Hugging Face's logo

qanastek
/
LLaMa-2-FrenchMedMCQA-Checkpoint

PEFT
Model card Files Community
qanastek commited on
Commit
ec57a8e
•
1 Parent(s): f185ca2

Upload 12 files

Browse files
Files changed (12) hide show
  1. README.md +32 -0
  2. adapter_config.json +21 -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 +24 -0
  8. tokenizer.json +0 -0
  9. tokenizer.model +3 -0
  10. tokenizer_config.json +32 -0
  11. trainer_state.json +826 -0
  12. 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 0.4.0
31
+
32
+ - PEFT 0.4.0
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
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
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35a5e5eba27d6ed069a8e9b86deabe524cc7dddea6ee770141fe4698422ad2c4
3
+ size 134263757
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f208d91e1fc324441fb21b0e11cc1b20b95688444438cf41108c22499d8e3a0
3
+ size 268514565
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ead3573694ce0465729afc0360ed7c15ff34ead9bf06c5be406efa0ae0e3eb3a
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7736097317b26660e1de69c529f297a4d81b185a114540c968acffdda13a974f
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "sp_model_kwargs": {},
23
+ "tokenizer_class": "LlamaTokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<unk>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
trainer_state.json ADDED
@@ -0,0 +1,826 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.94475138121547,
5
+ "global_step": 1350,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.07,
12
+ "learning_rate": 0.0002,
13
+ "loss": 1.9251,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.15,
18
+ "learning_rate": 0.0002,
19
+ "loss": 1.1925,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.22,
24
+ "learning_rate": 0.0002,
25
+ "loss": 0.6688,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.29,
30
+ "learning_rate": 0.0002,
31
+ "loss": 0.778,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.37,
36
+ "learning_rate": 0.0002,
37
+ "loss": 0.6743,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.44,
42
+ "learning_rate": 0.0002,
43
+ "loss": 0.569,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.52,
48
+ "learning_rate": 0.0002,
49
+ "loss": 0.598,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.59,
54
+ "learning_rate": 0.0002,
55
+ "loss": 0.6713,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.66,
60
+ "learning_rate": 0.0002,
61
+ "loss": 0.571,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.74,
66
+ "learning_rate": 0.0002,
67
+ "loss": 0.503,
68
+ "step": 100
69
+ },
70
+ {
71
+ "epoch": 0.81,
72
+ "learning_rate": 0.0002,
73
+ "loss": 0.7059,
74
+ "step": 110
75
+ },
76
+ {
77
+ "epoch": 0.88,
78
+ "learning_rate": 0.0002,
79
+ "loss": 0.5989,
80
+ "step": 120
81
+ },
82
+ {
83
+ "epoch": 0.96,
84
+ "learning_rate": 0.0002,
85
+ "loss": 0.4895,
86
+ "step": 130
87
+ },
88
+ {
89
+ "epoch": 1.03,
90
+ "learning_rate": 0.0002,
91
+ "loss": 0.623,
92
+ "step": 140
93
+ },
94
+ {
95
+ "epoch": 1.1,
96
+ "learning_rate": 0.0002,
97
+ "loss": 0.637,
98
+ "step": 150
99
+ },
100
+ {
101
+ "epoch": 1.18,
102
+ "learning_rate": 0.0002,
103
+ "loss": 0.5461,
104
+ "step": 160
105
+ },
106
+ {
107
+ "epoch": 1.25,
108
+ "learning_rate": 0.0002,
109
+ "loss": 0.48,
110
+ "step": 170
111
+ },
112
+ {
113
+ "epoch": 1.33,
114
+ "learning_rate": 0.0002,
115
+ "loss": 0.7108,
116
+ "step": 180
117
+ },
118
+ {
119
+ "epoch": 1.4,
120
+ "learning_rate": 0.0002,
121
+ "loss": 0.5659,
122
+ "step": 190
123
+ },
124
+ {
125
+ "epoch": 1.47,
126
+ "learning_rate": 0.0002,
127
+ "loss": 0.4692,
128
+ "step": 200
129
+ },
130
+ {
131
+ "epoch": 1.55,
132
+ "learning_rate": 0.0002,
133
+ "loss": 0.674,
134
+ "step": 210
135
+ },
136
+ {
137
+ "epoch": 1.62,
138
+ "learning_rate": 0.0002,
139
+ "loss": 0.5979,
140
+ "step": 220
141
+ },
142
+ {
143
+ "epoch": 1.69,
144
+ "learning_rate": 0.0002,
145
+ "loss": 0.484,
146
+ "step": 230
147
+ },
148
+ {
149
+ "epoch": 1.77,
150
+ "learning_rate": 0.0002,
151
+ "loss": 0.5799,
152
+ "step": 240
153
+ },
154
+ {
155
+ "epoch": 1.84,
156
+ "learning_rate": 0.0002,
157
+ "loss": 0.6141,
158
+ "step": 250
159
+ },
160
+ {
161
+ "epoch": 1.92,
162
+ "learning_rate": 0.0002,
163
+ "loss": 0.5177,
164
+ "step": 260
165
+ },
166
+ {
167
+ "epoch": 1.99,
168
+ "learning_rate": 0.0002,
169
+ "loss": 0.4582,
170
+ "step": 270
171
+ },
172
+ {
173
+ "epoch": 2.06,
174
+ "learning_rate": 0.0002,
175
+ "loss": 0.6667,
176
+ "step": 280
177
+ },
178
+ {
179
+ "epoch": 2.14,
180
+ "learning_rate": 0.0002,
181
+ "loss": 0.56,
182
+ "step": 290
183
+ },
184
+ {
185
+ "epoch": 2.21,
186
+ "learning_rate": 0.0002,
187
+ "loss": 0.4628,
188
+ "step": 300
189
+ },
190
+ {
191
+ "epoch": 2.28,
192
+ "learning_rate": 0.0002,
193
+ "loss": 0.5623,
194
+ "step": 310
195
+ },
196
+ {
197
+ "epoch": 2.36,
198
+ "learning_rate": 0.0002,
199
+ "loss": 0.6027,
200
+ "step": 320
201
+ },
202
+ {
203
+ "epoch": 2.43,
204
+ "learning_rate": 0.0002,
205
+ "loss": 0.4787,
206
+ "step": 330
207
+ },
208
+ {
209
+ "epoch": 2.5,
210
+ "learning_rate": 0.0002,
211
+ "loss": 0.4718,
212
+ "step": 340
213
+ },
214
+ {
215
+ "epoch": 2.58,
216
+ "learning_rate": 0.0002,
217
+ "loss": 0.6168,
218
+ "step": 350
219
+ },
220
+ {
221
+ "epoch": 2.65,
222
+ "learning_rate": 0.0002,
223
+ "loss": 0.5156,
224
+ "step": 360
225
+ },
226
+ {
227
+ "epoch": 2.73,
228
+ "learning_rate": 0.0002,
229
+ "loss": 0.4076,
230
+ "step": 370
231
+ },
232
+ {
233
+ "epoch": 2.8,
234
+ "learning_rate": 0.0002,
235
+ "loss": 0.6857,
236
+ "step": 380
237
+ },
238
+ {
239
+ "epoch": 2.87,
240
+ "learning_rate": 0.0002,
241
+ "loss": 0.5429,
242
+ "step": 390
243
+ },
244
+ {
245
+ "epoch": 2.95,
246
+ "learning_rate": 0.0002,
247
+ "loss": 0.43,
248
+ "step": 400
249
+ },
250
+ {
251
+ "epoch": 3.02,
252
+ "learning_rate": 0.0002,
253
+ "loss": 0.5163,
254
+ "step": 410
255
+ },
256
+ {
257
+ "epoch": 3.09,
258
+ "learning_rate": 0.0002,
259
+ "loss": 0.6072,
260
+ "step": 420
261
+ },
262
+ {
263
+ "epoch": 3.17,
264
+ "learning_rate": 0.0002,
265
+ "loss": 0.4804,
266
+ "step": 430
267
+ },
268
+ {
269
+ "epoch": 3.24,
270
+ "learning_rate": 0.0002,
271
+ "loss": 0.3655,
272
+ "step": 440
273
+ },
274
+ {
275
+ "epoch": 3.31,
276
+ "learning_rate": 0.0002,
277
+ "loss": 0.6351,
278
+ "step": 450
279
+ },
280
+ {
281
+ "epoch": 3.39,
282
+ "learning_rate": 0.0002,
283
+ "loss": 0.512,
284
+ "step": 460
285
+ },
286
+ {
287
+ "epoch": 3.46,
288
+ "learning_rate": 0.0002,
289
+ "loss": 0.3907,
290
+ "step": 470
291
+ },
292
+ {
293
+ "epoch": 3.54,
294
+ "learning_rate": 0.0002,
295
+ "loss": 0.5736,
296
+ "step": 480
297
+ },
298
+ {
299
+ "epoch": 3.61,
300
+ "learning_rate": 0.0002,
301
+ "loss": 0.5337,
302
+ "step": 490
303
+ },
304
+ {
305
+ "epoch": 3.68,
306
+ "learning_rate": 0.0002,
307
+ "loss": 0.4324,
308
+ "step": 500
309
+ },
310
+ {
311
+ "epoch": 3.76,
312
+ "learning_rate": 0.0002,
313
+ "loss": 0.4844,
314
+ "step": 510
315
+ },
316
+ {
317
+ "epoch": 3.83,
318
+ "learning_rate": 0.0002,
319
+ "loss": 0.5886,
320
+ "step": 520
321
+ },
322
+ {
323
+ "epoch": 3.9,
324
+ "learning_rate": 0.0002,
325
+ "loss": 0.4723,
326
+ "step": 530
327
+ },
328
+ {
329
+ "epoch": 3.98,
330
+ "learning_rate": 0.0002,
331
+ "loss": 0.3895,
332
+ "step": 540
333
+ },
334
+ {
335
+ "epoch": 4.05,
336
+ "learning_rate": 0.0002,
337
+ "loss": 0.58,
338
+ "step": 550
339
+ },
340
+ {
341
+ "epoch": 4.13,
342
+ "learning_rate": 0.0002,
343
+ "loss": 0.4998,
344
+ "step": 560
345
+ },
346
+ {
347
+ "epoch": 4.2,
348
+ "learning_rate": 0.0002,
349
+ "loss": 0.3901,
350
+ "step": 570
351
+ },
352
+ {
353
+ "epoch": 4.27,
354
+ "learning_rate": 0.0002,
355
+ "loss": 0.4494,
356
+ "step": 580
357
+ },
358
+ {
359
+ "epoch": 4.35,
360
+ "learning_rate": 0.0002,
361
+ "loss": 0.5282,
362
+ "step": 590
363
+ },
364
+ {
365
+ "epoch": 4.42,
366
+ "learning_rate": 0.0002,
367
+ "loss": 0.4162,
368
+ "step": 600
369
+ },
370
+ {
371
+ "epoch": 4.49,
372
+ "learning_rate": 0.0002,
373
+ "loss": 0.3818,
374
+ "step": 610
375
+ },
376
+ {
377
+ "epoch": 4.57,
378
+ "learning_rate": 0.0002,
379
+ "loss": 0.594,
380
+ "step": 620
381
+ },
382
+ {
383
+ "epoch": 4.64,
384
+ "learning_rate": 0.0002,
385
+ "loss": 0.4547,
386
+ "step": 630
387
+ },
388
+ {
389
+ "epoch": 4.71,
390
+ "learning_rate": 0.0002,
391
+ "loss": 0.3598,
392
+ "step": 640
393
+ },
394
+ {
395
+ "epoch": 4.79,
396
+ "learning_rate": 0.0002,
397
+ "loss": 0.5721,
398
+ "step": 650
399
+ },
400
+ {
401
+ "epoch": 4.86,
402
+ "learning_rate": 0.0002,
403
+ "loss": 0.4997,
404
+ "step": 660
405
+ },
406
+ {
407
+ "epoch": 4.94,
408
+ "learning_rate": 0.0002,
409
+ "loss": 0.3974,
410
+ "step": 670
411
+ },
412
+ {
413
+ "epoch": 5.01,
414
+ "learning_rate": 0.0002,
415
+ "loss": 0.4133,
416
+ "step": 680
417
+ },
418
+ {
419
+ "epoch": 5.08,
420
+ "learning_rate": 0.0002,
421
+ "loss": 0.5438,
422
+ "step": 690
423
+ },
424
+ {
425
+ "epoch": 5.16,
426
+ "learning_rate": 0.0002,
427
+ "loss": 0.408,
428
+ "step": 700
429
+ },
430
+ {
431
+ "epoch": 5.23,
432
+ "learning_rate": 0.0002,
433
+ "loss": 0.3157,
434
+ "step": 710
435
+ },
436
+ {
437
+ "epoch": 5.3,
438
+ "learning_rate": 0.0002,
439
+ "loss": 0.5219,
440
+ "step": 720
441
+ },
442
+ {
443
+ "epoch": 5.38,
444
+ "learning_rate": 0.0002,
445
+ "loss": 0.4365,
446
+ "step": 730
447
+ },
448
+ {
449
+ "epoch": 5.45,
450
+ "learning_rate": 0.0002,
451
+ "loss": 0.3586,
452
+ "step": 740
453
+ },
454
+ {
455
+ "epoch": 5.52,
456
+ "learning_rate": 0.0002,
457
+ "loss": 0.462,
458
+ "step": 750
459
+ },
460
+ {
461
+ "epoch": 5.6,
462
+ "learning_rate": 0.0002,
463
+ "loss": 0.4815,
464
+ "step": 760
465
+ },
466
+ {
467
+ "epoch": 5.67,
468
+ "learning_rate": 0.0002,
469
+ "loss": 0.3818,
470
+ "step": 770
471
+ },
472
+ {
473
+ "epoch": 5.75,
474
+ "learning_rate": 0.0002,
475
+ "loss": 0.3744,
476
+ "step": 780
477
+ },
478
+ {
479
+ "epoch": 5.82,
480
+ "learning_rate": 0.0002,
481
+ "loss": 0.5412,
482
+ "step": 790
483
+ },
484
+ {
485
+ "epoch": 5.89,
486
+ "learning_rate": 0.0002,
487
+ "loss": 0.4341,
488
+ "step": 800
489
+ },
490
+ {
491
+ "epoch": 5.97,
492
+ "learning_rate": 0.0002,
493
+ "loss": 0.3258,
494
+ "step": 810
495
+ },
496
+ {
497
+ "epoch": 6.04,
498
+ "learning_rate": 0.0002,
499
+ "loss": 0.4872,
500
+ "step": 820
501
+ },
502
+ {
503
+ "epoch": 6.11,
504
+ "learning_rate": 0.0002,
505
+ "loss": 0.4313,
506
+ "step": 830
507
+ },
508
+ {
509
+ "epoch": 6.19,
510
+ "learning_rate": 0.0002,
511
+ "loss": 0.3199,
512
+ "step": 840
513
+ },
514
+ {
515
+ "epoch": 6.26,
516
+ "learning_rate": 0.0002,
517
+ "loss": 0.3386,
518
+ "step": 850
519
+ },
520
+ {
521
+ "epoch": 6.34,
522
+ "learning_rate": 0.0002,
523
+ "loss": 0.4872,
524
+ "step": 860
525
+ },
526
+ {
527
+ "epoch": 6.41,
528
+ "learning_rate": 0.0002,
529
+ "loss": 0.3744,
530
+ "step": 870
531
+ },
532
+ {
533
+ "epoch": 6.48,
534
+ "learning_rate": 0.0002,
535
+ "loss": 0.277,
536
+ "step": 880
537
+ },
538
+ {
539
+ "epoch": 6.56,
540
+ "learning_rate": 0.0002,
541
+ "loss": 0.5125,
542
+ "step": 890
543
+ },
544
+ {
545
+ "epoch": 6.63,
546
+ "learning_rate": 0.0002,
547
+ "loss": 0.4132,
548
+ "step": 900
549
+ },
550
+ {
551
+ "epoch": 6.7,
552
+ "learning_rate": 0.0002,
553
+ "loss": 0.31,
554
+ "step": 910
555
+ },
556
+ {
557
+ "epoch": 6.78,
558
+ "learning_rate": 0.0002,
559
+ "loss": 0.4628,
560
+ "step": 920
561
+ },
562
+ {
563
+ "epoch": 6.85,
564
+ "learning_rate": 0.0002,
565
+ "loss": 0.4471,
566
+ "step": 930
567
+ },
568
+ {
569
+ "epoch": 6.92,
570
+ "learning_rate": 0.0002,
571
+ "loss": 0.3348,
572
+ "step": 940
573
+ },
574
+ {
575
+ "epoch": 7.0,
576
+ "learning_rate": 0.0002,
577
+ "loss": 0.3292,
578
+ "step": 950
579
+ },
580
+ {
581
+ "epoch": 7.07,
582
+ "learning_rate": 0.0002,
583
+ "loss": 0.4596,
584
+ "step": 960
585
+ },
586
+ {
587
+ "epoch": 7.15,
588
+ "learning_rate": 0.0002,
589
+ "loss": 0.3506,
590
+ "step": 970
591
+ },
592
+ {
593
+ "epoch": 7.22,
594
+ "learning_rate": 0.0002,
595
+ "loss": 0.2606,
596
+ "step": 980
597
+ },
598
+ {
599
+ "epoch": 7.29,
600
+ "learning_rate": 0.0002,
601
+ "loss": 0.4052,
602
+ "step": 990
603
+ },
604
+ {
605
+ "epoch": 7.37,
606
+ "learning_rate": 0.0002,
607
+ "loss": 0.3891,
608
+ "step": 1000
609
+ },
610
+ {
611
+ "epoch": 7.44,
612
+ "learning_rate": 0.0002,
613
+ "loss": 0.3116,
614
+ "step": 1010
615
+ },
616
+ {
617
+ "epoch": 7.51,
618
+ "learning_rate": 0.0002,
619
+ "loss": 0.3483,
620
+ "step": 1020
621
+ },
622
+ {
623
+ "epoch": 7.59,
624
+ "learning_rate": 0.0002,
625
+ "loss": 0.4398,
626
+ "step": 1030
627
+ },
628
+ {
629
+ "epoch": 7.66,
630
+ "learning_rate": 0.0002,
631
+ "loss": 0.3157,
632
+ "step": 1040
633
+ },
634
+ {
635
+ "epoch": 7.73,
636
+ "learning_rate": 0.0002,
637
+ "loss": 0.268,
638
+ "step": 1050
639
+ },
640
+ {
641
+ "epoch": 7.81,
642
+ "learning_rate": 0.0002,
643
+ "loss": 0.4692,
644
+ "step": 1060
645
+ },
646
+ {
647
+ "epoch": 7.88,
648
+ "learning_rate": 0.0002,
649
+ "loss": 0.3724,
650
+ "step": 1070
651
+ },
652
+ {
653
+ "epoch": 7.96,
654
+ "learning_rate": 0.0002,
655
+ "loss": 0.2665,
656
+ "step": 1080
657
+ },
658
+ {
659
+ "epoch": 8.03,
660
+ "learning_rate": 0.0002,
661
+ "loss": 0.3718,
662
+ "step": 1090
663
+ },
664
+ {
665
+ "epoch": 8.1,
666
+ "learning_rate": 0.0002,
667
+ "loss": 0.372,
668
+ "step": 1100
669
+ },
670
+ {
671
+ "epoch": 8.18,
672
+ "learning_rate": 0.0002,
673
+ "loss": 0.2868,
674
+ "step": 1110
675
+ },
676
+ {
677
+ "epoch": 8.25,
678
+ "learning_rate": 0.0002,
679
+ "loss": 0.2351,
680
+ "step": 1120
681
+ },
682
+ {
683
+ "epoch": 8.32,
684
+ "learning_rate": 0.0002,
685
+ "loss": 0.4212,
686
+ "step": 1130
687
+ },
688
+ {
689
+ "epoch": 8.4,
690
+ "learning_rate": 0.0002,
691
+ "loss": 0.3118,
692
+ "step": 1140
693
+ },
694
+ {
695
+ "epoch": 8.47,
696
+ "learning_rate": 0.0002,
697
+ "loss": 0.2195,
698
+ "step": 1150
699
+ },
700
+ {
701
+ "epoch": 8.55,
702
+ "learning_rate": 0.0002,
703
+ "loss": 0.3907,
704
+ "step": 1160
705
+ },
706
+ {
707
+ "epoch": 8.62,
708
+ "learning_rate": 0.0002,
709
+ "loss": 0.335,
710
+ "step": 1170
711
+ },
712
+ {
713
+ "epoch": 8.69,
714
+ "learning_rate": 0.0002,
715
+ "loss": 0.26,
716
+ "step": 1180
717
+ },
718
+ {
719
+ "epoch": 8.77,
720
+ "learning_rate": 0.0002,
721
+ "loss": 0.3481,
722
+ "step": 1190
723
+ },
724
+ {
725
+ "epoch": 8.84,
726
+ "learning_rate": 0.0002,
727
+ "loss": 0.3802,
728
+ "step": 1200
729
+ },
730
+ {
731
+ "epoch": 8.91,
732
+ "learning_rate": 0.0002,
733
+ "loss": 0.2834,
734
+ "step": 1210
735
+ },
736
+ {
737
+ "epoch": 8.99,
738
+ "learning_rate": 0.0002,
739
+ "loss": 0.2545,
740
+ "step": 1220
741
+ },
742
+ {
743
+ "epoch": 9.06,
744
+ "learning_rate": 0.0002,
745
+ "loss": 0.3557,
746
+ "step": 1230
747
+ },
748
+ {
749
+ "epoch": 9.13,
750
+ "learning_rate": 0.0002,
751
+ "loss": 0.2917,
752
+ "step": 1240
753
+ },
754
+ {
755
+ "epoch": 9.21,
756
+ "learning_rate": 0.0002,
757
+ "loss": 0.2154,
758
+ "step": 1250
759
+ },
760
+ {
761
+ "epoch": 9.28,
762
+ "learning_rate": 0.0002,
763
+ "loss": 0.2994,
764
+ "step": 1260
765
+ },
766
+ {
767
+ "epoch": 9.36,
768
+ "learning_rate": 0.0002,
769
+ "loss": 0.321,
770
+ "step": 1270
771
+ },
772
+ {
773
+ "epoch": 9.43,
774
+ "learning_rate": 0.0002,
775
+ "loss": 0.2344,
776
+ "step": 1280
777
+ },
778
+ {
779
+ "epoch": 9.5,
780
+ "learning_rate": 0.0002,
781
+ "loss": 0.2356,
782
+ "step": 1290
783
+ },
784
+ {
785
+ "epoch": 9.58,
786
+ "learning_rate": 0.0002,
787
+ "loss": 0.3661,
788
+ "step": 1300
789
+ },
790
+ {
791
+ "epoch": 9.65,
792
+ "learning_rate": 0.0002,
793
+ "loss": 0.2786,
794
+ "step": 1310
795
+ },
796
+ {
797
+ "epoch": 9.72,
798
+ "learning_rate": 0.0002,
799
+ "loss": 0.1928,
800
+ "step": 1320
801
+ },
802
+ {
803
+ "epoch": 9.8,
804
+ "learning_rate": 0.0002,
805
+ "loss": 0.3897,
806
+ "step": 1330
807
+ },
808
+ {
809
+ "epoch": 9.87,
810
+ "learning_rate": 0.0002,
811
+ "loss": 0.2978,
812
+ "step": 1340
813
+ },
814
+ {
815
+ "epoch": 9.94,
816
+ "learning_rate": 0.0002,
817
+ "loss": 0.2234,
818
+ "step": 1350
819
+ }
820
+ ],
821
+ "max_steps": 1350,
822
+ "num_train_epochs": 10,
823
+ "total_flos": 1.116092169148416e+17,
824
+ "trial_name": null,
825
+ "trial_params": null
826
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59eb0d276bf21e642f96952d43cda90b7a0a54cbfb0c5fda57e378ba3bb8fc5d
3
+ size 3963