Hugging Face's logo

wesley7137
/
tiny_llama_shopper_adapter

PEFT
Model card Files
xet
Community
wesley7137 commited on
Commit
31fb2d8
·
verified ·
1 Parent(s): 0e1a03f

Upload 13 files

Browse files
Files changed (13) hide show
  1. README.md +32 -0
  2. adapter_config.json +26 -0
  3. adapter_model.bin +3 -0
  4. added_tokens.json +3 -0
  5. optimizer.pt +3 -0
  6. rng_state.pth +3 -0
  7. scheduler.pt +3 -0
  8. special_tokens_map.json +24 -0
  9. tokenizer.json +0 -0
  10. tokenizer.model +3 -0
  11. tokenizer_config.json +40 -0
  12. trainer_state.json +616 -0
  13. 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 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
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
+ "k_proj",
19
+ "v_proj",
20
+ "out_proj",
21
+ "fc_in",
22
+ "fc_out",
23
+ "wte"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:226fcb1fa54552a43b77513753496bdb7373568017d39c6fae1a9a40ebc8dbc4
3
+ size 49068762
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:413644d0c77c5153038663058e43096cb95fc2e22c774b170a4fefd5cf815dbc
3
+ size 98122618
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3260b1397f47de551abc33856f18e72d3c68bfc401b2ff4b5b957fa33ec998d9
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb54cffa206db0c12f0795a9e4804d798628be7cb6d50b66106d7441bc5abccf
3
+ size 1064
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 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<s>",
29
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "legacy": false,
33
+ "model_max_length": 2048,
34
+ "pad_token": "</s>",
35
+ "padding_side": "right",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": false
40
+ }
trainer_state.json ADDED
@@ -0,0 +1,616 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.7548209366391183,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.03,
12
+ "learning_rate": 0.0002,
13
+ "loss": 1.6739,
14
+ "step": 5
15
+ },
16
+ {
17
+ "epoch": 0.06,
18
+ "learning_rate": 0.0002,
19
+ "loss": 1.4695,
20
+ "step": 10
21
+ },
22
+ {
23
+ "epoch": 0.08,
24
+ "learning_rate": 0.0002,
25
+ "loss": 1.3698,
26
+ "step": 15
27
+ },
28
+ {
29
+ "epoch": 0.11,
30
+ "learning_rate": 0.0002,
31
+ "loss": 1.31,
32
+ "step": 20
33
+ },
34
+ {
35
+ "epoch": 0.14,
36
+ "learning_rate": 0.0002,
37
+ "loss": 1.1747,
38
+ "step": 25
39
+ },
40
+ {
41
+ "epoch": 0.17,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.1566,
44
+ "step": 30
45
+ },
46
+ {
47
+ "epoch": 0.19,
48
+ "learning_rate": 0.0002,
49
+ "loss": 1.102,
50
+ "step": 35
51
+ },
52
+ {
53
+ "epoch": 0.22,
54
+ "learning_rate": 0.0002,
55
+ "loss": 1.2996,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 0.25,
60
+ "learning_rate": 0.0002,
61
+ "loss": 1.284,
62
+ "step": 45
63
+ },
64
+ {
65
+ "epoch": 0.28,
66
+ "learning_rate": 0.0002,
67
+ "loss": 1.1008,
68
+ "step": 50
69
+ },
70
+ {
71
+ "epoch": 0.3,
72
+ "learning_rate": 0.0002,
73
+ "loss": 0.8815,
74
+ "step": 55
75
+ },
76
+ {
77
+ "epoch": 0.33,
78
+ "learning_rate": 0.0002,
79
+ "loss": 0.8306,
80
+ "step": 60
81
+ },
82
+ {
83
+ "epoch": 0.36,
84
+ "learning_rate": 0.0002,
85
+ "loss": 1.0265,
86
+ "step": 65
87
+ },
88
+ {
89
+ "epoch": 0.39,
90
+ "learning_rate": 0.0002,
91
+ "loss": 0.9281,
92
+ "step": 70
93
+ },
94
+ {
95
+ "epoch": 0.41,
96
+ "learning_rate": 0.0002,
97
+ "loss": 0.9321,
98
+ "step": 75
99
+ },
100
+ {
101
+ "epoch": 0.44,
102
+ "learning_rate": 0.0002,
103
+ "loss": 0.8366,
104
+ "step": 80
105
+ },
106
+ {
107
+ "epoch": 0.47,
108
+ "learning_rate": 0.0002,
109
+ "loss": 1.1115,
110
+ "step": 85
111
+ },
112
+ {
113
+ "epoch": 0.5,
114
+ "learning_rate": 0.0002,
115
+ "loss": 1.0392,
116
+ "step": 90
117
+ },
118
+ {
119
+ "epoch": 0.52,
120
+ "learning_rate": 0.0002,
121
+ "loss": 1.0288,
122
+ "step": 95
123
+ },
124
+ {
125
+ "epoch": 0.55,
126
+ "learning_rate": 0.0002,
127
+ "loss": 0.7581,
128
+ "step": 100
129
+ },
130
+ {
131
+ "epoch": 0.58,
132
+ "learning_rate": 0.0002,
133
+ "loss": 0.8078,
134
+ "step": 105
135
+ },
136
+ {
137
+ "epoch": 0.61,
138
+ "learning_rate": 0.0002,
139
+ "loss": 0.8296,
140
+ "step": 110
141
+ },
142
+ {
143
+ "epoch": 0.63,
144
+ "learning_rate": 0.0002,
145
+ "loss": 0.9053,
146
+ "step": 115
147
+ },
148
+ {
149
+ "epoch": 0.66,
150
+ "learning_rate": 0.0002,
151
+ "loss": 0.9,
152
+ "step": 120
153
+ },
154
+ {
155
+ "epoch": 0.69,
156
+ "learning_rate": 0.0002,
157
+ "loss": 0.8384,
158
+ "step": 125
159
+ },
160
+ {
161
+ "epoch": 0.72,
162
+ "learning_rate": 0.0002,
163
+ "loss": 0.9651,
164
+ "step": 130
165
+ },
166
+ {
167
+ "epoch": 0.74,
168
+ "learning_rate": 0.0002,
169
+ "loss": 1.0384,
170
+ "step": 135
171
+ },
172
+ {
173
+ "epoch": 0.77,
174
+ "learning_rate": 0.0002,
175
+ "loss": 0.9916,
176
+ "step": 140
177
+ },
178
+ {
179
+ "epoch": 0.8,
180
+ "learning_rate": 0.0002,
181
+ "loss": 0.7081,
182
+ "step": 145
183
+ },
184
+ {
185
+ "epoch": 0.83,
186
+ "learning_rate": 0.0002,
187
+ "loss": 0.7966,
188
+ "step": 150
189
+ },
190
+ {
191
+ "epoch": 0.85,
192
+ "learning_rate": 0.0002,
193
+ "loss": 0.8907,
194
+ "step": 155
195
+ },
196
+ {
197
+ "epoch": 0.88,
198
+ "learning_rate": 0.0002,
199
+ "loss": 0.8284,
200
+ "step": 160
201
+ },
202
+ {
203
+ "epoch": 0.91,
204
+ "learning_rate": 0.0002,
205
+ "loss": 0.7204,
206
+ "step": 165
207
+ },
208
+ {
209
+ "epoch": 0.94,
210
+ "learning_rate": 0.0002,
211
+ "loss": 0.8712,
212
+ "step": 170
213
+ },
214
+ {
215
+ "epoch": 0.96,
216
+ "learning_rate": 0.0002,
217
+ "loss": 0.9699,
218
+ "step": 175
219
+ },
220
+ {
221
+ "epoch": 0.99,
222
+ "learning_rate": 0.0002,
223
+ "loss": 0.9726,
224
+ "step": 180
225
+ },
226
+ {
227
+ "epoch": 1.02,
228
+ "learning_rate": 0.0002,
229
+ "loss": 0.9618,
230
+ "step": 185
231
+ },
232
+ {
233
+ "epoch": 1.05,
234
+ "learning_rate": 0.0002,
235
+ "loss": 0.6762,
236
+ "step": 190
237
+ },
238
+ {
239
+ "epoch": 1.07,
240
+ "learning_rate": 0.0002,
241
+ "loss": 0.7073,
242
+ "step": 195
243
+ },
244
+ {
245
+ "epoch": 1.1,
246
+ "learning_rate": 0.0002,
247
+ "loss": 0.8257,
248
+ "step": 200
249
+ },
250
+ {
251
+ "epoch": 1.13,
252
+ "learning_rate": 0.0002,
253
+ "loss": 0.8218,
254
+ "step": 205
255
+ },
256
+ {
257
+ "epoch": 1.16,
258
+ "learning_rate": 0.0002,
259
+ "loss": 0.879,
260
+ "step": 210
261
+ },
262
+ {
263
+ "epoch": 1.18,
264
+ "learning_rate": 0.0002,
265
+ "loss": 0.7279,
266
+ "step": 215
267
+ },
268
+ {
269
+ "epoch": 1.21,
270
+ "learning_rate": 0.0002,
271
+ "loss": 0.8078,
272
+ "step": 220
273
+ },
274
+ {
275
+ "epoch": 1.24,
276
+ "learning_rate": 0.0002,
277
+ "loss": 0.9659,
278
+ "step": 225
279
+ },
280
+ {
281
+ "epoch": 1.27,
282
+ "learning_rate": 0.0002,
283
+ "loss": 0.9077,
284
+ "step": 230
285
+ },
286
+ {
287
+ "epoch": 1.29,
288
+ "learning_rate": 0.0002,
289
+ "loss": 0.8432,
290
+ "step": 235
291
+ },
292
+ {
293
+ "epoch": 1.32,
294
+ "learning_rate": 0.0002,
295
+ "loss": 0.6376,
296
+ "step": 240
297
+ },
298
+ {
299
+ "epoch": 1.35,
300
+ "learning_rate": 0.0002,
301
+ "loss": 0.6578,
302
+ "step": 245
303
+ },
304
+ {
305
+ "epoch": 1.38,
306
+ "learning_rate": 0.0002,
307
+ "loss": 0.7712,
308
+ "step": 250
309
+ },
310
+ {
311
+ "epoch": 1.4,
312
+ "learning_rate": 0.0002,
313
+ "loss": 0.7946,
314
+ "step": 255
315
+ },
316
+ {
317
+ "epoch": 1.43,
318
+ "learning_rate": 0.0002,
319
+ "loss": 0.714,
320
+ "step": 260
321
+ },
322
+ {
323
+ "epoch": 1.46,
324
+ "learning_rate": 0.0002,
325
+ "loss": 0.9,
326
+ "step": 265
327
+ },
328
+ {
329
+ "epoch": 1.49,
330
+ "learning_rate": 0.0002,
331
+ "loss": 0.8877,
332
+ "step": 270
333
+ },
334
+ {
335
+ "epoch": 1.52,
336
+ "learning_rate": 0.0002,
337
+ "loss": 0.8492,
338
+ "step": 275
339
+ },
340
+ {
341
+ "epoch": 1.54,
342
+ "learning_rate": 0.0002,
343
+ "loss": 0.7307,
344
+ "step": 280
345
+ },
346
+ {
347
+ "epoch": 1.57,
348
+ "learning_rate": 0.0002,
349
+ "loss": 0.6746,
350
+ "step": 285
351
+ },
352
+ {
353
+ "epoch": 1.6,
354
+ "learning_rate": 0.0002,
355
+ "loss": 0.7466,
356
+ "step": 290
357
+ },
358
+ {
359
+ "epoch": 1.63,
360
+ "learning_rate": 0.0002,
361
+ "loss": 0.6683,
362
+ "step": 295
363
+ },
364
+ {
365
+ "epoch": 1.65,
366
+ "learning_rate": 0.0002,
367
+ "loss": 0.8136,
368
+ "step": 300
369
+ },
370
+ {
371
+ "epoch": 1.68,
372
+ "learning_rate": 0.0002,
373
+ "loss": 0.6348,
374
+ "step": 305
375
+ },
376
+ {
377
+ "epoch": 1.71,
378
+ "learning_rate": 0.0002,
379
+ "loss": 0.8073,
380
+ "step": 310
381
+ },
382
+ {
383
+ "epoch": 1.74,
384
+ "learning_rate": 0.0002,
385
+ "loss": 0.9171,
386
+ "step": 315
387
+ },
388
+ {
389
+ "epoch": 1.76,
390
+ "learning_rate": 0.0002,
391
+ "loss": 0.9165,
392
+ "step": 320
393
+ },
394
+ {
395
+ "epoch": 1.79,
396
+ "learning_rate": 0.0002,
397
+ "loss": 0.7211,
398
+ "step": 325
399
+ },
400
+ {
401
+ "epoch": 1.82,
402
+ "learning_rate": 0.0002,
403
+ "loss": 0.5587,
404
+ "step": 330
405
+ },
406
+ {
407
+ "epoch": 1.85,
408
+ "learning_rate": 0.0002,
409
+ "loss": 0.7583,
410
+ "step": 335
411
+ },
412
+ {
413
+ "epoch": 1.87,
414
+ "learning_rate": 0.0002,
415
+ "loss": 0.7004,
416
+ "step": 340
417
+ },
418
+ {
419
+ "epoch": 1.9,
420
+ "learning_rate": 0.0002,
421
+ "loss": 0.7815,
422
+ "step": 345
423
+ },
424
+ {
425
+ "epoch": 1.93,
426
+ "learning_rate": 0.0002,
427
+ "loss": 0.6479,
428
+ "step": 350
429
+ },
430
+ {
431
+ "epoch": 1.96,
432
+ "learning_rate": 0.0002,
433
+ "loss": 0.8537,
434
+ "step": 355
435
+ },
436
+ {
437
+ "epoch": 1.98,
438
+ "learning_rate": 0.0002,
439
+ "loss": 0.862,
440
+ "step": 360
441
+ },
442
+ {
443
+ "epoch": 2.01,
444
+ "learning_rate": 0.0002,
445
+ "loss": 0.8366,
446
+ "step": 365
447
+ },
448
+ {
449
+ "epoch": 2.04,
450
+ "learning_rate": 0.0002,
451
+ "loss": 0.7606,
452
+ "step": 370
453
+ },
454
+ {
455
+ "epoch": 2.07,
456
+ "learning_rate": 0.0002,
457
+ "loss": 0.5288,
458
+ "step": 375
459
+ },
460
+ {
461
+ "epoch": 2.09,
462
+ "learning_rate": 0.0002,
463
+ "loss": 0.5945,
464
+ "step": 380
465
+ },
466
+ {
467
+ "epoch": 2.12,
468
+ "learning_rate": 0.0002,
469
+ "loss": 0.6433,
470
+ "step": 385
471
+ },
472
+ {
473
+ "epoch": 2.15,
474
+ "learning_rate": 0.0002,
475
+ "loss": 0.6962,
476
+ "step": 390
477
+ },
478
+ {
479
+ "epoch": 2.18,
480
+ "learning_rate": 0.0002,
481
+ "loss": 0.5828,
482
+ "step": 395
483
+ },
484
+ {
485
+ "epoch": 2.2,
486
+ "learning_rate": 0.0002,
487
+ "loss": 0.68,
488
+ "step": 400
489
+ },
490
+ {
491
+ "epoch": 2.23,
492
+ "learning_rate": 0.0002,
493
+ "loss": 0.7801,
494
+ "step": 405
495
+ },
496
+ {
497
+ "epoch": 2.26,
498
+ "learning_rate": 0.0002,
499
+ "loss": 0.7877,
500
+ "step": 410
501
+ },
502
+ {
503
+ "epoch": 2.29,
504
+ "learning_rate": 0.0002,
505
+ "loss": 0.8949,
506
+ "step": 415
507
+ },
508
+ {
509
+ "epoch": 2.31,
510
+ "learning_rate": 0.0002,
511
+ "loss": 0.4878,
512
+ "step": 420
513
+ },
514
+ {
515
+ "epoch": 2.34,
516
+ "learning_rate": 0.0002,
517
+ "loss": 0.5364,
518
+ "step": 425
519
+ },
520
+ {
521
+ "epoch": 2.37,
522
+ "learning_rate": 0.0002,
523
+ "loss": 0.667,
524
+ "step": 430
525
+ },
526
+ {
527
+ "epoch": 2.4,
528
+ "learning_rate": 0.0002,
529
+ "loss": 0.7271,
530
+ "step": 435
531
+ },
532
+ {
533
+ "epoch": 2.42,
534
+ "learning_rate": 0.0002,
535
+ "loss": 0.6242,
536
+ "step": 440
537
+ },
538
+ {
539
+ "epoch": 2.45,
540
+ "learning_rate": 0.0002,
541
+ "loss": 0.5735,
542
+ "step": 445
543
+ },
544
+ {
545
+ "epoch": 2.48,
546
+ "learning_rate": 0.0002,
547
+ "loss": 0.7495,
548
+ "step": 450
549
+ },
550
+ {
551
+ "epoch": 2.51,
552
+ "learning_rate": 0.0002,
553
+ "loss": 0.7836,
554
+ "step": 455
555
+ },
556
+ {
557
+ "epoch": 2.53,
558
+ "learning_rate": 0.0002,
559
+ "loss": 0.785,
560
+ "step": 460
561
+ },
562
+ {
563
+ "epoch": 2.56,
564
+ "learning_rate": 0.0002,
565
+ "loss": 0.5057,
566
+ "step": 465
567
+ },
568
+ {
569
+ "epoch": 2.59,
570
+ "learning_rate": 0.0002,
571
+ "loss": 0.5685,
572
+ "step": 470
573
+ },
574
+ {
575
+ "epoch": 2.62,
576
+ "learning_rate": 0.0002,
577
+ "loss": 0.6507,
578
+ "step": 475
579
+ },
580
+ {
581
+ "epoch": 2.64,
582
+ "learning_rate": 0.0002,
583
+ "loss": 0.6217,
584
+ "step": 480
585
+ },
586
+ {
587
+ "epoch": 2.67,
588
+ "learning_rate": 0.0002,
589
+ "loss": 0.6732,
590
+ "step": 485
591
+ },
592
+ {
593
+ "epoch": 2.7,
594
+ "learning_rate": 0.0002,
595
+ "loss": 0.7112,
596
+ "step": 490
597
+ },
598
+ {
599
+ "epoch": 2.73,
600
+ "learning_rate": 0.0002,
601
+ "loss": 0.6993,
602
+ "step": 495
603
+ },
604
+ {
605
+ "epoch": 2.75,
606
+ "learning_rate": 0.0002,
607
+ "loss": 0.7456,
608
+ "step": 500
609
+ }
610
+ ],
611
+ "max_steps": 543,
612
+ "num_train_epochs": 3,
613
+ "total_flos": 941285658353664.0,
614
+ "trial_name": null,
615
+ "trial_params": null
616
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c80ce929816631b6aab379c2acd80be368c4079b0014c31b30e773bebb8e9f49
3
+ size 4408