rbelanec commited on
Commit
0e75675
·
verified ·
1 Parent(s): 3b84110

Training in progress, step 1800

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +16 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5472c1f9bec50f5f74b4bf6bbc535ccec90b06be9d6ef38dcd99db3222ac866
3
  size 1638528
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f3acb56f006687b768c87a8b6473228fa3711c033c7c30d6c47b690ddfa3bda
3
  size 1638528
trainer_log.jsonl CHANGED
@@ -363,3 +363,19 @@
363
  {"current_steps": 1720, "total_steps": 1800, "loss": 0.2364, "lr": 6.15582970243117e-06, "epoch": 19.11111111111111, "percentage": 95.56, "elapsed_time": "0:05:14", "remaining_time": "0:00:14", "throughput": 1715.41, "total_tokens": 539072}
364
  {"current_steps": 1725, "total_steps": 1800, "loss": 0.2292, "lr": 5.42064076808646e-06, "epoch": 19.166666666666668, "percentage": 95.83, "elapsed_time": "0:05:15", "remaining_time": "0:00:13", "throughput": 1715.85, "total_tokens": 540608}
365
  {"current_steps": 1730, "total_steps": 1800, "loss": 0.2181, "lr": 4.731950694210896e-06, "epoch": 19.22222222222222, "percentage": 96.11, "elapsed_time": "0:05:15", "remaining_time": "0:00:12", "throughput": 1716.56, "total_tokens": 542208}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
363
  {"current_steps": 1720, "total_steps": 1800, "loss": 0.2364, "lr": 6.15582970243117e-06, "epoch": 19.11111111111111, "percentage": 95.56, "elapsed_time": "0:05:14", "remaining_time": "0:00:14", "throughput": 1715.41, "total_tokens": 539072}
364
  {"current_steps": 1725, "total_steps": 1800, "loss": 0.2292, "lr": 5.42064076808646e-06, "epoch": 19.166666666666668, "percentage": 95.83, "elapsed_time": "0:05:15", "remaining_time": "0:00:13", "throughput": 1715.85, "total_tokens": 540608}
365
  {"current_steps": 1730, "total_steps": 1800, "loss": 0.2181, "lr": 4.731950694210896e-06, "epoch": 19.22222222222222, "percentage": 96.11, "elapsed_time": "0:05:15", "remaining_time": "0:00:12", "throughput": 1716.56, "total_tokens": 542208}
366
+ {"current_steps": 1735, "total_steps": 1800, "loss": 0.2158, "lr": 4.089824229369155e-06, "epoch": 19.27777777777778, "percentage": 96.39, "elapsed_time": "0:05:16", "remaining_time": "0:00:11", "throughput": 1717.17, "total_tokens": 543776}
367
+ {"current_steps": 1740, "total_steps": 1800, "loss": 0.2367, "lr": 3.4943217443557664e-06, "epoch": 19.333333333333332, "percentage": 96.67, "elapsed_time": "0:05:17", "remaining_time": "0:00:10", "throughput": 1717.61, "total_tokens": 545280}
368
+ {"current_steps": 1745, "total_steps": 1800, "loss": 0.2391, "lr": 2.9454992265193214e-06, "epoch": 19.38888888888889, "percentage": 96.94, "elapsed_time": "0:05:18", "remaining_time": "0:00:10", "throughput": 1718.24, "total_tokens": 546848}
369
+ {"current_steps": 1750, "total_steps": 1800, "loss": 0.2222, "lr": 2.4434082744984598e-06, "epoch": 19.444444444444443, "percentage": 97.22, "elapsed_time": "0:05:19", "remaining_time": "0:00:09", "throughput": 1718.86, "total_tokens": 548416}
370
+ {"current_steps": 1755, "total_steps": 1800, "loss": 0.2254, "lr": 1.9880960933710836e-06, "epoch": 19.5, "percentage": 97.5, "elapsed_time": "0:05:19", "remaining_time": "0:00:08", "throughput": 1719.56, "total_tokens": 550016}
371
+ {"current_steps": 1760, "total_steps": 1800, "loss": 0.2311, "lr": 1.5796054902157964e-06, "epoch": 19.555555555555557, "percentage": 97.78, "elapsed_time": "0:05:20", "remaining_time": "0:00:07", "throughput": 1720.15, "total_tokens": 551584}
372
+ {"current_steps": 1765, "total_steps": 1800, "loss": 0.2217, "lr": 1.2179748700879012e-06, "epoch": 19.61111111111111, "percentage": 98.06, "elapsed_time": "0:05:21", "remaining_time": "0:00:06", "throughput": 1720.76, "total_tokens": 553152}
373
+ {"current_steps": 1770, "total_steps": 1800, "loss": 0.2209, "lr": 9.032382324080101e-07, "epoch": 19.666666666666668, "percentage": 98.33, "elapsed_time": "0:05:22", "remaining_time": "0:00:05", "throughput": 1721.45, "total_tokens": 554752}
374
+ {"current_steps": 1775, "total_steps": 1800, "loss": 0.2139, "lr": 6.354251677661571e-07, "epoch": 19.72222222222222, "percentage": 98.61, "elapsed_time": "0:05:23", "remaining_time": "0:00:04", "throughput": 1721.95, "total_tokens": 556288}
375
+ {"current_steps": 1780, "total_steps": 1800, "loss": 0.2146, "lr": 4.1456085513935646e-07, "epoch": 19.77777777777778, "percentage": 98.89, "elapsed_time": "0:05:23", "remaining_time": "0:00:03", "throughput": 1722.61, "total_tokens": 557888}
376
+ {"current_steps": 1785, "total_steps": 1800, "loss": 0.2389, "lr": 2.4066605952444145e-07, "epoch": 19.833333333333332, "percentage": 99.17, "elapsed_time": "0:05:24", "remaining_time": "0:00:02", "throughput": 1723.08, "total_tokens": 559424}
377
+ {"current_steps": 1790, "total_steps": 1800, "loss": 0.2248, "lr": 1.1375712998595855e-07, "epoch": 19.88888888888889, "percentage": 99.44, "elapsed_time": "0:05:25", "remaining_time": "0:00:01", "throughput": 1723.56, "total_tokens": 560960}
378
+ {"current_steps": 1795, "total_steps": 1800, "loss": 0.2216, "lr": 3.384599811889766e-08, "epoch": 19.944444444444443, "percentage": 99.72, "elapsed_time": "0:05:26", "remaining_time": "0:00:00", "throughput": 1724.31, "total_tokens": 562592}
379
+ {"current_steps": 1800, "total_steps": 1800, "loss": 0.2169, "lr": 9.40176926922387e-10, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:05:27", "remaining_time": "0:00:00", "throughput": 1724.49, "total_tokens": 564096}
380
+ {"current_steps": 1800, "total_steps": 1800, "eval_loss": 0.2441737949848175, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:05:27", "remaining_time": "0:00:00", "throughput": 1720.14, "total_tokens": 564096}
381
+ {"current_steps": 1800, "total_steps": 1800, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:05:28", "remaining_time": "0:00:00", "throughput": 1715.01, "total_tokens": 564096}