rbelanec commited on
Commit
e55735c
·
verified ·
1 Parent(s): 4ac5478

Training in progress, step 1440

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +17 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25ee9022fdd3e9466b208ba0dc7da9cbc8e833246b4e8d575a0adfb7ffa1c6cf
3
  size 58745928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4a8063d9b9ae95208579b781633808cde4724bd0d4288433618a556c2455f86
3
  size 58745928
trainer_log.jsonl CHANGED
@@ -298,3 +298,20 @@
298
  {"current_steps": 1415, "total_steps": 1800, "loss": 0.0, "lr": 6.683127646793411e-06, "epoch": 15.722222222222221, "percentage": 78.61, "elapsed_time": "0:05:22", "remaining_time": "0:01:27", "throughput": 1375.98, "total_tokens": 443616}
299
  {"current_steps": 1420, "total_steps": 1800, "loss": 0.0, "lr": 6.519014324435102e-06, "epoch": 15.777777777777779, "percentage": 78.89, "elapsed_time": "0:05:23", "remaining_time": "0:01:26", "throughput": 1376.53, "total_tokens": 445184}
300
  {"current_steps": 1425, "total_steps": 1800, "loss": 0.0, "lr": 6.356638528639955e-06, "epoch": 15.833333333333334, "percentage": 79.17, "elapsed_time": "0:05:24", "remaining_time": "0:01:25", "throughput": 1377.1, "total_tokens": 446752}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
298
  {"current_steps": 1415, "total_steps": 1800, "loss": 0.0, "lr": 6.683127646793411e-06, "epoch": 15.722222222222221, "percentage": 78.61, "elapsed_time": "0:05:22", "remaining_time": "0:01:27", "throughput": 1375.98, "total_tokens": 443616}
299
  {"current_steps": 1420, "total_steps": 1800, "loss": 0.0, "lr": 6.519014324435102e-06, "epoch": 15.777777777777779, "percentage": 78.89, "elapsed_time": "0:05:23", "remaining_time": "0:01:26", "throughput": 1376.53, "total_tokens": 445184}
300
  {"current_steps": 1425, "total_steps": 1800, "loss": 0.0, "lr": 6.356638528639955e-06, "epoch": 15.833333333333334, "percentage": 79.17, "elapsed_time": "0:05:24", "remaining_time": "0:01:25", "throughput": 1377.1, "total_tokens": 446752}
301
+ {"current_steps": 1430, "total_steps": 1800, "loss": 0.0, "lr": 6.196015525490825e-06, "epoch": 15.88888888888889, "percentage": 79.44, "elapsed_time": "0:05:25", "remaining_time": "0:01:24", "throughput": 1377.74, "total_tokens": 448352}
302
+ {"current_steps": 1435, "total_steps": 1800, "loss": 0.0, "lr": 6.037160416278278e-06, "epoch": 15.944444444444445, "percentage": 79.72, "elapsed_time": "0:05:26", "remaining_time": "0:01:23", "throughput": 1378.2, "total_tokens": 449888}
303
+ {"current_steps": 1440, "total_steps": 1800, "loss": 0.0, "lr": 5.880088136080814e-06, "epoch": 16.0, "percentage": 80.0, "elapsed_time": "0:05:27", "remaining_time": "0:01:21", "throughput": 1378.51, "total_tokens": 451424}
304
+ {"current_steps": 1440, "total_steps": 1800, "eval_loss": 0.10147368907928467, "epoch": 16.0, "percentage": 80.0, "elapsed_time": "0:05:28", "remaining_time": "0:01:22", "throughput": 1375.93, "total_tokens": 451424}
305
+ {"current_steps": 1445, "total_steps": 1800, "loss": 0.0, "lr": 5.724813452360736e-06, "epoch": 16.055555555555557, "percentage": 80.28, "elapsed_time": "0:05:30", "remaining_time": "0:01:21", "throughput": 1370.46, "total_tokens": 452992}
306
+ {"current_steps": 1450, "total_steps": 1800, "loss": 0.0, "lr": 5.571350963575728e-06, "epoch": 16.11111111111111, "percentage": 80.56, "elapsed_time": "0:05:31", "remaining_time": "0:01:20", "throughput": 1370.84, "total_tokens": 454496}
307
+ {"current_steps": 1455, "total_steps": 1800, "loss": 0.0, "lr": 5.4197150978063965e-06, "epoch": 16.166666666666668, "percentage": 80.83, "elapsed_time": "0:05:32", "remaining_time": "0:01:18", "throughput": 1371.48, "total_tokens": 456096}
308
+ {"current_steps": 1460, "total_steps": 1800, "loss": 0.0, "lr": 5.269920111399732e-06, "epoch": 16.22222222222222, "percentage": 81.11, "elapsed_time": "0:05:33", "remaining_time": "0:01:17", "throughput": 1370.62, "total_tokens": 457696}
309
+ {"current_steps": 1465, "total_steps": 1800, "loss": 0.0, "lr": 5.121980087628803e-06, "epoch": 16.27777777777778, "percentage": 81.39, "elapsed_time": "0:05:34", "remaining_time": "0:01:16", "throughput": 1371.14, "total_tokens": 459232}
310
+ {"current_steps": 1470, "total_steps": 1800, "loss": 0.0, "lr": 4.975908935368701e-06, "epoch": 16.333333333333332, "percentage": 81.67, "elapsed_time": "0:05:35", "remaining_time": "0:01:15", "throughput": 1371.83, "total_tokens": 460832}
311
+ {"current_steps": 1475, "total_steps": 1800, "loss": 0.0, "lr": 4.831720387788827e-06, "epoch": 16.38888888888889, "percentage": 81.94, "elapsed_time": "0:05:36", "remaining_time": "0:01:14", "throughput": 1372.52, "total_tokens": 462432}
312
+ {"current_steps": 1480, "total_steps": 1800, "loss": 0.0, "lr": 4.689428001061774e-06, "epoch": 16.444444444444443, "percentage": 82.22, "elapsed_time": "0:05:37", "remaining_time": "0:01:13", "throughput": 1373.12, "total_tokens": 464000}
313
+ {"current_steps": 1485, "total_steps": 1800, "loss": 0.0, "lr": 4.549045153088813e-06, "epoch": 16.5, "percentage": 82.5, "elapsed_time": "0:05:38", "remaining_time": "0:01:11", "throughput": 1373.65, "total_tokens": 465536}
314
+ {"current_steps": 1490, "total_steps": 1800, "loss": 0.0, "lr": 4.410585042242124e-06, "epoch": 16.555555555555557, "percentage": 82.78, "elapsed_time": "0:05:39", "remaining_time": "0:01:10", "throughput": 1374.32, "total_tokens": 467136}
315
+ {"current_steps": 1495, "total_steps": 1800, "loss": 0.0, "lr": 4.274060686123959e-06, "epoch": 16.61111111111111, "percentage": 83.06, "elapsed_time": "0:05:40", "remaining_time": "0:01:09", "throughput": 1374.86, "total_tokens": 468672}
316
+ {"current_steps": 1500, "total_steps": 1800, "loss": 0.0, "lr": 4.1394849203427284e-06, "epoch": 16.666666666666668, "percentage": 83.33, "elapsed_time": "0:05:41", "remaining_time": "0:01:08", "throughput": 1375.59, "total_tokens": 470272}
317
+ {"current_steps": 1505, "total_steps": 1800, "loss": 0.0, "lr": 4.006870397306256e-06, "epoch": 16.72222222222222, "percentage": 83.61, "elapsed_time": "0:05:42", "remaining_time": "0:01:07", "throughput": 1376.24, "total_tokens": 471872}