Upload folder using huggingface_hub
Browse files- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- trainer_state.json +73 -73
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -19,10 +19,10 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"dense_h_to_4h",
|
23 |
-
"query_key_value",
|
24 |
"dense",
|
25 |
-
"dense_4h_to_h"
|
|
|
|
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM"
|
28 |
}
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
|
|
|
|
22 |
"dense",
|
23 |
+
"dense_4h_to_h",
|
24 |
+
"query_key_value",
|
25 |
+
"dense_h_to_4h"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM"
|
28 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 134235712
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d8085a3ec6444fa842343baacacf463b6d3ef1190ecc1faeba351f273830f83
|
3 |
size 134235712
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 268514874
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64cfaf45221d21f9e9c90ed34cb19dc292a23bf18b30c64908fdecbb4b9a5977
|
3 |
size 268514874
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b88ecea2c59e76fab44c9b4ce134d0e84020512796c9fe1804ebd6c85f3347fa
|
3 |
size 14244
|
trainer_state.json
CHANGED
@@ -11,433 +11,433 @@
|
|
11 |
{
|
12 |
"epoch": 0.04,
|
13 |
"learning_rate": 8e-05,
|
14 |
-
"loss": 2.
|
15 |
"step": 2
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.08,
|
19 |
"learning_rate": 0.00016,
|
20 |
-
"loss": 2.
|
21 |
"step": 4
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.12,
|
25 |
"learning_rate": 0.0001999744599547812,
|
26 |
-
"loss": 2.
|
27 |
"step": 6
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.16,
|
31 |
"learning_rate": 0.00019977021786163598,
|
32 |
-
"loss": 2.
|
33 |
"step": 8
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.21,
|
37 |
"learning_rate": 0.00019936215093023884,
|
38 |
-
"loss": 2.
|
39 |
"step": 10
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.25,
|
43 |
"learning_rate": 0.00019875109281794825,
|
44 |
-
"loss": 2.
|
45 |
"step": 12
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.29,
|
49 |
"learning_rate": 0.00019793829188147406,
|
50 |
-
"loss": 2.
|
51 |
"step": 14
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.33,
|
55 |
"learning_rate": 0.00019692540862655585,
|
56 |
-
"loss": 2.
|
57 |
"step": 16
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.37,
|
61 |
"learning_rate": 0.00019571451231564525,
|
62 |
-
"loss": 2.
|
63 |
"step": 18
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.41,
|
67 |
"learning_rate": 0.00019430807674052092,
|
68 |
-
"loss": 2.
|
69 |
"step": 20
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.45,
|
73 |
"learning_rate": 0.00019270897516847403,
|
74 |
-
"loss": 2.
|
75 |
"step": 22
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.49,
|
79 |
"learning_rate": 0.00019092047447238773,
|
80 |
-
"loss": 2.
|
81 |
"step": 24
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.53,
|
85 |
"learning_rate": 0.00018894622845670283,
|
86 |
-
"loss": 2.
|
87 |
"step": 26
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.57,
|
91 |
"learning_rate": 0.00018679027039290497,
|
92 |
-
"loss": 2.
|
93 |
"step": 28
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.62,
|
97 |
"learning_rate": 0.00018445700477978205,
|
98 |
-
"loss": 2.
|
99 |
"step": 30
|
100 |
},
|
101 |
{
|
102 |
"epoch": 0.66,
|
103 |
"learning_rate": 0.00018195119834528534,
|
104 |
-
"loss": 2.
|
105 |
"step": 32
|
106 |
},
|
107 |
{
|
108 |
"epoch": 0.7,
|
109 |
"learning_rate": 0.00017927797030837768,
|
110 |
-
"loss": 2.
|
111 |
"step": 34
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.74,
|
115 |
"learning_rate": 0.0001764427819207624,
|
116 |
-
"loss": 2.
|
117 |
"step": 36
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.78,
|
121 |
"learning_rate": 0.00017345142530985887,
|
122 |
-
"loss": 2.
|
123 |
"step": 38
|
124 |
},
|
125 |
{
|
126 |
"epoch": 0.82,
|
127 |
"learning_rate": 0.00017031001164581828,
|
128 |
-
"loss": 2.
|
129 |
"step": 40
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.86,
|
133 |
"learning_rate": 0.0001670249586567531,
|
134 |
-
"loss": 2.
|
135 |
"step": 42
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.9,
|
139 |
"learning_rate": 0.0001636029775176862,
|
140 |
-
"loss": 2.
|
141 |
"step": 44
|
142 |
},
|
143 |
{
|
144 |
"epoch": 0.94,
|
145 |
"learning_rate": 0.00016005105914000507,
|
146 |
-
"loss": 2.
|
147 |
"step": 46
|
148 |
},
|
149 |
{
|
150 |
"epoch": 0.98,
|
151 |
"learning_rate": 0.0001563764598894301,
|
152 |
-
"loss": 2.
|
153 |
"step": 48
|
154 |
},
|
155 |
{
|
156 |
"epoch": 1.03,
|
157 |
"learning_rate": 0.00015258668676167546,
|
158 |
-
"loss": 2.
|
159 |
"step": 50
|
160 |
},
|
161 |
{
|
162 |
"epoch": 1.07,
|
163 |
"learning_rate": 0.000148689482046087,
|
164 |
-
"loss": 2.
|
165 |
"step": 52
|
166 |
},
|
167 |
{
|
168 |
"epoch": 1.11,
|
169 |
"learning_rate": 0.00014469280750858854,
|
170 |
-
"loss": 2.
|
171 |
"step": 54
|
172 |
},
|
173 |
{
|
174 |
"epoch": 1.15,
|
175 |
"learning_rate": 0.00014060482812625055,
|
176 |
-
"loss": 2.
|
177 |
"step": 56
|
178 |
},
|
179 |
{
|
180 |
"epoch": 1.19,
|
181 |
"learning_rate": 0.00013643389540670962,
|
182 |
-
"loss": 2.
|
183 |
"step": 58
|
184 |
},
|
185 |
{
|
186 |
"epoch": 1.23,
|
187 |
"learning_rate": 0.0001321885303265172,
|
188 |
-
"loss": 2.
|
189 |
"step": 60
|
190 |
},
|
191 |
{
|
192 |
"epoch": 1.27,
|
193 |
"learning_rate": 0.0001278774059232723,
|
194 |
-
"loss": 2.
|
195 |
"step": 62
|
196 |
},
|
197 |
{
|
198 |
"epoch": 1.31,
|
199 |
"learning_rate": 0.0001235093295771032,
|
200 |
-
"loss": 2.
|
201 |
"step": 64
|
202 |
},
|
203 |
{
|
204 |
"epoch": 1.35,
|
205 |
"learning_rate": 0.00011909322501769406,
|
206 |
-
"loss": 2.
|
207 |
"step": 66
|
208 |
},
|
209 |
{
|
210 |
"epoch": 1.39,
|
211 |
"learning_rate": 0.00011463811409361667,
|
212 |
-
"loss": 2.
|
213 |
"step": 68
|
214 |
},
|
215 |
{
|
216 |
"epoch": 1.44,
|
217 |
"learning_rate": 0.00011015309834121081,
|
218 |
-
"loss": 2.
|
219 |
"step": 70
|
220 |
},
|
221 |
{
|
222 |
"epoch": 1.48,
|
223 |
"learning_rate": 0.00010564734039066699,
|
224 |
-
"loss": 2.
|
225 |
"step": 72
|
226 |
},
|
227 |
{
|
228 |
"epoch": 1.52,
|
229 |
"learning_rate": 0.00010113004524729799,
|
230 |
-
"loss": 2.
|
231 |
"step": 74
|
232 |
},
|
233 |
{
|
234 |
"epoch": 1.56,
|
235 |
"learning_rate": 9.661044148624037e-05,
|
236 |
-
"loss": 2.
|
237 |
"step": 76
|
238 |
},
|
239 |
{
|
240 |
"epoch": 1.6,
|
241 |
"learning_rate": 9.209776239900453e-05,
|
242 |
-
"loss": 2.
|
243 |
"step": 78
|
244 |
},
|
245 |
{
|
246 |
"epoch": 1.64,
|
247 |
"learning_rate": 8.760122713038881e-05,
|
248 |
-
"loss": 2.
|
249 |
"step": 80
|
250 |
},
|
251 |
{
|
252 |
"epoch": 1.68,
|
253 |
"learning_rate": 8.313002184429529e-05,
|
254 |
-
"loss": 2.
|
255 |
"step": 82
|
256 |
},
|
257 |
{
|
258 |
"epoch": 1.72,
|
259 |
"learning_rate": 7.869328095692312e-05,
|
260 |
-
"loss": 2.
|
261 |
"step": 84
|
262 |
},
|
263 |
{
|
264 |
"epoch": 1.76,
|
265 |
"learning_rate": 7.430006847567972e-05,
|
266 |
-
"loss": 2.
|
267 |
"step": 86
|
268 |
},
|
269 |
{
|
270 |
"epoch": 1.81,
|
271 |
"learning_rate": 6.995935948193294e-05,
|
272 |
-
"loss": 2.
|
273 |
"step": 88
|
274 |
},
|
275 |
{
|
276 |
"epoch": 1.85,
|
277 |
"learning_rate": 6.568002179543409e-05,
|
278 |
-
"loss": 2.
|
279 |
"step": 90
|
280 |
},
|
281 |
{
|
282 |
"epoch": 1.89,
|
283 |
"learning_rate": 6.147079785787038e-05,
|
284 |
-
"loss": 2.
|
285 |
"step": 92
|
286 |
},
|
287 |
{
|
288 |
"epoch": 1.93,
|
289 |
"learning_rate": 5.734028687255751e-05,
|
290 |
-
"loss": 2.
|
291 |
"step": 94
|
292 |
},
|
293 |
{
|
294 |
"epoch": 1.97,
|
295 |
"learning_rate": 5.329692723675994e-05,
|
296 |
-
"loss": 2.
|
297 |
"step": 96
|
298 |
},
|
299 |
{
|
300 |
"epoch": 2.01,
|
301 |
"learning_rate": 4.934897930252886e-05,
|
302 |
-
"loss": 2.
|
303 |
"step": 98
|
304 |
},
|
305 |
{
|
306 |
"epoch": 2.05,
|
307 |
"learning_rate": 4.550450850127625e-05,
|
308 |
-
"loss": 2.
|
309 |
"step": 100
|
310 |
},
|
311 |
{
|
312 |
"epoch": 2.09,
|
313 |
"learning_rate": 4.1771368866560665e-05,
|
314 |
-
"loss": 2.
|
315 |
"step": 102
|
316 |
},
|
317 |
{
|
318 |
"epoch": 2.13,
|
319 |
"learning_rate": 3.815718698874672e-05,
|
320 |
-
"loss": 2.
|
321 |
"step": 104
|
322 |
},
|
323 |
{
|
324 |
"epoch": 2.17,
|
325 |
"learning_rate": 3.466934643431795e-05,
|
326 |
-
"loss": 2.
|
327 |
"step": 106
|
328 |
},
|
329 |
{
|
330 |
"epoch": 2.22,
|
331 |
"learning_rate": 3.131497266167357e-05,
|
332 |
-
"loss": 2.
|
333 |
"step": 108
|
334 |
},
|
335 |
{
|
336 |
"epoch": 2.26,
|
337 |
"learning_rate": 2.81009184642253e-05,
|
338 |
-
"loss":
|
339 |
"step": 110
|
340 |
},
|
341 |
{
|
342 |
"epoch": 2.3,
|
343 |
"learning_rate": 2.5033749970533015e-05,
|
344 |
-
"loss": 2.
|
345 |
"step": 112
|
346 |
},
|
347 |
{
|
348 |
"epoch": 2.34,
|
349 |
"learning_rate": 2.2119733230080408e-05,
|
350 |
-
"loss": 2.
|
351 |
"step": 114
|
352 |
},
|
353 |
{
|
354 |
"epoch": 2.38,
|
355 |
"learning_rate": 1.9364821412094857e-05,
|
356 |
-
"loss": 2.
|
357 |
"step": 116
|
358 |
},
|
359 |
{
|
360 |
"epoch": 2.42,
|
361 |
"learning_rate": 1.6774642643563953e-05,
|
362 |
-
"loss": 2.
|
363 |
"step": 118
|
364 |
},
|
365 |
{
|
366 |
"epoch": 2.46,
|
367 |
"learning_rate": 1.4354488511294417e-05,
|
368 |
-
"loss":
|
369 |
"step": 120
|
370 |
},
|
371 |
{
|
372 |
"epoch": 2.5,
|
373 |
"learning_rate": 1.2109303251503434e-05,
|
374 |
-
"loss":
|
375 |
"step": 122
|
376 |
},
|
377 |
{
|
378 |
"epoch": 2.54,
|
379 |
"learning_rate": 1.0043673649027518e-05,
|
380 |
-
"loss": 2.
|
381 |
"step": 124
|
382 |
},
|
383 |
{
|
384 |
"epoch": 2.58,
|
385 |
"learning_rate": 8.161819666783888e-06,
|
386 |
-
"loss": 2.
|
387 |
"step": 126
|
388 |
},
|
389 |
{
|
390 |
"epoch": 2.63,
|
391 |
"learning_rate": 6.467585824627887e-06,
|
392 |
-
"loss": 2.
|
393 |
"step": 128
|
394 |
},
|
395 |
{
|
396 |
"epoch": 2.67,
|
397 |
"learning_rate": 4.964433345219355e-06,
|
398 |
-
"loss": 2.
|
399 |
"step": 130
|
400 |
},
|
401 |
{
|
402 |
"epoch": 2.71,
|
403 |
"learning_rate": 3.655433082942972e-06,
|
404 |
-
"loss": 2.
|
405 |
"step": 132
|
406 |
},
|
407 |
{
|
408 |
"epoch": 2.75,
|
409 |
"learning_rate": 2.5432592503288e-06,
|
410 |
-
"loss": 2.
|
411 |
"step": 134
|
412 |
},
|
413 |
{
|
414 |
"epoch": 2.79,
|
415 |
"learning_rate": 1.6301839547892328e-06,
|
416 |
-
"loss": 2.
|
417 |
"step": 136
|
418 |
},
|
419 |
{
|
420 |
"epoch": 2.83,
|
421 |
"learning_rate": 9.180725568338044e-07,
|
422 |
-
"loss": 2.
|
423 |
"step": 138
|
424 |
},
|
425 |
{
|
426 |
"epoch": 2.87,
|
427 |
"learning_rate": 4.0837985924448984e-07,
|
428 |
-
"loss": 2.
|
429 |
"step": 140
|
430 |
},
|
431 |
{
|
432 |
"epoch": 2.91,
|
433 |
"learning_rate": 1.0214713499706597e-07,
|
434 |
-
"loss": 2.
|
435 |
"step": 142
|
436 |
},
|
437 |
{
|
438 |
"epoch": 2.95,
|
439 |
"learning_rate": 0.0,
|
440 |
-
"loss": 2.
|
441 |
"step": 144
|
442 |
}
|
443 |
],
|
@@ -445,7 +445,7 @@
|
|
445 |
"max_steps": 144,
|
446 |
"num_train_epochs": 3,
|
447 |
"save_steps": 500,
|
448 |
-
"total_flos":
|
449 |
"trial_name": null,
|
450 |
"trial_params": null
|
451 |
}
|
|
|
11 |
{
|
12 |
"epoch": 0.04,
|
13 |
"learning_rate": 8e-05,
|
14 |
+
"loss": 2.1159,
|
15 |
"step": 2
|
16 |
},
|
17 |
{
|
18 |
"epoch": 0.08,
|
19 |
"learning_rate": 0.00016,
|
20 |
+
"loss": 2.4844,
|
21 |
"step": 4
|
22 |
},
|
23 |
{
|
24 |
"epoch": 0.12,
|
25 |
"learning_rate": 0.0001999744599547812,
|
26 |
+
"loss": 2.6077,
|
27 |
"step": 6
|
28 |
},
|
29 |
{
|
30 |
"epoch": 0.16,
|
31 |
"learning_rate": 0.00019977021786163598,
|
32 |
+
"loss": 2.5077,
|
33 |
"step": 8
|
34 |
},
|
35 |
{
|
36 |
"epoch": 0.21,
|
37 |
"learning_rate": 0.00019936215093023884,
|
38 |
+
"loss": 2.5153,
|
39 |
"step": 10
|
40 |
},
|
41 |
{
|
42 |
"epoch": 0.25,
|
43 |
"learning_rate": 0.00019875109281794825,
|
44 |
+
"loss": 2.3988,
|
45 |
"step": 12
|
46 |
},
|
47 |
{
|
48 |
"epoch": 0.29,
|
49 |
"learning_rate": 0.00019793829188147406,
|
50 |
+
"loss": 2.3181,
|
51 |
"step": 14
|
52 |
},
|
53 |
{
|
54 |
"epoch": 0.33,
|
55 |
"learning_rate": 0.00019692540862655585,
|
56 |
+
"loss": 2.3074,
|
57 |
"step": 16
|
58 |
},
|
59 |
{
|
60 |
"epoch": 0.37,
|
61 |
"learning_rate": 0.00019571451231564525,
|
62 |
+
"loss": 2.5799,
|
63 |
"step": 18
|
64 |
},
|
65 |
{
|
66 |
"epoch": 0.41,
|
67 |
"learning_rate": 0.00019430807674052092,
|
68 |
+
"loss": 2.5704,
|
69 |
"step": 20
|
70 |
},
|
71 |
{
|
72 |
"epoch": 0.45,
|
73 |
"learning_rate": 0.00019270897516847403,
|
74 |
+
"loss": 2.3123,
|
75 |
"step": 22
|
76 |
},
|
77 |
{
|
78 |
"epoch": 0.49,
|
79 |
"learning_rate": 0.00019092047447238773,
|
80 |
+
"loss": 2.3193,
|
81 |
"step": 24
|
82 |
},
|
83 |
{
|
84 |
"epoch": 0.53,
|
85 |
"learning_rate": 0.00018894622845670283,
|
86 |
+
"loss": 2.3503,
|
87 |
"step": 26
|
88 |
},
|
89 |
{
|
90 |
"epoch": 0.57,
|
91 |
"learning_rate": 0.00018679027039290497,
|
92 |
+
"loss": 2.2122,
|
93 |
"step": 28
|
94 |
},
|
95 |
{
|
96 |
"epoch": 0.62,
|
97 |
"learning_rate": 0.00018445700477978205,
|
98 |
+
"loss": 2.3402,
|
99 |
"step": 30
|
100 |
},
|
101 |
{
|
102 |
"epoch": 0.66,
|
103 |
"learning_rate": 0.00018195119834528534,
|
104 |
+
"loss": 2.2695,
|
105 |
"step": 32
|
106 |
},
|
107 |
{
|
108 |
"epoch": 0.7,
|
109 |
"learning_rate": 0.00017927797030837768,
|
110 |
+
"loss": 2.4346,
|
111 |
"step": 34
|
112 |
},
|
113 |
{
|
114 |
"epoch": 0.74,
|
115 |
"learning_rate": 0.0001764427819207624,
|
116 |
+
"loss": 2.5551,
|
117 |
"step": 36
|
118 |
},
|
119 |
{
|
120 |
"epoch": 0.78,
|
121 |
"learning_rate": 0.00017345142530985887,
|
122 |
+
"loss": 2.1379,
|
123 |
"step": 38
|
124 |
},
|
125 |
{
|
126 |
"epoch": 0.82,
|
127 |
"learning_rate": 0.00017031001164581828,
|
128 |
+
"loss": 2.259,
|
129 |
"step": 40
|
130 |
},
|
131 |
{
|
132 |
"epoch": 0.86,
|
133 |
"learning_rate": 0.0001670249586567531,
|
134 |
+
"loss": 2.1868,
|
135 |
"step": 42
|
136 |
},
|
137 |
{
|
138 |
"epoch": 0.9,
|
139 |
"learning_rate": 0.0001636029775176862,
|
140 |
+
"loss": 2.4213,
|
141 |
"step": 44
|
142 |
},
|
143 |
{
|
144 |
"epoch": 0.94,
|
145 |
"learning_rate": 0.00016005105914000507,
|
146 |
+
"loss": 2.3686,
|
147 |
"step": 46
|
148 |
},
|
149 |
{
|
150 |
"epoch": 0.98,
|
151 |
"learning_rate": 0.0001563764598894301,
|
152 |
+
"loss": 2.2921,
|
153 |
"step": 48
|
154 |
},
|
155 |
{
|
156 |
"epoch": 1.03,
|
157 |
"learning_rate": 0.00015258668676167546,
|
158 |
+
"loss": 2.1,
|
159 |
"step": 50
|
160 |
},
|
161 |
{
|
162 |
"epoch": 1.07,
|
163 |
"learning_rate": 0.000148689482046087,
|
164 |
+
"loss": 2.1504,
|
165 |
"step": 52
|
166 |
},
|
167 |
{
|
168 |
"epoch": 1.11,
|
169 |
"learning_rate": 0.00014469280750858854,
|
170 |
+
"loss": 2.2671,
|
171 |
"step": 54
|
172 |
},
|
173 |
{
|
174 |
"epoch": 1.15,
|
175 |
"learning_rate": 0.00014060482812625055,
|
176 |
+
"loss": 2.3171,
|
177 |
"step": 56
|
178 |
},
|
179 |
{
|
180 |
"epoch": 1.19,
|
181 |
"learning_rate": 0.00013643389540670962,
|
182 |
+
"loss": 2.3209,
|
183 |
"step": 58
|
184 |
},
|
185 |
{
|
186 |
"epoch": 1.23,
|
187 |
"learning_rate": 0.0001321885303265172,
|
188 |
+
"loss": 2.3478,
|
189 |
"step": 60
|
190 |
},
|
191 |
{
|
192 |
"epoch": 1.27,
|
193 |
"learning_rate": 0.0001278774059232723,
|
194 |
+
"loss": 2.1167,
|
195 |
"step": 62
|
196 |
},
|
197 |
{
|
198 |
"epoch": 1.31,
|
199 |
"learning_rate": 0.0001235093295771032,
|
200 |
+
"loss": 2.1784,
|
201 |
"step": 64
|
202 |
},
|
203 |
{
|
204 |
"epoch": 1.35,
|
205 |
"learning_rate": 0.00011909322501769406,
|
206 |
+
"loss": 2.1854,
|
207 |
"step": 66
|
208 |
},
|
209 |
{
|
210 |
"epoch": 1.39,
|
211 |
"learning_rate": 0.00011463811409361667,
|
212 |
+
"loss": 2.5377,
|
213 |
"step": 68
|
214 |
},
|
215 |
{
|
216 |
"epoch": 1.44,
|
217 |
"learning_rate": 0.00011015309834121081,
|
218 |
+
"loss": 2.1904,
|
219 |
"step": 70
|
220 |
},
|
221 |
{
|
222 |
"epoch": 1.48,
|
223 |
"learning_rate": 0.00010564734039066699,
|
224 |
+
"loss": 2.2207,
|
225 |
"step": 72
|
226 |
},
|
227 |
{
|
228 |
"epoch": 1.52,
|
229 |
"learning_rate": 0.00010113004524729799,
|
230 |
+
"loss": 2.0583,
|
231 |
"step": 74
|
232 |
},
|
233 |
{
|
234 |
"epoch": 1.56,
|
235 |
"learning_rate": 9.661044148624037e-05,
|
236 |
+
"loss": 2.2241,
|
237 |
"step": 76
|
238 |
},
|
239 |
{
|
240 |
"epoch": 1.6,
|
241 |
"learning_rate": 9.209776239900453e-05,
|
242 |
+
"loss": 2.351,
|
243 |
"step": 78
|
244 |
},
|
245 |
{
|
246 |
"epoch": 1.64,
|
247 |
"learning_rate": 8.760122713038881e-05,
|
248 |
+
"loss": 2.2872,
|
249 |
"step": 80
|
250 |
},
|
251 |
{
|
252 |
"epoch": 1.68,
|
253 |
"learning_rate": 8.313002184429529e-05,
|
254 |
+
"loss": 2.4212,
|
255 |
"step": 82
|
256 |
},
|
257 |
{
|
258 |
"epoch": 1.72,
|
259 |
"learning_rate": 7.869328095692312e-05,
|
260 |
+
"loss": 2.2449,
|
261 |
"step": 84
|
262 |
},
|
263 |
{
|
264 |
"epoch": 1.76,
|
265 |
"learning_rate": 7.430006847567972e-05,
|
266 |
+
"loss": 2.1668,
|
267 |
"step": 86
|
268 |
},
|
269 |
{
|
270 |
"epoch": 1.81,
|
271 |
"learning_rate": 6.995935948193294e-05,
|
272 |
+
"loss": 2.3131,
|
273 |
"step": 88
|
274 |
},
|
275 |
{
|
276 |
"epoch": 1.85,
|
277 |
"learning_rate": 6.568002179543409e-05,
|
278 |
+
"loss": 2.3438,
|
279 |
"step": 90
|
280 |
},
|
281 |
{
|
282 |
"epoch": 1.89,
|
283 |
"learning_rate": 6.147079785787038e-05,
|
284 |
+
"loss": 2.3536,
|
285 |
"step": 92
|
286 |
},
|
287 |
{
|
288 |
"epoch": 1.93,
|
289 |
"learning_rate": 5.734028687255751e-05,
|
290 |
+
"loss": 2.3383,
|
291 |
"step": 94
|
292 |
},
|
293 |
{
|
294 |
"epoch": 1.97,
|
295 |
"learning_rate": 5.329692723675994e-05,
|
296 |
+
"loss": 2.35,
|
297 |
"step": 96
|
298 |
},
|
299 |
{
|
300 |
"epoch": 2.01,
|
301 |
"learning_rate": 4.934897930252886e-05,
|
302 |
+
"loss": 2.1033,
|
303 |
"step": 98
|
304 |
},
|
305 |
{
|
306 |
"epoch": 2.05,
|
307 |
"learning_rate": 4.550450850127625e-05,
|
308 |
+
"loss": 2.1835,
|
309 |
"step": 100
|
310 |
},
|
311 |
{
|
312 |
"epoch": 2.09,
|
313 |
"learning_rate": 4.1771368866560665e-05,
|
314 |
+
"loss": 2.2955,
|
315 |
"step": 102
|
316 |
},
|
317 |
{
|
318 |
"epoch": 2.13,
|
319 |
"learning_rate": 3.815718698874672e-05,
|
320 |
+
"loss": 2.4554,
|
321 |
"step": 104
|
322 |
},
|
323 |
{
|
324 |
"epoch": 2.17,
|
325 |
"learning_rate": 3.466934643431795e-05,
|
326 |
+
"loss": 2.3854,
|
327 |
"step": 106
|
328 |
},
|
329 |
{
|
330 |
"epoch": 2.22,
|
331 |
"learning_rate": 3.131497266167357e-05,
|
332 |
+
"loss": 2.2288,
|
333 |
"step": 108
|
334 |
},
|
335 |
{
|
336 |
"epoch": 2.26,
|
337 |
"learning_rate": 2.81009184642253e-05,
|
338 |
+
"loss": 2.0636,
|
339 |
"step": 110
|
340 |
},
|
341 |
{
|
342 |
"epoch": 2.3,
|
343 |
"learning_rate": 2.5033749970533015e-05,
|
344 |
+
"loss": 2.1865,
|
345 |
"step": 112
|
346 |
},
|
347 |
{
|
348 |
"epoch": 2.34,
|
349 |
"learning_rate": 2.2119733230080408e-05,
|
350 |
+
"loss": 2.0827,
|
351 |
"step": 114
|
352 |
},
|
353 |
{
|
354 |
"epoch": 2.38,
|
355 |
"learning_rate": 1.9364821412094857e-05,
|
356 |
+
"loss": 2.4395,
|
357 |
"step": 116
|
358 |
},
|
359 |
{
|
360 |
"epoch": 2.42,
|
361 |
"learning_rate": 1.6774642643563953e-05,
|
362 |
+
"loss": 2.2468,
|
363 |
"step": 118
|
364 |
},
|
365 |
{
|
366 |
"epoch": 2.46,
|
367 |
"learning_rate": 1.4354488511294417e-05,
|
368 |
+
"loss": 2.1809,
|
369 |
"step": 120
|
370 |
},
|
371 |
{
|
372 |
"epoch": 2.5,
|
373 |
"learning_rate": 1.2109303251503434e-05,
|
374 |
+
"loss": 2.072,
|
375 |
"step": 122
|
376 |
},
|
377 |
{
|
378 |
"epoch": 2.54,
|
379 |
"learning_rate": 1.0043673649027518e-05,
|
380 |
+
"loss": 2.1208,
|
381 |
"step": 124
|
382 |
},
|
383 |
{
|
384 |
"epoch": 2.58,
|
385 |
"learning_rate": 8.161819666783888e-06,
|
386 |
+
"loss": 2.1125,
|
387 |
"step": 126
|
388 |
},
|
389 |
{
|
390 |
"epoch": 2.63,
|
391 |
"learning_rate": 6.467585824627887e-06,
|
392 |
+
"loss": 2.3907,
|
393 |
"step": 128
|
394 |
},
|
395 |
{
|
396 |
"epoch": 2.67,
|
397 |
"learning_rate": 4.964433345219355e-06,
|
398 |
+
"loss": 2.3751,
|
399 |
"step": 130
|
400 |
},
|
401 |
{
|
402 |
"epoch": 2.71,
|
403 |
"learning_rate": 3.655433082942972e-06,
|
404 |
+
"loss": 2.252,
|
405 |
"step": 132
|
406 |
},
|
407 |
{
|
408 |
"epoch": 2.75,
|
409 |
"learning_rate": 2.5432592503288e-06,
|
410 |
+
"loss": 2.1179,
|
411 |
"step": 134
|
412 |
},
|
413 |
{
|
414 |
"epoch": 2.79,
|
415 |
"learning_rate": 1.6301839547892328e-06,
|
416 |
+
"loss": 2.1899,
|
417 |
"step": 136
|
418 |
},
|
419 |
{
|
420 |
"epoch": 2.83,
|
421 |
"learning_rate": 9.180725568338044e-07,
|
422 |
+
"loss": 2.1179,
|
423 |
"step": 138
|
424 |
},
|
425 |
{
|
426 |
"epoch": 2.87,
|
427 |
"learning_rate": 4.0837985924448984e-07,
|
428 |
+
"loss": 2.2198,
|
429 |
"step": 140
|
430 |
},
|
431 |
{
|
432 |
"epoch": 2.91,
|
433 |
"learning_rate": 1.0214713499706597e-07,
|
434 |
+
"loss": 2.2656,
|
435 |
"step": 142
|
436 |
},
|
437 |
{
|
438 |
"epoch": 2.95,
|
439 |
"learning_rate": 0.0,
|
440 |
+
"loss": 2.3361,
|
441 |
"step": 144
|
442 |
}
|
443 |
],
|
|
|
445 |
"max_steps": 144,
|
446 |
"num_train_epochs": 3,
|
447 |
"save_steps": 500,
|
448 |
+
"total_flos": 6357879457677312.0,
|
449 |
"trial_name": null,
|
450 |
"trial_params": null
|
451 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:332d53045b82e348cd70c54dd9bc8c38843358091acfbbdef3f4153fda65d0a5
|
3 |
size 4600
|