Training in progress, step 1000
Browse files- adapter_model.safetensors +1 -1
- debug.log +241 -1
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 332316480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60f39bf0e2d04be586e3cdf61f38e4002d8f4ccf2b3e7506a28c3eebf56ae883
|
| 3 |
size 332316480
|
debug.log
CHANGED
|
@@ -5197,4 +5197,244 @@ trainable params: 83,066,880 || all params: 2,697,408,768 || trainable%: 3.0795
|
|
| 5197 |
|
| 5198 |
|
| 5199 |
[A[2025-10-19 01:06:32,644] [INFO] [axolotl.core.trainers.base._save:664] [PID:42363] Saving model checkpoint to ./outputs/sft/gemma-2-2b-it-rp-sft-qlora/checkpoint-950
|
| 5200 |
|
| 5201 |
95%|ββββββββββββββββββββ | 951/1000 [6:03:56<25:30, 31.24s/it]
|
| 5202 |
|
| 5203 |
-
|
| 5204 |
95%|ββββββββββββββββββββ | 951/1000 [6:03:56<25:30, 31.24s/it]
|
|
|
|
| 5205 |
95%|ββββββββββββββββββββ | 951/1000 [6:03:56<25:30, 31.24s/it]
|
| 5206 |
95%|ββββββββββββββββββββ | 952/1000 [6:04:03<19:20, 24.18s/it]
|
| 5207 |
|
|
|
|
| 5208 |
95%|ββββββββββββββββββββ | 952/1000 [6:04:03<19:20, 24.18s/it]
|
| 5209 |
95%|ββββββββββββββββββββ | 953/1000 [6:04:11<15:03, 19.23s/it]
|
| 5210 |
|
|
|
|
| 5211 |
95%|ββββββββββββββββββββ | 953/1000 [6:04:11<15:03, 19.23s/it]
|
| 5212 |
95%|ββββββββββββββββββββ | 954/1000 [6:04:19<12:05, 15.77s/it]
|
| 5213 |
|
|
|
|
| 5214 |
95%|ββββββββββββββββββββ | 954/1000 [6:04:19<12:05, 15.77s/it]
|
| 5215 |
96%|ββββββββββββββββββββ | 955/1000 [6:04:27<10:00, 13.34s/it]
|
| 5216 |
|
|
|
|
| 5217 |
96%|ββββββββββββββββββββ | 955/1000 [6:04:27<10:00, 13.34s/it]
|
| 5218 |
96%|ββββββββββββββββββββ | 956/1000 [6:04:34<08:32, 11.64s/it]
|
| 5219 |
|
|
|
|
| 5220 |
96%|ββββββββββββββββββββ | 956/1000 [6:04:34<08:32, 11.64s/it]
|
| 5221 |
96%|ββββββββββββββββββββ | 957/1000 [6:04:42<07:29, 10.45s/it]
|
| 5222 |
|
|
|
|
| 5223 |
96%|ββββββββββββββββββββ | 957/1000 [6:04:42<07:29, 10.45s/it]
|
| 5224 |
96%|ββββββββββββββββββββ | 958/1000 [6:04:50<06:44, 9.62s/it]
|
| 5225 |
|
|
|
|
| 5226 |
96%|ββββββββββββββββββββ | 958/1000 [6:04:50<06:44, 9.62s/it]
|
| 5227 |
96%|βββββββββββββββββββββ| 959/1000 [6:04:57<06:11, 9.05s/it]
|
| 5228 |
|
|
|
|
| 5229 |
96%|βββββββββββββββββββββ| 959/1000 [6:04:57<06:11, 9.05s/it]
|
| 5230 |
96%|βββββββββββββββββββββ| 960/1000 [6:05:05<05:45, 8.64s/it]
|
| 5231 |
|
|
|
|
| 5232 |
96%|βββββββββββββββββββββ| 960/1000 [6:05:05<05:45, 8.64s/it]
|
| 5233 |
96%|βββββββββββββββββββββ| 961/1000 [6:05:13<05:26, 8.36s/it]
|
| 5234 |
|
|
|
|
| 5235 |
96%|βββββββββββββββββββββ| 961/1000 [6:05:13<05:26, 8.36s/it]
|
| 5236 |
96%|βββββββββββββββββββββ| 962/1000 [6:05:20<05:10, 8.16s/it]
|
| 5237 |
|
|
|
|
| 5238 |
96%|βββββββββββββββββββββ| 962/1000 [6:05:20<05:10, 8.16s/it]
|
| 5239 |
96%|βββββββββββββββββββββ| 963/1000 [6:05:28<04:56, 8.02s/it]
|
| 5240 |
|
|
|
|
| 5241 |
96%|βββββββββββββββββββββ| 963/1000 [6:05:28<04:56, 8.02s/it]
|
| 5242 |
96%|βββββββββββββββββββββ| 964/1000 [6:05:36<04:45, 7.92s/it]
|
| 5243 |
|
|
|
|
| 5244 |
96%|βββββββββββββββββββββ| 964/1000 [6:05:36<04:45, 7.92s/it]
|
| 5245 |
96%|βββββββββββββββββββββ| 965/1000 [6:05:43<04:35, 7.86s/it]
|
| 5246 |
|
|
|
|
| 5247 |
96%|βββββββββββββββββββββ| 965/1000 [6:05:43<04:35, 7.86s/it]
|
| 5248 |
97%|βββββββββββββββββββββ| 966/1000 [6:05:51<04:25, 7.81s/it]
|
| 5249 |
|
|
|
|
| 5250 |
97%|βββββββββββββββββββββ| 966/1000 [6:05:51<04:25, 7.81s/it]
|
| 5251 |
97%|βββββββββββββββββββββ| 967/1000 [6:05:59<04:16, 7.77s/it]
|
| 5252 |
|
|
|
|
| 5253 |
97%|βββββββββββββββββββββ| 967/1000 [6:05:59<04:16, 7.77s/it]
|
| 5254 |
97%|βββββββββββββββββββββ| 968/1000 [6:06:07<04:07, 7.75s/it]
|
| 5255 |
|
|
|
|
| 5256 |
97%|βββββββββββββββββββββ| 968/1000 [6:06:07<04:07, 7.75s/it]
|
| 5257 |
97%|βββββββββββββββββββββ| 969/1000 [6:06:14<03:59, 7.73s/it]
|
| 5258 |
|
|
|
|
| 5259 |
97%|βββββββββββββββββββββ| 969/1000 [6:06:14<03:59, 7.73s/it]
|
| 5260 |
97%|βββββββββββββββββββββ| 970/1000 [6:06:22<03:51, 7.72s/it]
|
| 5261 |
|
|
|
|
| 5262 |
97%|βββββββββββββββββββββ| 970/1000 [6:06:22<03:51, 7.72s/it]
|
| 5263 |
97%|βββββββββββββββββββββ| 971/1000 [6:06:30<03:43, 7.71s/it]
|
| 5264 |
|
|
|
|
| 5265 |
97%|βββββββββββββββββββββ| 971/1000 [6:06:30<03:43, 7.71s/it]
|
| 5266 |
97%|βββββββββββββββββββββ| 972/1000 [6:06:37<03:35, 7.71s/it]
|
| 5267 |
|
|
|
|
| 5268 |
97%|βββββββββββββββββββββ| 972/1000 [6:06:37<03:35, 7.71s/it]
|
| 5269 |
97%|βββββββββββββββββββββ| 973/1000 [6:06:45<03:28, 7.71s/it]
|
| 5270 |
|
|
|
|
| 5271 |
97%|βββββββββββββββββββββ| 973/1000 [6:06:45<03:28, 7.71s/it]
|
| 5272 |
97%|βββββββββββββββββββββ| 974/1000 [6:06:53<03:20, 7.70s/it]
|
| 5273 |
|
|
|
|
| 5274 |
97%|βββββββββββββββββββββ| 974/1000 [6:06:53<03:20, 7.70s/it]
|
| 5275 |
98%|βββββββββββββββββββββ| 975/1000 [6:07:00<03:12, 7.70s/it]
|
| 5276 |
|
|
|
|
| 5277 |
98%|βββββββββββββββββββββ| 975/1000 [6:07:00<03:12, 7.70s/it]
|
| 5278 |
98%|βββββββββββββββββββββ| 976/1000 [6:07:08<03:04, 7.70s/it]
|
| 5279 |
|
|
|
|
| 5280 |
98%|βββββββββββββββββββββ| 976/1000 [6:07:08<03:04, 7.70s/it]
|
| 5281 |
98%|βββββββββββββββββββββ| 977/1000 [6:07:16<02:57, 7.70s/it]
|
| 5282 |
|
|
|
|
| 5283 |
98%|βββββββββββββββββββββ| 977/1000 [6:07:16<02:57, 7.70s/it]
|
| 5284 |
98%|βββββββββββββββββββββ| 978/1000 [6:07:24<02:49, 7.70s/it]
|
| 5285 |
|
|
|
|
| 5286 |
98%|βββββββββββββββββββββ| 978/1000 [6:07:24<02:49, 7.70s/it]
|
| 5287 |
98%|βββββββββββββββββββββ| 979/1000 [6:07:31<02:41, 7.69s/it]
|
| 5288 |
|
|
|
|
| 5289 |
98%|βββββββββββββββββββββ| 979/1000 [6:07:31<02:41, 7.69s/it]
|
| 5290 |
98%|βββββββββββββββββββββ| 980/1000 [6:07:39<02:33, 7.70s/it]
|
| 5291 |
|
|
|
|
| 5292 |
98%|βββββββββββββββββββββ| 980/1000 [6:07:39<02:33, 7.70s/it]
|
| 5293 |
98%|βββββββββββββββββββββ| 981/1000 [6:07:47<02:26, 7.69s/it]
|
| 5294 |
|
|
|
|
| 5295 |
98%|βββββββββββββββββββββ| 981/1000 [6:07:47<02:26, 7.69s/it]
|
| 5296 |
98%|βββββββββββββββββββββ| 982/1000 [6:07:54<02:18, 7.69s/it]
|
| 5297 |
|
|
|
|
| 5298 |
98%|βββββββββββββββββββββ| 982/1000 [6:07:54<02:18, 7.69s/it]
|
| 5299 |
98%|βββββββββββββββββββββ| 983/1000 [6:08:02<02:10, 7.69s/it]
|
| 5300 |
|
|
|
|
| 5301 |
98%|βββββββββββββββββββββ| 983/1000 [6:08:02<02:10, 7.69s/it]
|
| 5302 |
98%|βββββββββββββββββββββ| 984/1000 [6:08:10<02:03, 7.70s/it]
|
| 5303 |
|
|
|
|
| 5304 |
98%|βββββββββββββββββββββ| 984/1000 [6:08:10<02:03, 7.70s/it]
|
| 5305 |
98%|βββββββββββββββββββββ| 985/1000 [6:08:17<01:55, 7.71s/it]
|
| 5306 |
|
|
|
|
| 5307 |
98%|βββββββββββββββββββββ| 985/1000 [6:08:17<01:55, 7.71s/it]
|
| 5308 |
99%|βββββββββββββββββββββ| 986/1000 [6:08:25<01:47, 7.70s/it]
|
| 5309 |
|
|
|
|
| 5310 |
99%|βββββββββββββββββββββ| 986/1000 [6:08:25<01:47, 7.70s/it]
|
| 5311 |
99%|βββββββββββββββββββββ| 987/1000 [6:08:33<01:40, 7.70s/it]
|
| 5312 |
|
|
|
|
| 5313 |
99%|βββββββββββββββββββββ| 987/1000 [6:08:33<01:40, 7.70s/it]
|
| 5314 |
99%|βββββββββββββββββββββ| 988/1000 [6:08:40<01:32, 7.70s/it]
|
| 5315 |
|
|
|
|
| 5316 |
99%|βββββββββββββββββββββ| 988/1000 [6:08:41<01:32, 7.70s/it]
|
| 5317 |
99%|βββββββββββββββββββββ| 989/1000 [6:08:48<01:24, 7.70s/it]
|
| 5318 |
|
|
|
|
| 5319 |
99%|βββββββββββββββββββββ| 989/1000 [6:08:48<01:24, 7.70s/it]
|
| 5320 |
99%|βββββββββββββββββββββ| 990/1000 [6:08:56<01:17, 7.70s/it]
|
| 5321 |
|
|
|
|
| 5322 |
99%|βββββββββββββββββββββ| 990/1000 [6:08:56<01:17, 7.70s/it]
|
| 5323 |
99%|βββββββββββββββββββββ| 991/1000 [6:09:04<01:09, 7.70s/it]
|
| 5324 |
|
|
|
|
| 5325 |
99%|βββββββββββββββββββββ| 991/1000 [6:09:04<01:09, 7.70s/it]
|
| 5326 |
99%|βββββββββββββββββββββ| 992/1000 [6:09:11<01:01, 7.70s/it]
|
| 5327 |
|
|
|
|
| 5328 |
99%|βββββββββββββββββββββ| 992/1000 [6:09:11<01:01, 7.70s/it]
|
| 5329 |
99%|βββββββββββββββββββββ| 993/1000 [6:09:19<00:53, 7.69s/it]
|
| 5330 |
|
|
|
|
| 5331 |
99%|βββββββββββββββββββββ| 993/1000 [6:09:19<00:53, 7.69s/it]
|
| 5332 |
99%|βββββββββββββββββββββ| 994/1000 [6:09:27<00:46, 7.70s/it]
|
| 5333 |
|
|
|
|
| 5334 |
99%|βββββββββββββββββββββ| 994/1000 [6:09:27<00:46, 7.70s/it]
|
| 5335 |
|
|
|
|
| 5336 |
|
|
|
|
| 5337 |
|
|
|
|
| 5338 |
|
|
|
|
| 5339 |
|
|
|
|
| 5340 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5341 |
0%| | 0/179 [00:00<?, ?it/s][A
|
|
|
|
| 5342 |
1%|β | 2/179 [00:00<00:28, 6.19it/s][A
|
|
|
|
| 5343 |
2%|β | 3/179 [00:00<00:40, 4.37it/s][A
|
|
|
|
| 5344 |
2%|β | 4/179 [00:00<00:46, 3.77it/s][A
|
|
|
|
| 5345 |
3%|β | 5/179 [00:01<01:17, 2.23it/s][A
|
|
|
|
| 5346 |
3%|β | 6/179 [00:02<01:08, 2.53it/s][A
|
|
|
|
| 5347 |
4%|β | 7/179 [00:02<01:04, 2.67it/s][A
|
|
|
|
| 5348 |
4%|ββ | 8/179 [00:02<01:01, 2.80it/s][A
|
|
|
|
| 5349 |
5%|ββ | 9/179 [00:03<01:09, 2.44it/s][A
|
|
|
|
| 5350 |
6%|ββ | 10/179 [00:03<01:03, 2.67it/s][A
|
|
|
|
| 5351 |
6%|ββ | 11/179 [00:03<01:00, 2.80it/s][A
|
|
|
|
| 5352 |
7%|ββ | 12/179 [00:04<00:57, 2.89it/s][A
|
|
|
|
| 5353 |
7%|ββ | 13/179 [00:04<01:06, 2.49it/s][A
|
|
|
|
| 5354 |
8%|ββ | 14/179 [00:04<01:00, 2.72it/s][A
|
|
|
|
| 5355 |
8%|ββ | 15/179 [00:05<00:58, 2.83it/s][A
|
|
|
|
| 5356 |
9%|βββ | 16/179 [00:05<00:56, 2.90it/s][A
|
|
|
|
| 5357 |
9%|βββ | 17/179 [00:06<01:04, 2.49it/s][A
|
|
|
|
| 5358 |
10%|βββ | 18/179 [00:06<00:59, 2.73it/s][A
|
|
|
|
| 5359 |
11%|βββ | 19/179 [00:06<00:56, 2.84it/s][A
|
|
|
|
| 5360 |
11%|βββ | 20/179 [00:07<00:54, 2.92it/s][A
|
|
|
|
| 5361 |
12%|βββ | 21/179 [00:07<01:02, 2.51it/s][A
|
|
|
|
| 5362 |
12%|βββ | 22/179 [00:07<00:57, 2.73it/s][A
|
|
|
|
| 5363 |
13%|ββββ | 23/179 [00:08<00:54, 2.84it/s][A
|
|
|
|
| 5364 |
13%|ββββ | 24/179 [00:08<00:53, 2.92it/s][A
|
|
|
|
| 5365 |
14%|ββββ | 25/179 [00:09<01:01, 2.51it/s][A
|
|
|
|
| 5366 |
15%|ββββ | 26/179 [00:09<00:55, 2.73it/s][A
|
|
|
|
| 5367 |
15%|ββββ | 27/179 [00:09<00:53, 2.84it/s][A
|
|
|
|
| 5368 |
16%|ββββ | 28/179 [00:10<00:51, 2.92it/s][A
|
|
|
|
| 5369 |
16%|ββββ | 29/179 [00:10<00:59, 2.51it/s][A
|
|
|
|
| 5370 |
17%|βββββ | 30/179 [00:10<00:54, 2.74it/s][A
|
|
|
|
| 5371 |
17%|βββββ | 31/179 [00:11<00:51, 2.85it/s][A
|
|
|
|
| 5372 |
18%|βββββ | 32/179 [00:11<00:50, 2.93it/s][A
|
|
|
|
| 5373 |
18%|βββββ | 33/179 [00:11<00:57, 2.52it/s][A
|
|
|
|
| 5374 |
19%|βββββ | 34/179 [00:12<00:52, 2.74it/s][A
|
|
|
|
| 5375 |
20%|βββββ | 35/179 [00:12<00:50, 2.85it/s][A
|
|
|
|
| 5376 |
20%|βββββ | 36/179 [00:12<00:48, 2.93it/s][A
|
|
|
|
| 5377 |
21%|ββββββ | 37/179 [00:13<00:56, 2.51it/s][A
|
|
|
|
| 5378 |
21%|ββββββ | 38/179 [00:13<00:51, 2.74it/s][A
|
|
|
|
| 5379 |
22%|ββββοΏ½οΏ½οΏ½β | 39/179 [00:14<00:49, 2.85it/s][A
|
|
|
|
| 5380 |
22%|ββββββ | 40/179 [00:14<00:47, 2.93it/s][A
|
|
|
|
| 5381 |
23%|ββββββ | 41/179 [00:14<00:54, 2.52it/s][A
|
|
|
|
| 5382 |
23%|ββββββ | 42/179 [00:15<00:49, 2.75it/s][A
|
|
|
|
| 5383 |
24%|ββββββ | 43/179 [00:15<00:47, 2.85it/s][A
|
|
|
|
| 5384 |
25%|βββββββ | 44/179 [00:15<00:46, 2.93it/s][A
|
|
|
|
| 5385 |
25%|βββββββ | 45/179 [00:16<00:53, 2.51it/s][A
|
|
|
|
| 5386 |
26%|βββββββ | 46/179 [00:16<00:48, 2.74it/s][A
|
|
|
|
| 5387 |
26%|βββββββ | 47/179 [00:16<00:46, 2.85it/s][A
|
|
|
|
| 5388 |
27%|βββββββ | 48/179 [00:17<00:44, 2.93it/s][A
|
|
|
|
| 5389 |
27%|βββββββ | 49/179 [00:17<00:51, 2.52it/s][A
|
|
|
|
| 5390 |
28%|βββββββ | 50/179 [00:18<00:47, 2.74it/s][A
|
|
|
|
| 5391 |
28%|βββββββ | 51/179 [00:18<00:45, 2.84it/s][A
|
|
|
|
| 5392 |
29%|ββββββββ | 52/179 [00:18<00:43, 2.92it/s][A
|
|
|
|
| 5393 |
30%|ββββββββ | 53/179 [00:19<00:50, 2.51it/s][A
|
|
|
|
| 5394 |
30%|ββββββββ | 54/179 [00:19<00:45, 2.73it/s][A
|
|
|
|
| 5395 |
31%|ββββββββ | 55/179 [00:19<00:43, 2.84it/s][A
|
|
|
|
| 5396 |
31%|ββββββββ | 56/179 [00:20<00:42, 2.92it/s][A
|
|
|
|
| 5397 |
32%|ββββββββ | 57/179 [00:20<00:48, 2.51it/s][A
|
|
|
|
| 5398 |
32%|ββββββββ | 58/179 [00:21<00:44, 2.74it/s][A
|
|
|
|
| 5399 |
33%|βββββββββ | 59/179 [00:21<00:42, 2.85it/s][A
|
|
|
|
| 5400 |
34%|βββββββββ | 60/179 [00:21<00:40, 2.92it/s][A
|
|
|
|
| 5401 |
34%|βββββββββ | 61/179 [00:22<00:46, 2.52it/s][A
|
|
|
|
| 5402 |
35%|βββββββββ | 62/179 [00:22<00:42, 2.73it/s][A
|
|
|
|
| 5403 |
35%|βββββββββ | 63/179 [00:22<00:40, 2.84it/s][A
|
|
|
|
| 5404 |
36%|βββββββββ | 64/179 [00:23<00:39, 2.92it/s][A
|
|
|
|
| 5405 |
36%|βββββββββ | 65/179 [00:23<00:45, 2.51it/s][A
|
|
|
|
| 5406 |
37%|ββββββββββ | 66/179 [00:23<00:41, 2.74it/s][A
|
|
|
|
| 5407 |
37%|ββββββββββ | 67/179 [00:24<00:39, 2.84it/s][A
|
|
|
|
| 5408 |
38%|ββββββββββ | 68/179 [00:24<00:37, 2.92it/s][A
|
|
|
|
| 5409 |
39%|ββββββββββ | 69/179 [00:25<00:43, 2.51it/s][A
|
|
|
|
| 5410 |
39%|ββββββββββ | 70/179 [00:25<00:39, 2.73it/s][A
|
|
|
|
| 5411 |
40%|ββββββββββ | 71/179 [00:25<00:37, 2.84it/s][A
|
|
|
|
| 5412 |
40%|ββββββββββ | 72/179 [00:26<00:36, 2.92it/s][A
|
|
|
|
| 5413 |
41%|βββββββββββ | 73/179 [00:26<00:42, 2.51it/s][A
|
|
|
|
| 5414 |
41%|βββββββββββ | 74/179 [00:26<00:38, 2.74it/s][A
|
|
|
|
| 5415 |
42%|βββββββββββ | 75/179 [00:27<00:36, 2.85it/s][A
|
|
|
|
| 5416 |
42%|βββββββββββ | 76/179 [00:27<00:35, 2.93it/s][A
|
|
|
|
| 5417 |
43%|βββββββββββ | 77/179 [00:28<00:44, 2.28it/s][A
|
|
|
|
| 5418 |
44%|βββββββββββ | 78/179 [00:28<00:39, 2.53it/s][A
|
|
|
|
| 5419 |
44%|βββββββββββ | 79/179 [00:28<00:37, 2.68it/s][A
|
|
|
|
| 5420 |
45%|ββββββββββββ | 80/179 [00:29<00:35, 2.80it/s][A
|
|
|
|
| 5421 |
45%|ββββββββββββ | 81/179 [00:29<00:39, 2.45it/s][A
|
|
|
|
| 5422 |
46%|ββββββββββββ | 82/179 [00:29<00:36, 2.69it/s][A
|
|
|
|
| 5423 |
46%|ββββββββββββ | 83/179 [00:30<00:34, 2.80it/s][A
|
|
|
|
| 5424 |
47%|ββββββββββββ | 84/179 [00:30<00:32, 2.89it/s][A
|
|
|
|
| 5425 |
47%|ββββββββββββ | 85/179 [00:31<00:43, 2.18it/s][A
|
|
|
|
| 5426 |
48%|ββββββββββββ | 86/179 [00:31<00:37, 2.45it/s][A
|
|
|
|
| 5427 |
49%|βββββββββββββ | 87/179 [00:31<00:35, 2.63it/s][A
|
|
|
|
| 5428 |
49%|βββββββββββββ | 88/179 [00:32<00:32, 2.76it/s][A
|
|
|
|
| 5429 |
50%|βββββββββββββ | 89/179 [00:32<00:37, 2.43it/s][A
|
|
|
|
| 5430 |
50%|βββββββββββββ | 90/179 [00:32<00:33, 2.67it/s][A
|
|
|
|
| 5431 |
51%|βββββββββββββ | 91/179 [00:33<00:31, 2.79it/s][A
|
|
|
|
| 5432 |
51%|βββββββββββββ | 92/179 [00:33<00:30, 2.88it/s][A
|
|
|
|
| 5433 |
52%|βββββββββββββ | 93/179 [00:34<00:34, 2.50it/s][A
|
|
|
|
| 5434 |
53%|ββββββββββββββ | 94/179 [00:34<00:31, 2.73it/s][A
|
|
|
|
| 5435 |
53%|ββββββββββββββ | 95/179 [00:34<00:29, 2.84it/s][A
|
|
|
|
| 5436 |
54%|ββββββββββββββ | 96/179 [00:35<00:28, 2.91it/s][A
|
|
|
|
| 5437 |
54%|ββββββββββββββ | 97/179 [00:35<00:32, 2.51it/s][A
|
|
|
|
| 5438 |
55%|ββββββββββββββ | 98/179 [00:35<00:29, 2.73it/s][A
|
|
|
|
| 5439 |
55%|ββββββββββββββ | 99/179 [00:36<00:28, 2.83it/s][A
|
|
|
|
| 5440 |
56%|ββββββββββββββ | 100/179 [00:36<00:27, 2.91it/s][A
|
|
|
|
| 5441 |
56%|ββββββββββββββ | 101/179 [00:37<00:31, 2.51it/s][A
|
|
|
|
| 5442 |
57%|ββββββββββββββ | 102/179 [00:37<00:28, 2.73it/s][A
|
|
|
|
| 5443 |
58%|ββββββββββββββ | 103/179 [00:37<00:26, 2.84it/s][A
|
|
|
|
| 5444 |
58%|ββββββββββββββ | 104/179 [00:38<00:25, 2.91it/s][A
|
|
|
|
| 5445 |
59%|ββββββββββββββ | 105/179 [00:38<00:29, 2.50it/s][A
|
|
|
|
| 5446 |
59%|βββββββββββββββ | 106/179 [00:38<00:26, 2.73it/s][A
|
|
|
|
| 5447 |
60%|βββββββββββββββ | 107/179 [00:39<00:25, 2.83it/s][A
|
|
|
|
| 5448 |
60%|βββββββββββββββ | 108/179 [00:39<00:24, 2.92it/s][A
|
|
|
|
| 5449 |
61%|βββββββββββββββ | 109/179 [00:39<00:27, 2.52it/s][A
|
|
|
|
| 5450 |
61%|βββββββββββββββ | 110/179 [00:40<00:25, 2.74it/s][A
|
|
|
|
| 5451 |
62%|βββββββββββββββ | 111/179 [00:40<00:23, 2.85it/s][A
|
|
|
|
| 5452 |
63%|βββββββββββββββ | 112/179 [00:40<00:22, 2.92it/s][A
|
|
|
|
| 5453 |
63%|ββββββββββββββββ | 113/179 [00:41<00:26, 2.51it/s][A
|
|
|
|
| 5454 |
64%|ββββββββββββββββ | 114/179 [00:41<00:23, 2.73it/s][A
|
|
|
|
| 5455 |
64%|ββββββββββββββββ | 115/179 [00:42<00:22, 2.84it/s][A
|
|
|
|
| 5456 |
65%|ββββββββββββββββ | 116/179 [00:42<00:21, 2.92it/s][A
|
|
|
|
| 5457 |
65%|ββββββββββββββββ | 117/179 [00:42<00:24, 2.51it/s][A
|
|
|
|
| 5458 |
66%|ββββββββββββββββ | 118/179 [00:43<00:22, 2.73it/s][A
|
|
|
|
| 5459 |
66%|ββββββββββββββββ | 119/179 [00:43<00:21, 2.84it/s][A
|
|
|
|
| 5460 |
67%|ββββββββββββββββ | 120/179 [00:43<00:20, 2.92it/s][A
|
|
|
|
| 5461 |
68%|βββββββββββββββββ | 121/179 [00:44<00:23, 2.52it/s][A
|
|
|
|
| 5462 |
68%|βββββββββββββββββ | 122/179 [00:44<00:20, 2.74it/s][A
|
|
|
|
| 5463 |
69%|βββββββββββββββββ | 123/179 [00:44<00:19, 2.85it/s][A
|
|
|
|
| 5464 |
69%|βββββββββββββββββ | 124/179 [00:45<00:18, 2.92it/s][A
|
|
|
|
| 5465 |
70%|βββββββββββββββββ | 125/179 [00:45<00:21, 2.52it/s][A
|
|
|
|
| 5466 |
70%|βββββββββββββββββ | 126/179 [00:46<00:19, 2.73it/s][A
|
|
|
|
| 5467 |
71%|βββββββββββββββββ | 127/179 [00:46<00:18, 2.84it/s][A
|
|
|
|
| 5468 |
72%|ββββββββββββββββββ | 128/179 [00:46<00:17, 2.91it/s][A
|
|
|
|
| 5469 |
72%|ββββββββββββββββββ | 129/179 [00:47<00:19, 2.51it/s][A
|
|
|
|
| 5470 |
73%|ββββββββββββββββββ | 130/179 [00:47<00:17, 2.73it/s][A
|
|
|
|
| 5471 |
73%|ββββββββββββββββββ | 131/179 [00:47<00:16, 2.84it/s][A
|
|
|
|
| 5472 |
74%|ββββββββββββββββββ | 132/179 [00:48<00:16, 2.91it/s][A
|
|
|
|
| 5473 |
74%|ββββββββββββββββββ | 133/179 [00:48<00:18, 2.50it/s][A
|
|
|
|
| 5474 |
75%|ββββββββββββββββββ | 134/179 [00:49<00:16, 2.72it/s][A
|
|
|
|
| 5475 |
75%|ββββββββββββββββββ | 135/179 [00:49<00:15, 2.83it/s][A
|
|
|
|
| 5476 |
76%|βββββββββββββββββββ | 136/179 [00:49<00:14, 2.91it/s][A
|
|
|
|
| 5477 |
77%|βββββββββββββββββββ | 137/179 [00:50<00:16, 2.51it/s][A
|
|
|
|
| 5478 |
77%|βββββββββββββββββββ | 138/179 [00:50<00:14, 2.74it/s][A
|
|
|
|
| 5479 |
78%|βββββββββββββββββββ | 139/179 [00:50<00:14, 2.83it/s][A
|
|
|
|
| 5480 |
78%|βββββββββββββββββββ | 140/179 [00:51<00:13, 2.91it/s][A
|
|
|
|
| 5481 |
79%|βββββββββββββββββββ | 141/179 [00:51<00:15, 2.51it/s][A
|
|
|
|
| 5482 |
79%|βββββββββββββββββββ | 142/179 [00:51<00:13, 2.73it/s][A
|
|
|
|
| 5483 |
80%|ββββββββββββββββββββ | 143/179 [00:52<00:12, 2.83it/s][A
|
|
|
|
| 5484 |
80%|ββββββββββββββββββββ | 144/179 [00:52<00:12, 2.91it/s][A
|
|
|
|
| 5485 |
81%|ββββββββββββββββββββ | 145/179 [00:53<00:13, 2.50it/s][A
|
|
|
|
| 5486 |
82%|ββββββββββββββββββββ | 146/179 [00:53<00:12, 2.73it/s][A
|
|
|
|
| 5487 |
82%|ββββββββββββββββββββ | 147/179 [00:53<00:11, 2.84it/s][A
|
|
|
|
| 5488 |
83%|ββββββββββββββββββββ | 148/179 [00:54<00:10, 2.92it/s][A
|
|
|
|
| 5489 |
83%|ββββββββββββββββββββ | 149/179 [00:54<00:11, 2.51it/s][A
|
|
|
|
| 5490 |
84%|ββββββββββββββββββββ | 150/179 [00:54<00:10, 2.74it/s][A
|
|
|
|
| 5491 |
84%|βββββββββββββββββββββ | 151/179 [00:55<00:09, 2.84it/s][A
|
|
|
|
| 5492 |
85%|βββββββββββββββββββββ | 152/179 [00:55<00:09, 2.92it/s][A
|
|
|
|
| 5493 |
85%|βββββββββββββββββββββ | 153/179 [00:56<00:10, 2.52it/s][A
|
|
|
|
| 5494 |
86%|βββββββββββββββββββββ | 154/179 [00:56<00:09, 2.74it/s][A
|
|
|
|
| 5495 |
87%|βββββββββββββββββββββ | 155/179 [00:56<00:08, 2.85it/s][A
|
|
|
|
| 5496 |
87%|βββββββββββββββββββββ | 156/179 [00:56<00:07, 2.92it/s][A
|
|
|
|
| 5497 |
88%|βββββββββββββββββββββ | 157/179 [00:57<00:08, 2.51it/s][A
|
|
|
|
| 5498 |
88%|ββββββββββββββββββββββ | 158/179 [00:57<00:07, 2.74it/s][A
|
|
|
|
| 5499 |
89%|ββββββββββββββββββββββ | 159/179 [00:58<00:07, 2.85it/s][A
|
|
|
|
| 5500 |
89%|ββββββββββββββββββββββ | 160/179 [00:58<00:06, 2.92it/s][A
|
|
|
|
| 5501 |
90%|ββββββββββββββββββββββ | 161/179 [00:58<00:07, 2.51it/s][A
|
|
|
|
| 5502 |
91%|ββββββββββββββββββββββ | 162/179 [00:59<00:06, 2.74it/s][A
|
|
|
|
| 5503 |
91%|ββββββββββββββββββββββ | 163/179 [00:59<00:05, 2.85it/s][A
|
|
|
|
| 5504 |
92%|ββββββββββββββββββββββ | 164/179 [00:59<00:05, 2.93it/s][A
|
|
|
|
| 5505 |
92%|ββββββββββββββββββββββ | 165/179 [01:00<00:05, 2.51it/s][A
|
|
|
|
| 5506 |
93%|βββββββββββββββββββββββ | 166/179 [01:00<00:04, 2.73it/s][A
|
|
|
|
| 5507 |
93%|βββββββββββββββββββββββ | 167/179 [01:01<00:04, 2.84it/s][A
|
|
|
|
| 5508 |
94%|βββββββββββββββββββββββ | 168/179 [01:01<00:03, 2.92it/s][A
|
|
|
|
| 5509 |
94%|βββββββββββββββββββββββ | 169/179 [01:01<00:03, 2.52it/s][A
|
|
|
|
| 5510 |
95%|βββββββββββββββββββββββ | 170/179 [01:02<00:03, 2.75it/s][A
|
|
|
|
| 5511 |
96%|βββββββββββββββββββββββ | 171/179 [01:02<00:02, 2.85it/s][A
|
|
|
|
| 5512 |
96%|βββββββββββββββββββββββ | 172/179 [01:02<00:02, 2.92it/s][A
|
|
|
|
| 5513 |
97%|ββββββββββββββββββββββββ| 173/179 [01:03<00:02, 2.52it/s][A
|
|
|
|
| 5514 |
97%|ββββββββββββββββββββββββ| 174/179 [01:03<00:01, 2.74it/s][A
|
|
|
|
| 5515 |
98%|ββββββββββββββββββββββββ| 175/179 [01:03<00:01, 2.85it/s][A
|
|
|
|
| 5516 |
98%|ββββββββββββββββββββββββ| 176/179 [01:04<00:01, 2.92it/s][A
|
|
|
|
| 5517 |
99%|ββββββββββββββββββββββββ| 177/179 [01:04<00:00, 2.52it/s][A
|
|
|
|
| 5518 |
99%|ββββββββββββββββββββββββ| 178/179 [01:05<00:00, 2.74it/s][A
|
|
|
|
| 5519 |
|
|
|
|
| 5520 |
|
|
|
|
|
|
|
|
|
|
| 5521 |
[A[2025-10-19 01:14:15,108] [INFO] [axolotl.core.trainers.base._save:664] [PID:42363] Saving model checkpoint to ./outputs/sft/gemma-2-2b-it-rp-sft-qlora/checkpoint-1000
|
|
|
|
| 5522 |
|
|
|
|
|
|
| 5197 |
|
| 5198 |
|
| 5199 |
[A[2025-10-19 01:06:32,644] [INFO] [axolotl.core.trainers.base._save:664] [PID:42363] Saving model checkpoint to ./outputs/sft/gemma-2-2b-it-rp-sft-qlora/checkpoint-950
|
| 5200 |
|
| 5201 |
95%|ββββββββββββββββββββ | 951/1000 [6:03:56<25:30, 31.24s/it]
|
| 5202 |
|
|
|
|
| 5203 |
95%|ββββββββββββββββββββ | 951/1000 [6:03:56<25:30, 31.24s/it]
|
| 5204 |
+
|
| 5205 |
95%|ββββββββββββββββββββ | 951/1000 [6:03:56<25:30, 31.24s/it]
|
| 5206 |
95%|ββββββββββββββββββββ | 952/1000 [6:04:03<19:20, 24.18s/it]
|
| 5207 |
|
| 5208 |
+
|
| 5209 |
95%|ββββββββββββββββββββ | 952/1000 [6:04:03<19:20, 24.18s/it]
|
| 5210 |
95%|ββββββββββββββββββββ | 953/1000 [6:04:11<15:03, 19.23s/it]
|
| 5211 |
|
| 5212 |
+
|
| 5213 |
95%|ββββββββββββββββββββ | 953/1000 [6:04:11<15:03, 19.23s/it]
|
| 5214 |
95%|ββββββββββββββββββββ | 954/1000 [6:04:19<12:05, 15.77s/it]
|
| 5215 |
|
| 5216 |
+
|
| 5217 |
95%|ββββββββββββββββββββ | 954/1000 [6:04:19<12:05, 15.77s/it]
|
| 5218 |
96%|ββββββββββββββββββββ | 955/1000 [6:04:27<10:00, 13.34s/it]
|
| 5219 |
|
| 5220 |
+
|
| 5221 |
96%|ββββββββββββββββββββ | 955/1000 [6:04:27<10:00, 13.34s/it]
|
| 5222 |
96%|ββββββββββββββββββββ | 956/1000 [6:04:34<08:32, 11.64s/it]
|
| 5223 |
|
| 5224 |
+
|
| 5225 |
96%|ββββββββββββββββββββ | 956/1000 [6:04:34<08:32, 11.64s/it]
|
| 5226 |
96%|ββββββββββββββββββββ | 957/1000 [6:04:42<07:29, 10.45s/it]
|
| 5227 |
|
| 5228 |
+
|
| 5229 |
96%|ββββββββββββββββββββ | 957/1000 [6:04:42<07:29, 10.45s/it]
|
| 5230 |
96%|ββββββββββββββββββββ | 958/1000 [6:04:50<06:44, 9.62s/it]
|
| 5231 |
|
| 5232 |
+
|
| 5233 |
96%|ββββββββββββββββββββ | 958/1000 [6:04:50<06:44, 9.62s/it]
|
| 5234 |
96%|βββββββββββββββββββββ| 959/1000 [6:04:57<06:11, 9.05s/it]
|
| 5235 |
|
| 5236 |
+
|
| 5237 |
96%|βββββββββββββββββββββ| 959/1000 [6:04:57<06:11, 9.05s/it]
|
| 5238 |
96%|βββββββββββββββββββββ| 960/1000 [6:05:05<05:45, 8.64s/it]
|
| 5239 |
|
| 5240 |
+
|
| 5241 |
96%|βββββββββββββββββββββ| 960/1000 [6:05:05<05:45, 8.64s/it]
|
| 5242 |
96%|βββββββββββββββββββββ| 961/1000 [6:05:13<05:26, 8.36s/it]
|
| 5243 |
|
| 5244 |
+
|
| 5245 |
96%|βββββββββββββββββββββ| 961/1000 [6:05:13<05:26, 8.36s/it]
|
| 5246 |
96%|βββββββββββββββββββββ| 962/1000 [6:05:20<05:10, 8.16s/it]
|
| 5247 |
|
| 5248 |
+
|
| 5249 |
96%|βββββββββββββββββββββ| 962/1000 [6:05:20<05:10, 8.16s/it]
|
| 5250 |
96%|βββββββββββββββββββββ| 963/1000 [6:05:28<04:56, 8.02s/it]
|
| 5251 |
|
| 5252 |
+
|
| 5253 |
96%|βββββββββββββββββββββ| 963/1000 [6:05:28<04:56, 8.02s/it]
|
| 5254 |
96%|βββββββββββββββββββββ| 964/1000 [6:05:36<04:45, 7.92s/it]
|
| 5255 |
|
| 5256 |
+
|
| 5257 |
96%|βββββββββββββββββββββ| 964/1000 [6:05:36<04:45, 7.92s/it]
|
| 5258 |
96%|βββββββββββββββββββββ| 965/1000 [6:05:43<04:35, 7.86s/it]
|
| 5259 |
|
| 5260 |
+
|
| 5261 |
96%|βββββββββββββββββββββ| 965/1000 [6:05:43<04:35, 7.86s/it]
|
| 5262 |
97%|βββββββββββββββββββββ| 966/1000 [6:05:51<04:25, 7.81s/it]
|
| 5263 |
|
| 5264 |
+
|
| 5265 |
97%|βββββββββββββββββββββ| 966/1000 [6:05:51<04:25, 7.81s/it]
|
| 5266 |
97%|βββββββββββββββββββββ| 967/1000 [6:05:59<04:16, 7.77s/it]
|
| 5267 |
|
| 5268 |
+
|
| 5269 |
97%|βββββββββββββββββββββ| 967/1000 [6:05:59<04:16, 7.77s/it]
|
| 5270 |
97%|βββββββββββββββββββββ| 968/1000 [6:06:07<04:07, 7.75s/it]
|
| 5271 |
|
| 5272 |
+
|
| 5273 |
97%|βββββββββββββββββββββ| 968/1000 [6:06:07<04:07, 7.75s/it]
|
| 5274 |
97%|βββββββββββββββββββββ| 969/1000 [6:06:14<03:59, 7.73s/it]
|
| 5275 |
|
| 5276 |
+
|
| 5277 |
97%|βββββββββββββββββββββ| 969/1000 [6:06:14<03:59, 7.73s/it]
|
| 5278 |
97%|βββββββββββββββββββββ| 970/1000 [6:06:22<03:51, 7.72s/it]
|
| 5279 |
|
| 5280 |
+
|
| 5281 |
97%|βββββββββββββββββββββ| 970/1000 [6:06:22<03:51, 7.72s/it]
|
| 5282 |
97%|βββββββββββββββββββββ| 971/1000 [6:06:30<03:43, 7.71s/it]
|
| 5283 |
|
| 5284 |
+
|
| 5285 |
97%|βββββββββββββββββββββ| 971/1000 [6:06:30<03:43, 7.71s/it]
|
| 5286 |
97%|βββββββββββββββββββββ| 972/1000 [6:06:37<03:35, 7.71s/it]
|
| 5287 |
|
| 5288 |
+
|
| 5289 |
97%|βββββββββββββββββββββ| 972/1000 [6:06:37<03:35, 7.71s/it]
|
| 5290 |
97%|βββββββββββββββββββββ| 973/1000 [6:06:45<03:28, 7.71s/it]
|
| 5291 |
|
| 5292 |
+
|
| 5293 |
97%|βββββββββββββββββββββ| 973/1000 [6:06:45<03:28, 7.71s/it]
|
| 5294 |
97%|βββββββββββββββββββββ| 974/1000 [6:06:53<03:20, 7.70s/it]
|
| 5295 |
|
| 5296 |
+
|
| 5297 |
97%|βββββββββββββββββββββ| 974/1000 [6:06:53<03:20, 7.70s/it]
|
| 5298 |
98%|βββββββββββββββββββββ| 975/1000 [6:07:00<03:12, 7.70s/it]
|
| 5299 |
|
| 5300 |
+
|
| 5301 |
98%|βββββββββββββββββββββ| 975/1000 [6:07:00<03:12, 7.70s/it]
|
| 5302 |
98%|βββββββββββββββββββββ| 976/1000 [6:07:08<03:04, 7.70s/it]
|
| 5303 |
|
| 5304 |
+
|
| 5305 |
98%|βββββββββββββββββββββ| 976/1000 [6:07:08<03:04, 7.70s/it]
|
| 5306 |
98%|βββββββββββββββββββββ| 977/1000 [6:07:16<02:57, 7.70s/it]
|
| 5307 |
|
| 5308 |
+
|
| 5309 |
98%|βββββββββββββββββββββ| 977/1000 [6:07:16<02:57, 7.70s/it]
|
| 5310 |
98%|βββββββββββββββββββββ| 978/1000 [6:07:24<02:49, 7.70s/it]
|
| 5311 |
|
| 5312 |
+
|
| 5313 |
98%|βββββββββββββββββββββ| 978/1000 [6:07:24<02:49, 7.70s/it]
|
| 5314 |
98%|βββββββββββββββββββββ| 979/1000 [6:07:31<02:41, 7.69s/it]
|
| 5315 |
|
| 5316 |
+
|
| 5317 |
98%|βββββββββββββββββββββ| 979/1000 [6:07:31<02:41, 7.69s/it]
|
| 5318 |
98%|βββββββββββββββββββββ| 980/1000 [6:07:39<02:33, 7.70s/it]
|
| 5319 |
|
| 5320 |
+
|
| 5321 |
98%|βββββββββββββββββββββ| 980/1000 [6:07:39<02:33, 7.70s/it]
|
| 5322 |
98%|βββββββββββββββββββββ| 981/1000 [6:07:47<02:26, 7.69s/it]
|
| 5323 |
|
| 5324 |
+
|
| 5325 |
98%|βββββββββββββββββββββ| 981/1000 [6:07:47<02:26, 7.69s/it]
|
| 5326 |
98%|βββββββββββββββββββββ| 982/1000 [6:07:54<02:18, 7.69s/it]
|
| 5327 |
|
| 5328 |
+
|
| 5329 |
98%|βββββββββββββββββββββ| 982/1000 [6:07:54<02:18, 7.69s/it]
|
| 5330 |
98%|βββββββββββββββββββββ| 983/1000 [6:08:02<02:10, 7.69s/it]
|
| 5331 |
|
| 5332 |
+
|
| 5333 |
98%|βββββββββββββββββββββ| 983/1000 [6:08:02<02:10, 7.69s/it]
|
| 5334 |
98%|βββββββββββββββββββββ| 984/1000 [6:08:10<02:03, 7.70s/it]
|
| 5335 |
|
| 5336 |
+
|
| 5337 |
98%|βββββββββββββββββββββ| 984/1000 [6:08:10<02:03, 7.70s/it]
|
| 5338 |
98%|βββββββββββββββββββββ| 985/1000 [6:08:17<01:55, 7.71s/it]
|
| 5339 |
|
| 5340 |
+
|
| 5341 |
98%|βββββββββββββββββββββ| 985/1000 [6:08:17<01:55, 7.71s/it]
|
| 5342 |
99%|βββββββββββββββββββββ| 986/1000 [6:08:25<01:47, 7.70s/it]
|
| 5343 |
|
| 5344 |
+
|
| 5345 |
99%|βββββββββββββββββββββ| 986/1000 [6:08:25<01:47, 7.70s/it]
|
| 5346 |
99%|βββββββββββββββββββββ| 987/1000 [6:08:33<01:40, 7.70s/it]
|
| 5347 |
|
| 5348 |
+
|
| 5349 |
99%|βββββββββββββββββββββ| 987/1000 [6:08:33<01:40, 7.70s/it]
|
| 5350 |
99%|βββββββββββββββββββββ| 988/1000 [6:08:40<01:32, 7.70s/it]
|
| 5351 |
|
| 5352 |
+
|
| 5353 |
99%|βββββββββββββββββββββ| 988/1000 [6:08:41<01:32, 7.70s/it]
|
| 5354 |
99%|βββββββββββββββββββββ| 989/1000 [6:08:48<01:24, 7.70s/it]
|
| 5355 |
|
| 5356 |
+
|
| 5357 |
99%|βββββββββββββββββββββ| 989/1000 [6:08:48<01:24, 7.70s/it]
|
| 5358 |
99%|βββββββββββββββββββββ| 990/1000 [6:08:56<01:17, 7.70s/it]
|
| 5359 |
|
| 5360 |
+
|
| 5361 |
99%|βββββββββββββββββββββ| 990/1000 [6:08:56<01:17, 7.70s/it]
|
| 5362 |
99%|βββββββββββββββββββββ| 991/1000 [6:09:04<01:09, 7.70s/it]
|
| 5363 |
|
| 5364 |
+
|
| 5365 |
99%|βββββββββββββββββββββ| 991/1000 [6:09:04<01:09, 7.70s/it]
|
| 5366 |
99%|βββββββββββββββββββββ| 992/1000 [6:09:11<01:01, 7.70s/it]
|
| 5367 |
|
| 5368 |
+
|
| 5369 |
99%|βββββββββββββββββββββ| 992/1000 [6:09:11<01:01, 7.70s/it]
|
| 5370 |
99%|βββββββββββββββββββββ| 993/1000 [6:09:19<00:53, 7.69s/it]
|
| 5371 |
|
| 5372 |
+
|
| 5373 |
99%|βββββββββββββββββββββ| 993/1000 [6:09:19<00:53, 7.69s/it]
|
| 5374 |
99%|βββββββββββββββββββββ| 994/1000 [6:09:27<00:46, 7.70s/it]
|
| 5375 |
|
| 5376 |
+
|
| 5377 |
99%|βββββββββββββββββββββ| 994/1000 [6:09:27<00:46, 7.70s/it]
|
| 5378 |
|
| 5379 |
+
|
| 5380 |
|
| 5381 |
+
|
| 5382 |
|
| 5383 |
+
|
| 5384 |
|
| 5385 |
+
|
| 5386 |
|
| 5387 |
+
|
| 5388 |
|
| 5389 |
+
|
| 5390 |
+
[2025-10-19 01:13:03,113] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:42363] generate_batches time: 1.5175468921661377
|
| 5391 |
+
[2025-10-19 01:13:04,532] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:42363] generate_batches time: 1.4183826446533203
|
| 5392 |
+
[2025-10-19 01:13:05,833] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:42363] generate_batches time: 1.3006186485290527
|
| 5393 |
+
[2025-10-19 01:13:07,214] [DEBUG] [axolotl.utils.samplers.multipack.__len__:462] [PID:42363] generate_batches time: 1.3808095455169678
|
| 5394 |
+
[2025-10-19 01:13:07,215] [INFO] [axolotl.utils.samplers.multipack.calc_min_len:438] [PID:42363] gather_len_batches: [179]
|
| 5395 |
+
|
| 5396 |
+
|
| 5397 |
0%| | 0/179 [00:00<?, ?it/s][A
|
| 5398 |
+
|
| 5399 |
1%|β | 2/179 [00:00<00:28, 6.19it/s][A
|
| 5400 |
+
|
| 5401 |
2%|β | 3/179 [00:00<00:40, 4.37it/s][A
|
| 5402 |
+
|
| 5403 |
2%|β | 4/179 [00:00<00:46, 3.77it/s][A
|
| 5404 |
+
|
| 5405 |
3%|β | 5/179 [00:01<01:17, 2.23it/s][A
|
| 5406 |
+
|
| 5407 |
3%|β | 6/179 [00:02<01:08, 2.53it/s][A
|
| 5408 |
+
|
| 5409 |
4%|β | 7/179 [00:02<01:04, 2.67it/s][A
|
| 5410 |
+
|
| 5411 |
4%|ββ | 8/179 [00:02<01:01, 2.80it/s][A
|
| 5412 |
+
|
| 5413 |
5%|ββ | 9/179 [00:03<01:09, 2.44it/s][A
|
| 5414 |
+
|
| 5415 |
6%|ββ | 10/179 [00:03<01:03, 2.67it/s][A
|
| 5416 |
+
|
| 5417 |
6%|ββ | 11/179 [00:03<01:00, 2.80it/s][A
|
| 5418 |
+
|
| 5419 |
7%|ββ | 12/179 [00:04<00:57, 2.89it/s][A
|
| 5420 |
+
|
| 5421 |
7%|ββ | 13/179 [00:04<01:06, 2.49it/s][A
|
| 5422 |
+
|
| 5423 |
8%|ββ | 14/179 [00:04<01:00, 2.72it/s][A
|
| 5424 |
+
|
| 5425 |
8%|ββ | 15/179 [00:05<00:58, 2.83it/s][A
|
| 5426 |
+
|
| 5427 |
9%|βββ | 16/179 [00:05<00:56, 2.90it/s][A
|
| 5428 |
+
|
| 5429 |
9%|βββ | 17/179 [00:06<01:04, 2.49it/s][A
|
| 5430 |
+
|
| 5431 |
10%|βββ | 18/179 [00:06<00:59, 2.73it/s][A
|
| 5432 |
+
|
| 5433 |
11%|βββ | 19/179 [00:06<00:56, 2.84it/s][A
|
| 5434 |
+
|
| 5435 |
11%|βββ | 20/179 [00:07<00:54, 2.92it/s][A
|
| 5436 |
+
|
| 5437 |
12%|βββ | 21/179 [00:07<01:02, 2.51it/s][A
|
| 5438 |
+
|
| 5439 |
12%|βββ | 22/179 [00:07<00:57, 2.73it/s][A
|
| 5440 |
+
|
| 5441 |
13%|ββββ | 23/179 [00:08<00:54, 2.84it/s][A
|
| 5442 |
+
|
| 5443 |
13%|ββββ | 24/179 [00:08<00:53, 2.92it/s][A
|
| 5444 |
+
|
| 5445 |
14%|ββββ | 25/179 [00:09<01:01, 2.51it/s][A
|
| 5446 |
+
|
| 5447 |
15%|ββββ | 26/179 [00:09<00:55, 2.73it/s][A
|
| 5448 |
+
|
| 5449 |
15%|ββββ | 27/179 [00:09<00:53, 2.84it/s][A
|
| 5450 |
+
|
| 5451 |
16%|ββββ | 28/179 [00:10<00:51, 2.92it/s][A
|
| 5452 |
+
|
| 5453 |
16%|ββββ | 29/179 [00:10<00:59, 2.51it/s][A
|
| 5454 |
+
|
| 5455 |
17%|βββββ | 30/179 [00:10<00:54, 2.74it/s][A
|
| 5456 |
+
|
| 5457 |
17%|βββββ | 31/179 [00:11<00:51, 2.85it/s][A
|
| 5458 |
+
|
| 5459 |
18%|βββββ | 32/179 [00:11<00:50, 2.93it/s][A
|
| 5460 |
+
|
| 5461 |
18%|βββββ | 33/179 [00:11<00:57, 2.52it/s][A
|
| 5462 |
+
|
| 5463 |
19%|βββββ | 34/179 [00:12<00:52, 2.74it/s][A
|
| 5464 |
+
|
| 5465 |
20%|βββββ | 35/179 [00:12<00:50, 2.85it/s][A
|
| 5466 |
+
|
| 5467 |
20%|βββββ | 36/179 [00:12<00:48, 2.93it/s][A
|
| 5468 |
+
|
| 5469 |
21%|ββββββ | 37/179 [00:13<00:56, 2.51it/s][A
|
| 5470 |
+
|
| 5471 |
21%|ββββββ | 38/179 [00:13<00:51, 2.74it/s][A
|
| 5472 |
+
|
| 5473 |
22%|ββββοΏ½οΏ½οΏ½β | 39/179 [00:14<00:49, 2.85it/s][A
|
| 5474 |
+
|
| 5475 |
22%|ββββββ | 40/179 [00:14<00:47, 2.93it/s][A
|
| 5476 |
+
|
| 5477 |
23%|ββββββ | 41/179 [00:14<00:54, 2.52it/s][A
|
| 5478 |
+
|
| 5479 |
23%|ββββββ | 42/179 [00:15<00:49, 2.75it/s][A
|
| 5480 |
+
|
| 5481 |
24%|ββββββ | 43/179 [00:15<00:47, 2.85it/s][A
|
| 5482 |
+
|
| 5483 |
25%|βββββββ | 44/179 [00:15<00:46, 2.93it/s][A
|
| 5484 |
+
|
| 5485 |
25%|βββββββ | 45/179 [00:16<00:53, 2.51it/s][A
|
| 5486 |
+
|
| 5487 |
26%|βββββββ | 46/179 [00:16<00:48, 2.74it/s][A
|
| 5488 |
+
|
| 5489 |
26%|βββββββ | 47/179 [00:16<00:46, 2.85it/s][A
|
| 5490 |
+
|
| 5491 |
27%|βββββββ | 48/179 [00:17<00:44, 2.93it/s][A
|
| 5492 |
+
|
| 5493 |
27%|βββββββ | 49/179 [00:17<00:51, 2.52it/s][A
|
| 5494 |
+
|
| 5495 |
28%|βββββββ | 50/179 [00:18<00:47, 2.74it/s][A
|
| 5496 |
+
|
| 5497 |
28%|βββββββ | 51/179 [00:18<00:45, 2.84it/s][A
|
| 5498 |
+
|
| 5499 |
29%|ββββββββ | 52/179 [00:18<00:43, 2.92it/s][A
|
| 5500 |
+
|
| 5501 |
30%|ββββββββ | 53/179 [00:19<00:50, 2.51it/s][A
|
| 5502 |
+
|
| 5503 |
30%|ββββββββ | 54/179 [00:19<00:45, 2.73it/s][A
|
| 5504 |
+
|
| 5505 |
31%|ββββββββ | 55/179 [00:19<00:43, 2.84it/s][A
|
| 5506 |
+
|
| 5507 |
31%|ββββββββ | 56/179 [00:20<00:42, 2.92it/s][A
|
| 5508 |
+
|
| 5509 |
32%|ββββββββ | 57/179 [00:20<00:48, 2.51it/s][A
|
| 5510 |
+
|
| 5511 |
32%|ββββββββ | 58/179 [00:21<00:44, 2.74it/s][A
|
| 5512 |
+
|
| 5513 |
33%|βββββββββ | 59/179 [00:21<00:42, 2.85it/s][A
|
| 5514 |
+
|
| 5515 |
34%|βββββββββ | 60/179 [00:21<00:40, 2.92it/s][A
|
| 5516 |
+
|
| 5517 |
34%|βββββββββ | 61/179 [00:22<00:46, 2.52it/s][A
|
| 5518 |
+
|
| 5519 |
35%|βββββββββ | 62/179 [00:22<00:42, 2.73it/s][A
|
| 5520 |
+
|
| 5521 |
35%|βββββββββ | 63/179 [00:22<00:40, 2.84it/s][A
|
| 5522 |
+
|
| 5523 |
36%|βββββββββ | 64/179 [00:23<00:39, 2.92it/s][A
|
| 5524 |
+
|
| 5525 |
36%|βββββββββ | 65/179 [00:23<00:45, 2.51it/s][A
|
| 5526 |
+
|
| 5527 |
37%|ββββββββββ | 66/179 [00:23<00:41, 2.74it/s][A
|
| 5528 |
+
|
| 5529 |
37%|ββββββββββ | 67/179 [00:24<00:39, 2.84it/s][A
|
| 5530 |
+
|
| 5531 |
38%|ββββββββββ | 68/179 [00:24<00:37, 2.92it/s][A
|
| 5532 |
+
|
| 5533 |
39%|ββββββββββ | 69/179 [00:25<00:43, 2.51it/s][A
|
| 5534 |
+
|
| 5535 |
39%|ββββββββββ | 70/179 [00:25<00:39, 2.73it/s][A
|
| 5536 |
+
|
| 5537 |
40%|ββββββββββ | 71/179 [00:25<00:37, 2.84it/s][A
|
| 5538 |
+
|
| 5539 |
40%|ββββββββββ | 72/179 [00:26<00:36, 2.92it/s][A
|
| 5540 |
+
|
| 5541 |
41%|βββββββββββ | 73/179 [00:26<00:42, 2.51it/s][A
|
| 5542 |
+
|
| 5543 |
41%|βββββββββββ | 74/179 [00:26<00:38, 2.74it/s][A
|
| 5544 |
+
|
| 5545 |
42%|βββββββββββ | 75/179 [00:27<00:36, 2.85it/s][A
|
| 5546 |
+
|
| 5547 |
42%|βββββββββββ | 76/179 [00:27<00:35, 2.93it/s][A
|
| 5548 |
+
|
| 5549 |
43%|βββββββββββ | 77/179 [00:28<00:44, 2.28it/s][A
|
| 5550 |
+
|
| 5551 |
44%|βββββββββββ | 78/179 [00:28<00:39, 2.53it/s][A
|
| 5552 |
+
|
| 5553 |
44%|βββββββββββ | 79/179 [00:28<00:37, 2.68it/s][A
|
| 5554 |
+
|
| 5555 |
45%|ββββββββββββ | 80/179 [00:29<00:35, 2.80it/s][A
|
| 5556 |
+
|
| 5557 |
45%|ββββββββββββ | 81/179 [00:29<00:39, 2.45it/s][A
|
| 5558 |
+
|
| 5559 |
46%|ββββββββββββ | 82/179 [00:29<00:36, 2.69it/s][A
|
| 5560 |
+
|
| 5561 |
46%|ββββββββββββ | 83/179 [00:30<00:34, 2.80it/s][A
|
| 5562 |
+
|
| 5563 |
47%|ββββββββββββ | 84/179 [00:30<00:32, 2.89it/s][A
|
| 5564 |
+
|
| 5565 |
47%|ββββββββββββ | 85/179 [00:31<00:43, 2.18it/s][A
|
| 5566 |
+
|
| 5567 |
48%|ββββββββββββ | 86/179 [00:31<00:37, 2.45it/s][A
|
| 5568 |
+
|
| 5569 |
49%|βββββββββββββ | 87/179 [00:31<00:35, 2.63it/s][A
|
| 5570 |
+
|
| 5571 |
49%|βββββββββββββ | 88/179 [00:32<00:32, 2.76it/s][A
|
| 5572 |
+
|
| 5573 |
50%|βββββββββββββ | 89/179 [00:32<00:37, 2.43it/s][A
|
| 5574 |
+
|
| 5575 |
50%|βββββββββββββ | 90/179 [00:32<00:33, 2.67it/s][A
|
| 5576 |
+
|
| 5577 |
51%|βββββββββββββ | 91/179 [00:33<00:31, 2.79it/s][A
|
| 5578 |
+
|
| 5579 |
51%|βββββββββββββ | 92/179 [00:33<00:30, 2.88it/s][A
|
| 5580 |
+
|
| 5581 |
52%|βββββββββββββ | 93/179 [00:34<00:34, 2.50it/s][A
|
| 5582 |
+
|
| 5583 |
53%|ββββββββββββββ | 94/179 [00:34<00:31, 2.73it/s][A
|
| 5584 |
+
|
| 5585 |
53%|ββββββββββββββ | 95/179 [00:34<00:29, 2.84it/s][A
|
| 5586 |
+
|
| 5587 |
54%|ββββββββββββββ | 96/179 [00:35<00:28, 2.91it/s][A
|
| 5588 |
+
|
| 5589 |
54%|ββββββββββββββ | 97/179 [00:35<00:32, 2.51it/s][A
|
| 5590 |
+
|
| 5591 |
55%|ββββββββββββββ | 98/179 [00:35<00:29, 2.73it/s][A
|
| 5592 |
+
|
| 5593 |
55%|ββββββββββββββ | 99/179 [00:36<00:28, 2.83it/s][A
|
| 5594 |
+
|
| 5595 |
56%|ββββββββββββββ | 100/179 [00:36<00:27, 2.91it/s][A
|
| 5596 |
+
|
| 5597 |
56%|ββββββββββββββ | 101/179 [00:37<00:31, 2.51it/s][A
|
| 5598 |
+
|
| 5599 |
57%|ββββββββββββββ | 102/179 [00:37<00:28, 2.73it/s][A
|
| 5600 |
+
|
| 5601 |
58%|ββββββββββββββ | 103/179 [00:37<00:26, 2.84it/s][A
|
| 5602 |
+
|
| 5603 |
58%|ββββββββββββββ | 104/179 [00:38<00:25, 2.91it/s][A
|
| 5604 |
+
|
| 5605 |
59%|ββββββββββββββ | 105/179 [00:38<00:29, 2.50it/s][A
|
| 5606 |
+
|
| 5607 |
59%|βββββββββββββββ | 106/179 [00:38<00:26, 2.73it/s][A
|
| 5608 |
+
|
| 5609 |
60%|βββββββββββββββ | 107/179 [00:39<00:25, 2.83it/s][A
|
| 5610 |
+
|
| 5611 |
60%|βββββββββββββββ | 108/179 [00:39<00:24, 2.92it/s][A
|
| 5612 |
+
|
| 5613 |
61%|βββββββββββββββ | 109/179 [00:39<00:27, 2.52it/s][A
|
| 5614 |
+
|
| 5615 |
61%|βββββββββββββββ | 110/179 [00:40<00:25, 2.74it/s][A
|
| 5616 |
+
|
| 5617 |
62%|βββββββββββββββ | 111/179 [00:40<00:23, 2.85it/s][A
|
| 5618 |
+
|
| 5619 |
63%|βββββββββββββββ | 112/179 [00:40<00:22, 2.92it/s][A
|
| 5620 |
+
|
| 5621 |
63%|ββββββββββββββββ | 113/179 [00:41<00:26, 2.51it/s][A
|
| 5622 |
+
|
| 5623 |
64%|ββββββββββββββββ | 114/179 [00:41<00:23, 2.73it/s][A
|
| 5624 |
+
|
| 5625 |
64%|ββββββββββββββββ | 115/179 [00:42<00:22, 2.84it/s][A
|
| 5626 |
+
|
| 5627 |
65%|ββββββββββββββββ | 116/179 [00:42<00:21, 2.92it/s][A
|
| 5628 |
+
|
| 5629 |
65%|ββββββββββββββββ | 117/179 [00:42<00:24, 2.51it/s][A
|
| 5630 |
+
|
| 5631 |
66%|ββββββββββββββββ | 118/179 [00:43<00:22, 2.73it/s][A
|
| 5632 |
+
|
| 5633 |
66%|ββββββββββββββββ | 119/179 [00:43<00:21, 2.84it/s][A
|
| 5634 |
+
|
| 5635 |
67%|ββββββββββββββββ | 120/179 [00:43<00:20, 2.92it/s][A
|
| 5636 |
+
|
| 5637 |
68%|βββββββββββββββββ | 121/179 [00:44<00:23, 2.52it/s][A
|
| 5638 |
+
|
| 5639 |
68%|βββββββββββββββββ | 122/179 [00:44<00:20, 2.74it/s][A
|
| 5640 |
+
|
| 5641 |
69%|βββββββββββββββββ | 123/179 [00:44<00:19, 2.85it/s][A
|
| 5642 |
+
|
| 5643 |
69%|βββββββββββββββββ | 124/179 [00:45<00:18, 2.92it/s][A
|
| 5644 |
+
|
| 5645 |
70%|βββββββββββββββββ | 125/179 [00:45<00:21, 2.52it/s][A
|
| 5646 |
+
|
| 5647 |
70%|βββββββββββββββββ | 126/179 [00:46<00:19, 2.73it/s][A
|
| 5648 |
+
|
| 5649 |
71%|βββββββββββββββββ | 127/179 [00:46<00:18, 2.84it/s][A
|
| 5650 |
+
|
| 5651 |
72%|ββββββββββββββββββ | 128/179 [00:46<00:17, 2.91it/s][A
|
| 5652 |
+
|
| 5653 |
72%|ββββββββββββββββββ | 129/179 [00:47<00:19, 2.51it/s][A
|
| 5654 |
+
|
| 5655 |
73%|ββββββββββββββββββ | 130/179 [00:47<00:17, 2.73it/s][A
|
| 5656 |
+
|
| 5657 |
73%|ββββββββββββββββββ | 131/179 [00:47<00:16, 2.84it/s][A
|
| 5658 |
+
|
| 5659 |
74%|ββββββββββββββββββ | 132/179 [00:48<00:16, 2.91it/s][A
|
| 5660 |
+
|
| 5661 |
74%|ββββββββββββββββββ | 133/179 [00:48<00:18, 2.50it/s][A
|
| 5662 |
+
|
| 5663 |
75%|ββββββββββββββββββ | 134/179 [00:49<00:16, 2.72it/s][A
|
| 5664 |
+
|
| 5665 |
75%|ββββββββββββββββββ | 135/179 [00:49<00:15, 2.83it/s][A
|
| 5666 |
+
|
| 5667 |
76%|βββββββββββββββββββ | 136/179 [00:49<00:14, 2.91it/s][A
|
| 5668 |
+
|
| 5669 |
77%|βββββββββββββββββββ | 137/179 [00:50<00:16, 2.51it/s][A
|
| 5670 |
+
|
| 5671 |
77%|βββββββββββββββββββ | 138/179 [00:50<00:14, 2.74it/s][A
|
| 5672 |
+
|
| 5673 |
78%|βββββββββββββββββββ | 139/179 [00:50<00:14, 2.83it/s][A
|
| 5674 |
+
|
| 5675 |
78%|βββββββββββββββββββ | 140/179 [00:51<00:13, 2.91it/s][A
|
| 5676 |
+
|
| 5677 |
79%|βββββββββββββββββββ | 141/179 [00:51<00:15, 2.51it/s][A
|
| 5678 |
+
|
| 5679 |
79%|βββββββββββββββββββ | 142/179 [00:51<00:13, 2.73it/s][A
|
| 5680 |
+
|
| 5681 |
80%|ββββββββββββββββββββ | 143/179 [00:52<00:12, 2.83it/s][A
|
| 5682 |
+
|
| 5683 |
80%|ββββββββββββββββββββ | 144/179 [00:52<00:12, 2.91it/s][A
|
| 5684 |
+
|
| 5685 |
81%|ββββββββββββββββββββ | 145/179 [00:53<00:13, 2.50it/s][A
|
| 5686 |
+
|
| 5687 |
82%|ββββββββββββββββββββ | 146/179 [00:53<00:12, 2.73it/s][A
|
| 5688 |
+
|
| 5689 |
82%|ββββββββββββββββββββ | 147/179 [00:53<00:11, 2.84it/s][A
|
| 5690 |
+
|
| 5691 |
83%|ββββββββββββββββββββ | 148/179 [00:54<00:10, 2.92it/s][A
|
| 5692 |
+
|
| 5693 |
83%|ββββββββββββββββββββ | 149/179 [00:54<00:11, 2.51it/s][A
|
| 5694 |
+
|
| 5695 |
84%|ββββββββββββββββββββ | 150/179 [00:54<00:10, 2.74it/s][A
|
| 5696 |
+
|
| 5697 |
84%|βββββββββββββββββββββ | 151/179 [00:55<00:09, 2.84it/s][A
|
| 5698 |
+
|
| 5699 |
85%|βββββββββββββββββββββ | 152/179 [00:55<00:09, 2.92it/s][A
|
| 5700 |
+
|
| 5701 |
85%|βββββββββββββββββββββ | 153/179 [00:56<00:10, 2.52it/s][A
|
| 5702 |
+
|
| 5703 |
86%|βββββββββββββββββββββ | 154/179 [00:56<00:09, 2.74it/s][A
|
| 5704 |
+
|
| 5705 |
87%|βββββββββββββββββββββ | 155/179 [00:56<00:08, 2.85it/s][A
|
| 5706 |
+
|
| 5707 |
87%|βββββββββββββββββββββ | 156/179 [00:56<00:07, 2.92it/s][A
|
| 5708 |
+
|
| 5709 |
88%|βββββββββββββββββββββ | 157/179 [00:57<00:08, 2.51it/s][A
|
| 5710 |
+
|
| 5711 |
88%|ββββββββββββββββββββββ | 158/179 [00:57<00:07, 2.74it/s][A
|
| 5712 |
+
|
| 5713 |
89%|ββββββββββββββββββββββ | 159/179 [00:58<00:07, 2.85it/s][A
|
| 5714 |
+
|
| 5715 |
89%|ββββββββββββββββββββββ | 160/179 [00:58<00:06, 2.92it/s][A
|
| 5716 |
+
|
| 5717 |
90%|ββββββββββββββββββββββ | 161/179 [00:58<00:07, 2.51it/s][A
|
| 5718 |
+
|
| 5719 |
91%|ββββββββββββββββββββββ | 162/179 [00:59<00:06, 2.74it/s][A
|
| 5720 |
+
|
| 5721 |
91%|ββββββββββββββββββββββ | 163/179 [00:59<00:05, 2.85it/s][A
|
| 5722 |
+
|
| 5723 |
92%|ββββββββββββββββββββββ | 164/179 [00:59<00:05, 2.93it/s][A
|
| 5724 |
+
|
| 5725 |
92%|ββββββββββββββββββββββ | 165/179 [01:00<00:05, 2.51it/s][A
|
| 5726 |
+
|
| 5727 |
93%|βββββββββββββββββββββββ | 166/179 [01:00<00:04, 2.73it/s][A
|
| 5728 |
+
|
| 5729 |
93%|βββββββββββββββββββββββ | 167/179 [01:01<00:04, 2.84it/s][A
|
| 5730 |
+
|
| 5731 |
94%|βββββββββββββββββββββββ | 168/179 [01:01<00:03, 2.92it/s][A
|
| 5732 |
+
|
| 5733 |
94%|βββββββββββββββββββββββ | 169/179 [01:01<00:03, 2.52it/s][A
|
| 5734 |
+
|
| 5735 |
95%|βββββββββββββββββββββββ | 170/179 [01:02<00:03, 2.75it/s][A
|
| 5736 |
+
|
| 5737 |
96%|βββββββββββββββββββββββ | 171/179 [01:02<00:02, 2.85it/s][A
|
| 5738 |
+
|
| 5739 |
96%|βββββββββββββββββββββββ | 172/179 [01:02<00:02, 2.92it/s][A
|
| 5740 |
+
|
| 5741 |
97%|ββββββββββββββββββββββββ| 173/179 [01:03<00:02, 2.52it/s][A
|
| 5742 |
+
|
| 5743 |
97%|ββββββββββββββββββββββββ| 174/179 [01:03<00:01, 2.74it/s][A
|
| 5744 |
+
|
| 5745 |
98%|ββββββββββββββββββββββββ| 175/179 [01:03<00:01, 2.85it/s][A
|
| 5746 |
+
|
| 5747 |
98%|ββββββββββββββββββββββββ| 176/179 [01:04<00:01, 2.92it/s][A
|
| 5748 |
+
|
| 5749 |
99%|ββββββββββββββββββββββββ| 177/179 [01:04<00:00, 2.52it/s][A
|
| 5750 |
+
|
| 5751 |
99%|ββββββββββββββββββββββββ| 178/179 [01:05<00:00, 2.74it/s][A
|
| 5752 |
+
|
| 5753 |
|
| 5754 |
+
|
| 5755 |
|
| 5756 |
+
|
| 5757 |
+
|
| 5758 |
+
|
| 5759 |
[A[2025-10-19 01:14:15,108] [INFO] [axolotl.core.trainers.base._save:664] [PID:42363] Saving model checkpoint to ./outputs/sft/gemma-2-2b-it-rp-sft-qlora/checkpoint-1000
|
| 5760 |
+
|
| 5761 |
|
| 5762 |
+
|