rbelanec commited on
Commit
7138191
·
verified ·
1 Parent(s): a3abea9

Training in progress, step 1080

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +20 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f7b61663d5465934c31edf09497284fabb5155a93f16a6ab29c8ead1a4188b2
3
  size 58745928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ab31619b826fac47eea0be4d66aa2499a233b78d65bc78c03e5a80532e935b4
3
  size 58745928
trainer_log.jsonl CHANGED
@@ -216,3 +216,23 @@
216
  {"current_steps": 1025, "total_steps": 1800, "loss": 0.0, "lr": 2.3352827570433036e-05, "epoch": 11.38888888888889, "percentage": 56.94, "elapsed_time": "0:03:54", "remaining_time": "0:02:57", "throughput": 1373.5, "total_tokens": 321536}
217
  {"current_steps": 1030, "total_steps": 1800, "loss": 0.0, "lr": 2.3111028677519804e-05, "epoch": 11.444444444444445, "percentage": 57.22, "elapsed_time": "0:03:55", "remaining_time": "0:02:55", "throughput": 1374.07, "total_tokens": 323040}
218
  {"current_steps": 1035, "total_steps": 1800, "loss": 0.0, "lr": 2.2869407379996088e-05, "epoch": 11.5, "percentage": 57.5, "elapsed_time": "0:03:56", "remaining_time": "0:02:54", "throughput": 1374.94, "total_tokens": 324608}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
216
  {"current_steps": 1025, "total_steps": 1800, "loss": 0.0, "lr": 2.3352827570433036e-05, "epoch": 11.38888888888889, "percentage": 56.94, "elapsed_time": "0:03:54", "remaining_time": "0:02:57", "throughput": 1373.5, "total_tokens": 321536}
217
  {"current_steps": 1030, "total_steps": 1800, "loss": 0.0, "lr": 2.3111028677519804e-05, "epoch": 11.444444444444445, "percentage": 57.22, "elapsed_time": "0:03:55", "remaining_time": "0:02:55", "throughput": 1374.07, "total_tokens": 323040}
218
  {"current_steps": 1035, "total_steps": 1800, "loss": 0.0, "lr": 2.2869407379996088e-05, "epoch": 11.5, "percentage": 57.5, "elapsed_time": "0:03:56", "remaining_time": "0:02:54", "throughput": 1374.94, "total_tokens": 324608}
219
+ {"current_steps": 1040, "total_steps": 1800, "loss": 0.0, "lr": 2.2627986394367938e-05, "epoch": 11.555555555555555, "percentage": 57.78, "elapsed_time": "0:03:57", "remaining_time": "0:02:53", "throughput": 1375.7, "total_tokens": 326144}
220
+ {"current_steps": 1045, "total_steps": 1800, "loss": 0.0, "lr": 2.238678841830867e-05, "epoch": 11.61111111111111, "percentage": 58.06, "elapsed_time": "0:03:58", "remaining_time": "0:02:52", "throughput": 1376.54, "total_tokens": 327712}
221
+ {"current_steps": 1050, "total_steps": 1800, "loss": 0.0, "lr": 2.2145836128524902e-05, "epoch": 11.666666666666666, "percentage": 58.33, "elapsed_time": "0:03:59", "remaining_time": "0:02:50", "throughput": 1377.22, "total_tokens": 329248}
222
+ {"current_steps": 1055, "total_steps": 1800, "loss": 0.0, "lr": 2.1905152178624595e-05, "epoch": 11.722222222222221, "percentage": 58.61, "elapsed_time": "0:04:00", "remaining_time": "0:02:49", "throughput": 1378.07, "total_tokens": 330816}
223
+ {"current_steps": 1060, "total_steps": 1800, "loss": 0.0, "lr": 2.1664759196987182e-05, "epoch": 11.777777777777779, "percentage": 58.89, "elapsed_time": "0:04:01", "remaining_time": "0:02:48", "throughput": 1379.0, "total_tokens": 332416}
224
+ {"current_steps": 1065, "total_steps": 1800, "loss": 0.0, "lr": 2.1424679784636144e-05, "epoch": 11.833333333333334, "percentage": 59.17, "elapsed_time": "0:04:02", "remaining_time": "0:02:47", "throughput": 1380.01, "total_tokens": 334016}
225
+ {"current_steps": 1070, "total_steps": 1800, "loss": 0.0, "lr": 2.118493651311413e-05, "epoch": 11.88888888888889, "percentage": 59.44, "elapsed_time": "0:04:03", "remaining_time": "0:02:45", "throughput": 1381.01, "total_tokens": 335616}
226
+ {"current_steps": 1075, "total_steps": 1800, "loss": 0.0, "lr": 2.0945551922360818e-05, "epoch": 11.944444444444445, "percentage": 59.72, "elapsed_time": "0:04:04", "remaining_time": "0:02:44", "throughput": 1381.75, "total_tokens": 337152}
227
+ {"current_steps": 1080, "total_steps": 1800, "loss": 0.0, "lr": 2.070654851859383e-05, "epoch": 12.0, "percentage": 60.0, "elapsed_time": "0:04:05", "remaining_time": "0:02:43", "throughput": 1382.68, "total_tokens": 338784}
228
+ {"current_steps": 1080, "total_steps": 1800, "eval_loss": 0.09843836724758148, "epoch": 12.0, "percentage": 60.0, "elapsed_time": "0:04:05", "remaining_time": "0:02:43", "throughput": 1379.31, "total_tokens": 338784}
229
+ {"current_steps": 1085, "total_steps": 1800, "loss": 0.0, "lr": 2.0467948772192713e-05, "epoch": 12.055555555555555, "percentage": 60.28, "elapsed_time": "0:04:08", "remaining_time": "0:02:44", "throughput": 1366.69, "total_tokens": 340288}
230
+ {"current_steps": 1090, "total_steps": 1800, "loss": 0.0, "lr": 2.022977511558638e-05, "epoch": 12.11111111111111, "percentage": 60.56, "elapsed_time": "0:04:09", "remaining_time": "0:02:42", "throughput": 1367.62, "total_tokens": 341888}
231
+ {"current_steps": 1095, "total_steps": 1800, "loss": 0.0, "lr": 1.9992049941144066e-05, "epoch": 12.166666666666666, "percentage": 60.83, "elapsed_time": "0:04:10", "remaining_time": "0:02:41", "throughput": 1368.48, "total_tokens": 343488}
232
+ {"current_steps": 1100, "total_steps": 1800, "loss": 0.0, "lr": 1.9754795599070068e-05, "epoch": 12.222222222222221, "percentage": 61.11, "elapsed_time": "0:04:12", "remaining_time": "0:02:40", "throughput": 1369.0, "total_tokens": 344992}
233
+ {"current_steps": 1105, "total_steps": 1800, "loss": 0.0, "lr": 1.9518034395302414e-05, "epoch": 12.277777777777779, "percentage": 61.39, "elapsed_time": "0:04:13", "remaining_time": "0:02:39", "throughput": 1367.8, "total_tokens": 346560}
234
+ {"current_steps": 1110, "total_steps": 1800, "loss": 0.0, "lr": 1.9281788589415804e-05, "epoch": 12.333333333333334, "percentage": 61.67, "elapsed_time": "0:04:14", "remaining_time": "0:02:38", "throughput": 1368.81, "total_tokens": 348160}
235
+ {"current_steps": 1115, "total_steps": 1800, "loss": 0.0, "lr": 1.9046080392528735e-05, "epoch": 12.38888888888889, "percentage": 61.94, "elapsed_time": "0:04:15", "remaining_time": "0:02:36", "throughput": 1369.75, "total_tokens": 349760}
236
+ {"current_steps": 1120, "total_steps": 1800, "loss": 0.0, "lr": 1.8810931965215356e-05, "epoch": 12.444444444444445, "percentage": 62.22, "elapsed_time": "0:04:16", "remaining_time": "0:02:35", "throughput": 1370.56, "total_tokens": 351328}
237
+ {"current_steps": 1125, "total_steps": 1800, "loss": 0.0, "lr": 1.857636541542195e-05, "epoch": 12.5, "percentage": 62.5, "elapsed_time": "0:04:17", "remaining_time": "0:02:34", "throughput": 1371.38, "total_tokens": 352896}
238
+ {"current_steps": 1130, "total_steps": 1800, "loss": 0.0, "lr": 1.8342402796388445e-05, "epoch": 12.555555555555555, "percentage": 62.78, "elapsed_time": "0:04:18", "remaining_time": "0:02:33", "throughput": 1372.22, "total_tokens": 354464}