Upload 11 files
Browse files- adapter_config.json +8 -7
- adapter_model.safetensors +1 -1
- optimizer.pt +2 -2
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- special_tokens_map.json +1 -7
- tokenizer.json +1 -1
- tokenizer_config.json +1 -1
- trainer_state.json +507 -507
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -9,8 +9,8 @@
|
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
"loftq_config": {},
|
12 |
-
"lora_alpha":
|
13 |
-
"lora_dropout": 0.
|
14 |
"megatron_config": null,
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
@@ -19,14 +19,15 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"v_proj",
|
24 |
-
"gate_proj",
|
25 |
"o_proj",
|
26 |
"k_proj",
|
27 |
-
"
|
28 |
-
"
|
|
|
|
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
|
|
31 |
"use_rslora": false
|
32 |
}
|
|
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
"megatron_config": null,
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"up_proj",
|
|
|
|
|
23 |
"o_proj",
|
24 |
"k_proj",
|
25 |
+
"v_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"q_proj",
|
28 |
+
"down_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
+
"use_dora": false,
|
32 |
"use_rslora": false
|
33 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100059752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30bab0b9dea1c7c75134a24b6a620a1446e251bbb44dacb18c40e28be1c0e457
|
3 |
size 100059752
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cce6610dd72225566912eb7bb7977b31fa7419fa47b1ecefb9b9623ee31783a
|
3 |
+
size 200250234
|
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 sha256:9ad8827bfa520afa6dc600912d89b46d095ceb0366d1f186df32cb28e1d43884
|
3 |
size 14244
|
scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19bcbcfd505eb4fc1a12c7d832a77268d82b4a9b82157e01d48b5fb1cf5fbcc1
|
3 |
size 1064
|
special_tokens_map.json
CHANGED
@@ -17,13 +17,7 @@
|
|
17 |
"rstrip": false,
|
18 |
"single_word": false
|
19 |
},
|
20 |
-
"pad_token":
|
21 |
-
"content": "<pad>",
|
22 |
-
"lstrip": false,
|
23 |
-
"normalized": false,
|
24 |
-
"rstrip": false,
|
25 |
-
"single_word": false
|
26 |
-
},
|
27 |
"unk_token": {
|
28 |
"content": "<unk>",
|
29 |
"lstrip": false,
|
|
|
17 |
"rstrip": false,
|
18 |
"single_word": false
|
19 |
},
|
20 |
+
"pad_token": "<eos>",
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"unk_token": {
|
22 |
"content": "<unk>",
|
23 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17478028
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f121dcf9b0ee3f768a249f3ad6b547c972b9a90bcd9556ee4aea5ebc7a2179b2
|
3 |
size 17478028
|
tokenizer_config.json
CHANGED
@@ -61,7 +61,7 @@
|
|
61 |
"eos_token": "<eos>",
|
62 |
"legacy": null,
|
63 |
"model_max_length": 1000000000000000019884624838656,
|
64 |
-
"pad_token": "<
|
65 |
"sp_model_kwargs": {},
|
66 |
"spaces_between_special_tokens": false,
|
67 |
"tokenizer_class": "GemmaTokenizer",
|
|
|
61 |
"eos_token": "<eos>",
|
62 |
"legacy": null,
|
63 |
"model_max_length": 1000000000000000019884624838656,
|
64 |
+
"pad_token": "<eos>",
|
65 |
"sp_model_kwargs": {},
|
66 |
"spaces_between_special_tokens": false,
|
67 |
"tokenizer_class": "GemmaTokenizer",
|
trainer_state.json
CHANGED
@@ -1,721 +1,721 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
-
"epoch":
|
13 |
-
"grad_norm":
|
14 |
-
"learning_rate": 0.
|
15 |
-
"loss":
|
16 |
-
"step":
|
17 |
},
|
18 |
{
|
19 |
-
"epoch":
|
20 |
-
"grad_norm":
|
21 |
"learning_rate": 0.0002,
|
22 |
-
"loss":
|
23 |
-
"step":
|
24 |
},
|
25 |
{
|
26 |
-
"epoch":
|
27 |
-
"grad_norm":
|
28 |
-
"learning_rate": 0.
|
29 |
-
"loss":
|
30 |
-
"step":
|
31 |
},
|
32 |
{
|
33 |
-
"epoch":
|
34 |
-
"grad_norm":
|
35 |
-
"learning_rate": 0.
|
36 |
-
"loss":
|
37 |
-
"step":
|
38 |
},
|
39 |
{
|
40 |
-
"epoch":
|
41 |
-
"grad_norm":
|
42 |
-
"learning_rate": 0.
|
43 |
-
"loss":
|
44 |
-
"step":
|
45 |
},
|
46 |
{
|
47 |
-
"epoch":
|
48 |
-
"grad_norm":
|
49 |
-
"learning_rate": 0.
|
50 |
-
"loss":
|
51 |
-
"step":
|
52 |
},
|
53 |
{
|
54 |
-
"epoch":
|
55 |
-
"grad_norm":
|
56 |
-
"learning_rate": 0.
|
57 |
-
"loss":
|
58 |
-
"step":
|
59 |
},
|
60 |
{
|
61 |
-
"epoch":
|
62 |
-
"grad_norm":
|
63 |
-
"learning_rate": 0.
|
64 |
-
"loss":
|
65 |
-
"step":
|
66 |
},
|
67 |
{
|
68 |
-
"epoch":
|
69 |
-
"grad_norm":
|
70 |
-
"learning_rate": 0.
|
71 |
-
"loss":
|
72 |
-
"step":
|
73 |
},
|
74 |
{
|
75 |
-
"epoch":
|
76 |
-
"grad_norm":
|
77 |
-
"learning_rate": 0.
|
78 |
-
"loss":
|
79 |
-
"step":
|
80 |
},
|
81 |
{
|
82 |
-
"epoch":
|
83 |
-
"grad_norm":
|
84 |
-
"learning_rate": 0.
|
85 |
-
"loss":
|
86 |
-
"step":
|
87 |
},
|
88 |
{
|
89 |
-
"epoch":
|
90 |
-
"grad_norm":
|
91 |
-
"learning_rate": 0.
|
92 |
-
"loss":
|
93 |
-
"step":
|
94 |
},
|
95 |
{
|
96 |
-
"epoch":
|
97 |
-
"grad_norm":
|
98 |
-
"learning_rate": 0.
|
99 |
-
"loss": 0.
|
100 |
-
"step":
|
101 |
},
|
102 |
{
|
103 |
-
"epoch": 14
|
104 |
-
"grad_norm":
|
105 |
-
"learning_rate": 0.
|
106 |
-
"loss": 0.
|
107 |
-
"step":
|
108 |
},
|
109 |
{
|
110 |
-
"epoch":
|
111 |
-
"grad_norm":
|
112 |
-
"learning_rate": 0.
|
113 |
-
"loss": 0.
|
114 |
-
"step":
|
115 |
},
|
116 |
{
|
117 |
-
"epoch":
|
118 |
-
"grad_norm":
|
119 |
-
"learning_rate": 0.
|
120 |
-
"loss": 0.
|
121 |
-
"step":
|
122 |
},
|
123 |
{
|
124 |
-
"epoch":
|
125 |
-
"grad_norm":
|
126 |
-
"learning_rate": 0.
|
127 |
-
"loss": 0.
|
128 |
-
"step":
|
129 |
},
|
130 |
{
|
131 |
-
"epoch":
|
132 |
-
"grad_norm":
|
133 |
-
"learning_rate": 0.
|
134 |
-
"loss": 0.
|
135 |
-
"step":
|
136 |
},
|
137 |
{
|
138 |
-
"epoch":
|
139 |
-
"grad_norm": 0.
|
140 |
-
"learning_rate": 0.
|
141 |
-
"loss": 0.
|
142 |
-
"step":
|
143 |
},
|
144 |
{
|
145 |
-
"epoch":
|
146 |
-
"grad_norm":
|
147 |
-
"learning_rate": 0.
|
148 |
-
"loss": 0.
|
149 |
-
"step":
|
150 |
},
|
151 |
{
|
152 |
-
"epoch":
|
153 |
-
"grad_norm":
|
154 |
-
"learning_rate": 0.
|
155 |
-
"loss": 0.
|
156 |
-
"step":
|
157 |
},
|
158 |
{
|
159 |
-
"epoch":
|
160 |
-
"grad_norm":
|
161 |
-
"learning_rate": 0.
|
162 |
-
"loss": 0.
|
163 |
-
"step":
|
164 |
},
|
165 |
{
|
166 |
-
"epoch":
|
167 |
-
"grad_norm":
|
168 |
-
"learning_rate": 0.
|
169 |
-
"loss": 0.
|
170 |
-
"step":
|
171 |
},
|
172 |
{
|
173 |
-
"epoch":
|
174 |
-
"grad_norm":
|
175 |
-
"learning_rate": 0.
|
176 |
-
"loss": 0.
|
177 |
-
"step":
|
178 |
},
|
179 |
{
|
180 |
-
"epoch":
|
181 |
-
"grad_norm":
|
182 |
-
"learning_rate": 0.
|
183 |
-
"loss": 0.
|
184 |
-
"step":
|
185 |
},
|
186 |
{
|
187 |
-
"epoch":
|
188 |
-
"grad_norm":
|
189 |
-
"learning_rate": 0.
|
190 |
-
"loss": 0.
|
191 |
-
"step":
|
192 |
},
|
193 |
{
|
194 |
-
"epoch":
|
195 |
-
"grad_norm":
|
196 |
-
"learning_rate": 0.
|
197 |
-
"loss": 0.
|
198 |
-
"step":
|
199 |
},
|
200 |
{
|
201 |
-
"epoch":
|
202 |
-
"grad_norm":
|
203 |
-
"learning_rate": 0.
|
204 |
-
"loss": 0.
|
205 |
-
"step":
|
206 |
},
|
207 |
{
|
208 |
-
"epoch":
|
209 |
-
"grad_norm":
|
210 |
-
"learning_rate": 0.
|
211 |
-
"loss": 0.
|
212 |
-
"step":
|
213 |
},
|
214 |
{
|
215 |
-
"epoch":
|
216 |
-
"grad_norm":
|
217 |
-
"learning_rate": 0.
|
218 |
-
"loss": 0.
|
219 |
-
"step":
|
220 |
},
|
221 |
{
|
222 |
-
"epoch":
|
223 |
-
"grad_norm":
|
224 |
-
"learning_rate": 0.
|
225 |
-
"loss": 0.
|
226 |
-
"step":
|
227 |
},
|
228 |
{
|
229 |
-
"epoch":
|
230 |
-
"grad_norm":
|
231 |
-
"learning_rate": 0.
|
232 |
-
"loss": 0.
|
233 |
-
"step":
|
234 |
},
|
235 |
{
|
236 |
-
"epoch":
|
237 |
-
"grad_norm":
|
238 |
-
"learning_rate": 0.
|
239 |
-
"loss": 0.
|
240 |
-
"step":
|
241 |
},
|
242 |
{
|
243 |
-
"epoch":
|
244 |
-
"grad_norm":
|
245 |
-
"learning_rate": 0.
|
246 |
-
"loss": 0.
|
247 |
-
"step":
|
248 |
},
|
249 |
{
|
250 |
-
"epoch":
|
251 |
-
"grad_norm":
|
252 |
-
"learning_rate": 0.
|
253 |
-
"loss": 0.
|
254 |
-
"step":
|
255 |
},
|
256 |
{
|
257 |
-
"epoch":
|
258 |
-
"grad_norm":
|
259 |
-
"learning_rate": 0.
|
260 |
-
"loss": 0.
|
261 |
-
"step":
|
262 |
},
|
263 |
{
|
264 |
-
"epoch":
|
265 |
-
"grad_norm":
|
266 |
-
"learning_rate": 0.
|
267 |
-
"loss": 0.
|
268 |
-
"step":
|
269 |
},
|
270 |
{
|
271 |
-
"epoch":
|
272 |
-
"grad_norm":
|
273 |
-
"learning_rate": 0.
|
274 |
-
"loss": 0.
|
275 |
-
"step":
|
276 |
},
|
277 |
{
|
278 |
-
"epoch":
|
279 |
-
"grad_norm":
|
280 |
-
"learning_rate": 0.
|
281 |
-
"loss": 0.
|
282 |
-
"step":
|
283 |
},
|
284 |
{
|
285 |
-
"epoch":
|
286 |
-
"grad_norm":
|
287 |
-
"learning_rate": 0.
|
288 |
-
"loss": 0.
|
289 |
-
"step":
|
290 |
},
|
291 |
{
|
292 |
-
"epoch":
|
293 |
-
"grad_norm":
|
294 |
-
"learning_rate": 0.
|
295 |
-
"loss": 0.
|
296 |
-
"step":
|
297 |
},
|
298 |
{
|
299 |
-
"epoch":
|
300 |
-
"grad_norm":
|
301 |
-
"learning_rate": 0.
|
302 |
-
"loss": 0.
|
303 |
-
"step":
|
304 |
},
|
305 |
{
|
306 |
-
"epoch":
|
307 |
-
"grad_norm":
|
308 |
-
"learning_rate": 0.
|
309 |
-
"loss": 0.
|
310 |
-
"step":
|
311 |
},
|
312 |
{
|
313 |
-
"epoch":
|
314 |
-
"grad_norm":
|
315 |
-
"learning_rate": 0.
|
316 |
-
"loss": 0.
|
317 |
-
"step":
|
318 |
},
|
319 |
{
|
320 |
-
"epoch":
|
321 |
-
"grad_norm":
|
322 |
-
"learning_rate": 0.
|
323 |
-
"loss": 0.
|
324 |
-
"step":
|
325 |
},
|
326 |
{
|
327 |
-
"epoch":
|
328 |
-
"grad_norm":
|
329 |
-
"learning_rate": 0.
|
330 |
-
"loss": 0.
|
331 |
-
"step":
|
332 |
},
|
333 |
{
|
334 |
-
"epoch":
|
335 |
-
"grad_norm":
|
336 |
-
"learning_rate": 0.
|
337 |
-
"loss": 0.
|
338 |
-
"step":
|
339 |
},
|
340 |
{
|
341 |
-
"epoch":
|
342 |
-
"grad_norm":
|
343 |
-
"learning_rate": 0.
|
344 |
-
"loss": 0.
|
345 |
-
"step":
|
346 |
},
|
347 |
{
|
348 |
-
"epoch":
|
349 |
-
"grad_norm":
|
350 |
-
"learning_rate": 0.
|
351 |
-
"loss": 0.
|
352 |
-
"step":
|
353 |
},
|
354 |
{
|
355 |
-
"epoch":
|
356 |
-
"grad_norm":
|
357 |
-
"learning_rate": 0.
|
358 |
-
"loss": 0.
|
359 |
-
"step":
|
360 |
},
|
361 |
{
|
362 |
-
"epoch":
|
363 |
-
"grad_norm":
|
364 |
-
"learning_rate": 0.
|
365 |
-
"loss": 0.
|
366 |
-
"step":
|
367 |
},
|
368 |
{
|
369 |
-
"epoch":
|
370 |
-
"grad_norm":
|
371 |
-
"learning_rate": 0.
|
372 |
-
"loss": 0.
|
373 |
-
"step":
|
374 |
},
|
375 |
{
|
376 |
-
"epoch":
|
377 |
-
"grad_norm":
|
378 |
-
"learning_rate":
|
379 |
-
"loss": 0.
|
380 |
-
"step":
|
381 |
},
|
382 |
{
|
383 |
-
"epoch":
|
384 |
-
"grad_norm":
|
385 |
-
"learning_rate":
|
386 |
-
"loss": 0.
|
387 |
-
"step":
|
388 |
},
|
389 |
{
|
390 |
-
"epoch":
|
391 |
-
"grad_norm":
|
392 |
-
"learning_rate":
|
393 |
-
"loss": 0.
|
394 |
-
"step":
|
395 |
},
|
396 |
{
|
397 |
-
"epoch":
|
398 |
-
"grad_norm":
|
399 |
-
"learning_rate":
|
400 |
-
"loss": 0.
|
401 |
-
"step":
|
402 |
},
|
403 |
{
|
404 |
-
"epoch":
|
405 |
-
"grad_norm":
|
406 |
-
"learning_rate":
|
407 |
-
"loss": 0.
|
408 |
-
"step":
|
409 |
},
|
410 |
{
|
411 |
-
"epoch":
|
412 |
-
"grad_norm":
|
413 |
-
"learning_rate":
|
414 |
-
"loss": 0.
|
415 |
-
"step":
|
416 |
},
|
417 |
{
|
418 |
-
"epoch":
|
419 |
-
"grad_norm":
|
420 |
-
"learning_rate":
|
421 |
-
"loss": 0.
|
422 |
-
"step":
|
423 |
},
|
424 |
{
|
425 |
-
"epoch":
|
426 |
-
"grad_norm":
|
427 |
-
"learning_rate":
|
428 |
-
"loss": 0.
|
429 |
-
"step":
|
430 |
},
|
431 |
{
|
432 |
-
"epoch":
|
433 |
-
"grad_norm":
|
434 |
-
"learning_rate":
|
435 |
-
"loss": 0.
|
436 |
-
"step":
|
437 |
},
|
438 |
{
|
439 |
-
"epoch":
|
440 |
-
"grad_norm":
|
441 |
-
"learning_rate":
|
442 |
-
"loss": 0.
|
443 |
-
"step":
|
444 |
},
|
445 |
{
|
446 |
-
"epoch":
|
447 |
-
"grad_norm":
|
448 |
-
"learning_rate":
|
449 |
-
"loss": 0.
|
450 |
-
"step":
|
451 |
},
|
452 |
{
|
453 |
-
"epoch":
|
454 |
-
"grad_norm":
|
455 |
-
"learning_rate":
|
456 |
-
"loss": 0.
|
457 |
-
"step":
|
458 |
},
|
459 |
{
|
460 |
-
"epoch":
|
461 |
-
"grad_norm":
|
462 |
-
"learning_rate":
|
463 |
-
"loss": 0.
|
464 |
-
"step":
|
465 |
},
|
466 |
{
|
467 |
-
"epoch":
|
468 |
-
"grad_norm":
|
469 |
-
"learning_rate":
|
470 |
-
"loss": 0.
|
471 |
-
"step":
|
472 |
},
|
473 |
{
|
474 |
-
"epoch":
|
475 |
-
"grad_norm":
|
476 |
-
"learning_rate":
|
477 |
-
"loss": 0.
|
478 |
-
"step":
|
479 |
},
|
480 |
{
|
481 |
-
"epoch":
|
482 |
-
"grad_norm":
|
483 |
-
"learning_rate":
|
484 |
-
"loss": 0.
|
485 |
-
"step":
|
486 |
},
|
487 |
{
|
488 |
-
"epoch":
|
489 |
-
"grad_norm":
|
490 |
-
"learning_rate":
|
491 |
-
"loss": 0.
|
492 |
-
"step":
|
493 |
},
|
494 |
{
|
495 |
-
"epoch":
|
496 |
-
"grad_norm":
|
497 |
-
"learning_rate":
|
498 |
-
"loss": 0.
|
499 |
-
"step":
|
500 |
},
|
501 |
{
|
502 |
-
"epoch":
|
503 |
-
"grad_norm":
|
504 |
-
"learning_rate":
|
505 |
-
"loss": 0.
|
506 |
-
"step":
|
507 |
},
|
508 |
{
|
509 |
-
"epoch":
|
510 |
-
"grad_norm":
|
511 |
-
"learning_rate":
|
512 |
-
"loss": 0.
|
513 |
-
"step":
|
514 |
},
|
515 |
{
|
516 |
-
"epoch":
|
517 |
-
"grad_norm":
|
518 |
-
"learning_rate":
|
519 |
-
"loss": 0.
|
520 |
-
"step":
|
521 |
},
|
522 |
{
|
523 |
-
"epoch":
|
524 |
-
"grad_norm":
|
525 |
-
"learning_rate":
|
526 |
-
"loss": 0.
|
527 |
-
"step":
|
528 |
},
|
529 |
{
|
530 |
-
"epoch":
|
531 |
-
"grad_norm":
|
532 |
-
"learning_rate":
|
533 |
-
"loss": 0.
|
534 |
-
"step":
|
535 |
},
|
536 |
{
|
537 |
-
"epoch":
|
538 |
-
"grad_norm":
|
539 |
-
"learning_rate":
|
540 |
-
"loss": 0.
|
541 |
-
"step":
|
542 |
},
|
543 |
{
|
544 |
-
"epoch":
|
545 |
-
"grad_norm":
|
546 |
-
"learning_rate":
|
547 |
-
"loss": 0.
|
548 |
-
"step":
|
549 |
},
|
550 |
{
|
551 |
-
"epoch":
|
552 |
-
"grad_norm":
|
553 |
-
"learning_rate":
|
554 |
-
"loss": 0.
|
555 |
-
"step":
|
556 |
},
|
557 |
{
|
558 |
-
"epoch":
|
559 |
-
"grad_norm":
|
560 |
-
"learning_rate":
|
561 |
-
"loss": 0.
|
562 |
-
"step":
|
563 |
},
|
564 |
{
|
565 |
-
"epoch":
|
566 |
-
"grad_norm":
|
567 |
-
"learning_rate":
|
568 |
-
"loss": 0.
|
569 |
-
"step":
|
570 |
},
|
571 |
{
|
572 |
-
"epoch":
|
573 |
-
"grad_norm":
|
574 |
-
"learning_rate":
|
575 |
-
"loss": 0.
|
576 |
-
"step":
|
577 |
},
|
578 |
{
|
579 |
-
"epoch":
|
580 |
-
"grad_norm":
|
581 |
-
"learning_rate":
|
582 |
-
"loss": 0.
|
583 |
-
"step":
|
584 |
},
|
585 |
{
|
586 |
-
"epoch":
|
587 |
-
"grad_norm":
|
588 |
-
"learning_rate":
|
589 |
-
"loss": 0.
|
590 |
-
"step":
|
591 |
},
|
592 |
{
|
593 |
-
"epoch":
|
594 |
-
"grad_norm":
|
595 |
-
"learning_rate":
|
596 |
-
"loss": 0.
|
597 |
-
"step":
|
598 |
},
|
599 |
{
|
600 |
-
"epoch":
|
601 |
-
"grad_norm":
|
602 |
-
"learning_rate":
|
603 |
-
"loss": 0.
|
604 |
-
"step":
|
605 |
},
|
606 |
{
|
607 |
-
"epoch":
|
608 |
-
"grad_norm":
|
609 |
-
"learning_rate":
|
610 |
-
"loss": 0.
|
611 |
-
"step":
|
612 |
},
|
613 |
{
|
614 |
-
"epoch":
|
615 |
-
"grad_norm":
|
616 |
-
"learning_rate":
|
617 |
-
"loss": 0.
|
618 |
-
"step":
|
619 |
},
|
620 |
{
|
621 |
-
"epoch":
|
622 |
-
"grad_norm":
|
623 |
-
"learning_rate":
|
624 |
-
"loss": 0.
|
625 |
-
"step":
|
626 |
},
|
627 |
{
|
628 |
-
"epoch":
|
629 |
-
"grad_norm":
|
630 |
-
"learning_rate":
|
631 |
-
"loss": 0.
|
632 |
-
"step":
|
633 |
},
|
634 |
{
|
635 |
-
"epoch":
|
636 |
-
"grad_norm":
|
637 |
-
"learning_rate":
|
638 |
-
"loss": 0.
|
639 |
-
"step":
|
640 |
},
|
641 |
{
|
642 |
-
"epoch":
|
643 |
-
"grad_norm":
|
644 |
-
"learning_rate":
|
645 |
-
"loss": 0.
|
646 |
-
"step":
|
647 |
},
|
648 |
{
|
649 |
-
"epoch":
|
650 |
-
"grad_norm":
|
651 |
-
"learning_rate":
|
652 |
-
"loss": 0.
|
653 |
-
"step":
|
654 |
},
|
655 |
{
|
656 |
-
"epoch":
|
657 |
-
"grad_norm":
|
658 |
-
"learning_rate":
|
659 |
-
"loss": 0.
|
660 |
-
"step":
|
661 |
},
|
662 |
{
|
663 |
-
"epoch":
|
664 |
-
"grad_norm":
|
665 |
-
"learning_rate":
|
666 |
-
"loss": 0.
|
667 |
-
"step":
|
668 |
},
|
669 |
{
|
670 |
-
"epoch":
|
671 |
-
"grad_norm":
|
672 |
-
"learning_rate":
|
673 |
-
"loss": 0.
|
674 |
-
"step":
|
675 |
},
|
676 |
{
|
677 |
-
"epoch":
|
678 |
-
"grad_norm":
|
679 |
-
"learning_rate":
|
680 |
-
"loss": 0.
|
681 |
-
"step":
|
682 |
},
|
683 |
{
|
684 |
-
"epoch":
|
685 |
-
"grad_norm":
|
686 |
-
"learning_rate":
|
687 |
-
"loss": 0.
|
688 |
-
"step":
|
689 |
},
|
690 |
{
|
691 |
-
"epoch":
|
692 |
-
"grad_norm":
|
693 |
-
"learning_rate":
|
694 |
-
"loss": 0.
|
695 |
-
"step":
|
696 |
},
|
697 |
{
|
698 |
-
"epoch":
|
699 |
-
"grad_norm":
|
700 |
-
"learning_rate":
|
701 |
-
"loss": 0.
|
702 |
-
"step":
|
703 |
},
|
704 |
{
|
705 |
-
"epoch":
|
706 |
-
"grad_norm":
|
707 |
-
"learning_rate":
|
708 |
-
"loss": 0.
|
709 |
-
"step":
|
710 |
}
|
711 |
],
|
712 |
-
"logging_steps":
|
713 |
-
"max_steps":
|
714 |
"num_input_tokens_seen": 0,
|
715 |
-
"num_train_epochs":
|
716 |
-
"save_steps":
|
717 |
-
"total_flos":
|
718 |
-
"train_batch_size":
|
719 |
"trial_name": null,
|
720 |
"trial_params": null
|
721 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.113590263691684,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.08,
|
13 |
+
"grad_norm": 16.835479736328125,
|
14 |
+
"learning_rate": 0.0002,
|
15 |
+
"loss": 3.766,
|
16 |
+
"step": 10
|
17 |
},
|
18 |
{
|
19 |
+
"epoch": 0.16,
|
20 |
+
"grad_norm": 15.441985130310059,
|
21 |
"learning_rate": 0.0002,
|
22 |
+
"loss": 1.4106,
|
23 |
+
"step": 20
|
24 |
},
|
25 |
{
|
26 |
+
"epoch": 0.24,
|
27 |
+
"grad_norm": 13.51206111907959,
|
28 |
+
"learning_rate": 0.0002,
|
29 |
+
"loss": 1.1355,
|
30 |
+
"step": 30
|
31 |
},
|
32 |
{
|
33 |
+
"epoch": 0.32,
|
34 |
+
"grad_norm": 14.920987129211426,
|
35 |
+
"learning_rate": 0.0002,
|
36 |
+
"loss": 0.9941,
|
37 |
+
"step": 40
|
38 |
},
|
39 |
{
|
40 |
+
"epoch": 0.41,
|
41 |
+
"grad_norm": 8.289106369018555,
|
42 |
+
"learning_rate": 0.0002,
|
43 |
+
"loss": 0.8887,
|
44 |
+
"step": 50
|
45 |
},
|
46 |
{
|
47 |
+
"epoch": 0.49,
|
48 |
+
"grad_norm": 8.003510475158691,
|
49 |
+
"learning_rate": 0.0002,
|
50 |
+
"loss": 0.8275,
|
51 |
+
"step": 60
|
52 |
},
|
53 |
{
|
54 |
+
"epoch": 0.57,
|
55 |
+
"grad_norm": 7.877600193023682,
|
56 |
+
"learning_rate": 0.0002,
|
57 |
+
"loss": 0.798,
|
58 |
+
"step": 70
|
59 |
},
|
60 |
{
|
61 |
+
"epoch": 0.65,
|
62 |
+
"grad_norm": 2.8833744525909424,
|
63 |
+
"learning_rate": 0.0002,
|
64 |
+
"loss": 0.8464,
|
65 |
+
"step": 80
|
66 |
},
|
67 |
{
|
68 |
+
"epoch": 0.73,
|
69 |
+
"grad_norm": 8.206995964050293,
|
70 |
+
"learning_rate": 0.0002,
|
71 |
+
"loss": 0.7849,
|
72 |
+
"step": 90
|
73 |
},
|
74 |
{
|
75 |
+
"epoch": 0.81,
|
76 |
+
"grad_norm": 7.678927421569824,
|
77 |
+
"learning_rate": 0.0002,
|
78 |
+
"loss": 0.7184,
|
79 |
+
"step": 100
|
80 |
},
|
81 |
{
|
82 |
+
"epoch": 0.89,
|
83 |
+
"grad_norm": 7.089763164520264,
|
84 |
+
"learning_rate": 0.0002,
|
85 |
+
"loss": 0.7099,
|
86 |
+
"step": 110
|
87 |
},
|
88 |
{
|
89 |
+
"epoch": 0.97,
|
90 |
+
"grad_norm": 5.643054485321045,
|
91 |
+
"learning_rate": 0.0002,
|
92 |
+
"loss": 0.6989,
|
93 |
+
"step": 120
|
94 |
},
|
95 |
{
|
96 |
+
"epoch": 1.05,
|
97 |
+
"grad_norm": 7.985189914703369,
|
98 |
+
"learning_rate": 0.0002,
|
99 |
+
"loss": 0.6394,
|
100 |
+
"step": 130
|
101 |
},
|
102 |
{
|
103 |
+
"epoch": 1.14,
|
104 |
+
"grad_norm": 7.676026344299316,
|
105 |
+
"learning_rate": 0.0002,
|
106 |
+
"loss": 0.5882,
|
107 |
+
"step": 140
|
108 |
},
|
109 |
{
|
110 |
+
"epoch": 1.22,
|
111 |
+
"grad_norm": 8.714900016784668,
|
112 |
+
"learning_rate": 0.0002,
|
113 |
+
"loss": 0.5707,
|
114 |
+
"step": 150
|
115 |
},
|
116 |
{
|
117 |
+
"epoch": 1.3,
|
118 |
+
"grad_norm": 5.221066474914551,
|
119 |
+
"learning_rate": 0.0002,
|
120 |
+
"loss": 0.5345,
|
121 |
+
"step": 160
|
122 |
},
|
123 |
{
|
124 |
+
"epoch": 1.38,
|
125 |
+
"grad_norm": 9.008663177490234,
|
126 |
+
"learning_rate": 0.0002,
|
127 |
+
"loss": 0.5568,
|
128 |
+
"step": 170
|
129 |
},
|
130 |
{
|
131 |
+
"epoch": 1.46,
|
132 |
+
"grad_norm": 6.81847620010376,
|
133 |
+
"learning_rate": 0.0002,
|
134 |
+
"loss": 0.5249,
|
135 |
+
"step": 180
|
136 |
},
|
137 |
{
|
138 |
+
"epoch": 1.54,
|
139 |
+
"grad_norm": 0.8458152413368225,
|
140 |
+
"learning_rate": 0.0002,
|
141 |
+
"loss": 0.491,
|
142 |
+
"step": 190
|
143 |
},
|
144 |
{
|
145 |
+
"epoch": 1.62,
|
146 |
+
"grad_norm": 7.401742935180664,
|
147 |
+
"learning_rate": 0.0002,
|
148 |
+
"loss": 0.514,
|
149 |
+
"step": 200
|
150 |
},
|
151 |
{
|
152 |
+
"epoch": 1.7,
|
153 |
+
"grad_norm": 7.641871452331543,
|
154 |
+
"learning_rate": 0.0002,
|
155 |
+
"loss": 0.5557,
|
156 |
+
"step": 210
|
157 |
},
|
158 |
{
|
159 |
+
"epoch": 1.78,
|
160 |
+
"grad_norm": 5.442512512207031,
|
161 |
+
"learning_rate": 0.0002,
|
162 |
+
"loss": 0.5314,
|
163 |
+
"step": 220
|
164 |
},
|
165 |
{
|
166 |
+
"epoch": 1.87,
|
167 |
+
"grad_norm": 8.104277610778809,
|
168 |
+
"learning_rate": 0.0002,
|
169 |
+
"loss": 0.4907,
|
170 |
+
"step": 230
|
171 |
},
|
172 |
{
|
173 |
+
"epoch": 1.95,
|
174 |
+
"grad_norm": 6.416436195373535,
|
175 |
+
"learning_rate": 0.0002,
|
176 |
+
"loss": 0.5092,
|
177 |
+
"step": 240
|
178 |
},
|
179 |
{
|
180 |
+
"epoch": 2.03,
|
181 |
+
"grad_norm": 3.008178949356079,
|
182 |
+
"learning_rate": 0.0002,
|
183 |
+
"loss": 0.4633,
|
184 |
+
"step": 250
|
185 |
},
|
186 |
{
|
187 |
+
"epoch": 2.11,
|
188 |
+
"grad_norm": 9.349288940429688,
|
189 |
+
"learning_rate": 0.0002,
|
190 |
+
"loss": 0.378,
|
191 |
+
"step": 260
|
192 |
},
|
193 |
{
|
194 |
+
"epoch": 2.19,
|
195 |
+
"grad_norm": 6.459526062011719,
|
196 |
+
"learning_rate": 0.0002,
|
197 |
+
"loss": 0.3765,
|
198 |
+
"step": 270
|
199 |
},
|
200 |
{
|
201 |
+
"epoch": 2.27,
|
202 |
+
"grad_norm": 7.634103775024414,
|
203 |
+
"learning_rate": 0.0002,
|
204 |
+
"loss": 0.3819,
|
205 |
+
"step": 280
|
206 |
},
|
207 |
{
|
208 |
+
"epoch": 2.35,
|
209 |
+
"grad_norm": 9.084547996520996,
|
210 |
+
"learning_rate": 0.0002,
|
211 |
+
"loss": 0.3703,
|
212 |
+
"step": 290
|
213 |
},
|
214 |
{
|
215 |
+
"epoch": 2.43,
|
216 |
+
"grad_norm": 2.535707473754883,
|
217 |
+
"learning_rate": 0.0002,
|
218 |
+
"loss": 0.3501,
|
219 |
+
"step": 300
|
220 |
},
|
221 |
{
|
222 |
+
"epoch": 2.52,
|
223 |
+
"grad_norm": 7.023160457611084,
|
224 |
+
"learning_rate": 0.0002,
|
225 |
+
"loss": 0.3491,
|
226 |
+
"step": 310
|
227 |
},
|
228 |
{
|
229 |
+
"epoch": 2.6,
|
230 |
+
"grad_norm": 9.15241527557373,
|
231 |
+
"learning_rate": 0.0002,
|
232 |
+
"loss": 0.3592,
|
233 |
+
"step": 320
|
234 |
},
|
235 |
{
|
236 |
+
"epoch": 2.68,
|
237 |
+
"grad_norm": 3.0726027488708496,
|
238 |
+
"learning_rate": 0.0002,
|
239 |
+
"loss": 0.3641,
|
240 |
+
"step": 330
|
241 |
},
|
242 |
{
|
243 |
+
"epoch": 2.76,
|
244 |
+
"grad_norm": 5.8857879638671875,
|
245 |
+
"learning_rate": 0.0002,
|
246 |
+
"loss": 0.3553,
|
247 |
+
"step": 340
|
248 |
},
|
249 |
{
|
250 |
+
"epoch": 2.84,
|
251 |
+
"grad_norm": 8.316734313964844,
|
252 |
+
"learning_rate": 0.0002,
|
253 |
+
"loss": 0.36,
|
254 |
+
"step": 350
|
255 |
},
|
256 |
{
|
257 |
+
"epoch": 2.92,
|
258 |
+
"grad_norm": 3.8568618297576904,
|
259 |
+
"learning_rate": 0.0002,
|
260 |
+
"loss": 0.3607,
|
261 |
+
"step": 360
|
262 |
},
|
263 |
{
|
264 |
+
"epoch": 3.0,
|
265 |
+
"grad_norm": 6.664178848266602,
|
266 |
+
"learning_rate": 0.0002,
|
267 |
+
"loss": 0.3716,
|
268 |
+
"step": 370
|
269 |
},
|
270 |
{
|
271 |
+
"epoch": 3.08,
|
272 |
+
"grad_norm": 9.07357406616211,
|
273 |
+
"learning_rate": 0.0002,
|
274 |
+
"loss": 0.242,
|
275 |
+
"step": 380
|
276 |
},
|
277 |
{
|
278 |
+
"epoch": 3.16,
|
279 |
+
"grad_norm": 4.3498921394348145,
|
280 |
+
"learning_rate": 0.0002,
|
281 |
+
"loss": 0.2588,
|
282 |
+
"step": 390
|
283 |
},
|
284 |
{
|
285 |
+
"epoch": 3.25,
|
286 |
+
"grad_norm": 6.539889812469482,
|
287 |
+
"learning_rate": 0.0002,
|
288 |
+
"loss": 0.2523,
|
289 |
+
"step": 400
|
290 |
},
|
291 |
{
|
292 |
+
"epoch": 3.33,
|
293 |
+
"grad_norm": 8.80722427368164,
|
294 |
+
"learning_rate": 0.0002,
|
295 |
+
"loss": 0.2388,
|
296 |
+
"step": 410
|
297 |
},
|
298 |
{
|
299 |
+
"epoch": 3.41,
|
300 |
+
"grad_norm": 5.052772521972656,
|
301 |
+
"learning_rate": 0.0002,
|
302 |
+
"loss": 0.2524,
|
303 |
+
"step": 420
|
304 |
},
|
305 |
{
|
306 |
+
"epoch": 3.49,
|
307 |
+
"grad_norm": 5.22416877746582,
|
308 |
+
"learning_rate": 0.0002,
|
309 |
+
"loss": 0.2452,
|
310 |
+
"step": 430
|
311 |
},
|
312 |
{
|
313 |
+
"epoch": 3.57,
|
314 |
+
"grad_norm": 8.989995956420898,
|
315 |
+
"learning_rate": 0.0002,
|
316 |
+
"loss": 0.2558,
|
317 |
+
"step": 440
|
318 |
},
|
319 |
{
|
320 |
+
"epoch": 3.65,
|
321 |
+
"grad_norm": 2.628777027130127,
|
322 |
+
"learning_rate": 0.0002,
|
323 |
+
"loss": 0.2449,
|
324 |
+
"step": 450
|
325 |
},
|
326 |
{
|
327 |
+
"epoch": 3.73,
|
328 |
+
"grad_norm": 5.890882968902588,
|
329 |
+
"learning_rate": 0.0002,
|
330 |
+
"loss": 0.2591,
|
331 |
+
"step": 460
|
332 |
},
|
333 |
{
|
334 |
+
"epoch": 3.81,
|
335 |
+
"grad_norm": 8.577589988708496,
|
336 |
+
"learning_rate": 0.0002,
|
337 |
+
"loss": 0.2557,
|
338 |
+
"step": 470
|
339 |
},
|
340 |
{
|
341 |
+
"epoch": 3.89,
|
342 |
+
"grad_norm": 5.092458724975586,
|
343 |
+
"learning_rate": 0.0002,
|
344 |
+
"loss": 0.2603,
|
345 |
+
"step": 480
|
346 |
},
|
347 |
{
|
348 |
+
"epoch": 3.98,
|
349 |
+
"grad_norm": 5.97870397567749,
|
350 |
+
"learning_rate": 0.0002,
|
351 |
+
"loss": 0.2676,
|
352 |
+
"step": 490
|
353 |
},
|
354 |
{
|
355 |
+
"epoch": 4.06,
|
356 |
+
"grad_norm": 8.259415626525879,
|
357 |
+
"learning_rate": 0.0002,
|
358 |
+
"loss": 0.2051,
|
359 |
+
"step": 500
|
360 |
},
|
361 |
{
|
362 |
+
"epoch": 4.14,
|
363 |
+
"grad_norm": 7.2230072021484375,
|
364 |
+
"learning_rate": 0.0002,
|
365 |
+
"loss": 0.1467,
|
366 |
+
"step": 510
|
367 |
},
|
368 |
{
|
369 |
+
"epoch": 4.22,
|
370 |
+
"grad_norm": 6.01918888092041,
|
371 |
+
"learning_rate": 0.0002,
|
372 |
+
"loss": 0.1713,
|
373 |
+
"step": 520
|
374 |
},
|
375 |
{
|
376 |
+
"epoch": 4.3,
|
377 |
+
"grad_norm": 8.41965103149414,
|
378 |
+
"learning_rate": 0.0002,
|
379 |
+
"loss": 0.1803,
|
380 |
+
"step": 530
|
381 |
},
|
382 |
{
|
383 |
+
"epoch": 4.38,
|
384 |
+
"grad_norm": 4.342984676361084,
|
385 |
+
"learning_rate": 0.0002,
|
386 |
+
"loss": 0.1769,
|
387 |
+
"step": 540
|
388 |
},
|
389 |
{
|
390 |
+
"epoch": 4.46,
|
391 |
+
"grad_norm": 6.167740821838379,
|
392 |
+
"learning_rate": 0.0002,
|
393 |
+
"loss": 0.1763,
|
394 |
+
"step": 550
|
395 |
},
|
396 |
{
|
397 |
+
"epoch": 4.54,
|
398 |
+
"grad_norm": 8.30461597442627,
|
399 |
+
"learning_rate": 0.0002,
|
400 |
+
"loss": 0.1716,
|
401 |
+
"step": 560
|
402 |
},
|
403 |
{
|
404 |
+
"epoch": 4.62,
|
405 |
+
"grad_norm": 3.77854323387146,
|
406 |
+
"learning_rate": 0.0002,
|
407 |
+
"loss": 0.1679,
|
408 |
+
"step": 570
|
409 |
},
|
410 |
{
|
411 |
+
"epoch": 4.71,
|
412 |
+
"grad_norm": 5.807821273803711,
|
413 |
+
"learning_rate": 0.0002,
|
414 |
+
"loss": 0.1775,
|
415 |
+
"step": 580
|
416 |
},
|
417 |
{
|
418 |
+
"epoch": 4.79,
|
419 |
+
"grad_norm": 7.620412349700928,
|
420 |
+
"learning_rate": 0.0002,
|
421 |
+
"loss": 0.1769,
|
422 |
+
"step": 590
|
423 |
},
|
424 |
{
|
425 |
+
"epoch": 4.87,
|
426 |
+
"grad_norm": 6.027496814727783,
|
427 |
+
"learning_rate": 0.0002,
|
428 |
+
"loss": 0.1828,
|
429 |
+
"step": 600
|
430 |
},
|
431 |
{
|
432 |
+
"epoch": 4.95,
|
433 |
+
"grad_norm": 5.835544109344482,
|
434 |
+
"learning_rate": 0.0002,
|
435 |
+
"loss": 0.1783,
|
436 |
+
"step": 610
|
437 |
},
|
438 |
{
|
439 |
+
"epoch": 5.03,
|
440 |
+
"grad_norm": 7.455280780792236,
|
441 |
+
"learning_rate": 0.0002,
|
442 |
+
"loss": 0.1545,
|
443 |
+
"step": 620
|
444 |
},
|
445 |
{
|
446 |
+
"epoch": 5.11,
|
447 |
+
"grad_norm": 3.6531035900115967,
|
448 |
+
"learning_rate": 0.0002,
|
449 |
+
"loss": 0.1213,
|
450 |
+
"step": 630
|
451 |
},
|
452 |
{
|
453 |
+
"epoch": 5.19,
|
454 |
+
"grad_norm": 6.005002498626709,
|
455 |
+
"learning_rate": 0.0002,
|
456 |
+
"loss": 0.1211,
|
457 |
+
"step": 640
|
458 |
},
|
459 |
{
|
460 |
+
"epoch": 5.27,
|
461 |
+
"grad_norm": 8.0129976272583,
|
462 |
+
"learning_rate": 0.0002,
|
463 |
+
"loss": 0.1268,
|
464 |
+
"step": 650
|
465 |
},
|
466 |
{
|
467 |
+
"epoch": 5.35,
|
468 |
+
"grad_norm": 4.5181169509887695,
|
469 |
+
"learning_rate": 0.0002,
|
470 |
+
"loss": 0.1215,
|
471 |
+
"step": 660
|
472 |
},
|
473 |
{
|
474 |
+
"epoch": 5.44,
|
475 |
+
"grad_norm": 5.109263896942139,
|
476 |
+
"learning_rate": 0.0002,
|
477 |
+
"loss": 0.1264,
|
478 |
+
"step": 670
|
479 |
},
|
480 |
{
|
481 |
+
"epoch": 5.52,
|
482 |
+
"grad_norm": 7.003955364227295,
|
483 |
+
"learning_rate": 0.0002,
|
484 |
+
"loss": 0.1332,
|
485 |
+
"step": 680
|
486 |
},
|
487 |
{
|
488 |
+
"epoch": 5.6,
|
489 |
+
"grad_norm": 4.416803359985352,
|
490 |
+
"learning_rate": 0.0002,
|
491 |
+
"loss": 0.1333,
|
492 |
+
"step": 690
|
493 |
},
|
494 |
{
|
495 |
+
"epoch": 5.68,
|
496 |
+
"grad_norm": 4.775448322296143,
|
497 |
+
"learning_rate": 0.0002,
|
498 |
+
"loss": 0.1384,
|
499 |
+
"step": 700
|
500 |
},
|
501 |
{
|
502 |
+
"epoch": 5.76,
|
503 |
+
"grad_norm": 6.8711018562316895,
|
504 |
+
"learning_rate": 0.0002,
|
505 |
+
"loss": 0.1388,
|
506 |
+
"step": 710
|
507 |
},
|
508 |
{
|
509 |
+
"epoch": 5.84,
|
510 |
+
"grad_norm": 4.3299760818481445,
|
511 |
+
"learning_rate": 0.0002,
|
512 |
+
"loss": 0.1392,
|
513 |
+
"step": 720
|
514 |
},
|
515 |
{
|
516 |
+
"epoch": 5.92,
|
517 |
+
"grad_norm": 4.7512006759643555,
|
518 |
+
"learning_rate": 0.0002,
|
519 |
+
"loss": 0.1477,
|
520 |
+
"step": 730
|
521 |
},
|
522 |
{
|
523 |
+
"epoch": 6.0,
|
524 |
+
"grad_norm": 6.701217174530029,
|
525 |
+
"learning_rate": 0.0002,
|
526 |
+
"loss": 0.1401,
|
527 |
+
"step": 740
|
528 |
},
|
529 |
{
|
530 |
+
"epoch": 6.09,
|
531 |
+
"grad_norm": 4.163561820983887,
|
532 |
+
"learning_rate": 0.0002,
|
533 |
+
"loss": 0.099,
|
534 |
+
"step": 750
|
535 |
},
|
536 |
{
|
537 |
+
"epoch": 6.17,
|
538 |
+
"grad_norm": 4.784251689910889,
|
539 |
+
"learning_rate": 0.0002,
|
540 |
+
"loss": 0.1025,
|
541 |
+
"step": 760
|
542 |
},
|
543 |
{
|
544 |
+
"epoch": 6.25,
|
545 |
+
"grad_norm": 7.253482341766357,
|
546 |
+
"learning_rate": 0.0002,
|
547 |
+
"loss": 0.1019,
|
548 |
+
"step": 770
|
549 |
},
|
550 |
{
|
551 |
+
"epoch": 6.33,
|
552 |
+
"grad_norm": 4.389810085296631,
|
553 |
+
"learning_rate": 0.0002,
|
554 |
+
"loss": 0.1052,
|
555 |
+
"step": 780
|
556 |
},
|
557 |
{
|
558 |
+
"epoch": 6.41,
|
559 |
+
"grad_norm": 4.857180595397949,
|
560 |
+
"learning_rate": 0.0002,
|
561 |
+
"loss": 0.1065,
|
562 |
+
"step": 790
|
563 |
},
|
564 |
{
|
565 |
+
"epoch": 6.49,
|
566 |
+
"grad_norm": 6.876203536987305,
|
567 |
+
"learning_rate": 0.0002,
|
568 |
+
"loss": 0.1092,
|
569 |
+
"step": 800
|
570 |
},
|
571 |
{
|
572 |
+
"epoch": 6.57,
|
573 |
+
"grad_norm": 4.4614715576171875,
|
574 |
+
"learning_rate": 0.0002,
|
575 |
+
"loss": 0.112,
|
576 |
+
"step": 810
|
577 |
},
|
578 |
{
|
579 |
+
"epoch": 6.65,
|
580 |
+
"grad_norm": 5.019026756286621,
|
581 |
+
"learning_rate": 0.0002,
|
582 |
+
"loss": 0.1127,
|
583 |
+
"step": 820
|
584 |
},
|
585 |
{
|
586 |
+
"epoch": 6.73,
|
587 |
+
"grad_norm": 6.864689350128174,
|
588 |
+
"learning_rate": 0.0002,
|
589 |
+
"loss": 0.1131,
|
590 |
+
"step": 830
|
591 |
},
|
592 |
{
|
593 |
+
"epoch": 6.82,
|
594 |
+
"grad_norm": 4.057292938232422,
|
595 |
+
"learning_rate": 0.0002,
|
596 |
+
"loss": 0.113,
|
597 |
+
"step": 840
|
598 |
},
|
599 |
{
|
600 |
+
"epoch": 6.9,
|
601 |
+
"grad_norm": 4.780605792999268,
|
602 |
+
"learning_rate": 0.0002,
|
603 |
+
"loss": 0.1122,
|
604 |
+
"step": 850
|
605 |
},
|
606 |
{
|
607 |
+
"epoch": 6.98,
|
608 |
+
"grad_norm": 6.377821445465088,
|
609 |
+
"learning_rate": 0.0002,
|
610 |
+
"loss": 0.1153,
|
611 |
+
"step": 860
|
612 |
},
|
613 |
{
|
614 |
+
"epoch": 7.06,
|
615 |
+
"grad_norm": 3.6482489109039307,
|
616 |
+
"learning_rate": 0.0002,
|
617 |
+
"loss": 0.0962,
|
618 |
+
"step": 870
|
619 |
},
|
620 |
{
|
621 |
+
"epoch": 7.14,
|
622 |
+
"grad_norm": 4.848484516143799,
|
623 |
+
"learning_rate": 0.0002,
|
624 |
+
"loss": 0.0892,
|
625 |
+
"step": 880
|
626 |
},
|
627 |
{
|
628 |
+
"epoch": 7.22,
|
629 |
+
"grad_norm": 6.297725677490234,
|
630 |
+
"learning_rate": 0.0002,
|
631 |
+
"loss": 0.0913,
|
632 |
+
"step": 890
|
633 |
},
|
634 |
{
|
635 |
+
"epoch": 7.3,
|
636 |
+
"grad_norm": 3.4698007106781006,
|
637 |
+
"learning_rate": 0.0002,
|
638 |
+
"loss": 0.0927,
|
639 |
+
"step": 900
|
640 |
},
|
641 |
{
|
642 |
+
"epoch": 7.38,
|
643 |
+
"grad_norm": 4.614325523376465,
|
644 |
+
"learning_rate": 0.0002,
|
645 |
+
"loss": 0.0933,
|
646 |
+
"step": 910
|
647 |
},
|
648 |
{
|
649 |
+
"epoch": 7.46,
|
650 |
+
"grad_norm": 6.8649163246154785,
|
651 |
+
"learning_rate": 0.0002,
|
652 |
+
"loss": 0.0951,
|
653 |
+
"step": 920
|
654 |
},
|
655 |
{
|
656 |
+
"epoch": 7.55,
|
657 |
+
"grad_norm": 3.5742478370666504,
|
658 |
+
"learning_rate": 0.0002,
|
659 |
+
"loss": 0.0975,
|
660 |
+
"step": 930
|
661 |
},
|
662 |
{
|
663 |
+
"epoch": 7.63,
|
664 |
+
"grad_norm": 4.66102409362793,
|
665 |
+
"learning_rate": 0.0002,
|
666 |
+
"loss": 0.0971,
|
667 |
+
"step": 940
|
668 |
},
|
669 |
{
|
670 |
+
"epoch": 7.71,
|
671 |
+
"grad_norm": 6.615488052368164,
|
672 |
+
"learning_rate": 0.0002,
|
673 |
+
"loss": 0.0992,
|
674 |
+
"step": 950
|
675 |
},
|
676 |
{
|
677 |
+
"epoch": 7.79,
|
678 |
+
"grad_norm": 4.218813419342041,
|
679 |
+
"learning_rate": 0.0002,
|
680 |
+
"loss": 0.1021,
|
681 |
+
"step": 960
|
682 |
},
|
683 |
{
|
684 |
+
"epoch": 7.87,
|
685 |
+
"grad_norm": 4.6225905418396,
|
686 |
+
"learning_rate": 0.0002,
|
687 |
+
"loss": 0.1012,
|
688 |
+
"step": 970
|
689 |
},
|
690 |
{
|
691 |
+
"epoch": 7.95,
|
692 |
+
"grad_norm": 6.005787372589111,
|
693 |
+
"learning_rate": 0.0002,
|
694 |
+
"loss": 0.1059,
|
695 |
+
"step": 980
|
696 |
},
|
697 |
{
|
698 |
+
"epoch": 8.03,
|
699 |
+
"grad_norm": 3.2653019428253174,
|
700 |
+
"learning_rate": 0.0002,
|
701 |
+
"loss": 0.0929,
|
702 |
+
"step": 990
|
703 |
},
|
704 |
{
|
705 |
+
"epoch": 8.11,
|
706 |
+
"grad_norm": 5.000682353973389,
|
707 |
+
"learning_rate": 0.0002,
|
708 |
+
"loss": 0.0787,
|
709 |
+
"step": 1000
|
710 |
}
|
711 |
],
|
712 |
+
"logging_steps": 10,
|
713 |
+
"max_steps": 1000,
|
714 |
"num_input_tokens_seen": 0,
|
715 |
+
"num_train_epochs": 9,
|
716 |
+
"save_steps": 10,
|
717 |
+
"total_flos": 1.9346683868368896e+17,
|
718 |
+
"train_batch_size": 4,
|
719 |
"trial_name": null,
|
720 |
"trial_params": null
|
721 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5aeb7d0bde59078e1e1c3e2885309fbf387057d92c56bdc99ab0b821e37d3da
|
3 |
size 4984
|