AlekseyKorshuk
commited on
Commit
·
1790f07
1
Parent(s):
3b4951b
huggingartists
Browse files- README.md +3 -3
- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +35 -959
- training_args.bin +1 -1
README.md
CHANGED
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
45 |
dataset = load_dataset("huggingartists/queen")
|
46 |
```
|
47 |
|
48 |
-
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/
|
49 |
|
50 |
## Training procedure
|
51 |
|
52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Queen's lyrics.
|
53 |
|
54 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/
|
55 |
|
56 |
-
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/
|
57 |
|
58 |
## How to use
|
59 |
|
|
|
45 |
dataset = load_dataset("huggingartists/queen")
|
46 |
```
|
47 |
|
48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/29edwcv0/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
|
49 |
|
50 |
## Training procedure
|
51 |
|
52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Queen's lyrics.
|
53 |
|
54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/135qvcfh) for full transparency and reproducibility.
|
55 |
|
56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/135qvcfh/artifacts) is logged and versioned.
|
57 |
|
58 |
## How to use
|
59 |
|
evaluation.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"eval_loss": 0.
|
|
|
1 |
+
{"eval_loss": 0.9767317771911621, "eval_runtime": 2.1966, "eval_samples_per_second": 43.704, "eval_steps_per_second": 5.463, "epoch": 12.0}
|
flax_model.msgpack
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 497764120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d59d4092b6fbaa70e9f950aa8fcb06e8531e931e125851c1d4493cca00a1d6d3
|
3 |
size 497764120
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 995604017
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ee8cef8141948570d21835c08d084a9b314fbdef3ba8f904e6e203013456a0d
|
3 |
size 995604017
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 510396521
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c3308c600cab57fc29528fed25a3b6bbe8e7e16d4e20d2e4b9967b339a59a76b
|
3 |
size 510396521
|
rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afadc6c82078abf8ebc3154d7c31c5702ef7fa29db799979801c5d8393338a19
|
3 |
size 14503
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d825f1ad452557c55ae3db5704cfc8ff0c2aef068797ec1bf426331ec8788e52
|
3 |
size 623
|
trainer_state.json
CHANGED
@@ -1,1026 +1,102 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "output/queen/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
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.
|
13 |
-
"loss":
|
14 |
"step": 5
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.15,
|
18 |
"learning_rate": 0.0001300082017869573,
|
19 |
-
"loss":
|
20 |
"step": 10
|
21 |
},
|
22 |
{
|
23 |
"epoch": 0.22,
|
24 |
-
"learning_rate": 0.
|
25 |
-
"loss":
|
26 |
"step": 15
|
27 |
},
|
28 |
{
|
29 |
"epoch": 0.29,
|
30 |
-
"learning_rate": 0.
|
31 |
-
"loss":
|
32 |
"step": 20
|
33 |
},
|
34 |
{
|
35 |
"epoch": 0.37,
|
36 |
-
"learning_rate": 9.
|
37 |
-
"loss":
|
38 |
"step": 25
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.44,
|
42 |
-
"learning_rate": 8.
|
43 |
-
"loss":
|
44 |
"step": 30
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.51,
|
48 |
"learning_rate": 6.543181473690228e-05,
|
49 |
-
"loss":
|
50 |
"step": 35
|
51 |
},
|
52 |
{
|
53 |
"epoch": 0.59,
|
54 |
-
"learning_rate": 4.
|
55 |
-
"loss":
|
56 |
"step": 40
|
57 |
},
|
58 |
{
|
59 |
"epoch": 0.66,
|
60 |
-
"learning_rate": 3.
|
61 |
-
"loss":
|
62 |
"step": 45
|
63 |
},
|
64 |
{
|
65 |
"epoch": 0.74,
|
66 |
-
"learning_rate": 2.
|
67 |
-
"loss":
|
68 |
"step": 50
|
69 |
},
|
70 |
{
|
71 |
"epoch": 0.81,
|
72 |
-
"learning_rate": 1.
|
73 |
-
"loss":
|
74 |
"step": 55
|
75 |
},
|
76 |
{
|
77 |
"epoch": 0.88,
|
78 |
-
"learning_rate": 4.
|
79 |
-
"loss":
|
80 |
"step": 60
|
81 |
},
|
82 |
{
|
83 |
"epoch": 0.96,
|
84 |
-
"learning_rate": 6.
|
85 |
-
"loss":
|
86 |
"step": 65
|
87 |
},
|
88 |
{
|
89 |
"epoch": 1.0,
|
90 |
-
"eval_loss":
|
91 |
-
"eval_runtime":
|
92 |
-
"eval_samples_per_second":
|
93 |
-
"eval_steps_per_second":
|
94 |
"step": 68
|
95 |
-
},
|
96 |
-
{
|
97 |
-
"epoch": 1.03,
|
98 |
-
"learning_rate": 2.926355061606279e-07,
|
99 |
-
"loss": 2.8201,
|
100 |
-
"step": 70
|
101 |
-
},
|
102 |
-
{
|
103 |
-
"epoch": 1.1,
|
104 |
-
"learning_rate": 3.55617957525975e-06,
|
105 |
-
"loss": 2.7876,
|
106 |
-
"step": 75
|
107 |
-
},
|
108 |
-
{
|
109 |
-
"epoch": 1.18,
|
110 |
-
"learning_rate": 1.0275104488948473e-05,
|
111 |
-
"loss": 2.8738,
|
112 |
-
"step": 80
|
113 |
-
},
|
114 |
-
{
|
115 |
-
"epoch": 1.25,
|
116 |
-
"learning_rate": 2.009247481060283e-05,
|
117 |
-
"loss": 2.6439,
|
118 |
-
"step": 85
|
119 |
-
},
|
120 |
-
{
|
121 |
-
"epoch": 1.32,
|
122 |
-
"learning_rate": 3.2486753626613365e-05,
|
123 |
-
"loss": 2.5993,
|
124 |
-
"step": 90
|
125 |
-
},
|
126 |
-
{
|
127 |
-
"epoch": 1.4,
|
128 |
-
"learning_rate": 4.679950861668151e-05,
|
129 |
-
"loss": 2.7072,
|
130 |
-
"step": 95
|
131 |
-
},
|
132 |
-
{
|
133 |
-
"epoch": 1.47,
|
134 |
-
"learning_rate": 6.227039054081748e-05,
|
135 |
-
"loss": 2.7465,
|
136 |
-
"step": 100
|
137 |
-
},
|
138 |
-
{
|
139 |
-
"epoch": 1.54,
|
140 |
-
"learning_rate": 7.807752594969911e-05,
|
141 |
-
"loss": 2.5926,
|
142 |
-
"step": 105
|
143 |
-
},
|
144 |
-
{
|
145 |
-
"epoch": 1.62,
|
146 |
-
"learning_rate": 9.338117830043867e-05,
|
147 |
-
"loss": 2.7178,
|
148 |
-
"step": 110
|
149 |
-
},
|
150 |
-
{
|
151 |
-
"epoch": 1.69,
|
152 |
-
"learning_rate": 0.00010736835802938978,
|
153 |
-
"loss": 2.7027,
|
154 |
-
"step": 115
|
155 |
-
},
|
156 |
-
{
|
157 |
-
"epoch": 1.76,
|
158 |
-
"learning_rate": 0.00011929601172133719,
|
159 |
-
"loss": 2.4457,
|
160 |
-
"step": 120
|
161 |
-
},
|
162 |
-
{
|
163 |
-
"epoch": 1.84,
|
164 |
-
"learning_rate": 0.00012853049599834097,
|
165 |
-
"loss": 2.6806,
|
166 |
-
"step": 125
|
167 |
-
},
|
168 |
-
{
|
169 |
-
"epoch": 1.91,
|
170 |
-
"learning_rate": 0.00013458123912165538,
|
171 |
-
"loss": 2.4508,
|
172 |
-
"step": 130
|
173 |
-
},
|
174 |
-
{
|
175 |
-
"epoch": 1.99,
|
176 |
-
"learning_rate": 0.00013712680207144277,
|
177 |
-
"loss": 2.6492,
|
178 |
-
"step": 135
|
179 |
-
},
|
180 |
-
{
|
181 |
-
"epoch": 2.0,
|
182 |
-
"eval_loss": 2.3717236518859863,
|
183 |
-
"eval_runtime": 4.3106,
|
184 |
-
"eval_samples_per_second": 22.039,
|
185 |
-
"eval_steps_per_second": 2.784,
|
186 |
-
"step": 136
|
187 |
-
},
|
188 |
-
{
|
189 |
-
"epoch": 2.0,
|
190 |
-
"eval_loss": 2.222139835357666,
|
191 |
-
"eval_runtime": 3.7161,
|
192 |
-
"eval_samples_per_second": 23.412,
|
193 |
-
"eval_steps_per_second": 2.96,
|
194 |
-
"step": 138
|
195 |
-
},
|
196 |
-
{
|
197 |
-
"epoch": 2.03,
|
198 |
-
"learning_rate": 0.00013691577939766304,
|
199 |
-
"loss": 2.3223,
|
200 |
-
"step": 140
|
201 |
-
},
|
202 |
-
{
|
203 |
-
"epoch": 2.1,
|
204 |
-
"learning_rate": 0.00013374528334456193,
|
205 |
-
"loss": 2.4227,
|
206 |
-
"step": 145
|
207 |
-
},
|
208 |
-
{
|
209 |
-
"epoch": 2.17,
|
210 |
-
"learning_rate": 0.00012721317115188912,
|
211 |
-
"loss": 2.3956,
|
212 |
-
"step": 150
|
213 |
-
},
|
214 |
-
{
|
215 |
-
"epoch": 2.25,
|
216 |
-
"learning_rate": 0.00011765651179294606,
|
217 |
-
"loss": 2.3273,
|
218 |
-
"step": 155
|
219 |
-
},
|
220 |
-
{
|
221 |
-
"epoch": 2.32,
|
222 |
-
"learning_rate": 0.0001055684464238085,
|
223 |
-
"loss": 2.4048,
|
224 |
-
"step": 160
|
225 |
-
},
|
226 |
-
{
|
227 |
-
"epoch": 2.39,
|
228 |
-
"learning_rate": 9.157274139492967e-05,
|
229 |
-
"loss": 2.4168,
|
230 |
-
"step": 165
|
231 |
-
},
|
232 |
-
{
|
233 |
-
"epoch": 2.46,
|
234 |
-
"learning_rate": 7.639160076306266e-05,
|
235 |
-
"loss": 2.4496,
|
236 |
-
"step": 170
|
237 |
-
},
|
238 |
-
{
|
239 |
-
"epoch": 2.54,
|
240 |
-
"learning_rate": 6.0808399236937385e-05,
|
241 |
-
"loss": 2.0669,
|
242 |
-
"step": 175
|
243 |
-
},
|
244 |
-
{
|
245 |
-
"epoch": 2.61,
|
246 |
-
"learning_rate": 4.5627258605070364e-05,
|
247 |
-
"loss": 2.2692,
|
248 |
-
"step": 180
|
249 |
-
},
|
250 |
-
{
|
251 |
-
"epoch": 2.68,
|
252 |
-
"learning_rate": 3.1631553576191535e-05,
|
253 |
-
"loss": 2.1242,
|
254 |
-
"step": 185
|
255 |
-
},
|
256 |
-
{
|
257 |
-
"epoch": 2.75,
|
258 |
-
"learning_rate": 1.954348820705391e-05,
|
259 |
-
"loss": 2.3064,
|
260 |
-
"step": 190
|
261 |
-
},
|
262 |
-
{
|
263 |
-
"epoch": 2.83,
|
264 |
-
"learning_rate": 9.986828848110892e-06,
|
265 |
-
"loss": 2.146,
|
266 |
-
"step": 195
|
267 |
-
},
|
268 |
-
{
|
269 |
-
"epoch": 2.9,
|
270 |
-
"learning_rate": 3.454716655438096e-06,
|
271 |
-
"loss": 2.3787,
|
272 |
-
"step": 200
|
273 |
-
},
|
274 |
-
{
|
275 |
-
"epoch": 2.97,
|
276 |
-
"learning_rate": 2.8422060233695394e-07,
|
277 |
-
"loss": 2.2533,
|
278 |
-
"step": 205
|
279 |
-
},
|
280 |
-
{
|
281 |
-
"epoch": 3.0,
|
282 |
-
"eval_loss": 2.043508768081665,
|
283 |
-
"eval_runtime": 3.8679,
|
284 |
-
"eval_samples_per_second": 22.493,
|
285 |
-
"eval_steps_per_second": 2.844,
|
286 |
-
"step": 207
|
287 |
-
},
|
288 |
-
{
|
289 |
-
"epoch": 3.04,
|
290 |
-
"learning_rate": 6.389441019077102e-07,
|
291 |
-
"loss": 2.1995,
|
292 |
-
"step": 210
|
293 |
-
},
|
294 |
-
{
|
295 |
-
"epoch": 3.12,
|
296 |
-
"learning_rate": 4.500582770777967e-06,
|
297 |
-
"loss": 2.2239,
|
298 |
-
"step": 215
|
299 |
-
},
|
300 |
-
{
|
301 |
-
"epoch": 3.19,
|
302 |
-
"learning_rate": 1.166986896886688e-05,
|
303 |
-
"loss": 2.1124,
|
304 |
-
"step": 220
|
305 |
-
},
|
306 |
-
{
|
307 |
-
"epoch": 3.26,
|
308 |
-
"learning_rate": 2.177685437520025e-05,
|
309 |
-
"loss": 2.2442,
|
310 |
-
"step": 225
|
311 |
-
},
|
312 |
-
{
|
313 |
-
"epoch": 3.33,
|
314 |
-
"learning_rate": 3.4300000000000014e-05,
|
315 |
-
"loss": 2.0765,
|
316 |
-
"step": 230
|
317 |
-
},
|
318 |
-
{
|
319 |
-
"epoch": 3.41,
|
320 |
-
"learning_rate": 4.859308855339902e-05,
|
321 |
-
"loss": 2.042,
|
322 |
-
"step": 235
|
323 |
-
},
|
324 |
-
{
|
325 |
-
"epoch": 3.48,
|
326 |
-
"learning_rate": 6.391857044318346e-05,
|
327 |
-
"loss": 2.0462,
|
328 |
-
"step": 240
|
329 |
-
},
|
330 |
-
{
|
331 |
-
"epoch": 3.55,
|
332 |
-
"learning_rate": 7.948562268689874e-05,
|
333 |
-
"loss": 1.9776,
|
334 |
-
"step": 245
|
335 |
-
},
|
336 |
-
{
|
337 |
-
"epoch": 3.62,
|
338 |
-
"learning_rate": 9.449095682862937e-05,
|
339 |
-
"loss": 2.1824,
|
340 |
-
"step": 250
|
341 |
-
},
|
342 |
-
{
|
343 |
-
"epoch": 3.7,
|
344 |
-
"learning_rate": 0.0001081602700970798,
|
345 |
-
"loss": 1.996,
|
346 |
-
"step": 255
|
347 |
-
},
|
348 |
-
{
|
349 |
-
"epoch": 3.77,
|
350 |
-
"learning_rate": 0.00011978820084915117,
|
351 |
-
"loss": 2.1329,
|
352 |
-
"step": 260
|
353 |
-
},
|
354 |
-
{
|
355 |
-
"epoch": 3.84,
|
356 |
-
"learning_rate": 0.00012877472652481797,
|
357 |
-
"loss": 2.1854,
|
358 |
-
"step": 265
|
359 |
-
},
|
360 |
-
{
|
361 |
-
"epoch": 3.91,
|
362 |
-
"learning_rate": 0.00013465612591205902,
|
363 |
-
"loss": 1.8201,
|
364 |
-
"step": 270
|
365 |
-
},
|
366 |
-
{
|
367 |
-
"epoch": 3.99,
|
368 |
-
"learning_rate": 0.00013712890801216552,
|
369 |
-
"loss": 1.8969,
|
370 |
-
"step": 275
|
371 |
-
},
|
372 |
-
{
|
373 |
-
"epoch": 4.0,
|
374 |
-
"eval_loss": 1.9531660079956055,
|
375 |
-
"eval_runtime": 3.8382,
|
376 |
-
"eval_samples_per_second": 22.667,
|
377 |
-
"eval_steps_per_second": 2.866,
|
378 |
-
"step": 276
|
379 |
-
},
|
380 |
-
{
|
381 |
-
"epoch": 4.06,
|
382 |
-
"learning_rate": 0.0001360654727320747,
|
383 |
-
"loss": 1.817,
|
384 |
-
"step": 280
|
385 |
-
},
|
386 |
-
{
|
387 |
-
"epoch": 4.13,
|
388 |
-
"learning_rate": 0.0001315206952832741,
|
389 |
-
"loss": 1.6319,
|
390 |
-
"step": 285
|
391 |
-
},
|
392 |
-
{
|
393 |
-
"epoch": 4.2,
|
394 |
-
"learning_rate": 0.00012372909452021153,
|
395 |
-
"loss": 1.7738,
|
396 |
-
"step": 290
|
397 |
-
},
|
398 |
-
{
|
399 |
-
"epoch": 4.28,
|
400 |
-
"learning_rate": 0.00011309273133714503,
|
401 |
-
"loss": 1.7757,
|
402 |
-
"step": 295
|
403 |
-
},
|
404 |
-
{
|
405 |
-
"epoch": 4.35,
|
406 |
-
"learning_rate": 0.0001001604615883571,
|
407 |
-
"loss": 1.9699,
|
408 |
-
"step": 300
|
409 |
-
},
|
410 |
-
{
|
411 |
-
"epoch": 4.42,
|
412 |
-
"learning_rate": 8.5599614119113e-05,
|
413 |
-
"loss": 1.9681,
|
414 |
-
"step": 305
|
415 |
-
},
|
416 |
-
{
|
417 |
-
"epoch": 4.49,
|
418 |
-
"learning_rate": 7.016155537292879e-05,
|
419 |
-
"loss": 1.9245,
|
420 |
-
"step": 310
|
421 |
-
},
|
422 |
-
{
|
423 |
-
"epoch": 4.57,
|
424 |
-
"learning_rate": 5.464291750458938e-05,
|
425 |
-
"loss": 1.7497,
|
426 |
-
"step": 315
|
427 |
-
},
|
428 |
-
{
|
429 |
-
"epoch": 4.64,
|
430 |
-
"learning_rate": 3.98444906994169e-05,
|
431 |
-
"loss": 1.7975,
|
432 |
-
"step": 320
|
433 |
-
},
|
434 |
-
{
|
435 |
-
"epoch": 4.71,
|
436 |
-
"learning_rate": 2.6529900930537204e-05,
|
437 |
-
"loss": 1.6675,
|
438 |
-
"step": 325
|
439 |
-
},
|
440 |
-
{
|
441 |
-
"epoch": 4.78,
|
442 |
-
"learning_rate": 1.5386205457676833e-05,
|
443 |
-
"loss": 1.9876,
|
444 |
-
"step": 330
|
445 |
-
},
|
446 |
-
{
|
447 |
-
"epoch": 4.86,
|
448 |
-
"learning_rate": 6.988439412050469e-06,
|
449 |
-
"loss": 1.691,
|
450 |
-
"step": 335
|
451 |
-
},
|
452 |
-
{
|
453 |
-
"epoch": 4.93,
|
454 |
-
"learning_rate": 1.7699429285993718e-06,
|
455 |
-
"loss": 1.8689,
|
456 |
-
"step": 340
|
457 |
-
},
|
458 |
-
{
|
459 |
-
"epoch": 5.0,
|
460 |
-
"learning_rate": 0.0,
|
461 |
-
"loss": 1.9327,
|
462 |
-
"step": 345
|
463 |
-
},
|
464 |
-
{
|
465 |
-
"epoch": 5.0,
|
466 |
-
"eval_loss": 1.8510653972625732,
|
467 |
-
"eval_runtime": 3.8275,
|
468 |
-
"eval_samples_per_second": 22.73,
|
469 |
-
"eval_steps_per_second": 2.874,
|
470 |
-
"step": 345
|
471 |
-
},
|
472 |
-
{
|
473 |
-
"epoch": 5.07,
|
474 |
-
"learning_rate": 1.7699429285993566e-06,
|
475 |
-
"loss": 1.5991,
|
476 |
-
"step": 350
|
477 |
-
},
|
478 |
-
{
|
479 |
-
"epoch": 5.14,
|
480 |
-
"learning_rate": 6.988439412050431e-06,
|
481 |
-
"loss": 1.6155,
|
482 |
-
"step": 355
|
483 |
-
},
|
484 |
-
{
|
485 |
-
"epoch": 5.22,
|
486 |
-
"learning_rate": 1.538620545767678e-05,
|
487 |
-
"loss": 1.6707,
|
488 |
-
"step": 360
|
489 |
-
},
|
490 |
-
{
|
491 |
-
"epoch": 5.29,
|
492 |
-
"learning_rate": 2.6529900930537035e-05,
|
493 |
-
"loss": 1.7262,
|
494 |
-
"step": 365
|
495 |
-
},
|
496 |
-
{
|
497 |
-
"epoch": 5.36,
|
498 |
-
"learning_rate": 3.984449069941682e-05,
|
499 |
-
"loss": 1.7087,
|
500 |
-
"step": 370
|
501 |
-
},
|
502 |
-
{
|
503 |
-
"epoch": 5.43,
|
504 |
-
"learning_rate": 5.4642917504589295e-05,
|
505 |
-
"loss": 1.7766,
|
506 |
-
"step": 375
|
507 |
-
},
|
508 |
-
{
|
509 |
-
"epoch": 5.51,
|
510 |
-
"learning_rate": 7.016155537292883e-05,
|
511 |
-
"loss": 1.5992,
|
512 |
-
"step": 380
|
513 |
-
},
|
514 |
-
{
|
515 |
-
"epoch": 5.58,
|
516 |
-
"learning_rate": 8.559961411911291e-05,
|
517 |
-
"loss": 1.6561,
|
518 |
-
"step": 385
|
519 |
-
},
|
520 |
-
{
|
521 |
-
"epoch": 5.65,
|
522 |
-
"learning_rate": 0.00010016046158835702,
|
523 |
-
"loss": 1.6108,
|
524 |
-
"step": 390
|
525 |
-
},
|
526 |
-
{
|
527 |
-
"epoch": 5.72,
|
528 |
-
"learning_rate": 0.00011309273133714504,
|
529 |
-
"loss": 1.6236,
|
530 |
-
"step": 395
|
531 |
-
},
|
532 |
-
{
|
533 |
-
"epoch": 5.8,
|
534 |
-
"learning_rate": 0.0001237290945202115,
|
535 |
-
"loss": 1.6319,
|
536 |
-
"step": 400
|
537 |
-
},
|
538 |
-
{
|
539 |
-
"epoch": 5.87,
|
540 |
-
"learning_rate": 0.00013152069528327408,
|
541 |
-
"loss": 1.4268,
|
542 |
-
"step": 405
|
543 |
-
},
|
544 |
-
{
|
545 |
-
"epoch": 5.94,
|
546 |
-
"learning_rate": 0.00013606547273207472,
|
547 |
-
"loss": 1.7278,
|
548 |
-
"step": 410
|
549 |
-
},
|
550 |
-
{
|
551 |
-
"epoch": 6.0,
|
552 |
-
"eval_loss": 1.8254233598709106,
|
553 |
-
"eval_runtime": 3.854,
|
554 |
-
"eval_samples_per_second": 22.574,
|
555 |
-
"eval_steps_per_second": 2.854,
|
556 |
-
"step": 414
|
557 |
-
},
|
558 |
-
{
|
559 |
-
"epoch": 6.01,
|
560 |
-
"learning_rate": 0.00013712890801216552,
|
561 |
-
"loss": 1.8762,
|
562 |
-
"step": 415
|
563 |
-
},
|
564 |
-
{
|
565 |
-
"epoch": 6.09,
|
566 |
-
"learning_rate": 0.00013465612591205902,
|
567 |
-
"loss": 1.4495,
|
568 |
-
"step": 420
|
569 |
-
},
|
570 |
-
{
|
571 |
-
"epoch": 6.16,
|
572 |
-
"learning_rate": 0.00012877472652481797,
|
573 |
-
"loss": 1.5224,
|
574 |
-
"step": 425
|
575 |
-
},
|
576 |
-
{
|
577 |
-
"epoch": 6.23,
|
578 |
-
"learning_rate": 0.00011978820084915123,
|
579 |
-
"loss": 1.5038,
|
580 |
-
"step": 430
|
581 |
-
},
|
582 |
-
{
|
583 |
-
"epoch": 6.3,
|
584 |
-
"learning_rate": 0.00010816027009708009,
|
585 |
-
"loss": 1.4097,
|
586 |
-
"step": 435
|
587 |
-
},
|
588 |
-
{
|
589 |
-
"epoch": 6.38,
|
590 |
-
"learning_rate": 9.449095682862935e-05,
|
591 |
-
"loss": 1.3203,
|
592 |
-
"step": 440
|
593 |
-
},
|
594 |
-
{
|
595 |
-
"epoch": 6.45,
|
596 |
-
"learning_rate": 7.948562268689883e-05,
|
597 |
-
"loss": 1.3634,
|
598 |
-
"step": 445
|
599 |
-
},
|
600 |
-
{
|
601 |
-
"epoch": 6.52,
|
602 |
-
"learning_rate": 6.39185704431838e-05,
|
603 |
-
"loss": 1.4181,
|
604 |
-
"step": 450
|
605 |
-
},
|
606 |
-
{
|
607 |
-
"epoch": 6.59,
|
608 |
-
"learning_rate": 4.859308855339899e-05,
|
609 |
-
"loss": 1.5025,
|
610 |
-
"step": 455
|
611 |
-
},
|
612 |
-
{
|
613 |
-
"epoch": 6.67,
|
614 |
-
"learning_rate": 3.429999999999998e-05,
|
615 |
-
"loss": 1.5881,
|
616 |
-
"step": 460
|
617 |
-
},
|
618 |
-
{
|
619 |
-
"epoch": 6.74,
|
620 |
-
"learning_rate": 2.1776854375200487e-05,
|
621 |
-
"loss": 1.5042,
|
622 |
-
"step": 465
|
623 |
-
},
|
624 |
-
{
|
625 |
-
"epoch": 6.81,
|
626 |
-
"learning_rate": 1.1669868968866859e-05,
|
627 |
-
"loss": 1.4229,
|
628 |
-
"step": 470
|
629 |
-
},
|
630 |
-
{
|
631 |
-
"epoch": 6.88,
|
632 |
-
"learning_rate": 4.500582770777952e-06,
|
633 |
-
"loss": 1.5551,
|
634 |
-
"step": 475
|
635 |
-
},
|
636 |
-
{
|
637 |
-
"epoch": 6.96,
|
638 |
-
"learning_rate": 6.389441019077407e-07,
|
639 |
-
"loss": 1.6253,
|
640 |
-
"step": 480
|
641 |
-
},
|
642 |
-
{
|
643 |
-
"epoch": 7.0,
|
644 |
-
"eval_loss": 1.787222146987915,
|
645 |
-
"eval_runtime": 3.8357,
|
646 |
-
"eval_samples_per_second": 22.681,
|
647 |
-
"eval_steps_per_second": 2.868,
|
648 |
-
"step": 483
|
649 |
-
},
|
650 |
-
{
|
651 |
-
"epoch": 7.03,
|
652 |
-
"learning_rate": 2.8422060233696156e-07,
|
653 |
-
"loss": 1.5683,
|
654 |
-
"step": 485
|
655 |
-
},
|
656 |
-
{
|
657 |
-
"epoch": 7.1,
|
658 |
-
"learning_rate": 3.4547166554380356e-06,
|
659 |
-
"loss": 1.1749,
|
660 |
-
"step": 490
|
661 |
-
},
|
662 |
-
{
|
663 |
-
"epoch": 7.17,
|
664 |
-
"learning_rate": 9.986828848110785e-06,
|
665 |
-
"loss": 1.2655,
|
666 |
-
"step": 495
|
667 |
-
},
|
668 |
-
{
|
669 |
-
"epoch": 7.25,
|
670 |
-
"learning_rate": 1.9543488207053935e-05,
|
671 |
-
"loss": 1.3456,
|
672 |
-
"step": 500
|
673 |
-
},
|
674 |
-
{
|
675 |
-
"epoch": 7.32,
|
676 |
-
"learning_rate": 3.163155357619136e-05,
|
677 |
-
"loss": 1.2074,
|
678 |
-
"step": 505
|
679 |
-
},
|
680 |
-
{
|
681 |
-
"epoch": 7.39,
|
682 |
-
"learning_rate": 4.5627258605070174e-05,
|
683 |
-
"loss": 1.3068,
|
684 |
-
"step": 510
|
685 |
-
},
|
686 |
-
{
|
687 |
-
"epoch": 7.46,
|
688 |
-
"learning_rate": 6.080839923693748e-05,
|
689 |
-
"loss": 1.1119,
|
690 |
-
"step": 515
|
691 |
-
},
|
692 |
-
{
|
693 |
-
"epoch": 7.54,
|
694 |
-
"learning_rate": 7.639160076306239e-05,
|
695 |
-
"loss": 1.3026,
|
696 |
-
"step": 520
|
697 |
-
},
|
698 |
-
{
|
699 |
-
"epoch": 7.61,
|
700 |
-
"learning_rate": 9.15727413949297e-05,
|
701 |
-
"loss": 1.4164,
|
702 |
-
"step": 525
|
703 |
-
},
|
704 |
-
{
|
705 |
-
"epoch": 7.68,
|
706 |
-
"learning_rate": 0.00010556844642380854,
|
707 |
-
"loss": 1.6188,
|
708 |
-
"step": 530
|
709 |
-
},
|
710 |
-
{
|
711 |
-
"epoch": 7.75,
|
712 |
-
"learning_rate": 0.00011765651179294598,
|
713 |
-
"loss": 1.438,
|
714 |
-
"step": 535
|
715 |
-
},
|
716 |
-
{
|
717 |
-
"epoch": 7.83,
|
718 |
-
"learning_rate": 0.00012721317115188917,
|
719 |
-
"loss": 1.267,
|
720 |
-
"step": 540
|
721 |
-
},
|
722 |
-
{
|
723 |
-
"epoch": 7.9,
|
724 |
-
"learning_rate": 0.00013374528334456193,
|
725 |
-
"loss": 1.2976,
|
726 |
-
"step": 545
|
727 |
-
},
|
728 |
-
{
|
729 |
-
"epoch": 7.97,
|
730 |
-
"learning_rate": 0.00013691577939766304,
|
731 |
-
"loss": 1.4411,
|
732 |
-
"step": 550
|
733 |
-
},
|
734 |
-
{
|
735 |
-
"epoch": 8.0,
|
736 |
-
"eval_loss": 1.795061707496643,
|
737 |
-
"eval_runtime": 3.8467,
|
738 |
-
"eval_samples_per_second": 22.617,
|
739 |
-
"eval_steps_per_second": 2.86,
|
740 |
-
"step": 552
|
741 |
-
},
|
742 |
-
{
|
743 |
-
"epoch": 8.04,
|
744 |
-
"learning_rate": 0.0001365610558980923,
|
745 |
-
"loss": 1.266,
|
746 |
-
"step": 555
|
747 |
-
},
|
748 |
-
{
|
749 |
-
"epoch": 8.12,
|
750 |
-
"learning_rate": 0.000132699417229222,
|
751 |
-
"loss": 1.2792,
|
752 |
-
"step": 560
|
753 |
-
},
|
754 |
-
{
|
755 |
-
"epoch": 8.19,
|
756 |
-
"learning_rate": 0.0001255301310311332,
|
757 |
-
"loss": 1.2561,
|
758 |
-
"step": 565
|
759 |
-
},
|
760 |
-
{
|
761 |
-
"epoch": 8.26,
|
762 |
-
"learning_rate": 0.00011542314562479977,
|
763 |
-
"loss": 1.2462,
|
764 |
-
"step": 570
|
765 |
-
},
|
766 |
-
{
|
767 |
-
"epoch": 8.33,
|
768 |
-
"learning_rate": 0.00010289999999999993,
|
769 |
-
"loss": 1.2013,
|
770 |
-
"step": 575
|
771 |
-
},
|
772 |
-
{
|
773 |
-
"epoch": 8.41,
|
774 |
-
"learning_rate": 8.860691144660113e-05,
|
775 |
-
"loss": 1.2052,
|
776 |
-
"step": 580
|
777 |
-
},
|
778 |
-
{
|
779 |
-
"epoch": 8.48,
|
780 |
-
"learning_rate": 7.328142955681657e-05,
|
781 |
-
"loss": 1.3885,
|
782 |
-
"step": 585
|
783 |
-
},
|
784 |
-
{
|
785 |
-
"epoch": 8.55,
|
786 |
-
"learning_rate": 5.771437731310106e-05,
|
787 |
-
"loss": 1.0822,
|
788 |
-
"step": 590
|
789 |
-
},
|
790 |
-
{
|
791 |
-
"epoch": 8.62,
|
792 |
-
"learning_rate": 4.270904317137078e-05,
|
793 |
-
"loss": 1.3064,
|
794 |
-
"step": 595
|
795 |
-
},
|
796 |
-
{
|
797 |
-
"epoch": 8.7,
|
798 |
-
"learning_rate": 2.9039729902920224e-05,
|
799 |
-
"loss": 1.2009,
|
800 |
-
"step": 600
|
801 |
-
},
|
802 |
-
{
|
803 |
-
"epoch": 8.77,
|
804 |
-
"learning_rate": 1.7411799150848703e-05,
|
805 |
-
"loss": 1.2057,
|
806 |
-
"step": 605
|
807 |
-
},
|
808 |
-
{
|
809 |
-
"epoch": 8.84,
|
810 |
-
"learning_rate": 8.425273475182102e-06,
|
811 |
-
"loss": 1.1498,
|
812 |
-
"step": 610
|
813 |
-
},
|
814 |
-
{
|
815 |
-
"epoch": 8.91,
|
816 |
-
"learning_rate": 2.5438740879410024e-06,
|
817 |
-
"loss": 1.0197,
|
818 |
-
"step": 615
|
819 |
-
},
|
820 |
-
{
|
821 |
-
"epoch": 8.99,
|
822 |
-
"learning_rate": 7.109198783448199e-08,
|
823 |
-
"loss": 1.1622,
|
824 |
-
"step": 620
|
825 |
-
},
|
826 |
-
{
|
827 |
-
"epoch": 9.0,
|
828 |
-
"eval_loss": 1.775342345237732,
|
829 |
-
"eval_runtime": 3.8327,
|
830 |
-
"eval_samples_per_second": 22.699,
|
831 |
-
"eval_steps_per_second": 2.87,
|
832 |
-
"step": 621
|
833 |
-
},
|
834 |
-
{
|
835 |
-
"epoch": 9.19,
|
836 |
-
"learning_rate": 1.2005173242556402e-05,
|
837 |
-
"loss": 1.3691,
|
838 |
-
"step": 625
|
839 |
-
},
|
840 |
-
{
|
841 |
-
"epoch": 9.26,
|
842 |
-
"learning_rate": 2.2384478845846314e-05,
|
843 |
-
"loss": 1.5005,
|
844 |
-
"step": 630
|
845 |
-
},
|
846 |
-
{
|
847 |
-
"epoch": 9.34,
|
848 |
-
"learning_rate": 3.5218932770313436e-05,
|
849 |
-
"loss": 1.4065,
|
850 |
-
"step": 635
|
851 |
-
},
|
852 |
-
{
|
853 |
-
"epoch": 9.41,
|
854 |
-
"learning_rate": 4.982671888105515e-05,
|
855 |
-
"loss": 1.3225,
|
856 |
-
"step": 640
|
857 |
-
},
|
858 |
-
{
|
859 |
-
"epoch": 9.49,
|
860 |
-
"learning_rate": 6.543181473690211e-05,
|
861 |
-
"loss": 1.0367,
|
862 |
-
"step": 645
|
863 |
-
},
|
864 |
-
{
|
865 |
-
"epoch": 9.56,
|
866 |
-
"learning_rate": 8.120521692221662e-05,
|
867 |
-
"loss": 1.1784,
|
868 |
-
"step": 650
|
869 |
-
},
|
870 |
-
{
|
871 |
-
"epoch": 9.63,
|
872 |
-
"learning_rate": 9.630898093421192e-05,
|
873 |
-
"loss": 1.2778,
|
874 |
-
"step": 655
|
875 |
-
},
|
876 |
-
{
|
877 |
-
"epoch": 9.71,
|
878 |
-
"learning_rate": 0.00010994073605561679,
|
879 |
-
"loss": 1.3754,
|
880 |
-
"step": 660
|
881 |
-
},
|
882 |
-
{
|
883 |
-
"epoch": 9.78,
|
884 |
-
"learning_rate": 0.00012137631040942535,
|
885 |
-
"loss": 1.1983,
|
886 |
-
"step": 665
|
887 |
-
},
|
888 |
-
{
|
889 |
-
"epoch": 9.85,
|
890 |
-
"learning_rate": 0.00013000820178695732,
|
891 |
-
"loss": 1.3077,
|
892 |
-
"step": 670
|
893 |
-
},
|
894 |
-
{
|
895 |
-
"epoch": 9.93,
|
896 |
-
"learning_rate": 0.0001353778505291435,
|
897 |
-
"loss": 1.4969,
|
898 |
-
"step": 675
|
899 |
-
},
|
900 |
-
{
|
901 |
-
"epoch": 10.0,
|
902 |
-
"learning_rate": 0.0001372,
|
903 |
-
"loss": 1.3263,
|
904 |
-
"step": 680
|
905 |
-
},
|
906 |
-
{
|
907 |
-
"epoch": 10.0,
|
908 |
-
"eval_loss": 1.0593422651290894,
|
909 |
-
"eval_runtime": 1.2161,
|
910 |
-
"eval_samples_per_second": 75.649,
|
911 |
-
"eval_steps_per_second": 9.867,
|
912 |
-
"step": 680
|
913 |
-
},
|
914 |
-
{
|
915 |
-
"epoch": 9.93,
|
916 |
-
"learning_rate": 0.00013543005707140072,
|
917 |
-
"loss": 1.2301,
|
918 |
-
"step": 685
|
919 |
-
},
|
920 |
-
{
|
921 |
-
"epoch": 10.0,
|
922 |
-
"learning_rate": 0.0001372,
|
923 |
-
"loss": 1.2039,
|
924 |
-
"step": 690
|
925 |
-
},
|
926 |
-
{
|
927 |
-
"epoch": 10.0,
|
928 |
-
"eval_loss": 0.9929937720298767,
|
929 |
-
"eval_runtime": 1.7672,
|
930 |
-
"eval_samples_per_second": 48.098,
|
931 |
-
"eval_steps_per_second": 6.224,
|
932 |
-
"step": 690
|
933 |
-
},
|
934 |
-
{
|
935 |
-
"epoch": 10.07,
|
936 |
-
"learning_rate": 0.00013543005707140074,
|
937 |
-
"loss": 1.1894,
|
938 |
-
"step": 695
|
939 |
-
},
|
940 |
-
{
|
941 |
-
"epoch": 10.14,
|
942 |
-
"learning_rate": 0.0001302115605879495,
|
943 |
-
"loss": 1.2106,
|
944 |
-
"step": 700
|
945 |
-
},
|
946 |
-
{
|
947 |
-
"epoch": 10.22,
|
948 |
-
"learning_rate": 0.00012181379454232323,
|
949 |
-
"loss": 1.144,
|
950 |
-
"step": 705
|
951 |
-
},
|
952 |
-
{
|
953 |
-
"epoch": 10.29,
|
954 |
-
"learning_rate": 0.00011067009906946301,
|
955 |
-
"loss": 1.3006,
|
956 |
-
"step": 710
|
957 |
-
},
|
958 |
-
{
|
959 |
-
"epoch": 10.36,
|
960 |
-
"learning_rate": 9.735550930058323e-05,
|
961 |
-
"loss": 1.2147,
|
962 |
-
"step": 715
|
963 |
-
},
|
964 |
-
{
|
965 |
-
"epoch": 10.43,
|
966 |
-
"learning_rate": 8.255708249541075e-05,
|
967 |
-
"loss": 1.1931,
|
968 |
-
"step": 720
|
969 |
-
},
|
970 |
-
{
|
971 |
-
"epoch": 10.51,
|
972 |
-
"learning_rate": 6.703844462707122e-05,
|
973 |
-
"loss": 1.2735,
|
974 |
-
"step": 725
|
975 |
-
},
|
976 |
-
{
|
977 |
-
"epoch": 10.58,
|
978 |
-
"learning_rate": 5.160038588088712e-05,
|
979 |
-
"loss": 1.1695,
|
980 |
-
"step": 730
|
981 |
-
},
|
982 |
-
{
|
983 |
-
"epoch": 10.65,
|
984 |
-
"learning_rate": 3.703953841164302e-05,
|
985 |
-
"loss": 1.2219,
|
986 |
-
"step": 735
|
987 |
-
},
|
988 |
-
{
|
989 |
-
"epoch": 10.72,
|
990 |
-
"learning_rate": 2.4107268662854985e-05,
|
991 |
-
"loss": 1.1271,
|
992 |
-
"step": 740
|
993 |
-
},
|
994 |
-
{
|
995 |
-
"epoch": 10.8,
|
996 |
-
"learning_rate": 1.3470905479788523e-05,
|
997 |
-
"loss": 1.2963,
|
998 |
-
"step": 745
|
999 |
-
},
|
1000 |
-
{
|
1001 |
-
"epoch": 10.87,
|
1002 |
-
"learning_rate": 5.679304716725944e-06,
|
1003 |
-
"loss": 1.0029,
|
1004 |
-
"step": 750
|
1005 |
-
},
|
1006 |
-
{
|
1007 |
-
"epoch": 10.94,
|
1008 |
-
"learning_rate": 1.1345272679252971e-06,
|
1009 |
-
"loss": 1.2789,
|
1010 |
-
"step": 755
|
1011 |
-
},
|
1012 |
-
{
|
1013 |
-
"epoch": 11.0,
|
1014 |
-
"eval_loss": 0.9721857309341431,
|
1015 |
-
"eval_runtime": 1.8495,
|
1016 |
-
"eval_samples_per_second": 45.957,
|
1017 |
-
"eval_steps_per_second": 5.947,
|
1018 |
-
"step": 759
|
1019 |
}
|
1020 |
],
|
1021 |
-
"max_steps":
|
1022 |
-
"num_train_epochs":
|
1023 |
-
"total_flos":
|
1024 |
"trial_name": null,
|
1025 |
"trial_params": null
|
1026 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9767317771911621,
|
3 |
+
"best_model_checkpoint": "output/queen/checkpoint-68",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 68,
|
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": 0.00013537785052914348,
|
13 |
+
"loss": 0.8946,
|
14 |
"step": 5
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.15,
|
18 |
"learning_rate": 0.0001300082017869573,
|
19 |
+
"loss": 1.1571,
|
20 |
"step": 10
|
21 |
},
|
22 |
{
|
23 |
"epoch": 0.22,
|
24 |
+
"learning_rate": 0.00012137631040942562,
|
25 |
+
"loss": 1.0891,
|
26 |
"step": 15
|
27 |
},
|
28 |
{
|
29 |
"epoch": 0.29,
|
30 |
+
"learning_rate": 0.00010994073605561692,
|
31 |
+
"loss": 1.0026,
|
32 |
"step": 20
|
33 |
},
|
34 |
{
|
35 |
"epoch": 0.37,
|
36 |
+
"learning_rate": 9.63089809342121e-05,
|
37 |
+
"loss": 0.8956,
|
38 |
"step": 25
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.44,
|
42 |
+
"learning_rate": 8.120521692221655e-05,
|
43 |
+
"loss": 1.0037,
|
44 |
"step": 30
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.51,
|
48 |
"learning_rate": 6.543181473690228e-05,
|
49 |
+
"loss": 0.9259,
|
50 |
"step": 35
|
51 |
},
|
52 |
{
|
53 |
"epoch": 0.59,
|
54 |
+
"learning_rate": 4.982671888105533e-05,
|
55 |
+
"loss": 0.9391,
|
56 |
"step": 40
|
57 |
},
|
58 |
{
|
59 |
"epoch": 0.66,
|
60 |
+
"learning_rate": 3.52189327703136e-05,
|
61 |
+
"loss": 0.897,
|
62 |
"step": 45
|
63 |
},
|
64 |
{
|
65 |
"epoch": 0.74,
|
66 |
+
"learning_rate": 2.2384478845846266e-05,
|
67 |
+
"loss": 0.969,
|
68 |
"step": 50
|
69 |
},
|
70 |
{
|
71 |
"epoch": 0.81,
|
72 |
+
"learning_rate": 1.2005173242556645e-05,
|
73 |
+
"loss": 0.9795,
|
74 |
"step": 55
|
75 |
},
|
76 |
{
|
77 |
"epoch": 0.88,
|
78 |
+
"learning_rate": 4.632405062861206e-06,
|
79 |
+
"loss": 1.0966,
|
80 |
"step": 60
|
81 |
},
|
82 |
{
|
83 |
"epoch": 0.96,
|
84 |
+
"learning_rate": 6.578444419609618e-07,
|
85 |
+
"loss": 0.9097,
|
86 |
"step": 65
|
87 |
},
|
88 |
{
|
89 |
"epoch": 1.0,
|
90 |
+
"eval_loss": 0.9767317771911621,
|
91 |
+
"eval_runtime": 2.0747,
|
92 |
+
"eval_samples_per_second": 46.272,
|
93 |
+
"eval_steps_per_second": 5.784,
|
94 |
"step": 68
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
95 |
}
|
96 |
],
|
97 |
+
"max_steps": 816,
|
98 |
+
"num_train_epochs": 12,
|
99 |
+
"total_flos": 70156910592000.0,
|
100 |
"trial_name": null,
|
101 |
"trial_params": null
|
102 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3311
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de2b73e108df809dd60f215a7871329eac5738c939f3a5b41fa7a79d90523567
|
3 |
size 3311
|