rbelanec commited on
Commit
f3aa6b8
verified
1 Parent(s): 4d9f5bc

Training in progress, step 200

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:b78b1ec9cf6afa93077b396b7f597d60636c4ce6a51a8479ada777ac4fb35c8f
3
  size 8388736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:679d03e8b10d2e4224bd848e0825dc20c19528640c44dc22a8aa1585c85a17a6
3
  size 8388736
trainer_log.jsonl CHANGED
@@ -27,3 +27,20 @@
27
  {"current_steps": 130, "total_steps": 1000, "loss": 0.128, "lr": 9.974403544143942e-06, "epoch": 2.6, "percentage": 13.0, "elapsed_time": "0:00:23", "remaining_time": "0:02:36", "throughput": 3551.4, "total_tokens": 82880}
28
  {"current_steps": 135, "total_steps": 1000, "loss": 0.2987, "lr": 9.964827540532685e-06, "epoch": 2.7, "percentage": 13.5, "elapsed_time": "0:00:24", "remaining_time": "0:02:34", "throughput": 3583.48, "total_tokens": 86560}
29
  {"current_steps": 140, "total_steps": 1000, "loss": 0.2105, "lr": 9.953739202357219e-06, "epoch": 2.8, "percentage": 14.0, "elapsed_time": "0:00:24", "remaining_time": "0:02:32", "throughput": 3600.02, "total_tokens": 89184}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  {"current_steps": 130, "total_steps": 1000, "loss": 0.128, "lr": 9.974403544143942e-06, "epoch": 2.6, "percentage": 13.0, "elapsed_time": "0:00:23", "remaining_time": "0:02:36", "throughput": 3551.4, "total_tokens": 82880}
28
  {"current_steps": 135, "total_steps": 1000, "loss": 0.2987, "lr": 9.964827540532685e-06, "epoch": 2.7, "percentage": 13.5, "elapsed_time": "0:00:24", "remaining_time": "0:02:34", "throughput": 3583.48, "total_tokens": 86560}
29
  {"current_steps": 140, "total_steps": 1000, "loss": 0.2105, "lr": 9.953739202357219e-06, "epoch": 2.8, "percentage": 14.0, "elapsed_time": "0:00:24", "remaining_time": "0:02:32", "throughput": 3600.02, "total_tokens": 89184}
30
+ {"current_steps": 145, "total_steps": 1000, "loss": 0.2897, "lr": 9.941141907232766e-06, "epoch": 2.9, "percentage": 14.5, "elapsed_time": "0:00:25", "remaining_time": "0:02:30", "throughput": 3619.43, "total_tokens": 92256}
31
+ {"current_steps": 150, "total_steps": 1000, "loss": 0.2661, "lr": 9.927039492417452e-06, "epoch": 3.0, "percentage": 15.0, "elapsed_time": "0:00:26", "remaining_time": "0:02:28", "throughput": 3631.41, "total_tokens": 95168}
32
+ {"current_steps": 155, "total_steps": 1000, "loss": 0.3519, "lr": 9.911436253643445e-06, "epoch": 3.1, "percentage": 15.5, "elapsed_time": "0:00:27", "remaining_time": "0:02:27", "throughput": 3640.57, "total_tokens": 98528}
33
+ {"current_steps": 160, "total_steps": 1000, "loss": 0.21, "lr": 9.894336943808426e-06, "epoch": 3.2, "percentage": 16.0, "elapsed_time": "0:00:27", "remaining_time": "0:02:25", "throughput": 3657.09, "total_tokens": 101408}
34
+ {"current_steps": 165, "total_steps": 1000, "loss": 0.2593, "lr": 9.875746771527817e-06, "epoch": 3.3, "percentage": 16.5, "elapsed_time": "0:00:28", "remaining_time": "0:02:24", "throughput": 3677.26, "total_tokens": 104736}
35
+ {"current_steps": 170, "total_steps": 1000, "loss": 0.2082, "lr": 9.85567139954818e-06, "epoch": 3.4, "percentage": 17.0, "elapsed_time": "0:00:29", "remaining_time": "0:02:22", "throughput": 3694.3, "total_tokens": 107840}
36
+ {"current_steps": 175, "total_steps": 1000, "loss": 0.2665, "lr": 9.834116943022299e-06, "epoch": 3.5, "percentage": 17.5, "elapsed_time": "0:00:29", "remaining_time": "0:02:21", "throughput": 3716.01, "total_tokens": 111392}
37
+ {"current_steps": 180, "total_steps": 1000, "loss": 0.2304, "lr": 9.811089967646427e-06, "epoch": 3.6, "percentage": 18.0, "elapsed_time": "0:00:30", "remaining_time": "0:02:20", "throughput": 3732.71, "total_tokens": 114720}
38
+ {"current_steps": 185, "total_steps": 1000, "loss": 0.1639, "lr": 9.786597487660336e-06, "epoch": 3.7, "percentage": 18.5, "elapsed_time": "0:00:31", "remaining_time": "0:02:18", "throughput": 3745.37, "total_tokens": 117632}
39
+ {"current_steps": 190, "total_steps": 1000, "loss": 0.2323, "lr": 9.760646963710694e-06, "epoch": 3.8, "percentage": 19.0, "elapsed_time": "0:00:32", "remaining_time": "0:02:16", "throughput": 3754.73, "total_tokens": 120512}
40
+ {"current_steps": 195, "total_steps": 1000, "loss": 0.3111, "lr": 9.733246300578482e-06, "epoch": 3.9, "percentage": 19.5, "elapsed_time": "0:00:32", "remaining_time": "0:02:16", "throughput": 3773.77, "total_tokens": 124352}
41
+ {"current_steps": 200, "total_steps": 1000, "loss": 0.2692, "lr": 9.704403844771128e-06, "epoch": 4.0, "percentage": 20.0, "elapsed_time": "0:00:33", "remaining_time": "0:02:14", "throughput": 3775.67, "total_tokens": 127136}
42
+ {"current_steps": 200, "total_steps": 1000, "eval_loss": 0.25425606966018677, "epoch": 4.0, "percentage": 20.0, "elapsed_time": "0:00:34", "remaining_time": "0:02:18", "throughput": 3665.76, "total_tokens": 127136}
43
+ {"current_steps": 205, "total_steps": 1000, "loss": 0.1771, "lr": 9.674128381980073e-06, "epoch": 4.1, "percentage": 20.5, "elapsed_time": "0:00:36", "remaining_time": "0:02:22", "throughput": 3534.01, "total_tokens": 129664}
44
+ {"current_steps": 210, "total_steps": 1000, "loss": 0.2857, "lr": 9.642429134404568e-06, "epoch": 4.2, "percentage": 21.0, "elapsed_time": "0:00:37", "remaining_time": "0:02:20", "throughput": 3537.82, "total_tokens": 132128}
45
+ {"current_steps": 215, "total_steps": 1000, "loss": 0.2155, "lr": 9.609315757942504e-06, "epoch": 4.3, "percentage": 21.5, "elapsed_time": "0:00:38", "remaining_time": "0:02:19", "throughput": 3548.19, "total_tokens": 135200}
46
+ {"current_steps": 220, "total_steps": 1000, "loss": 0.2055, "lr": 9.574798339249124e-06, "epoch": 4.4, "percentage": 22.0, "elapsed_time": "0:00:38", "remaining_time": "0:02:17", "throughput": 3563.76, "total_tokens": 138368}