AlekseyKorshuk
commited on
Commit
•
e355cf0
1
Parent(s):
a5353af
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 +1191 -197
- training_args.bin +1 -1
README.md
CHANGED
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
45 |
dataset = load_dataset("huggingartists/egor-letov")
|
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 Егор Летов (Egor Letov)'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/egor-letov")
|
46 |
```
|
47 |
|
48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1omrcegx/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 Егор Летов (Egor Letov)'s lyrics.
|
53 |
|
54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3lk60u9h) for full transparency and reproducibility.
|
55 |
|
56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3lk60u9h/artifacts) is logged and versioned.
|
57 |
|
58 |
## How to use
|
59 |
|
evaluation.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"eval_loss": 1.
|
|
|
1 |
+
{"eval_loss": 1.4437962770462036, "eval_runtime": 5.737, "eval_samples_per_second": 42.008, "eval_steps_per_second": 5.404, "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:cd4287d13e5f03dddc3260cec0e0859042d58e9cbc920ca2aab49146c55a692d
|
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:fc7491d57edddd1344d39bab43ee9ee9d2e1bd19f9a6b5329c7a8b9e898023b3
|
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 510403817
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6b20d2ab52b7dcc03710f4a70f0baf6084d166e84c464d12a918de1aec2b876
|
3 |
size 510403817
|
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 sha256:1378376a42ff39fe4d328320073157ca77cc617aabb73778fdb86c5108bf91ca
|
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 sha256:5ea2789b1fe1320c872e3caeb49da788995e1cf09ec8ae9708f4b5a577f7ff68
|
3 |
size 623
|
trainer_state.json
CHANGED
@@ -1,410 +1,1404 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "output/egor-letov/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": 0.03,
|
12 |
-
"learning_rate": 0.
|
13 |
-
"loss":
|
14 |
"step": 5
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.06,
|
18 |
-
"learning_rate": 0.
|
19 |
-
"loss":
|
20 |
"step": 10
|
21 |
},
|
22 |
{
|
23 |
"epoch": 0.09,
|
24 |
-
"learning_rate": 0.
|
25 |
-
"loss":
|
26 |
"step": 15
|
27 |
},
|
28 |
{
|
29 |
-
"epoch": 0.
|
30 |
-
"learning_rate": 0.
|
31 |
-
"loss":
|
32 |
"step": 20
|
33 |
},
|
34 |
{
|
35 |
-
"epoch": 0.
|
36 |
-
"learning_rate": 0.
|
37 |
-
"loss":
|
38 |
"step": 25
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.19,
|
42 |
-
"learning_rate": 0.
|
43 |
-
"loss": 1.
|
44 |
"step": 30
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.22,
|
48 |
-
"learning_rate": 0.
|
49 |
-
"loss": 1.
|
50 |
"step": 35
|
51 |
},
|
52 |
{
|
53 |
"epoch": 0.25,
|
54 |
-
"learning_rate": 0.
|
55 |
-
"loss": 1.
|
56 |
"step": 40
|
57 |
},
|
58 |
{
|
59 |
"epoch": 0.28,
|
60 |
-
"learning_rate": 0.
|
61 |
-
"loss": 1.
|
62 |
"step": 45
|
63 |
},
|
64 |
{
|
65 |
"epoch": 0.31,
|
66 |
-
"learning_rate": 0.
|
67 |
-
"loss": 1.
|
68 |
"step": 50
|
69 |
},
|
70 |
{
|
71 |
-
"epoch": 0.
|
72 |
-
"learning_rate": 0.
|
73 |
-
"loss": 1.
|
74 |
"step": 55
|
75 |
},
|
76 |
{
|
77 |
-
"epoch": 0.
|
78 |
-
"learning_rate": 9.
|
79 |
-
"loss": 1.
|
80 |
"step": 60
|
81 |
},
|
82 |
{
|
83 |
-
"epoch": 0.
|
84 |
-
"learning_rate": 8.
|
85 |
-
"loss": 1.
|
86 |
"step": 65
|
87 |
},
|
88 |
{
|
89 |
-
"epoch": 0.
|
90 |
-
"learning_rate": 8.
|
91 |
-
"loss": 1.
|
92 |
"step": 70
|
93 |
},
|
94 |
{
|
95 |
-
"epoch": 0.
|
96 |
-
"learning_rate": 7.
|
97 |
-
"loss": 1.
|
98 |
"step": 75
|
99 |
},
|
100 |
{
|
101 |
-
"epoch": 0.
|
102 |
-
"learning_rate": 6.
|
103 |
-
"loss": 1.
|
104 |
"step": 80
|
105 |
},
|
106 |
{
|
107 |
-
"epoch": 0.
|
108 |
-
"learning_rate": 6.
|
109 |
-
"loss": 1.
|
110 |
"step": 85
|
111 |
},
|
112 |
{
|
113 |
-
"epoch": 0.
|
114 |
-
"learning_rate": 5.
|
115 |
-
"loss": 1.
|
116 |
"step": 90
|
117 |
},
|
118 |
{
|
119 |
-
"epoch": 0.
|
120 |
-
"learning_rate":
|
121 |
-
"loss": 1.
|
122 |
"step": 95
|
123 |
},
|
124 |
{
|
125 |
-
"epoch": 0.
|
126 |
-
"learning_rate": 4.
|
127 |
-
"loss": 1.
|
128 |
"step": 100
|
129 |
},
|
130 |
{
|
131 |
-
"epoch": 0.
|
132 |
-
"learning_rate": 3.
|
133 |
-
"loss": 1.
|
134 |
"step": 105
|
135 |
},
|
136 |
{
|
137 |
-
"epoch": 0.
|
138 |
-
"learning_rate":
|
139 |
-
"loss": 1.
|
140 |
"step": 110
|
141 |
},
|
142 |
{
|
143 |
-
"epoch": 0.
|
144 |
-
"learning_rate": 2.
|
145 |
-
"loss": 1.
|
146 |
"step": 115
|
147 |
},
|
148 |
{
|
149 |
-
"epoch": 0.
|
150 |
-
"learning_rate":
|
151 |
-
"loss": 1.
|
152 |
"step": 120
|
153 |
},
|
154 |
{
|
155 |
-
"epoch": 0.
|
156 |
-
"learning_rate": 1.
|
157 |
-
"loss": 1.
|
158 |
"step": 125
|
159 |
},
|
160 |
{
|
161 |
-
"epoch": 0.
|
162 |
-
"learning_rate": 1.
|
163 |
-
"loss": 1.
|
164 |
"step": 130
|
165 |
},
|
166 |
{
|
167 |
-
"epoch": 0.
|
168 |
-
"learning_rate":
|
169 |
-
"loss": 1.
|
170 |
"step": 135
|
171 |
},
|
172 |
{
|
173 |
-
"epoch": 0.
|
174 |
-
"learning_rate":
|
175 |
-
"loss": 1.
|
176 |
"step": 140
|
177 |
},
|
178 |
{
|
179 |
-
"epoch": 0.
|
180 |
-
"learning_rate":
|
181 |
-
"loss": 1.
|
182 |
"step": 145
|
183 |
},
|
184 |
{
|
185 |
-
"epoch": 0.
|
186 |
-
"learning_rate": 1.
|
187 |
-
"loss": 1.
|
188 |
"step": 150
|
189 |
},
|
190 |
{
|
191 |
-
"epoch": 0.
|
192 |
-
"learning_rate":
|
193 |
-
"loss": 1.
|
194 |
"step": 155
|
195 |
},
|
196 |
{
|
197 |
-
"epoch": 0
|
198 |
-
"
|
199 |
-
"
|
200 |
-
"
|
|
|
|
|
201 |
},
|
202 |
{
|
203 |
-
"epoch": 1.
|
204 |
-
"
|
205 |
-
"
|
206 |
-
"
|
207 |
-
"eval_steps_per_second": 2.872,
|
208 |
-
"step": 162
|
209 |
},
|
210 |
{
|
211 |
"epoch": 1.04,
|
212 |
-
"learning_rate":
|
213 |
-
"loss": 1.
|
214 |
"step": 165
|
215 |
},
|
216 |
{
|
217 |
-
"epoch": 1.
|
218 |
-
"learning_rate": 1.
|
219 |
-
"loss": 1.
|
220 |
"step": 170
|
221 |
},
|
222 |
{
|
223 |
-
"epoch": 1.
|
224 |
-
"learning_rate": 3.
|
225 |
-
"loss": 1.
|
226 |
"step": 175
|
227 |
},
|
228 |
{
|
229 |
-
"epoch": 1.
|
230 |
-
"learning_rate":
|
231 |
-
"loss": 1.
|
232 |
"step": 180
|
233 |
},
|
234 |
{
|
235 |
-
"epoch": 1.
|
236 |
-
"learning_rate":
|
237 |
-
"loss": 1.
|
238 |
"step": 185
|
239 |
},
|
240 |
{
|
241 |
-
"epoch": 1.
|
242 |
-
"learning_rate": 1.
|
243 |
-
"loss": 1.
|
244 |
"step": 190
|
245 |
},
|
246 |
{
|
247 |
"epoch": 1.23,
|
248 |
-
"learning_rate": 1.
|
249 |
-
"loss": 1.
|
250 |
"step": 195
|
251 |
},
|
252 |
{
|
253 |
-
"epoch": 1.
|
254 |
-
"learning_rate": 2.
|
255 |
-
"loss": 1.
|
256 |
"step": 200
|
257 |
},
|
258 |
{
|
259 |
-
"epoch": 1.
|
260 |
-
"learning_rate": 2.
|
261 |
-
"loss": 1.
|
262 |
"step": 205
|
263 |
},
|
264 |
{
|
265 |
-
"epoch": 1.
|
266 |
-
"learning_rate": 3.
|
267 |
-
"loss": 1.
|
268 |
"step": 210
|
269 |
},
|
270 |
{
|
271 |
-
"epoch": 1.
|
272 |
-
"learning_rate": 3.
|
273 |
-
"loss": 1.
|
274 |
"step": 215
|
275 |
},
|
276 |
{
|
277 |
-
"epoch": 1.
|
278 |
-
"learning_rate": 4.
|
279 |
-
"loss": 1.
|
280 |
"step": 220
|
281 |
},
|
282 |
{
|
283 |
"epoch": 1.42,
|
284 |
-
"learning_rate": 5.
|
285 |
-
"loss": 1.
|
286 |
"step": 225
|
287 |
},
|
288 |
{
|
289 |
-
"epoch": 1.
|
290 |
-
"learning_rate": 5.
|
291 |
-
"loss": 1.
|
292 |
"step": 230
|
293 |
},
|
294 |
{
|
295 |
-
"epoch": 1.
|
296 |
-
"learning_rate": 6.
|
297 |
-
"loss": 1.
|
298 |
"step": 235
|
299 |
},
|
300 |
{
|
301 |
-
"epoch": 1.
|
302 |
-
"learning_rate": 7.
|
303 |
-
"loss": 1.
|
304 |
"step": 240
|
305 |
},
|
306 |
{
|
307 |
-
"epoch": 1.
|
308 |
-
"learning_rate": 7.
|
309 |
-
"loss": 1.
|
310 |
"step": 245
|
311 |
},
|
312 |
{
|
313 |
-
"epoch": 1.
|
314 |
-
"learning_rate": 8.
|
315 |
-
"loss": 1.
|
316 |
"step": 250
|
317 |
},
|
318 |
{
|
319 |
-
"epoch": 1.
|
320 |
-
"learning_rate": 9.
|
321 |
-
"loss": 1.
|
322 |
"step": 255
|
323 |
},
|
324 |
{
|
325 |
-
"epoch": 1.
|
326 |
-
"learning_rate": 9.
|
327 |
-
"loss": 1.
|
328 |
"step": 260
|
329 |
},
|
330 |
{
|
331 |
-
"epoch": 1.
|
332 |
-
"learning_rate": 0.
|
333 |
-
"loss": 1.
|
334 |
"step": 265
|
335 |
},
|
336 |
{
|
337 |
-
"epoch": 1.
|
338 |
-
"learning_rate": 0.
|
339 |
-
"loss": 1.
|
340 |
"step": 270
|
341 |
},
|
342 |
{
|
343 |
-
"epoch": 1.
|
344 |
-
"learning_rate": 0.
|
345 |
-
"loss": 1.
|
346 |
"step": 275
|
347 |
},
|
348 |
{
|
349 |
-
"epoch": 1.
|
350 |
-
"learning_rate": 0.
|
351 |
-
"loss": 1.
|
352 |
"step": 280
|
353 |
},
|
354 |
{
|
355 |
-
"epoch": 1.
|
356 |
-
"learning_rate": 0.
|
357 |
-
"loss": 1.
|
358 |
"step": 285
|
359 |
},
|
360 |
{
|
361 |
-
"epoch": 1.
|
362 |
-
"learning_rate": 0.
|
363 |
-
"loss": 1.
|
364 |
"step": 290
|
365 |
},
|
366 |
{
|
367 |
-
"epoch": 1.
|
368 |
-
"learning_rate": 0.
|
369 |
-
"loss": 1.
|
370 |
"step": 295
|
371 |
},
|
372 |
{
|
373 |
-
"epoch": 1.
|
374 |
-
"learning_rate": 0.
|
375 |
-
"loss": 1.
|
376 |
"step": 300
|
377 |
},
|
378 |
{
|
379 |
-
"epoch": 1.
|
380 |
-
"learning_rate": 0.
|
381 |
-
"loss": 1.
|
382 |
"step": 305
|
383 |
},
|
384 |
{
|
385 |
-
"epoch": 1.
|
386 |
-
"learning_rate": 0.
|
387 |
-
"loss": 1.
|
388 |
"step": 310
|
389 |
},
|
390 |
{
|
391 |
-
"epoch": 1.
|
392 |
-
"learning_rate": 0.
|
393 |
-
"loss": 1.
|
394 |
"step": 315
|
395 |
},
|
396 |
{
|
397 |
"epoch": 2.0,
|
398 |
-
"eval_loss": 1.
|
399 |
-
"eval_runtime":
|
400 |
-
"eval_samples_per_second":
|
401 |
-
"eval_steps_per_second":
|
402 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
403 |
}
|
404 |
],
|
405 |
-
"max_steps":
|
406 |
-
"num_train_epochs":
|
407 |
-
"total_flos":
|
408 |
"trial_name": null,
|
409 |
"trial_params": null
|
410 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.4437962770462036,
|
3 |
+
"best_model_checkpoint": "output/egor-letov/checkpoint-1113",
|
4 |
+
"epoch": 7.0,
|
5 |
+
"global_step": 1113,
|
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": 0.00013686550750800417,
|
13 |
+
"loss": 1.7651,
|
14 |
"step": 5
|
15 |
},
|
16 |
{
|
17 |
"epoch": 0.06,
|
18 |
+
"learning_rate": 0.00013586529199199337,
|
19 |
+
"loss": 1.744,
|
20 |
"step": 10
|
21 |
},
|
22 |
{
|
23 |
"epoch": 0.09,
|
24 |
+
"learning_rate": 0.00013420910752136943,
|
25 |
+
"loss": 1.6316,
|
26 |
"step": 15
|
27 |
},
|
28 |
{
|
29 |
+
"epoch": 0.13,
|
30 |
+
"learning_rate": 0.0001319131051535897,
|
31 |
+
"loss": 1.6707,
|
32 |
"step": 20
|
33 |
},
|
34 |
{
|
35 |
+
"epoch": 0.16,
|
36 |
+
"learning_rate": 0.0001289996754295761,
|
37 |
+
"loss": 1.6026,
|
38 |
"step": 25
|
39 |
},
|
40 |
{
|
41 |
"epoch": 0.19,
|
42 |
+
"learning_rate": 0.00012549723002188386,
|
43 |
+
"loss": 1.6338,
|
44 |
"step": 30
|
45 |
},
|
46 |
{
|
47 |
"epoch": 0.22,
|
48 |
+
"learning_rate": 0.00012143992466498807,
|
49 |
+
"loss": 1.592,
|
50 |
"step": 35
|
51 |
},
|
52 |
{
|
53 |
"epoch": 0.25,
|
54 |
+
"learning_rate": 0.00011686732606966479,
|
55 |
+
"loss": 1.6485,
|
56 |
"step": 40
|
57 |
},
|
58 |
{
|
59 |
"epoch": 0.28,
|
60 |
+
"learning_rate": 0.00011182402606970537,
|
61 |
+
"loss": 1.5618,
|
62 |
"step": 45
|
63 |
},
|
64 |
{
|
65 |
"epoch": 0.31,
|
66 |
+
"learning_rate": 0.00010635920676379414,
|
67 |
+
"loss": 1.639,
|
68 |
"step": 50
|
69 |
},
|
70 |
{
|
71 |
+
"epoch": 0.35,
|
72 |
+
"learning_rate": 0.00010052616089327038,
|
73 |
+
"loss": 1.616,
|
74 |
"step": 55
|
75 |
},
|
76 |
{
|
77 |
+
"epoch": 0.38,
|
78 |
+
"learning_rate": 9.438177213303676e-05,
|
79 |
+
"loss": 1.6779,
|
80 |
"step": 60
|
81 |
},
|
82 |
{
|
83 |
+
"epoch": 0.41,
|
84 |
+
"learning_rate": 8.798596036379876e-05,
|
85 |
+
"loss": 1.6006,
|
86 |
"step": 65
|
87 |
},
|
88 |
{
|
89 |
+
"epoch": 0.44,
|
90 |
+
"learning_rate": 8.140109733532407e-05,
|
91 |
+
"loss": 1.6413,
|
92 |
"step": 70
|
93 |
},
|
94 |
{
|
95 |
+
"epoch": 0.47,
|
96 |
+
"learning_rate": 7.469139841915332e-05,
|
97 |
+
"loss": 1.6066,
|
98 |
"step": 75
|
99 |
},
|
100 |
{
|
101 |
+
"epoch": 0.5,
|
102 |
+
"learning_rate": 6.792229638237148e-05,
|
103 |
+
"loss": 1.5749,
|
104 |
"step": 80
|
105 |
},
|
106 |
{
|
107 |
+
"epoch": 0.53,
|
108 |
+
"learning_rate": 6.11598032893766e-05,
|
109 |
+
"loss": 1.5668,
|
110 |
"step": 85
|
111 |
},
|
112 |
{
|
113 |
+
"epoch": 0.57,
|
114 |
+
"learning_rate": 5.446986675436074e-05,
|
115 |
+
"loss": 1.6693,
|
116 |
"step": 90
|
117 |
},
|
118 |
{
|
119 |
+
"epoch": 0.6,
|
120 |
+
"learning_rate": 4.7917726822305834e-05,
|
121 |
+
"loss": 1.5177,
|
122 |
"step": 95
|
123 |
},
|
124 |
{
|
125 |
+
"epoch": 0.63,
|
126 |
+
"learning_rate": 4.156727975017365e-05,
|
127 |
+
"loss": 1.5749,
|
128 |
"step": 100
|
129 |
},
|
130 |
{
|
131 |
+
"epoch": 0.66,
|
132 |
+
"learning_rate": 3.5480454892670955e-05,
|
133 |
+
"loss": 1.7175,
|
134 |
"step": 105
|
135 |
},
|
136 |
{
|
137 |
+
"epoch": 0.69,
|
138 |
+
"learning_rate": 2.9716610769183376e-05,
|
139 |
+
"loss": 1.5363,
|
140 |
"step": 110
|
141 |
},
|
142 |
{
|
143 |
+
"epoch": 0.72,
|
144 |
+
"learning_rate": 2.433195620141175e-05,
|
145 |
+
"loss": 1.5101,
|
146 |
"step": 115
|
147 |
},
|
148 |
{
|
149 |
+
"epoch": 0.75,
|
150 |
+
"learning_rate": 1.9379002166758904e-05,
|
151 |
+
"loss": 1.454,
|
152 |
"step": 120
|
153 |
},
|
154 |
{
|
155 |
+
"epoch": 0.79,
|
156 |
+
"learning_rate": 1.4906049712973773e-05,
|
157 |
+
"loss": 1.5586,
|
158 |
"step": 125
|
159 |
},
|
160 |
{
|
161 |
+
"epoch": 0.82,
|
162 |
+
"learning_rate": 1.0956718927894408e-05,
|
163 |
+
"loss": 1.5785,
|
164 |
"step": 130
|
165 |
},
|
166 |
{
|
167 |
+
"epoch": 0.85,
|
168 |
+
"learning_rate": 7.569523557760334e-06,
|
169 |
+
"loss": 1.542,
|
170 |
"step": 135
|
171 |
},
|
172 |
{
|
173 |
+
"epoch": 0.88,
|
174 |
+
"learning_rate": 4.777495422403531e-06,
|
175 |
+
"loss": 1.5961,
|
176 |
"step": 140
|
177 |
},
|
178 |
{
|
179 |
+
"epoch": 0.91,
|
180 |
+
"learning_rate": 2.607862290008129e-06,
|
181 |
+
"loss": 1.5725,
|
182 |
"step": 145
|
183 |
},
|
184 |
{
|
185 |
+
"epoch": 0.94,
|
186 |
+
"learning_rate": 1.0817823527948728e-06,
|
187 |
+
"loss": 1.5678,
|
188 |
"step": 150
|
189 |
},
|
190 |
{
|
191 |
+
"epoch": 0.97,
|
192 |
+
"learning_rate": 2.1413789301400542e-07,
|
193 |
+
"loss": 1.5592,
|
194 |
"step": 155
|
195 |
},
|
196 |
{
|
197 |
+
"epoch": 1.0,
|
198 |
+
"eval_loss": 1.5221866369247437,
|
199 |
+
"eval_runtime": 5.3885,
|
200 |
+
"eval_samples_per_second": 44.725,
|
201 |
+
"eval_steps_per_second": 5.753,
|
202 |
+
"step": 159
|
203 |
},
|
204 |
{
|
205 |
+
"epoch": 1.01,
|
206 |
+
"learning_rate": 1.339015140952895e-08,
|
207 |
+
"loss": 1.5752,
|
208 |
+
"step": 160
|
|
|
|
|
209 |
},
|
210 |
{
|
211 |
"epoch": 1.04,
|
212 |
+
"learning_rate": 4.814968134727319e-07,
|
213 |
+
"loss": 1.6004,
|
214 |
"step": 165
|
215 |
},
|
216 |
{
|
217 |
+
"epoch": 1.07,
|
218 |
+
"learning_rate": 1.6138929181565955e-06,
|
219 |
+
"loss": 1.6208,
|
220 |
"step": 170
|
221 |
},
|
222 |
{
|
223 |
+
"epoch": 1.1,
|
224 |
+
"learning_rate": 3.399535375228382e-06,
|
225 |
+
"loss": 1.5048,
|
226 |
"step": 175
|
227 |
},
|
228 |
{
|
229 |
+
"epoch": 1.13,
|
230 |
+
"learning_rate": 5.821010657128918e-06,
|
231 |
+
"loss": 1.5368,
|
232 |
"step": 180
|
233 |
},
|
234 |
{
|
235 |
+
"epoch": 1.16,
|
236 |
+
"learning_rate": 8.854704615130833e-06,
|
237 |
+
"loss": 1.4625,
|
238 |
"step": 185
|
239 |
},
|
240 |
{
|
241 |
+
"epoch": 1.19,
|
242 |
+
"learning_rate": 1.247103276375417e-05,
|
243 |
+
"loss": 1.5028,
|
244 |
"step": 190
|
245 |
},
|
246 |
{
|
247 |
"epoch": 1.23,
|
248 |
+
"learning_rate": 1.663472878771286e-05,
|
249 |
+
"loss": 1.5655,
|
250 |
"step": 195
|
251 |
},
|
252 |
{
|
253 |
+
"epoch": 1.26,
|
254 |
+
"learning_rate": 2.130518845788256e-05,
|
255 |
+
"loss": 1.6462,
|
256 |
"step": 200
|
257 |
},
|
258 |
{
|
259 |
+
"epoch": 1.29,
|
260 |
+
"learning_rate": 2.6436865602431155e-05,
|
261 |
+
"loss": 1.5009,
|
262 |
"step": 205
|
263 |
},
|
264 |
{
|
265 |
+
"epoch": 1.32,
|
266 |
+
"learning_rate": 3.197971627161538e-05,
|
267 |
+
"loss": 1.4222,
|
268 |
"step": 210
|
269 |
},
|
270 |
{
|
271 |
+
"epoch": 1.35,
|
272 |
+
"learning_rate": 3.7879686764761665e-05,
|
273 |
+
"loss": 1.4581,
|
274 |
"step": 215
|
275 |
},
|
276 |
{
|
277 |
+
"epoch": 1.38,
|
278 |
+
"learning_rate": 4.407924076020964e-05,
|
279 |
+
"loss": 1.5815,
|
280 |
"step": 220
|
281 |
},
|
282 |
{
|
283 |
"epoch": 1.42,
|
284 |
+
"learning_rate": 5.0517920407661895e-05,
|
285 |
+
"loss": 1.4586,
|
286 |
"step": 225
|
287 |
},
|
288 |
{
|
289 |
+
"epoch": 1.45,
|
290 |
+
"learning_rate": 5.713293591118741e-05,
|
291 |
+
"loss": 1.6639,
|
292 |
"step": 230
|
293 |
},
|
294 |
{
|
295 |
+
"epoch": 1.48,
|
296 |
+
"learning_rate": 6.385977785328257e-05,
|
297 |
+
"loss": 1.4835,
|
298 |
"step": 235
|
299 |
},
|
300 |
{
|
301 |
+
"epoch": 1.51,
|
302 |
+
"learning_rate": 7.063284628862755e-05,
|
303 |
+
"loss": 1.4511,
|
304 |
"step": 240
|
305 |
},
|
306 |
{
|
307 |
+
"epoch": 1.54,
|
308 |
+
"learning_rate": 7.738609047263356e-05,
|
309 |
+
"loss": 1.5574,
|
310 |
"step": 245
|
311 |
},
|
312 |
{
|
313 |
+
"epoch": 1.57,
|
314 |
+
"learning_rate": 8.405365298617052e-05,
|
315 |
+
"loss": 1.5211,
|
316 |
"step": 250
|
317 |
},
|
318 |
{
|
319 |
+
"epoch": 1.6,
|
320 |
+
"learning_rate": 9.057051197499065e-05,
|
321 |
+
"loss": 1.5923,
|
322 |
"step": 255
|
323 |
},
|
324 |
{
|
325 |
+
"epoch": 1.64,
|
326 |
+
"learning_rate": 9.687311524075133e-05,
|
327 |
+
"loss": 1.4926,
|
328 |
"step": 260
|
329 |
},
|
330 |
{
|
331 |
+
"epoch": 1.67,
|
332 |
+
"learning_rate": 0.00010289999999999994,
|
333 |
+
"loss": 1.5,
|
334 |
"step": 265
|
335 |
},
|
336 |
{
|
337 |
+
"epoch": 1.7,
|
338 |
+
"learning_rate": 0.00010859239226725281,
|
339 |
+
"loss": 1.6531,
|
340 |
"step": 270
|
341 |
},
|
342 |
{
|
343 |
+
"epoch": 1.73,
|
344 |
+
"learning_rate": 0.00011389478001700268,
|
345 |
+
"loss": 1.5839,
|
346 |
"step": 275
|
347 |
},
|
348 |
{
|
349 |
+
"epoch": 1.76,
|
350 |
+
"learning_rate": 0.0001187554545351989,
|
351 |
+
"loss": 1.5527,
|
352 |
"step": 280
|
353 |
},
|
354 |
{
|
355 |
+
"epoch": 1.79,
|
356 |
+
"learning_rate": 0.00012312701468095597,
|
357 |
+
"loss": 1.4811,
|
358 |
"step": 285
|
359 |
},
|
360 |
{
|
361 |
+
"epoch": 1.82,
|
362 |
+
"learning_rate": 0.0001269668291409485,
|
363 |
+
"loss": 1.6154,
|
364 |
"step": 290
|
365 |
},
|
366 |
{
|
367 |
+
"epoch": 1.86,
|
368 |
+
"learning_rate": 0.0001302374521686013,
|
369 |
+
"loss": 1.611,
|
370 |
"step": 295
|
371 |
},
|
372 |
{
|
373 |
+
"epoch": 1.89,
|
374 |
+
"learning_rate": 0.00013290698875380067,
|
375 |
+
"loss": 1.5892,
|
376 |
"step": 300
|
377 |
},
|
378 |
{
|
379 |
+
"epoch": 1.92,
|
380 |
+
"learning_rate": 0.0001349494056620028,
|
381 |
+
"loss": 1.4601,
|
382 |
"step": 305
|
383 |
},
|
384 |
{
|
385 |
+
"epoch": 1.95,
|
386 |
+
"learning_rate": 0.0001363447853094957,
|
387 |
+
"loss": 1.4863,
|
388 |
"step": 310
|
389 |
},
|
390 |
{
|
391 |
+
"epoch": 1.98,
|
392 |
+
"learning_rate": 0.00013707951999903243,
|
393 |
+
"loss": 1.5381,
|
394 |
"step": 315
|
395 |
},
|
396 |
{
|
397 |
"epoch": 2.0,
|
398 |
+
"eval_loss": 1.5293655395507812,
|
399 |
+
"eval_runtime": 5.7302,
|
400 |
+
"eval_samples_per_second": 42.058,
|
401 |
+
"eval_steps_per_second": 5.41,
|
402 |
+
"step": 318
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 2.01,
|
406 |
+
"learning_rate": 0.00013714644462165502,
|
407 |
+
"loss": 1.4756,
|
408 |
+
"step": 320
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 2.04,
|
412 |
+
"learning_rate": 0.00013654490653060552,
|
413 |
+
"loss": 1.538,
|
414 |
+
"step": 325
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"epoch": 2.08,
|
418 |
+
"learning_rate": 0.00013528077190591619,
|
419 |
+
"loss": 1.4616,
|
420 |
+
"step": 330
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"epoch": 2.11,
|
424 |
+
"learning_rate": 0.00013336636854761124,
|
425 |
+
"loss": 1.4735,
|
426 |
+
"step": 335
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 2.14,
|
430 |
+
"learning_rate": 0.00013082036565539916,
|
431 |
+
"loss": 1.3918,
|
432 |
+
"step": 340
|
433 |
+
},
|
434 |
+
{
|
435 |
+
"epoch": 2.17,
|
436 |
+
"learning_rate": 0.00012766759176724058,
|
437 |
+
"loss": 1.4803,
|
438 |
+
"step": 345
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"epoch": 2.2,
|
442 |
+
"learning_rate": 0.00012393879263224768,
|
443 |
+
"loss": 1.6293,
|
444 |
+
"step": 350
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 2.23,
|
448 |
+
"learning_rate": 0.00011967033137913236,
|
449 |
+
"loss": 1.5226,
|
450 |
+
"step": 355
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 2.26,
|
454 |
+
"learning_rate": 0.00011490383390414918,
|
455 |
+
"loss": 1.5126,
|
456 |
+
"step": 360
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 2.3,
|
460 |
+
"learning_rate": 0.00010968578293670085,
|
461 |
+
"loss": 1.5304,
|
462 |
+
"step": 365
|
463 |
+
},
|
464 |
+
{
|
465 |
+
"epoch": 2.33,
|
466 |
+
"learning_rate": 0.00010406706474126147,
|
467 |
+
"loss": 1.4686,
|
468 |
+
"step": 370
|
469 |
+
},
|
470 |
+
{
|
471 |
+
"epoch": 2.36,
|
472 |
+
"learning_rate": 9.810247287616943e-05,
|
473 |
+
"loss": 1.4261,
|
474 |
+
"step": 375
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 2.39,
|
478 |
+
"learning_rate": 9.185017384861683e-05,
|
479 |
+
"loss": 1.4695,
|
480 |
+
"step": 380
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 2.42,
|
484 |
+
"learning_rate": 8.537113987675073e-05,
|
485 |
+
"loss": 1.4489,
|
486 |
+
"step": 385
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 2.45,
|
490 |
+
"learning_rate": 7.872855429057032e-05,
|
491 |
+
"loss": 1.5209,
|
492 |
+
"step": 390
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 2.48,
|
496 |
+
"learning_rate": 7.198719537013416e-05,
|
497 |
+
"loss": 1.4409,
|
498 |
+
"step": 395
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 2.52,
|
502 |
+
"learning_rate": 6.521280462986591e-05,
|
503 |
+
"loss": 1.4272,
|
504 |
+
"step": 400
|
505 |
+
},
|
506 |
+
{
|
507 |
+
"epoch": 2.55,
|
508 |
+
"learning_rate": 5.847144570942975e-05,
|
509 |
+
"loss": 1.4187,
|
510 |
+
"step": 405
|
511 |
+
},
|
512 |
+
{
|
513 |
+
"epoch": 2.58,
|
514 |
+
"learning_rate": 5.1828860123249337e-05,
|
515 |
+
"loss": 1.4412,
|
516 |
+
"step": 410
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 2.61,
|
520 |
+
"learning_rate": 4.5349826151383235e-05,
|
521 |
+
"loss": 1.536,
|
522 |
+
"step": 415
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 2.64,
|
526 |
+
"learning_rate": 3.909752712383064e-05,
|
527 |
+
"loss": 1.468,
|
528 |
+
"step": 420
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 2.67,
|
532 |
+
"learning_rate": 3.31329352587386e-05,
|
533 |
+
"loss": 1.4604,
|
534 |
+
"step": 425
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 2.7,
|
538 |
+
"learning_rate": 2.7514217063299194e-05,
|
539 |
+
"loss": 1.4515,
|
540 |
+
"step": 430
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 2.74,
|
544 |
+
"learning_rate": 2.229616609585087e-05,
|
545 |
+
"loss": 1.4215,
|
546 |
+
"step": 435
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 2.77,
|
550 |
+
"learning_rate": 1.7529668620867685e-05,
|
551 |
+
"loss": 1.4177,
|
552 |
+
"step": 440
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 2.8,
|
556 |
+
"learning_rate": 1.3261207367752373e-05,
|
557 |
+
"loss": 1.4707,
|
558 |
+
"step": 445
|
559 |
+
},
|
560 |
+
{
|
561 |
+
"epoch": 2.83,
|
562 |
+
"learning_rate": 9.53240823275947e-06,
|
563 |
+
"loss": 1.4591,
|
564 |
+
"step": 450
|
565 |
+
},
|
566 |
+
{
|
567 |
+
"epoch": 2.86,
|
568 |
+
"learning_rate": 6.379634344600892e-06,
|
569 |
+
"loss": 1.5216,
|
570 |
+
"step": 455
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 2.89,
|
574 |
+
"learning_rate": 3.833631452388783e-06,
|
575 |
+
"loss": 1.4972,
|
576 |
+
"step": 460
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 2.92,
|
580 |
+
"learning_rate": 1.919228094083838e-06,
|
581 |
+
"loss": 1.5209,
|
582 |
+
"step": 465
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 2.96,
|
586 |
+
"learning_rate": 6.550934693944858e-07,
|
587 |
+
"loss": 1.45,
|
588 |
+
"step": 470
|
589 |
+
},
|
590 |
+
{
|
591 |
+
"epoch": 2.99,
|
592 |
+
"learning_rate": 5.35553783449795e-08,
|
593 |
+
"loss": 1.4454,
|
594 |
+
"step": 475
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 3.0,
|
598 |
+
"eval_loss": 1.4749490022659302,
|
599 |
+
"eval_runtime": 5.7804,
|
600 |
+
"eval_samples_per_second": 41.693,
|
601 |
+
"eval_steps_per_second": 5.363,
|
602 |
+
"step": 477
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 3.02,
|
606 |
+
"learning_rate": 1.2048000096755528e-07,
|
607 |
+
"loss": 1.5049,
|
608 |
+
"step": 480
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 3.05,
|
612 |
+
"learning_rate": 8.552146905042678e-07,
|
613 |
+
"loss": 1.4016,
|
614 |
+
"step": 485
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 3.08,
|
618 |
+
"learning_rate": 2.2505943379971545e-06,
|
619 |
+
"loss": 1.4147,
|
620 |
+
"step": 490
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 3.11,
|
624 |
+
"learning_rate": 4.293011246199337e-06,
|
625 |
+
"loss": 1.3828,
|
626 |
+
"step": 495
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 3.14,
|
630 |
+
"learning_rate": 6.9625478313987545e-06,
|
631 |
+
"loss": 1.431,
|
632 |
+
"step": 500
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 3.18,
|
636 |
+
"learning_rate": 1.023317085905152e-05,
|
637 |
+
"loss": 1.4227,
|
638 |
+
"step": 505
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 3.21,
|
642 |
+
"learning_rate": 1.4072985319043966e-05,
|
643 |
+
"loss": 1.4611,
|
644 |
+
"step": 510
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 3.24,
|
648 |
+
"learning_rate": 1.8444545464801038e-05,
|
649 |
+
"loss": 1.3548,
|
650 |
+
"step": 515
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 3.27,
|
654 |
+
"learning_rate": 2.330521998299726e-05,
|
655 |
+
"loss": 1.4269,
|
656 |
+
"step": 520
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 3.3,
|
660 |
+
"learning_rate": 2.8607607732747138e-05,
|
661 |
+
"loss": 1.4122,
|
662 |
+
"step": 525
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 3.33,
|
666 |
+
"learning_rate": 3.429999999999989e-05,
|
667 |
+
"loss": 1.42,
|
668 |
+
"step": 530
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 3.36,
|
672 |
+
"learning_rate": 4.032688475924871e-05,
|
673 |
+
"loss": 1.388,
|
674 |
+
"step": 535
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 3.4,
|
678 |
+
"learning_rate": 4.66294880250094e-05,
|
679 |
+
"loss": 1.369,
|
680 |
+
"step": 540
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 3.43,
|
684 |
+
"learning_rate": 5.3146347013829526e-05,
|
685 |
+
"loss": 1.3512,
|
686 |
+
"step": 545
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 3.46,
|
690 |
+
"learning_rate": 5.981390952736637e-05,
|
691 |
+
"loss": 1.3807,
|
692 |
+
"step": 550
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 3.49,
|
696 |
+
"learning_rate": 6.656715371137237e-05,
|
697 |
+
"loss": 1.466,
|
698 |
+
"step": 555
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 3.52,
|
702 |
+
"learning_rate": 7.334022214671736e-05,
|
703 |
+
"loss": 1.3711,
|
704 |
+
"step": 560
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 3.55,
|
708 |
+
"learning_rate": 8.006706408881251e-05,
|
709 |
+
"loss": 1.3797,
|
710 |
+
"step": 565
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 3.58,
|
714 |
+
"learning_rate": 8.668207959233792e-05,
|
715 |
+
"loss": 1.413,
|
716 |
+
"step": 570
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 3.62,
|
720 |
+
"learning_rate": 9.312075923979041e-05,
|
721 |
+
"loss": 1.3859,
|
722 |
+
"step": 575
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 3.65,
|
726 |
+
"learning_rate": 9.932031323523837e-05,
|
727 |
+
"loss": 1.4853,
|
728 |
+
"step": 580
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 3.68,
|
732 |
+
"learning_rate": 0.00010522028372838466,
|
733 |
+
"loss": 1.3925,
|
734 |
+
"step": 585
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 3.71,
|
738 |
+
"learning_rate": 0.0001107631343975688,
|
739 |
+
"loss": 1.4442,
|
740 |
+
"step": 590
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 3.74,
|
744 |
+
"learning_rate": 0.00011589481154211739,
|
745 |
+
"loss": 1.5125,
|
746 |
+
"step": 595
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 3.77,
|
750 |
+
"learning_rate": 0.00012056527121228708,
|
751 |
+
"loss": 1.3964,
|
752 |
+
"step": 600
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 3.81,
|
756 |
+
"learning_rate": 0.0001247289672362458,
|
757 |
+
"loss": 1.4655,
|
758 |
+
"step": 605
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 3.84,
|
762 |
+
"learning_rate": 0.00012834529538486908,
|
763 |
+
"loss": 1.3898,
|
764 |
+
"step": 610
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 3.87,
|
768 |
+
"learning_rate": 0.00013137898934287108,
|
769 |
+
"loss": 1.4001,
|
770 |
+
"step": 615
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 3.9,
|
774 |
+
"learning_rate": 0.00013380046462477163,
|
775 |
+
"loss": 1.4248,
|
776 |
+
"step": 620
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 3.93,
|
780 |
+
"learning_rate": 0.0001355861070818434,
|
781 |
+
"loss": 1.3956,
|
782 |
+
"step": 625
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 3.96,
|
786 |
+
"learning_rate": 0.00013671850318652725,
|
787 |
+
"loss": 1.4704,
|
788 |
+
"step": 630
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 3.99,
|
792 |
+
"learning_rate": 0.0001371866098485905,
|
793 |
+
"loss": 1.4419,
|
794 |
+
"step": 635
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 4.0,
|
798 |
+
"eval_loss": 1.4980032444000244,
|
799 |
+
"eval_runtime": 5.8381,
|
800 |
+
"eval_samples_per_second": 41.28,
|
801 |
+
"eval_steps_per_second": 5.31,
|
802 |
+
"step": 636
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 4.03,
|
806 |
+
"learning_rate": 0.000136985862106986,
|
807 |
+
"loss": 1.3728,
|
808 |
+
"step": 640
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 4.06,
|
812 |
+
"learning_rate": 0.00013611821764720515,
|
813 |
+
"loss": 1.3237,
|
814 |
+
"step": 645
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 4.09,
|
818 |
+
"learning_rate": 0.00013459213770999185,
|
819 |
+
"loss": 1.3533,
|
820 |
+
"step": 650
|
821 |
+
},
|
822 |
+
{
|
823 |
+
"epoch": 4.12,
|
824 |
+
"learning_rate": 0.00013242250457759646,
|
825 |
+
"loss": 1.4508,
|
826 |
+
"step": 655
|
827 |
+
},
|
828 |
+
{
|
829 |
+
"epoch": 4.15,
|
830 |
+
"learning_rate": 0.00012963047644223966,
|
831 |
+
"loss": 1.4551,
|
832 |
+
"step": 660
|
833 |
+
},
|
834 |
+
{
|
835 |
+
"epoch": 4.18,
|
836 |
+
"learning_rate": 0.00012624328107210575,
|
837 |
+
"loss": 1.3913,
|
838 |
+
"step": 665
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 4.21,
|
842 |
+
"learning_rate": 0.00012229395028702628,
|
843 |
+
"loss": 1.3365,
|
844 |
+
"step": 670
|
845 |
+
},
|
846 |
+
{
|
847 |
+
"epoch": 4.25,
|
848 |
+
"learning_rate": 0.00011782099783324114,
|
849 |
+
"loss": 1.4044,
|
850 |
+
"step": 675
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 4.28,
|
854 |
+
"learning_rate": 0.00011286804379858831,
|
855 |
+
"loss": 1.3806,
|
856 |
+
"step": 680
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 4.31,
|
860 |
+
"learning_rate": 0.00010748338923081678,
|
861 |
+
"loss": 1.3692,
|
862 |
+
"step": 685
|
863 |
+
},
|
864 |
+
{
|
865 |
+
"epoch": 4.34,
|
866 |
+
"learning_rate": 0.00010171954510732902,
|
867 |
+
"loss": 1.3377,
|
868 |
+
"step": 690
|
869 |
+
},
|
870 |
+
{
|
871 |
+
"epoch": 4.37,
|
872 |
+
"learning_rate": 9.56327202498263e-05,
|
873 |
+
"loss": 1.3899,
|
874 |
+
"step": 695
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 4.4,
|
878 |
+
"learning_rate": 8.928227317769412e-05,
|
879 |
+
"loss": 1.3824,
|
880 |
+
"step": 700
|
881 |
+
},
|
882 |
+
{
|
883 |
+
"epoch": 4.43,
|
884 |
+
"learning_rate": 8.273013324563958e-05,
|
885 |
+
"loss": 1.3517,
|
886 |
+
"step": 705
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 4.47,
|
890 |
+
"learning_rate": 7.604019671062341e-05,
|
891 |
+
"loss": 1.3471,
|
892 |
+
"step": 710
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 4.5,
|
896 |
+
"learning_rate": 6.927770361762859e-05,
|
897 |
+
"loss": 1.363,
|
898 |
+
"step": 715
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 4.53,
|
902 |
+
"learning_rate": 6.250860158084675e-05,
|
903 |
+
"loss": 1.4238,
|
904 |
+
"step": 720
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 4.56,
|
908 |
+
"learning_rate": 5.5798902664676055e-05,
|
909 |
+
"loss": 1.3159,
|
910 |
+
"step": 725
|
911 |
+
},
|
912 |
+
{
|
913 |
+
"epoch": 4.59,
|
914 |
+
"learning_rate": 4.921403963620114e-05,
|
915 |
+
"loss": 1.3496,
|
916 |
+
"step": 730
|
917 |
+
},
|
918 |
+
{
|
919 |
+
"epoch": 4.62,
|
920 |
+
"learning_rate": 4.2818227866963195e-05,
|
921 |
+
"loss": 1.3717,
|
922 |
+
"step": 735
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 4.65,
|
926 |
+
"learning_rate": 3.667383910672979e-05,
|
927 |
+
"loss": 1.4263,
|
928 |
+
"step": 740
|
929 |
+
},
|
930 |
+
{
|
931 |
+
"epoch": 4.69,
|
932 |
+
"learning_rate": 3.084079323620607e-05,
|
933 |
+
"loss": 1.4238,
|
934 |
+
"step": 745
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 4.72,
|
938 |
+
"learning_rate": 2.537597393029464e-05,
|
939 |
+
"loss": 1.3789,
|
940 |
+
"step": 750
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 4.75,
|
944 |
+
"learning_rate": 2.0332673930335262e-05,
|
945 |
+
"loss": 1.2943,
|
946 |
+
"step": 755
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 4.78,
|
950 |
+
"learning_rate": 1.576007533501198e-05,
|
951 |
+
"loss": 1.4457,
|
952 |
+
"step": 760
|
953 |
+
},
|
954 |
+
{
|
955 |
+
"epoch": 4.81,
|
956 |
+
"learning_rate": 1.170276997811622e-05,
|
957 |
+
"loss": 1.3882,
|
958 |
+
"step": 765
|
959 |
+
},
|
960 |
+
{
|
961 |
+
"epoch": 4.84,
|
962 |
+
"learning_rate": 8.200324570423858e-06,
|
963 |
+
"loss": 1.3435,
|
964 |
+
"step": 770
|
965 |
+
},
|
966 |
+
{
|
967 |
+
"epoch": 4.87,
|
968 |
+
"learning_rate": 5.286894846410311e-06,
|
969 |
+
"loss": 1.3625,
|
970 |
+
"step": 775
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 4.91,
|
974 |
+
"learning_rate": 2.9908924786306224e-06,
|
975 |
+
"loss": 1.3336,
|
976 |
+
"step": 780
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 4.94,
|
980 |
+
"learning_rate": 1.3347080080066949e-06,
|
981 |
+
"loss": 1.3698,
|
982 |
+
"step": 785
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 4.97,
|
986 |
+
"learning_rate": 3.34492491995841e-07,
|
987 |
+
"loss": 1.3109,
|
988 |
+
"step": 790
|
989 |
+
},
|
990 |
+
{
|
991 |
+
"epoch": 5.0,
|
992 |
+
"learning_rate": 0.0,
|
993 |
+
"loss": 1.3807,
|
994 |
+
"step": 795
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 5.0,
|
998 |
+
"eval_loss": 1.4533822536468506,
|
999 |
+
"eval_runtime": 5.8855,
|
1000 |
+
"eval_samples_per_second": 40.948,
|
1001 |
+
"eval_steps_per_second": 5.267,
|
1002 |
+
"step": 795
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"epoch": 5.03,
|
1006 |
+
"learning_rate": 3.3449249199583335e-07,
|
1007 |
+
"loss": 1.2678,
|
1008 |
+
"step": 800
|
1009 |
+
},
|
1010 |
+
{
|
1011 |
+
"epoch": 5.06,
|
1012 |
+
"learning_rate": 1.334708008006672e-06,
|
1013 |
+
"loss": 1.2155,
|
1014 |
+
"step": 805
|
1015 |
+
},
|
1016 |
+
{
|
1017 |
+
"epoch": 5.09,
|
1018 |
+
"learning_rate": 2.990892478630592e-06,
|
1019 |
+
"loss": 1.265,
|
1020 |
+
"step": 810
|
1021 |
+
},
|
1022 |
+
{
|
1023 |
+
"epoch": 5.13,
|
1024 |
+
"learning_rate": 5.286894846410265e-06,
|
1025 |
+
"loss": 1.2533,
|
1026 |
+
"step": 815
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 5.16,
|
1030 |
+
"learning_rate": 8.200324570423804e-06,
|
1031 |
+
"loss": 1.2628,
|
1032 |
+
"step": 820
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 5.19,
|
1036 |
+
"learning_rate": 1.1702769978116159e-05,
|
1037 |
+
"loss": 1.321,
|
1038 |
+
"step": 825
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 5.22,
|
1042 |
+
"learning_rate": 1.5760075335011905e-05,
|
1043 |
+
"loss": 1.3229,
|
1044 |
+
"step": 830
|
1045 |
+
},
|
1046 |
+
{
|
1047 |
+
"epoch": 5.25,
|
1048 |
+
"learning_rate": 2.0332673930335177e-05,
|
1049 |
+
"loss": 1.3257,
|
1050 |
+
"step": 835
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 5.28,
|
1054 |
+
"learning_rate": 2.537597393029455e-05,
|
1055 |
+
"loss": 1.3373,
|
1056 |
+
"step": 840
|
1057 |
+
},
|
1058 |
+
{
|
1059 |
+
"epoch": 5.31,
|
1060 |
+
"learning_rate": 3.0840793236205985e-05,
|
1061 |
+
"loss": 1.2971,
|
1062 |
+
"step": 845
|
1063 |
+
},
|
1064 |
+
{
|
1065 |
+
"epoch": 5.35,
|
1066 |
+
"learning_rate": 3.667383910672968e-05,
|
1067 |
+
"loss": 1.1974,
|
1068 |
+
"step": 850
|
1069 |
+
},
|
1070 |
+
{
|
1071 |
+
"epoch": 5.38,
|
1072 |
+
"learning_rate": 4.281822786696309e-05,
|
1073 |
+
"loss": 1.3887,
|
1074 |
+
"step": 855
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 5.41,
|
1078 |
+
"learning_rate": 4.921403963620103e-05,
|
1079 |
+
"loss": 1.3505,
|
1080 |
+
"step": 860
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 5.44,
|
1084 |
+
"learning_rate": 5.579890266467594e-05,
|
1085 |
+
"loss": 1.319,
|
1086 |
+
"step": 865
|
1087 |
+
},
|
1088 |
+
{
|
1089 |
+
"epoch": 5.47,
|
1090 |
+
"learning_rate": 6.250860158084664e-05,
|
1091 |
+
"loss": 1.3255,
|
1092 |
+
"step": 870
|
1093 |
+
},
|
1094 |
+
{
|
1095 |
+
"epoch": 5.5,
|
1096 |
+
"learning_rate": 6.927770361762848e-05,
|
1097 |
+
"loss": 1.2311,
|
1098 |
+
"step": 875
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 5.53,
|
1102 |
+
"learning_rate": 7.604019671062329e-05,
|
1103 |
+
"loss": 1.3552,
|
1104 |
+
"step": 880
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 5.57,
|
1108 |
+
"learning_rate": 8.273013324563947e-05,
|
1109 |
+
"loss": 1.3885,
|
1110 |
+
"step": 885
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 5.6,
|
1114 |
+
"learning_rate": 8.928227317769401e-05,
|
1115 |
+
"loss": 1.3314,
|
1116 |
+
"step": 890
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 5.63,
|
1120 |
+
"learning_rate": 9.563272024982619e-05,
|
1121 |
+
"loss": 1.3202,
|
1122 |
+
"step": 895
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 5.66,
|
1126 |
+
"learning_rate": 0.00010171954510732891,
|
1127 |
+
"loss": 1.3272,
|
1128 |
+
"step": 900
|
1129 |
+
},
|
1130 |
+
{
|
1131 |
+
"epoch": 5.69,
|
1132 |
+
"learning_rate": 0.00010748338923081667,
|
1133 |
+
"loss": 1.2248,
|
1134 |
+
"step": 905
|
1135 |
+
},
|
1136 |
+
{
|
1137 |
+
"epoch": 5.72,
|
1138 |
+
"learning_rate": 0.00011286804379858823,
|
1139 |
+
"loss": 1.3777,
|
1140 |
+
"step": 910
|
1141 |
+
},
|
1142 |
+
{
|
1143 |
+
"epoch": 5.75,
|
1144 |
+
"learning_rate": 0.00011782099783324106,
|
1145 |
+
"loss": 1.3051,
|
1146 |
+
"step": 915
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"epoch": 5.79,
|
1150 |
+
"learning_rate": 0.0001222939502870262,
|
1151 |
+
"loss": 1.3295,
|
1152 |
+
"step": 920
|
1153 |
+
},
|
1154 |
+
{
|
1155 |
+
"epoch": 5.82,
|
1156 |
+
"learning_rate": 0.0001262432810721057,
|
1157 |
+
"loss": 1.3102,
|
1158 |
+
"step": 925
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"epoch": 5.85,
|
1162 |
+
"learning_rate": 0.00012963047644223957,
|
1163 |
+
"loss": 1.409,
|
1164 |
+
"step": 930
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 5.88,
|
1168 |
+
"learning_rate": 0.0001324225045775964,
|
1169 |
+
"loss": 1.3435,
|
1170 |
+
"step": 935
|
1171 |
+
},
|
1172 |
+
{
|
1173 |
+
"epoch": 5.91,
|
1174 |
+
"learning_rate": 0.00013459213770999182,
|
1175 |
+
"loss": 1.3775,
|
1176 |
+
"step": 940
|
1177 |
+
},
|
1178 |
+
{
|
1179 |
+
"epoch": 5.94,
|
1180 |
+
"learning_rate": 0.00013611821764720515,
|
1181 |
+
"loss": 1.3406,
|
1182 |
+
"step": 945
|
1183 |
+
},
|
1184 |
+
{
|
1185 |
+
"epoch": 5.97,
|
1186 |
+
"learning_rate": 0.000136985862106986,
|
1187 |
+
"loss": 1.4464,
|
1188 |
+
"step": 950
|
1189 |
+
},
|
1190 |
+
{
|
1191 |
+
"epoch": 6.0,
|
1192 |
+
"eval_loss": 1.4797894954681396,
|
1193 |
+
"eval_runtime": 5.9157,
|
1194 |
+
"eval_samples_per_second": 40.739,
|
1195 |
+
"eval_steps_per_second": 5.24,
|
1196 |
+
"step": 954
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 6.01,
|
1200 |
+
"learning_rate": 0.0001371866098485905,
|
1201 |
+
"loss": 1.2626,
|
1202 |
+
"step": 955
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 6.04,
|
1206 |
+
"learning_rate": 0.00013671850318652725,
|
1207 |
+
"loss": 1.2796,
|
1208 |
+
"step": 960
|
1209 |
+
},
|
1210 |
+
{
|
1211 |
+
"epoch": 6.07,
|
1212 |
+
"learning_rate": 0.00013558610708184343,
|
1213 |
+
"loss": 1.1514,
|
1214 |
+
"step": 965
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 6.1,
|
1218 |
+
"learning_rate": 0.00013380046462477168,
|
1219 |
+
"loss": 1.3043,
|
1220 |
+
"step": 970
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 6.13,
|
1224 |
+
"learning_rate": 0.00013137898934287106,
|
1225 |
+
"loss": 1.327,
|
1226 |
+
"step": 975
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 6.16,
|
1230 |
+
"learning_rate": 0.00012834529538486924,
|
1231 |
+
"loss": 1.214,
|
1232 |
+
"step": 980
|
1233 |
+
},
|
1234 |
+
{
|
1235 |
+
"epoch": 6.19,
|
1236 |
+
"learning_rate": 0.00012472896723624585,
|
1237 |
+
"loss": 1.1638,
|
1238 |
+
"step": 985
|
1239 |
+
},
|
1240 |
+
{
|
1241 |
+
"epoch": 6.23,
|
1242 |
+
"learning_rate": 0.00012056527121228703,
|
1243 |
+
"loss": 1.3165,
|
1244 |
+
"step": 990
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"epoch": 6.26,
|
1248 |
+
"learning_rate": 0.00011589481154211748,
|
1249 |
+
"loss": 1.3327,
|
1250 |
+
"step": 995
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 6.29,
|
1254 |
+
"learning_rate": 0.00011076313439756889,
|
1255 |
+
"loss": 1.3318,
|
1256 |
+
"step": 1000
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 6.32,
|
1260 |
+
"learning_rate": 0.00010522028372838475,
|
1261 |
+
"loss": 1.3088,
|
1262 |
+
"step": 1005
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 6.35,
|
1266 |
+
"learning_rate": 9.932031323523849e-05,
|
1267 |
+
"loss": 1.4023,
|
1268 |
+
"step": 1010
|
1269 |
+
},
|
1270 |
+
{
|
1271 |
+
"epoch": 6.38,
|
1272 |
+
"learning_rate": 9.312075923979029e-05,
|
1273 |
+
"loss": 1.2767,
|
1274 |
+
"step": 1015
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 6.42,
|
1278 |
+
"learning_rate": 8.668207959233826e-05,
|
1279 |
+
"loss": 1.3357,
|
1280 |
+
"step": 1020
|
1281 |
+
},
|
1282 |
+
{
|
1283 |
+
"epoch": 6.45,
|
1284 |
+
"learning_rate": 8.006706408881263e-05,
|
1285 |
+
"loss": 1.2732,
|
1286 |
+
"step": 1025
|
1287 |
+
},
|
1288 |
+
{
|
1289 |
+
"epoch": 6.48,
|
1290 |
+
"learning_rate": 7.334022214671723e-05,
|
1291 |
+
"loss": 1.2055,
|
1292 |
+
"step": 1030
|
1293 |
+
},
|
1294 |
+
{
|
1295 |
+
"epoch": 6.51,
|
1296 |
+
"learning_rate": 6.656715371137249e-05,
|
1297 |
+
"loss": 1.3083,
|
1298 |
+
"step": 1035
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 6.54,
|
1302 |
+
"learning_rate": 5.981390952736648e-05,
|
1303 |
+
"loss": 1.3757,
|
1304 |
+
"step": 1040
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 6.57,
|
1308 |
+
"learning_rate": 5.314634701382964e-05,
|
1309 |
+
"loss": 1.2944,
|
1310 |
+
"step": 1045
|
1311 |
+
},
|
1312 |
+
{
|
1313 |
+
"epoch": 6.6,
|
1314 |
+
"learning_rate": 4.66294880250095e-05,
|
1315 |
+
"loss": 1.3276,
|
1316 |
+
"step": 1050
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"epoch": 6.64,
|
1320 |
+
"learning_rate": 4.032688475924859e-05,
|
1321 |
+
"loss": 1.2886,
|
1322 |
+
"step": 1055
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 6.67,
|
1326 |
+
"learning_rate": 3.4300000000000204e-05,
|
1327 |
+
"loss": 1.2137,
|
1328 |
+
"step": 1060
|
1329 |
+
},
|
1330 |
+
{
|
1331 |
+
"epoch": 6.7,
|
1332 |
+
"learning_rate": 2.8607607732747236e-05,
|
1333 |
+
"loss": 1.2814,
|
1334 |
+
"step": 1065
|
1335 |
+
},
|
1336 |
+
{
|
1337 |
+
"epoch": 6.73,
|
1338 |
+
"learning_rate": 2.3305219982997162e-05,
|
1339 |
+
"loss": 1.2878,
|
1340 |
+
"step": 1070
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 6.76,
|
1344 |
+
"learning_rate": 1.844454546480112e-05,
|
1345 |
+
"loss": 1.2616,
|
1346 |
+
"step": 1075
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 6.79,
|
1350 |
+
"learning_rate": 1.4072985319044034e-05,
|
1351 |
+
"loss": 1.2864,
|
1352 |
+
"step": 1080
|
1353 |
+
},
|
1354 |
+
{
|
1355 |
+
"epoch": 6.82,
|
1356 |
+
"learning_rate": 1.0233170859051581e-05,
|
1357 |
+
"loss": 1.3714,
|
1358 |
+
"step": 1085
|
1359 |
+
},
|
1360 |
+
{
|
1361 |
+
"epoch": 6.86,
|
1362 |
+
"learning_rate": 6.962547831398808e-06,
|
1363 |
+
"loss": 1.2827,
|
1364 |
+
"step": 1090
|
1365 |
+
},
|
1366 |
+
{
|
1367 |
+
"epoch": 6.89,
|
1368 |
+
"learning_rate": 4.293011246199291e-06,
|
1369 |
+
"loss": 1.3028,
|
1370 |
+
"step": 1095
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 6.92,
|
1374 |
+
"learning_rate": 2.250594337997246e-06,
|
1375 |
+
"loss": 1.2778,
|
1376 |
+
"step": 1100
|
1377 |
+
},
|
1378 |
+
{
|
1379 |
+
"epoch": 6.95,
|
1380 |
+
"learning_rate": 8.552146905042907e-07,
|
1381 |
+
"loss": 1.2184,
|
1382 |
+
"step": 1105
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 6.98,
|
1386 |
+
"learning_rate": 1.2048000096754006e-07,
|
1387 |
+
"loss": 1.241,
|
1388 |
+
"step": 1110
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 7.0,
|
1392 |
+
"eval_loss": 1.4437962770462036,
|
1393 |
+
"eval_runtime": 5.9385,
|
1394 |
+
"eval_samples_per_second": 40.583,
|
1395 |
+
"eval_steps_per_second": 5.22,
|
1396 |
+
"step": 1113
|
1397 |
}
|
1398 |
],
|
1399 |
+
"max_steps": 1908,
|
1400 |
+
"num_train_epochs": 12,
|
1401 |
+
"total_flos": 1163272126464000.0,
|
1402 |
"trial_name": null,
|
1403 |
"trial_params": null
|
1404 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3055
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d29a7fadb1f47d3f5370d5b1eccc8a69c510597d58478dd78798440ba68baf96
|
3 |
size 3055
|