss": 2.5586,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.32,
163
+ "learning_rate": 0.0008375,
164
+ "loss": 2.6952,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.34,
169
+ "learning_rate": 0.0008312500000000001,
170
+ "loss": 2.6349,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.35,
175
+ "learning_rate": 0.000825,
176
+ "loss": 2.7674,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.36,
181
+ "learning_rate": 0.00081875,
182
+ "loss": 2.6728,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.37,
187
+ "learning_rate": 0.0008125000000000001,
188
+ "loss": 2.7608,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.39,
193
+ "learning_rate": 0.00080625,
194
+ "loss": 2.5593,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.4,
199
+ "learning_rate": 0.0008,
200
+ "loss": 2.6426,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.41,
205
+ "learning_rate": 0.00079375,
206
+ "loss": 2.7065,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.42,
211
+ "learning_rate": 0.0007875,
212
+ "loss": 2.7022,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.44,
217
+ "learning_rate": 0.00078125,
218
+ "loss": 2.6398,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.45,
223
+ "learning_rate": 0.0007750000000000001,
224
+ "loss": 2.5589,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.46,
229
+ "learning_rate": 0.00076875,
230
+ "loss": 2.7217,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.47,
235
+ "learning_rate": 0.0007624999999999999,
236
+ "loss": 2.7152,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.49,
241
+ "learning_rate": 0.00075625,
242
+ "loss": 2.6679,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.5,
247
+ "learning_rate": 0.00075,
248
+ "loss": 2.5681,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.51,
253
+ "learning_rate": 0.00074375,
254
+ "loss": 2.6518,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.52,
259
+ "learning_rate": 0.0007375000000000001,
260
+ "loss": 2.6684,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.53,
265
+ "learning_rate": 0.00073125,
266
+ "loss": 2.6757,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.55,
271
+ "learning_rate": 0.000725,
272
+ "loss": 2.6836,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.56,
277
+ "learning_rate": 0.00071875,
278
+ "loss": 2.685,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.57,
283
+ "learning_rate": 0.0007125,
284
+ "loss": 2.6512,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.58,
289
+ "learning_rate": 0.0007062500000000001,
290
+ "loss": 2.6766,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.6,
295
+ "learning_rate": 0.0007,
296
+ "loss": 2.5773,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.61,
301
+ "learning_rate": 0.00069375,
302
+ "loss": 2.7344,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.62,
307
+ "learning_rate": 0.0006875,
308
+ "loss": 2.6468,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.63,
313
+ "learning_rate": 0.00068125,
314
+ "loss": 2.6663,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.65,
319
+ "learning_rate": 0.000675,
320
+ "loss": 2.6363,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.66,
325
+ "learning_rate": 0.00066875,
326
+ "loss": 2.7287,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.67,
331
+ "learning_rate": 0.0006625,
332
+ "loss": 2.7259,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.68,
337
+ "learning_rate": 0.00065625,
338
+ "loss": 2.6912,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.7,
343
+ "learning_rate": 0.0006500000000000001,
344
+ "loss": 2.5956,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.71,
349
+ "learning_rate": 0.00064375,
350
+ "loss": 2.7398,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.72,
355
+ "learning_rate": 0.0006374999999999999,
356
+ "loss": 2.7265,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.73,
361
+ "learning_rate": 0.00063125,
362
+ "loss": 2.6031,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.75,
367
+ "learning_rate": 0.000625,
368
+ "loss": 2.6263,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.76,
373
+ "learning_rate": 0.00061875,
374
+ "loss": 2.6544,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.77,
379
+ "learning_rate": 0.0006125000000000001,
380
+ "loss": 2.7403,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.78,
385
+ "learning_rate": 0.00060625,
386
+ "loss": 2.6565,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.8,
391
+ "learning_rate": 0.0006,
392
+ "loss": 2.7286,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.81,
397
+ "learning_rate": 0.00059375,
398
+ "loss": 2.7061,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.82,
403
+ "learning_rate": 0.0005875,
404
+ "loss": 2.5849,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.83,
409
+ "learning_rate": 0.0005812500000000001,
410
+ "loss": 2.6668,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.85,
415
+ "learning_rate": 0.000575,
416
+ "loss": 2.6454,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.86,
421
+ "learning_rate": 0.00056875,
422
+ "loss": 2.635,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.87,
427
+ "learning_rate": 0.0005625000000000001,
428
+ "loss": 2.6358,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.88,
433
+ "learning_rate": 0.00055625,
434
+ "loss": 2.6379,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.9,
439
+ "learning_rate": 0.00055,
440
+ "loss": 2.6447,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.91,
445
+ "learning_rate": 0.00054375,
446
+ "loss": 2.6083,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.92,
451
+ "learning_rate": 0.0005375,
452
+ "loss": 2.6816,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.93,
457
+ "learning_rate": 0.00053125,
458
+ "loss": 2.6415,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.95,
463
+ "learning_rate": 0.0005250000000000001,
464
+ "loss": 2.6407,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.96,
469
+ "learning_rate": 0.00051875,
470
+ "loss": 2.6056,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.97,
475
+ "learning_rate": 0.0005124999999999999,
476
+ "loss": 2.5552,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.98,
481
+ "learning_rate": 0.00050625,
482
+ "loss": 2.6193,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 1.0,
487
+ "learning_rate": 0.0005,
488
+ "loss": 2.5949,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 1.01,
493
+ "learning_rate": 0.00049375,
494
+ "loss": 2.5104,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 1.02,
499
+ "learning_rate": 0.0004875,
500
+ "loss": 2.4372,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 1.03,
505
+ "learning_rate": 0.00048125,
506
+ "loss": 2.3689,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 1.05,
511
+ "learning_rate": 0.000475,
512
+ "loss": 2.5339,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 1.06,
517
+ "learning_rate": 0.00046875,
518
+ "loss": 2.5443,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 1.07,
523
+ "learning_rate": 0.0004625,
524
+ "loss": 2.4477,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 1.08,
529
+ "learning_rate": 0.00045625,
530
+ "loss": 2.4904,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 1.09,
535
+ "learning_rate": 0.00045000000000000004,
536
+ "loss": 2.43,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 1.11,
541
+ "learning_rate": 0.00044374999999999997,
542
+ "loss": 2.476,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 1.12,
547
+ "learning_rate": 0.0004375,
548
+ "loss": 2.5321,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 1.13,
553
+ "learning_rate": 0.00043125000000000005,
554
+ "loss": 2.4374,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 1.14,
559
+ "learning_rate": 0.000425,
560
+ "loss": 2.4265,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 1.16,
565
+ "learning_rate": 0.00041875,
566
+ "loss": 2.4505,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 1.17,
571
+ "learning_rate": 0.0004125,
572
+ "loss": 2.4275,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 1.18,
577
+ "learning_rate": 0.00040625000000000004,
578
+ "loss": 2.4458,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 1.19,
583
+ "learning_rate": 0.0004,
584
+ "loss": 2.5226,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 1.21,
589
+ "learning_rate": 0.00039375,
590
+ "loss": 2.4048,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 1.22,
595
+ "learning_rate": 0.00038750000000000004,
596
+ "loss": 2.5091,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 1.23,
601
+ "learning_rate": 0.00038124999999999997,
602
+ "loss": 2.4583,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 1.24,
607
+ "learning_rate": 0.000375,
608
+ "loss": 2.4678,
609
+ "step": 100
610
+ }
611
+ ],
612
+ "logging_steps": 1,
613
+ "max_steps": 160,
614
+ "num_train_epochs": 2,
615
+ "save_steps": 100,
616
+ "total_flos": 2.588289853513728e+16,
617
+ "trial_name": null,
618
+ "trial_params": null
619
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81575686b087f7a47dde3ff139848be704047c90bfa69764a56ebff4b68eac6b
3
+ size 4027
runs/Aug29_01-39-38_98262386854b/events.out.tfevents.1693273208.98262386854b.758.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5710a6ac936a4252700fd475a4d4f788c793f156364a2c01e6cb75aced70224c
3
+ size 5546
runs/Aug29_01-49-27_98262386854b/events.out.tfevents.1693273789.98262386854b.3388.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:391c19532d7f6a0c7134131564ce9ced72b95e99bca3f7b7f2216331416d6a0d
3
+ size 29715
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8291144372c961e4bb5e841fffac18d6de3c2cd9923b1c2756f21ca32b4be72
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81575686b087f7a47dde3ff139848be704047c90bfa69764a56ebff4b68eac6b
3
  size 4027