CreatorPhan commited on
Commit
fc5ff04
1 Parent(s): 70e89a4

Upload folder using huggingface_hub (#1)

Browse files

- Upload folder using huggingface_hub (bbc0c4f53496b4fe5077e873edd1869cedd23a6a)

.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
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": "bigscience/bloomz-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:b48cecd6618c73c7a7cffa0108482a2f595d548824e9cb0ceed18f6b01b431f5
3
+ size 39409357
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4117e82e3f4a13d4d3c632534da146dbcfeb8848db542a70fdd0ab0bba79f4c
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:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
3
+ size 14575
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1b95a57afe07d0e96b2b542f2c7ae1cb370a427ad645d9a3dc3f75e11e05694
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 sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
3
+ size 14500570
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": 0.28368794326241137,
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": 0.0,
13
+ "learning_rate": 0.0001994318181818182,
14
+ "loss": 2.7526,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.00019886363636363637,
20
+ "loss": 2.6231,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 0.00019829545454545455,
26
+ "loss": 2.5691,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 0.00019772727272727273,
32
+ "loss": 2.5755,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 0.00019715909090909094,
38
+ "loss": 2.5077,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.02,
43
+ "learning_rate": 0.0001965909090909091,
44
+ "loss": 2.4698,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "learning_rate": 0.00019602272727272727,
50
+ "loss": 2.4541,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.02,
55
+ "learning_rate": 0.00019545454545454548,
56
+ "loss": 2.4764,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.03,
61
+ "learning_rate": 0.00019488636363636366,
62
+ "loss": 2.4176,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.03,
67
+ "learning_rate": 0.0001943181818181818,
68
+ "loss": 2.396,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.03,
73
+ "learning_rate": 0.00019375000000000002,
74
+ "loss": 2.3929,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.03,
79
+ "learning_rate": 0.0001931818181818182,
80
+ "loss": 2.405,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.04,
85
+ "learning_rate": 0.00019261363636363635,
86
+ "loss": 2.3947,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.04,
91
+ "learning_rate": 0.00019204545454545456,
92
+ "loss": 2.4164,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.04,
97
+ "learning_rate": 0.00019147727272727274,
98
+ "loss": 2.373,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.05,
103
+ "learning_rate": 0.00019090909090909092,
104
+ "loss": 2.3552,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.05,
109
+ "learning_rate": 0.0001903409090909091,
110
+ "loss": 2.3988,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.05,
115
+ "learning_rate": 0.00018977272727272728,
116
+ "loss": 2.3826,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.05,
121
+ "learning_rate": 0.00018920454545454546,
122
+ "loss": 2.3672,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.06,
127
+ "learning_rate": 0.00018863636363636364,
128
+ "loss": 2.3885,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.06,
133
+ "learning_rate": 0.00018806818181818182,
134
+ "loss": 2.3043,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.06,
139
+ "learning_rate": 0.0001875,
140
+ "loss": 2.2597,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.07,
145
+ "learning_rate": 0.00018693181818181818,
146
+ "loss": 2.3457,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.07,
151
+ "learning_rate": 0.00018636363636363636,
152
+ "loss": 2.3409,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.07,
157
+ "learning_rate": 0.00018579545454545454,
158
+ "loss": 2.303,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.07,
163
+ "learning_rate": 0.00018522727272727273,
164
+ "loss": 2.3253,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.08,
169
+ "learning_rate": 0.00018465909090909093,
170
+ "loss": 2.3453,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.08,
175
+ "learning_rate": 0.00018409090909090909,
176
+ "loss": 2.3151,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.08,
181
+ "learning_rate": 0.00018352272727272727,
182
+ "loss": 2.3457,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.09,
187
+ "learning_rate": 0.00018295454545454547,
188
+ "loss": 2.2792,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.09,
193
+ "learning_rate": 0.00018238636363636365,
194
+ "loss": 2.3257,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.09,
199
+ "learning_rate": 0.00018181818181818183,
200
+ "loss": 2.353,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.09,
205
+ "learning_rate": 0.00018125000000000001,
206
+ "loss": 2.2633,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.1,
211
+ "learning_rate": 0.0001806818181818182,
212
+ "loss": 2.3089,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.1,
217
+ "learning_rate": 0.00018011363636363638,
218
+ "loss": 2.3085,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.1,
223
+ "learning_rate": 0.00017954545454545456,
224
+ "loss": 2.2746,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.1,
229
+ "learning_rate": 0.00017897727272727274,
230
+ "loss": 2.3212,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.11,
235
+ "learning_rate": 0.00017840909090909092,
236
+ "loss": 2.2991,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.11,
241
+ "learning_rate": 0.0001778409090909091,
242
+ "loss": 2.2807,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.11,
247
+ "learning_rate": 0.00017727272727272728,
248
+ "loss": 2.3342,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.12,
253
+ "learning_rate": 0.00017670454545454546,
254
+ "loss": 2.3144,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.12,
259
+ "learning_rate": 0.00017613636363636366,
260
+ "loss": 2.3084,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.12,
265
+ "learning_rate": 0.00017556818181818182,
266
+ "loss": 2.3032,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.12,
271
+ "learning_rate": 0.000175,
272
+ "loss": 2.3105,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.13,
277
+ "learning_rate": 0.0001744318181818182,
278
+ "loss": 2.3101,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.13,
283
+ "learning_rate": 0.00017386363636363636,
284
+ "loss": 2.313,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.13,
289
+ "learning_rate": 0.00017329545454545454,
290
+ "loss": 2.293,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.14,
295
+ "learning_rate": 0.00017272727272727275,
296
+ "loss": 2.2807,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.14,
301
+ "learning_rate": 0.00017215909090909093,
302
+ "loss": 2.2665,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.14,
307
+ "learning_rate": 0.00017159090909090908,
308
+ "loss": 2.2626,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.14,
313
+ "learning_rate": 0.0001710227272727273,
314
+ "loss": 2.2839,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.15,
319
+ "learning_rate": 0.00017045454545454547,
320
+ "loss": 2.2865,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.15,
325
+ "learning_rate": 0.00016988636363636365,
326
+ "loss": 2.2788,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.15,
331
+ "learning_rate": 0.00016931818181818183,
332
+ "loss": 2.2622,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.16,
337
+ "learning_rate": 0.00016875,
338
+ "loss": 2.3121,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.16,
343
+ "learning_rate": 0.0001681818181818182,
344
+ "loss": 2.2958,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.16,
349
+ "learning_rate": 0.00016761363636363637,
350
+ "loss": 2.2898,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.16,
355
+ "learning_rate": 0.00016704545454545455,
356
+ "loss": 2.2903,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.17,
361
+ "learning_rate": 0.00016647727272727273,
362
+ "loss": 2.3393,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.17,
367
+ "learning_rate": 0.00016590909090909094,
368
+ "loss": 2.3086,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.17,
373
+ "learning_rate": 0.0001653409090909091,
374
+ "loss": 2.2739,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.18,
379
+ "learning_rate": 0.00016477272727272727,
380
+ "loss": 2.252,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.18,
385
+ "learning_rate": 0.00016420454545454548,
386
+ "loss": 2.2868,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.18,
391
+ "learning_rate": 0.00016363636363636366,
392
+ "loss": 2.2301,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.18,
397
+ "learning_rate": 0.0001630681818181818,
398
+ "loss": 2.2563,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.19,
403
+ "learning_rate": 0.00016250000000000002,
404
+ "loss": 2.2552,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.19,
409
+ "learning_rate": 0.0001619318181818182,
410
+ "loss": 2.2615,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.19,
415
+ "learning_rate": 0.00016136363636363635,
416
+ "loss": 2.3237,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.2,
421
+ "learning_rate": 0.00016079545454545456,
422
+ "loss": 2.2741,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.2,
427
+ "learning_rate": 0.00016022727272727274,
428
+ "loss": 2.2152,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.2,
433
+ "learning_rate": 0.00015965909090909092,
434
+ "loss": 2.2558,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.2,
439
+ "learning_rate": 0.0001590909090909091,
440
+ "loss": 2.2293,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.21,
445
+ "learning_rate": 0.00015852272727272728,
446
+ "loss": 2.2278,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.21,
451
+ "learning_rate": 0.00015795454545454546,
452
+ "loss": 2.2583,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.21,
457
+ "learning_rate": 0.00015738636363636364,
458
+ "loss": 2.2609,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.22,
463
+ "learning_rate": 0.00015681818181818182,
464
+ "loss": 2.2955,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.22,
469
+ "learning_rate": 0.00015625,
470
+ "loss": 2.2359,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.22,
475
+ "learning_rate": 0.00015568181818181818,
476
+ "loss": 2.2427,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.22,
481
+ "learning_rate": 0.00015511363636363636,
482
+ "loss": 2.2632,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.23,
487
+ "learning_rate": 0.00015454545454545454,
488
+ "loss": 2.2649,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.23,
493
+ "learning_rate": 0.00015397727272727272,
494
+ "loss": 2.2347,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.23,
499
+ "learning_rate": 0.00015340909090909093,
500
+ "loss": 2.2439,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.24,
505
+ "learning_rate": 0.00015284090909090909,
506
+ "loss": 2.267,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.24,
511
+ "learning_rate": 0.00015227272727272727,
512
+ "loss": 2.2682,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.24,
517
+ "learning_rate": 0.00015170454545454547,
518
+ "loss": 2.2477,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.24,
523
+ "learning_rate": 0.00015113636363636365,
524
+ "loss": 2.2534,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.25,
529
+ "learning_rate": 0.0001505681818181818,
530
+ "loss": 2.2609,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.25,
535
+ "learning_rate": 0.00015000000000000001,
536
+ "loss": 2.2381,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.25,
541
+ "learning_rate": 0.0001494318181818182,
542
+ "loss": 2.2505,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.26,
547
+ "learning_rate": 0.00014886363636363635,
548
+ "loss": 2.2628,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.26,
553
+ "learning_rate": 0.00014829545454545455,
554
+ "loss": 2.1874,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.26,
559
+ "learning_rate": 0.00014772727272727274,
560
+ "loss": 2.2024,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.26,
565
+ "learning_rate": 0.00014715909090909092,
566
+ "loss": 2.2453,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.27,
571
+ "learning_rate": 0.0001465909090909091,
572
+ "loss": 2.259,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.27,
577
+ "learning_rate": 0.00014602272727272728,
578
+ "loss": 2.2304,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.27,
583
+ "learning_rate": 0.00014545454545454546,
584
+ "loss": 2.2179,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.28,
589
+ "learning_rate": 0.00014488636363636366,
590
+ "loss": 2.2497,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.28,
595
+ "learning_rate": 0.00014431818181818182,
596
+ "loss": 2.2458,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.28,
601
+ "learning_rate": 0.00014375,
602
+ "loss": 2.2438,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.28,
607
+ "learning_rate": 0.0001431818181818182,
608
+ "loss": 2.2461,
609
+ "step": 100
610
+ }
611
+ ],
612
+ "logging_steps": 1,
613
+ "max_steps": 352,
614
+ "num_train_epochs": 1,
615
+ "save_steps": 100,
616
+ "total_flos": 2.5310590559514624e+17,
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 sha256:1a5b74f951ff7697f1beb8eddc25d8ee6bd52b872686edb3386a0f175a1ad4d7
3
+ size 4155
checkpoint-200/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-200/adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "bigscience/bloomz-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-200/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef5676439520bbd6b7affbfdd5426ee86c36da5919981c62a81b11b15320b157
3
+ size 39409357
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e600237232f316285ceb2d11454617de44bb17dcfff8a4a1825f81e2b426acf7
3
+ size 78844421
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2278a87cdf86c3f9219223c847f6b27f6b7f15b8226b617f38936e8ff2cbcde
3
+ size 14575
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898d955e60dd57555592ca4fb8c65e192f6200775fde821cba3649020f5028d8
3
+ size 627
checkpoint-200/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-200/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b00d7db4df5df2e3f01cacc3feda246002a672f3356eec7f4b04a22eb0dfbe
3
+ size 14500570
checkpoint-200/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-200/trainer_state.json ADDED
@@ -0,0 +1,1219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5673758865248227,
5
+ "eval_steps": 500,
6
+ "global_step": 200,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 0.0001994318181818182,
14
+ "loss": 2.7526,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.01,
19
+ "learning_rate": 0.00019886363636363637,
20
+ "loss": 2.6231,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.01,
25
+ "learning_rate": 0.00019829545454545455,
26
+ "loss": 2.5691,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 0.01,
31
+ "learning_rate": 0.00019772727272727273,
32
+ "loss": 2.5755,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 0.01,
37
+ "learning_rate": 0.00019715909090909094,
38
+ "loss": 2.5077,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 0.02,
43
+ "learning_rate": 0.0001965909090909091,
44
+ "loss": 2.4698,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 0.02,
49
+ "learning_rate": 0.00019602272727272727,
50
+ "loss": 2.4541,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 0.02,
55
+ "learning_rate": 0.00019545454545454548,
56
+ "loss": 2.4764,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 0.03,
61
+ "learning_rate": 0.00019488636363636366,
62
+ "loss": 2.4176,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 0.03,
67
+ "learning_rate": 0.0001943181818181818,
68
+ "loss": 2.396,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 0.03,
73
+ "learning_rate": 0.00019375000000000002,
74
+ "loss": 2.3929,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 0.03,
79
+ "learning_rate": 0.0001931818181818182,
80
+ "loss": 2.405,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 0.04,
85
+ "learning_rate": 0.00019261363636363635,
86
+ "loss": 2.3947,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 0.04,
91
+ "learning_rate": 0.00019204545454545456,
92
+ "loss": 2.4164,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 0.04,
97
+ "learning_rate": 0.00019147727272727274,
98
+ "loss": 2.373,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 0.05,
103
+ "learning_rate": 0.00019090909090909092,
104
+ "loss": 2.3552,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 0.05,
109
+ "learning_rate": 0.0001903409090909091,
110
+ "loss": 2.3988,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 0.05,
115
+ "learning_rate": 0.00018977272727272728,
116
+ "loss": 2.3826,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 0.05,
121
+ "learning_rate": 0.00018920454545454546,
122
+ "loss": 2.3672,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 0.06,
127
+ "learning_rate": 0.00018863636363636364,
128
+ "loss": 2.3885,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 0.06,
133
+ "learning_rate": 0.00018806818181818182,
134
+ "loss": 2.3043,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 0.06,
139
+ "learning_rate": 0.0001875,
140
+ "loss": 2.2597,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 0.07,
145
+ "learning_rate": 0.00018693181818181818,
146
+ "loss": 2.3457,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 0.07,
151
+ "learning_rate": 0.00018636363636363636,
152
+ "loss": 2.3409,
153
+ "step": 24
154
+ },
155
+ {
156
+ "epoch": 0.07,
157
+ "learning_rate": 0.00018579545454545454,
158
+ "loss": 2.303,
159
+ "step": 25
160
+ },
161
+ {
162
+ "epoch": 0.07,
163
+ "learning_rate": 0.00018522727272727273,
164
+ "loss": 2.3253,
165
+ "step": 26
166
+ },
167
+ {
168
+ "epoch": 0.08,
169
+ "learning_rate": 0.00018465909090909093,
170
+ "loss": 2.3453,
171
+ "step": 27
172
+ },
173
+ {
174
+ "epoch": 0.08,
175
+ "learning_rate": 0.00018409090909090909,
176
+ "loss": 2.3151,
177
+ "step": 28
178
+ },
179
+ {
180
+ "epoch": 0.08,
181
+ "learning_rate": 0.00018352272727272727,
182
+ "loss": 2.3457,
183
+ "step": 29
184
+ },
185
+ {
186
+ "epoch": 0.09,
187
+ "learning_rate": 0.00018295454545454547,
188
+ "loss": 2.2792,
189
+ "step": 30
190
+ },
191
+ {
192
+ "epoch": 0.09,
193
+ "learning_rate": 0.00018238636363636365,
194
+ "loss": 2.3257,
195
+ "step": 31
196
+ },
197
+ {
198
+ "epoch": 0.09,
199
+ "learning_rate": 0.00018181818181818183,
200
+ "loss": 2.353,
201
+ "step": 32
202
+ },
203
+ {
204
+ "epoch": 0.09,
205
+ "learning_rate": 0.00018125000000000001,
206
+ "loss": 2.2633,
207
+ "step": 33
208
+ },
209
+ {
210
+ "epoch": 0.1,
211
+ "learning_rate": 0.0001806818181818182,
212
+ "loss": 2.3089,
213
+ "step": 34
214
+ },
215
+ {
216
+ "epoch": 0.1,
217
+ "learning_rate": 0.00018011363636363638,
218
+ "loss": 2.3085,
219
+ "step": 35
220
+ },
221
+ {
222
+ "epoch": 0.1,
223
+ "learning_rate": 0.00017954545454545456,
224
+ "loss": 2.2746,
225
+ "step": 36
226
+ },
227
+ {
228
+ "epoch": 0.1,
229
+ "learning_rate": 0.00017897727272727274,
230
+ "loss": 2.3212,
231
+ "step": 37
232
+ },
233
+ {
234
+ "epoch": 0.11,
235
+ "learning_rate": 0.00017840909090909092,
236
+ "loss": 2.2991,
237
+ "step": 38
238
+ },
239
+ {
240
+ "epoch": 0.11,
241
+ "learning_rate": 0.0001778409090909091,
242
+ "loss": 2.2807,
243
+ "step": 39
244
+ },
245
+ {
246
+ "epoch": 0.11,
247
+ "learning_rate": 0.00017727272727272728,
248
+ "loss": 2.3342,
249
+ "step": 40
250
+ },
251
+ {
252
+ "epoch": 0.12,
253
+ "learning_rate": 0.00017670454545454546,
254
+ "loss": 2.3144,
255
+ "step": 41
256
+ },
257
+ {
258
+ "epoch": 0.12,
259
+ "learning_rate": 0.00017613636363636366,
260
+ "loss": 2.3084,
261
+ "step": 42
262
+ },
263
+ {
264
+ "epoch": 0.12,
265
+ "learning_rate": 0.00017556818181818182,
266
+ "loss": 2.3032,
267
+ "step": 43
268
+ },
269
+ {
270
+ "epoch": 0.12,
271
+ "learning_rate": 0.000175,
272
+ "loss": 2.3105,
273
+ "step": 44
274
+ },
275
+ {
276
+ "epoch": 0.13,
277
+ "learning_rate": 0.0001744318181818182,
278
+ "loss": 2.3101,
279
+ "step": 45
280
+ },
281
+ {
282
+ "epoch": 0.13,
283
+ "learning_rate": 0.00017386363636363636,
284
+ "loss": 2.313,
285
+ "step": 46
286
+ },
287
+ {
288
+ "epoch": 0.13,
289
+ "learning_rate": 0.00017329545454545454,
290
+ "loss": 2.293,
291
+ "step": 47
292
+ },
293
+ {
294
+ "epoch": 0.14,
295
+ "learning_rate": 0.00017272727272727275,
296
+ "loss": 2.2807,
297
+ "step": 48
298
+ },
299
+ {
300
+ "epoch": 0.14,
301
+ "learning_rate": 0.00017215909090909093,
302
+ "loss": 2.2665,
303
+ "step": 49
304
+ },
305
+ {
306
+ "epoch": 0.14,
307
+ "learning_rate": 0.00017159090909090908,
308
+ "loss": 2.2626,
309
+ "step": 50
310
+ },
311
+ {
312
+ "epoch": 0.14,
313
+ "learning_rate": 0.0001710227272727273,
314
+ "loss": 2.2839,
315
+ "step": 51
316
+ },
317
+ {
318
+ "epoch": 0.15,
319
+ "learning_rate": 0.00017045454545454547,
320
+ "loss": 2.2865,
321
+ "step": 52
322
+ },
323
+ {
324
+ "epoch": 0.15,
325
+ "learning_rate": 0.00016988636363636365,
326
+ "loss": 2.2788,
327
+ "step": 53
328
+ },
329
+ {
330
+ "epoch": 0.15,
331
+ "learning_rate": 0.00016931818181818183,
332
+ "loss": 2.2622,
333
+ "step": 54
334
+ },
335
+ {
336
+ "epoch": 0.16,
337
+ "learning_rate": 0.00016875,
338
+ "loss": 2.3121,
339
+ "step": 55
340
+ },
341
+ {
342
+ "epoch": 0.16,
343
+ "learning_rate": 0.0001681818181818182,
344
+ "loss": 2.2958,
345
+ "step": 56
346
+ },
347
+ {
348
+ "epoch": 0.16,
349
+ "learning_rate": 0.00016761363636363637,
350
+ "loss": 2.2898,
351
+ "step": 57
352
+ },
353
+ {
354
+ "epoch": 0.16,
355
+ "learning_rate": 0.00016704545454545455,
356
+ "loss": 2.2903,
357
+ "step": 58
358
+ },
359
+ {
360
+ "epoch": 0.17,
361
+ "learning_rate": 0.00016647727272727273,
362
+ "loss": 2.3393,
363
+ "step": 59
364
+ },
365
+ {
366
+ "epoch": 0.17,
367
+ "learning_rate": 0.00016590909090909094,
368
+ "loss": 2.3086,
369
+ "step": 60
370
+ },
371
+ {
372
+ "epoch": 0.17,
373
+ "learning_rate": 0.0001653409090909091,
374
+ "loss": 2.2739,
375
+ "step": 61
376
+ },
377
+ {
378
+ "epoch": 0.18,
379
+ "learning_rate": 0.00016477272727272727,
380
+ "loss": 2.252,
381
+ "step": 62
382
+ },
383
+ {
384
+ "epoch": 0.18,
385
+ "learning_rate": 0.00016420454545454548,
386
+ "loss": 2.2868,
387
+ "step": 63
388
+ },
389
+ {
390
+ "epoch": 0.18,
391
+ "learning_rate": 0.00016363636363636366,
392
+ "loss": 2.2301,
393
+ "step": 64
394
+ },
395
+ {
396
+ "epoch": 0.18,
397
+ "learning_rate": 0.0001630681818181818,
398
+ "loss": 2.2563,
399
+ "step": 65
400
+ },
401
+ {
402
+ "epoch": 0.19,
403
+ "learning_rate": 0.00016250000000000002,
404
+ "loss": 2.2552,
405
+ "step": 66
406
+ },
407
+ {
408
+ "epoch": 0.19,
409
+ "learning_rate": 0.0001619318181818182,
410
+ "loss": 2.2615,
411
+ "step": 67
412
+ },
413
+ {
414
+ "epoch": 0.19,
415
+ "learning_rate": 0.00016136363636363635,
416
+ "loss": 2.3237,
417
+ "step": 68
418
+ },
419
+ {
420
+ "epoch": 0.2,
421
+ "learning_rate": 0.00016079545454545456,
422
+ "loss": 2.2741,
423
+ "step": 69
424
+ },
425
+ {
426
+ "epoch": 0.2,
427
+ "learning_rate": 0.00016022727272727274,
428
+ "loss": 2.2152,
429
+ "step": 70
430
+ },
431
+ {
432
+ "epoch": 0.2,
433
+ "learning_rate": 0.00015965909090909092,
434
+ "loss": 2.2558,
435
+ "step": 71
436
+ },
437
+ {
438
+ "epoch": 0.2,
439
+ "learning_rate": 0.0001590909090909091,
440
+ "loss": 2.2293,
441
+ "step": 72
442
+ },
443
+ {
444
+ "epoch": 0.21,
445
+ "learning_rate": 0.00015852272727272728,
446
+ "loss": 2.2278,
447
+ "step": 73
448
+ },
449
+ {
450
+ "epoch": 0.21,
451
+ "learning_rate": 0.00015795454545454546,
452
+ "loss": 2.2583,
453
+ "step": 74
454
+ },
455
+ {
456
+ "epoch": 0.21,
457
+ "learning_rate": 0.00015738636363636364,
458
+ "loss": 2.2609,
459
+ "step": 75
460
+ },
461
+ {
462
+ "epoch": 0.22,
463
+ "learning_rate": 0.00015681818181818182,
464
+ "loss": 2.2955,
465
+ "step": 76
466
+ },
467
+ {
468
+ "epoch": 0.22,
469
+ "learning_rate": 0.00015625,
470
+ "loss": 2.2359,
471
+ "step": 77
472
+ },
473
+ {
474
+ "epoch": 0.22,
475
+ "learning_rate": 0.00015568181818181818,
476
+ "loss": 2.2427,
477
+ "step": 78
478
+ },
479
+ {
480
+ "epoch": 0.22,
481
+ "learning_rate": 0.00015511363636363636,
482
+ "loss": 2.2632,
483
+ "step": 79
484
+ },
485
+ {
486
+ "epoch": 0.23,
487
+ "learning_rate": 0.00015454545454545454,
488
+ "loss": 2.2649,
489
+ "step": 80
490
+ },
491
+ {
492
+ "epoch": 0.23,
493
+ "learning_rate": 0.00015397727272727272,
494
+ "loss": 2.2347,
495
+ "step": 81
496
+ },
497
+ {
498
+ "epoch": 0.23,
499
+ "learning_rate": 0.00015340909090909093,
500
+ "loss": 2.2439,
501
+ "step": 82
502
+ },
503
+ {
504
+ "epoch": 0.24,
505
+ "learning_rate": 0.00015284090909090909,
506
+ "loss": 2.267,
507
+ "step": 83
508
+ },
509
+ {
510
+ "epoch": 0.24,
511
+ "learning_rate": 0.00015227272727272727,
512
+ "loss": 2.2682,
513
+ "step": 84
514
+ },
515
+ {
516
+ "epoch": 0.24,
517
+ "learning_rate": 0.00015170454545454547,
518
+ "loss": 2.2477,
519
+ "step": 85
520
+ },
521
+ {
522
+ "epoch": 0.24,
523
+ "learning_rate": 0.00015113636363636365,
524
+ "loss": 2.2534,
525
+ "step": 86
526
+ },
527
+ {
528
+ "epoch": 0.25,
529
+ "learning_rate": 0.0001505681818181818,
530
+ "loss": 2.2609,
531
+ "step": 87
532
+ },
533
+ {
534
+ "epoch": 0.25,
535
+ "learning_rate": 0.00015000000000000001,
536
+ "loss": 2.2381,
537
+ "step": 88
538
+ },
539
+ {
540
+ "epoch": 0.25,
541
+ "learning_rate": 0.0001494318181818182,
542
+ "loss": 2.2505,
543
+ "step": 89
544
+ },
545
+ {
546
+ "epoch": 0.26,
547
+ "learning_rate": 0.00014886363636363635,
548
+ "loss": 2.2628,
549
+ "step": 90
550
+ },
551
+ {
552
+ "epoch": 0.26,
553
+ "learning_rate": 0.00014829545454545455,
554
+ "loss": 2.1874,
555
+ "step": 91
556
+ },
557
+ {
558
+ "epoch": 0.26,
559
+ "learning_rate": 0.00014772727272727274,
560
+ "loss": 2.2024,
561
+ "step": 92
562
+ },
563
+ {
564
+ "epoch": 0.26,
565
+ "learning_rate": 0.00014715909090909092,
566
+ "loss": 2.2453,
567
+ "step": 93
568
+ },
569
+ {
570
+ "epoch": 0.27,
571
+ "learning_rate": 0.0001465909090909091,
572
+ "loss": 2.259,
573
+ "step": 94
574
+ },
575
+ {
576
+ "epoch": 0.27,
577
+ "learning_rate": 0.00014602272727272728,
578
+ "loss": 2.2304,
579
+ "step": 95
580
+ },
581
+ {
582
+ "epoch": 0.27,
583
+ "learning_rate": 0.00014545454545454546,
584
+ "loss": 2.2179,
585
+ "step": 96
586
+ },
587
+ {
588
+ "epoch": 0.28,
589
+ "learning_rate": 0.00014488636363636366,
590
+ "loss": 2.2497,
591
+ "step": 97
592
+ },
593
+ {
594
+ "epoch": 0.28,
595
+ "learning_rate": 0.00014431818181818182,
596
+ "loss": 2.2458,
597
+ "step": 98
598
+ },
599
+ {
600
+ "epoch": 0.28,
601
+ "learning_rate": 0.00014375,
602
+ "loss": 2.2438,
603
+ "step": 99
604
+ },
605
+ {
606
+ "epoch": 0.28,
607
+ "learning_rate": 0.0001431818181818182,
608
+ "loss": 2.2461,
609
+ "step": 100
610
+ },
611
+ {
612
+ "epoch": 0.29,
613
+ "learning_rate": 0.00014261363636363636,
614
+ "loss": 2.1966,
615
+ "step": 101
616
+ },
617
+ {
618
+ "epoch": 0.29,
619
+ "learning_rate": 0.00014204545454545454,
620
+ "loss": 2.2191,
621
+ "step": 102
622
+ },
623
+ {
624
+ "epoch": 0.29,
625
+ "learning_rate": 0.00014147727272727275,
626
+ "loss": 2.1765,
627
+ "step": 103
628
+ },
629
+ {
630
+ "epoch": 0.3,
631
+ "learning_rate": 0.00014090909090909093,
632
+ "loss": 2.1917,
633
+ "step": 104
634
+ },
635
+ {
636
+ "epoch": 0.3,
637
+ "learning_rate": 0.00014034090909090908,
638
+ "loss": 2.2025,
639
+ "step": 105
640
+ },
641
+ {
642
+ "epoch": 0.3,
643
+ "learning_rate": 0.0001397727272727273,
644
+ "loss": 2.2496,
645
+ "step": 106
646
+ },
647
+ {
648
+ "epoch": 0.3,
649
+ "learning_rate": 0.00013920454545454547,
650
+ "loss": 2.2012,
651
+ "step": 107
652
+ },
653
+ {
654
+ "epoch": 0.31,
655
+ "learning_rate": 0.00013863636363636365,
656
+ "loss": 2.2051,
657
+ "step": 108
658
+ },
659
+ {
660
+ "epoch": 0.31,
661
+ "learning_rate": 0.00013806818181818183,
662
+ "loss": 2.2027,
663
+ "step": 109
664
+ },
665
+ {
666
+ "epoch": 0.31,
667
+ "learning_rate": 0.0001375,
668
+ "loss": 2.21,
669
+ "step": 110
670
+ },
671
+ {
672
+ "epoch": 0.31,
673
+ "learning_rate": 0.0001369318181818182,
674
+ "loss": 2.2501,
675
+ "step": 111
676
+ },
677
+ {
678
+ "epoch": 0.32,
679
+ "learning_rate": 0.00013636363636363637,
680
+ "loss": 2.1916,
681
+ "step": 112
682
+ },
683
+ {
684
+ "epoch": 0.32,
685
+ "learning_rate": 0.00013579545454545455,
686
+ "loss": 2.1972,
687
+ "step": 113
688
+ },
689
+ {
690
+ "epoch": 0.32,
691
+ "learning_rate": 0.00013522727272727273,
692
+ "loss": 2.1821,
693
+ "step": 114
694
+ },
695
+ {
696
+ "epoch": 0.33,
697
+ "learning_rate": 0.00013465909090909094,
698
+ "loss": 2.2448,
699
+ "step": 115
700
+ },
701
+ {
702
+ "epoch": 0.33,
703
+ "learning_rate": 0.0001340909090909091,
704
+ "loss": 2.2253,
705
+ "step": 116
706
+ },
707
+ {
708
+ "epoch": 0.33,
709
+ "learning_rate": 0.00013352272727272727,
710
+ "loss": 2.2088,
711
+ "step": 117
712
+ },
713
+ {
714
+ "epoch": 0.33,
715
+ "learning_rate": 0.00013295454545454548,
716
+ "loss": 2.2203,
717
+ "step": 118
718
+ },
719
+ {
720
+ "epoch": 0.34,
721
+ "learning_rate": 0.00013238636363636366,
722
+ "loss": 2.2236,
723
+ "step": 119
724
+ },
725
+ {
726
+ "epoch": 0.34,
727
+ "learning_rate": 0.0001318181818181818,
728
+ "loss": 2.2074,
729
+ "step": 120
730
+ },
731
+ {
732
+ "epoch": 0.34,
733
+ "learning_rate": 0.00013125000000000002,
734
+ "loss": 2.2355,
735
+ "step": 121
736
+ },
737
+ {
738
+ "epoch": 0.35,
739
+ "learning_rate": 0.0001306818181818182,
740
+ "loss": 2.2215,
741
+ "step": 122
742
+ },
743
+ {
744
+ "epoch": 0.35,
745
+ "learning_rate": 0.00013011363636363635,
746
+ "loss": 2.1854,
747
+ "step": 123
748
+ },
749
+ {
750
+ "epoch": 0.35,
751
+ "learning_rate": 0.00012954545454545456,
752
+ "loss": 2.2046,
753
+ "step": 124
754
+ },
755
+ {
756
+ "epoch": 0.35,
757
+ "learning_rate": 0.00012897727272727274,
758
+ "loss": 2.2079,
759
+ "step": 125
760
+ },
761
+ {
762
+ "epoch": 0.36,
763
+ "learning_rate": 0.00012840909090909092,
764
+ "loss": 2.2204,
765
+ "step": 126
766
+ },
767
+ {
768
+ "epoch": 0.36,
769
+ "learning_rate": 0.0001278409090909091,
770
+ "loss": 2.2223,
771
+ "step": 127
772
+ },
773
+ {
774
+ "epoch": 0.36,
775
+ "learning_rate": 0.00012727272727272728,
776
+ "loss": 2.2149,
777
+ "step": 128
778
+ },
779
+ {
780
+ "epoch": 0.37,
781
+ "learning_rate": 0.00012670454545454546,
782
+ "loss": 2.1887,
783
+ "step": 129
784
+ },
785
+ {
786
+ "epoch": 0.37,
787
+ "learning_rate": 0.00012613636363636364,
788
+ "loss": 2.1908,
789
+ "step": 130
790
+ },
791
+ {
792
+ "epoch": 0.37,
793
+ "learning_rate": 0.00012556818181818182,
794
+ "loss": 2.2434,
795
+ "step": 131
796
+ },
797
+ {
798
+ "epoch": 0.37,
799
+ "learning_rate": 0.000125,
800
+ "loss": 2.2169,
801
+ "step": 132
802
+ },
803
+ {
804
+ "epoch": 0.38,
805
+ "learning_rate": 0.00012443181818181818,
806
+ "loss": 2.2113,
807
+ "step": 133
808
+ },
809
+ {
810
+ "epoch": 0.38,
811
+ "learning_rate": 0.00012386363636363636,
812
+ "loss": 2.2334,
813
+ "step": 134
814
+ },
815
+ {
816
+ "epoch": 0.38,
817
+ "learning_rate": 0.00012329545454545454,
818
+ "loss": 2.2034,
819
+ "step": 135
820
+ },
821
+ {
822
+ "epoch": 0.39,
823
+ "learning_rate": 0.00012272727272727272,
824
+ "loss": 2.2297,
825
+ "step": 136
826
+ },
827
+ {
828
+ "epoch": 0.39,
829
+ "learning_rate": 0.00012215909090909093,
830
+ "loss": 2.2049,
831
+ "step": 137
832
+ },
833
+ {
834
+ "epoch": 0.39,
835
+ "learning_rate": 0.00012159090909090908,
836
+ "loss": 2.1773,
837
+ "step": 138
838
+ },
839
+ {
840
+ "epoch": 0.39,
841
+ "learning_rate": 0.00012102272727272728,
842
+ "loss": 2.2057,
843
+ "step": 139
844
+ },
845
+ {
846
+ "epoch": 0.4,
847
+ "learning_rate": 0.00012045454545454546,
848
+ "loss": 2.1652,
849
+ "step": 140
850
+ },
851
+ {
852
+ "epoch": 0.4,
853
+ "learning_rate": 0.00011988636363636365,
854
+ "loss": 2.2157,
855
+ "step": 141
856
+ },
857
+ {
858
+ "epoch": 0.4,
859
+ "learning_rate": 0.00011931818181818182,
860
+ "loss": 2.1987,
861
+ "step": 142
862
+ },
863
+ {
864
+ "epoch": 0.41,
865
+ "learning_rate": 0.00011875,
866
+ "loss": 2.1666,
867
+ "step": 143
868
+ },
869
+ {
870
+ "epoch": 0.41,
871
+ "learning_rate": 0.0001181818181818182,
872
+ "loss": 2.1734,
873
+ "step": 144
874
+ },
875
+ {
876
+ "epoch": 0.41,
877
+ "learning_rate": 0.00011761363636363636,
878
+ "loss": 2.2221,
879
+ "step": 145
880
+ },
881
+ {
882
+ "epoch": 0.41,
883
+ "learning_rate": 0.00011704545454545454,
884
+ "loss": 2.1488,
885
+ "step": 146
886
+ },
887
+ {
888
+ "epoch": 0.42,
889
+ "learning_rate": 0.00011647727272727273,
890
+ "loss": 2.1487,
891
+ "step": 147
892
+ },
893
+ {
894
+ "epoch": 0.42,
895
+ "learning_rate": 0.00011590909090909093,
896
+ "loss": 2.1678,
897
+ "step": 148
898
+ },
899
+ {
900
+ "epoch": 0.42,
901
+ "learning_rate": 0.00011534090909090908,
902
+ "loss": 2.1988,
903
+ "step": 149
904
+ },
905
+ {
906
+ "epoch": 0.43,
907
+ "learning_rate": 0.00011477272727272728,
908
+ "loss": 2.1803,
909
+ "step": 150
910
+ },
911
+ {
912
+ "epoch": 0.43,
913
+ "learning_rate": 0.00011420454545454547,
914
+ "loss": 2.1671,
915
+ "step": 151
916
+ },
917
+ {
918
+ "epoch": 0.43,
919
+ "learning_rate": 0.00011363636363636365,
920
+ "loss": 2.1472,
921
+ "step": 152
922
+ },
923
+ {
924
+ "epoch": 0.43,
925
+ "learning_rate": 0.00011306818181818182,
926
+ "loss": 2.1456,
927
+ "step": 153
928
+ },
929
+ {
930
+ "epoch": 0.44,
931
+ "learning_rate": 0.00011250000000000001,
932
+ "loss": 2.1769,
933
+ "step": 154
934
+ },
935
+ {
936
+ "epoch": 0.44,
937
+ "learning_rate": 0.00011193181818181819,
938
+ "loss": 2.1484,
939
+ "step": 155
940
+ },
941
+ {
942
+ "epoch": 0.44,
943
+ "learning_rate": 0.00011136363636363636,
944
+ "loss": 2.1862,
945
+ "step": 156
946
+ },
947
+ {
948
+ "epoch": 0.45,
949
+ "learning_rate": 0.00011079545454545455,
950
+ "loss": 2.1088,
951
+ "step": 157
952
+ },
953
+ {
954
+ "epoch": 0.45,
955
+ "learning_rate": 0.00011022727272727273,
956
+ "loss": 2.1746,
957
+ "step": 158
958
+ },
959
+ {
960
+ "epoch": 0.45,
961
+ "learning_rate": 0.00010965909090909093,
962
+ "loss": 2.1609,
963
+ "step": 159
964
+ },
965
+ {
966
+ "epoch": 0.45,
967
+ "learning_rate": 0.00010909090909090909,
968
+ "loss": 2.2089,
969
+ "step": 160
970
+ },
971
+ {
972
+ "epoch": 0.46,
973
+ "learning_rate": 0.00010852272727272727,
974
+ "loss": 2.1862,
975
+ "step": 161
976
+ },
977
+ {
978
+ "epoch": 0.46,
979
+ "learning_rate": 0.00010795454545454547,
980
+ "loss": 2.1844,
981
+ "step": 162
982
+ },
983
+ {
984
+ "epoch": 0.46,
985
+ "learning_rate": 0.00010738636363636365,
986
+ "loss": 2.1717,
987
+ "step": 163
988
+ },
989
+ {
990
+ "epoch": 0.47,
991
+ "learning_rate": 0.00010681818181818181,
992
+ "loss": 2.1764,
993
+ "step": 164
994
+ },
995
+ {
996
+ "epoch": 0.47,
997
+ "learning_rate": 0.00010625000000000001,
998
+ "loss": 2.1642,
999
+ "step": 165
1000
+ },
1001
+ {
1002
+ "epoch": 0.47,
1003
+ "learning_rate": 0.00010568181818181819,
1004
+ "loss": 2.164,
1005
+ "step": 166
1006
+ },
1007
+ {
1008
+ "epoch": 0.47,
1009
+ "learning_rate": 0.00010511363636363635,
1010
+ "loss": 2.1743,
1011
+ "step": 167
1012
+ },
1013
+ {
1014
+ "epoch": 0.48,
1015
+ "learning_rate": 0.00010454545454545455,
1016
+ "loss": 2.1688,
1017
+ "step": 168
1018
+ },
1019
+ {
1020
+ "epoch": 0.48,
1021
+ "learning_rate": 0.00010397727272727273,
1022
+ "loss": 2.1756,
1023
+ "step": 169
1024
+ },
1025
+ {
1026
+ "epoch": 0.48,
1027
+ "learning_rate": 0.00010340909090909092,
1028
+ "loss": 2.1488,
1029
+ "step": 170
1030
+ },
1031
+ {
1032
+ "epoch": 0.49,
1033
+ "learning_rate": 0.00010284090909090909,
1034
+ "loss": 2.1558,
1035
+ "step": 171
1036
+ },
1037
+ {
1038
+ "epoch": 0.49,
1039
+ "learning_rate": 0.00010227272727272727,
1040
+ "loss": 2.1551,
1041
+ "step": 172
1042
+ },
1043
+ {
1044
+ "epoch": 0.49,
1045
+ "learning_rate": 0.00010170454545454546,
1046
+ "loss": 2.1462,
1047
+ "step": 173
1048
+ },
1049
+ {
1050
+ "epoch": 0.49,
1051
+ "learning_rate": 0.00010113636363636366,
1052
+ "loss": 2.134,
1053
+ "step": 174
1054
+ },
1055
+ {
1056
+ "epoch": 0.5,
1057
+ "learning_rate": 0.00010056818181818181,
1058
+ "loss": 2.1278,
1059
+ "step": 175
1060
+ },
1061
+ {
1062
+ "epoch": 0.5,
1063
+ "learning_rate": 0.0001,
1064
+ "loss": 2.1436,
1065
+ "step": 176
1066
+ },
1067
+ {
1068
+ "epoch": 0.5,
1069
+ "learning_rate": 9.943181818181819e-05,
1070
+ "loss": 2.142,
1071
+ "step": 177
1072
+ },
1073
+ {
1074
+ "epoch": 0.5,
1075
+ "learning_rate": 9.886363636363637e-05,
1076
+ "loss": 2.1481,
1077
+ "step": 178
1078
+ },
1079
+ {
1080
+ "epoch": 0.51,
1081
+ "learning_rate": 9.829545454545455e-05,
1082
+ "loss": 2.1406,
1083
+ "step": 179
1084
+ },
1085
+ {
1086
+ "epoch": 0.51,
1087
+ "learning_rate": 9.772727272727274e-05,
1088
+ "loss": 2.1555,
1089
+ "step": 180
1090
+ },
1091
+ {
1092
+ "epoch": 0.51,
1093
+ "learning_rate": 9.71590909090909e-05,
1094
+ "loss": 2.1667,
1095
+ "step": 181
1096
+ },
1097
+ {
1098
+ "epoch": 0.52,
1099
+ "learning_rate": 9.65909090909091e-05,
1100
+ "loss": 2.1455,
1101
+ "step": 182
1102
+ },
1103
+ {
1104
+ "epoch": 0.52,
1105
+ "learning_rate": 9.602272727272728e-05,
1106
+ "loss": 2.1447,
1107
+ "step": 183
1108
+ },
1109
+ {
1110
+ "epoch": 0.52,
1111
+ "learning_rate": 9.545454545454546e-05,
1112
+ "loss": 2.1642,
1113
+ "step": 184
1114
+ },
1115
+ {
1116
+ "epoch": 0.52,
1117
+ "learning_rate": 9.488636363636364e-05,
1118
+ "loss": 2.1278,
1119
+ "step": 185
1120
+ },
1121
+ {
1122
+ "epoch": 0.53,
1123
+ "learning_rate": 9.431818181818182e-05,
1124
+ "loss": 2.1548,
1125
+ "step": 186
1126
+ },
1127
+ {
1128
+ "epoch": 0.53,
1129
+ "learning_rate": 9.375e-05,
1130
+ "loss": 2.1506,
1131
+ "step": 187
1132
+ },
1133
+ {
1134
+ "epoch": 0.53,
1135
+ "learning_rate": 9.318181818181818e-05,
1136
+ "loss": 2.1649,
1137
+ "step": 188
1138
+ },
1139
+ {
1140
+ "epoch": 0.54,
1141
+ "learning_rate": 9.261363636363636e-05,
1142
+ "loss": 2.1824,
1143
+ "step": 189
1144
+ },
1145
+ {
1146
+ "epoch": 0.54,
1147
+ "learning_rate": 9.204545454545454e-05,
1148
+ "loss": 2.1451,
1149
+ "step": 190
1150
+ },
1151
+ {
1152
+ "epoch": 0.54,
1153
+ "learning_rate": 9.147727272727274e-05,
1154
+ "loss": 2.089,
1155
+ "step": 191
1156
+ },
1157
+ {
1158
+ "epoch": 0.54,
1159
+ "learning_rate": 9.090909090909092e-05,
1160
+ "loss": 2.1457,
1161
+ "step": 192
1162
+ },
1163
+ {
1164
+ "epoch": 0.55,
1165
+ "learning_rate": 9.03409090909091e-05,
1166
+ "loss": 2.1647,
1167
+ "step": 193
1168
+ },
1169
+ {
1170
+ "epoch": 0.55,
1171
+ "learning_rate": 8.977272727272728e-05,
1172
+ "loss": 2.1464,
1173
+ "step": 194
1174
+ },
1175
+ {
1176
+ "epoch": 0.55,
1177
+ "learning_rate": 8.920454545454546e-05,
1178
+ "loss": 2.116,
1179
+ "step": 195
1180
+ },
1181
+ {
1182
+ "epoch": 0.56,
1183
+ "learning_rate": 8.863636363636364e-05,
1184
+ "loss": 2.1326,
1185
+ "step": 196
1186
+ },
1187
+ {
1188
+ "epoch": 0.56,
1189
+ "learning_rate": 8.806818181818183e-05,
1190
+ "loss": 2.1248,
1191
+ "step": 197
1192
+ },
1193
+ {
1194
+ "epoch": 0.56,
1195
+ "learning_rate": 8.75e-05,
1196
+ "loss": 2.172,
1197
+ "step": 198
1198
+ },
1199
+ {
1200
+ "epoch": 0.56,
1201
+ "learning_rate": 8.693181818181818e-05,
1202
+ "loss": 2.1478,
1203
+ "step": 199
1204
+ },
1205
+ {
1206
+ "epoch": 0.57,
1207
+ "learning_rate": 8.636363636363637e-05,
1208
+ "loss": 2.1691,
1209
+ "step": 200
1210
+ }
1211
+ ],
1212
+ "logging_steps": 1,
1213
+ "max_steps": 352,
1214
+ "num_train_epochs": 1,
1215
+ "save_steps": 100,
1216
+ "total_flos": 5.0683926177970176e+17,
1217
+ "trial_name": null,
1218
+ "trial_params": null
1219
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a5b74f951ff7697f1beb8eddc25d8ee6bd52b872686edb3386a0f175a1ad4d7
3
+ size 4155
runs/Sep14_06-43-20_ThanhHa/events.out.tfevents.1694648632.ThanhHa.406390.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60ecf207842dcf293dbf430296d116b0f4abab21d192e183362824485f19b13a
3
+ size 50565