rbelanec commited on
Commit
c60f932
verified
1 Parent(s): cb9e1a3

Training in progress, step 3160

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_log.jsonl +30 -0
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:505315aec3fe201b1b1d645986c61f813991f01a9dcb8b8014dd46173b5a26c9
3
  size 798032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f3aab0b206392861fc6328bd0e02f4085bda3cc2130c743a8fe977926ac8ab9
3
  size 798032
trainer_log.jsonl CHANGED
@@ -621,3 +621,33 @@
621
  {"current_steps": 3010, "total_steps": 3160, "loss": 0.0609, "lr": 3.469743008868542e-07, "epoch": 19.050632911392405, "percentage": 95.25, "elapsed_time": "0:09:07", "remaining_time": "0:00:27", "throughput": 2489.06, "total_tokens": 1362832}
622
  {"current_steps": 3015, "total_steps": 3160, "loss": 0.058, "lr": 3.244253154627619e-07, "epoch": 19.082278481012658, "percentage": 95.41, "elapsed_time": "0:09:08", "remaining_time": "0:00:26", "throughput": 2488.94, "total_tokens": 1365072}
623
  {"current_steps": 3020, "total_steps": 3160, "loss": 0.0696, "lr": 3.026290730670206e-07, "epoch": 19.11392405063291, "percentage": 95.57, "elapsed_time": "0:09:09", "remaining_time": "0:00:25", "throughput": 2489.38, "total_tokens": 1367440}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
621
  {"current_steps": 3010, "total_steps": 3160, "loss": 0.0609, "lr": 3.469743008868542e-07, "epoch": 19.050632911392405, "percentage": 95.25, "elapsed_time": "0:09:07", "remaining_time": "0:00:27", "throughput": 2489.06, "total_tokens": 1362832}
622
  {"current_steps": 3015, "total_steps": 3160, "loss": 0.058, "lr": 3.244253154627619e-07, "epoch": 19.082278481012658, "percentage": 95.41, "elapsed_time": "0:09:08", "remaining_time": "0:00:26", "throughput": 2488.94, "total_tokens": 1365072}
623
  {"current_steps": 3020, "total_steps": 3160, "loss": 0.0696, "lr": 3.026290730670206e-07, "epoch": 19.11392405063291, "percentage": 95.57, "elapsed_time": "0:09:09", "remaining_time": "0:00:25", "throughput": 2489.38, "total_tokens": 1367440}
624
+ {"current_steps": 3025, "total_steps": 3160, "loss": 0.0703, "lr": 2.8158623860692344e-07, "epoch": 19.145569620253166, "percentage": 95.73, "elapsed_time": "0:09:10", "remaining_time": "0:00:24", "throughput": 2489.72, "total_tokens": 1369744}
625
+ {"current_steps": 3030, "total_steps": 3160, "loss": 0.1613, "lr": 2.612974540065982e-07, "epoch": 19.17721518987342, "percentage": 95.89, "elapsed_time": "0:09:11", "remaining_time": "0:00:23", "throughput": 2489.96, "total_tokens": 1371984}
626
+ {"current_steps": 3035, "total_steps": 3160, "loss": 0.0604, "lr": 2.417633381874534e-07, "epoch": 19.20886075949367, "percentage": 96.04, "elapsed_time": "0:09:11", "remaining_time": "0:00:22", "throughput": 2490.3, "total_tokens": 1374288}
627
+ {"current_steps": 3040, "total_steps": 3160, "loss": 0.0791, "lr": 2.2298448704926034e-07, "epoch": 19.240506329113924, "percentage": 96.2, "elapsed_time": "0:09:12", "remaining_time": "0:00:21", "throughput": 2490.5, "total_tokens": 1376496}
628
+ {"current_steps": 3045, "total_steps": 3160, "loss": 0.1412, "lr": 2.0496147345200055e-07, "epoch": 19.272151898734176, "percentage": 96.36, "elapsed_time": "0:09:13", "remaining_time": "0:00:20", "throughput": 2490.74, "total_tokens": 1378736}
629
+ {"current_steps": 3050, "total_steps": 3160, "loss": 0.0683, "lr": 1.8769484719839136e-07, "epoch": 19.303797468354432, "percentage": 96.52, "elapsed_time": "0:09:14", "remaining_time": "0:00:19", "throughput": 2490.95, "total_tokens": 1380944}
630
+ {"current_steps": 3055, "total_steps": 3160, "loss": 0.0494, "lr": 1.7118513501709066e-07, "epoch": 19.335443037974684, "percentage": 96.68, "elapsed_time": "0:09:15", "remaining_time": "0:00:19", "throughput": 2491.28, "total_tokens": 1383248}
631
+ {"current_steps": 3060, "total_steps": 3160, "loss": 0.0989, "lr": 1.5543284054665708e-07, "epoch": 19.367088607594937, "percentage": 96.84, "elapsed_time": "0:09:16", "remaining_time": "0:00:18", "throughput": 2491.52, "total_tokens": 1385488}
632
+ {"current_steps": 3065, "total_steps": 3160, "loss": 0.1038, "lr": 1.4043844432016506e-07, "epoch": 19.39873417721519, "percentage": 96.99, "elapsed_time": "0:09:16", "remaining_time": "0:00:17", "throughput": 2491.81, "total_tokens": 1387760}
633
+ {"current_steps": 3070, "total_steps": 3160, "loss": 0.0772, "lr": 1.2620240375055826e-07, "epoch": 19.430379746835442, "percentage": 97.15, "elapsed_time": "0:09:17", "remaining_time": "0:00:16", "throughput": 2492.3, "total_tokens": 1390192}
634
+ {"current_steps": 3075, "total_steps": 3160, "loss": 0.0799, "lr": 1.1272515311669119e-07, "epoch": 19.462025316455698, "percentage": 97.31, "elapsed_time": "0:09:18", "remaining_time": "0:00:15", "throughput": 2492.59, "total_tokens": 1392464}
635
+ {"current_steps": 3080, "total_steps": 3160, "loss": 0.0707, "lr": 1.0000710355008159e-07, "epoch": 19.49367088607595, "percentage": 97.47, "elapsed_time": "0:09:19", "remaining_time": "0:00:14", "throughput": 2492.92, "total_tokens": 1394768}
636
+ {"current_steps": 3085, "total_steps": 3160, "loss": 0.1053, "lr": 8.804864302236482e-08, "epoch": 19.525316455696203, "percentage": 97.63, "elapsed_time": "0:09:20", "remaining_time": "0:00:13", "throughput": 2493.25, "total_tokens": 1397072}
637
+ {"current_steps": 3090, "total_steps": 3160, "loss": 0.0658, "lr": 7.685013633347005e-08, "epoch": 19.556962025316455, "percentage": 97.78, "elapsed_time": "0:09:21", "remaining_time": "0:00:12", "throughput": 2493.53, "total_tokens": 1399344}
638
+ {"current_steps": 3095, "total_steps": 3160, "loss": 0.1311, "lr": 6.641192510047634e-08, "epoch": 19.588607594936708, "percentage": 97.94, "elapsed_time": "0:09:22", "remaining_time": "0:00:11", "throughput": 2493.72, "total_tokens": 1401552}
639
+ {"current_steps": 3100, "total_steps": 3160, "loss": 0.0816, "lr": 5.673432774720433e-08, "epoch": 19.620253164556964, "percentage": 98.1, "elapsed_time": "0:09:22", "remaining_time": "0:00:10", "throughput": 2493.91, "total_tokens": 1403760}
640
+ {"current_steps": 3105, "total_steps": 3160, "loss": 0.0421, "lr": 4.7817639494499025e-08, "epoch": 19.651898734177216, "percentage": 98.26, "elapsed_time": "0:09:23", "remaining_time": "0:00:09", "throughput": 2494.14, "total_tokens": 1406000}
641
+ {"current_steps": 3110, "total_steps": 3160, "loss": 0.1217, "lr": 3.9662132351214744e-08, "epoch": 19.68354430379747, "percentage": 98.42, "elapsed_time": "0:09:24", "remaining_time": "0:00:09", "throughput": 2494.44, "total_tokens": 1408208}
642
+ {"current_steps": 3115, "total_steps": 3160, "loss": 0.0513, "lr": 3.2268055105932894e-08, "epoch": 19.71518987341772, "percentage": 98.58, "elapsed_time": "0:09:25", "remaining_time": "0:00:08", "throughput": 2494.62, "total_tokens": 1410416}
643
+ {"current_steps": 3120, "total_steps": 3160, "loss": 0.033, "lr": 2.5635633319359698e-08, "epoch": 19.746835443037973, "percentage": 98.73, "elapsed_time": "0:09:26", "remaining_time": "0:00:07", "throughput": 2494.76, "total_tokens": 1412592}
644
+ {"current_steps": 3125, "total_steps": 3160, "loss": 0.0805, "lr": 1.976506931745392e-08, "epoch": 19.77848101265823, "percentage": 98.89, "elapsed_time": "0:09:27", "remaining_time": "0:00:06", "throughput": 2495.17, "total_tokens": 1414960}
645
+ {"current_steps": 3130, "total_steps": 3160, "loss": 0.1069, "lr": 1.465654218524848e-08, "epoch": 19.810126582278482, "percentage": 99.05, "elapsed_time": "0:09:27", "remaining_time": "0:00:05", "throughput": 2495.45, "total_tokens": 1417232}
646
+ {"current_steps": 3135, "total_steps": 3160, "loss": 0.0578, "lr": 1.0310207761388135e-08, "epoch": 19.841772151898734, "percentage": 99.21, "elapsed_time": "0:09:28", "remaining_time": "0:00:04", "throughput": 2495.82, "total_tokens": 1419568}
647
+ {"current_steps": 3140, "total_steps": 3160, "loss": 0.1281, "lr": 6.726198633386083e-09, "epoch": 19.873417721518987, "percentage": 99.37, "elapsed_time": "0:09:29", "remaining_time": "0:00:03", "throughput": 2496.0, "total_tokens": 1421776}
648
+ {"current_steps": 3145, "total_steps": 3160, "loss": 0.0797, "lr": 3.904624133560519e-09, "epoch": 19.90506329113924, "percentage": 99.53, "elapsed_time": "0:09:30", "remaining_time": "0:00:02", "throughput": 2496.22, "total_tokens": 1424016}
649
+ {"current_steps": 3150, "total_steps": 3160, "loss": 0.0434, "lr": 1.84557033571231e-09, "epoch": 19.936708860759495, "percentage": 99.68, "elapsed_time": "0:09:31", "remaining_time": "0:00:01", "throughput": 2496.5, "total_tokens": 1426288}
650
+ {"current_steps": 3155, "total_steps": 3160, "loss": 0.1777, "lr": 5.491000525020828e-10, "epoch": 19.968354430379748, "percentage": 99.84, "elapsed_time": "0:09:32", "remaining_time": "0:00:00", "throughput": 2496.81, "total_tokens": 1428592}
651
+ {"current_steps": 3160, "total_steps": 3160, "loss": 0.0834, "lr": 1.5252833521217648e-11, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:09:33", "remaining_time": "0:00:00", "throughput": 2496.56, "total_tokens": 1430592}
652
+ {"current_steps": 3160, "total_steps": 3160, "eval_loss": 0.214238703250885, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:09:34", "remaining_time": "0:00:00", "throughput": 2491.94, "total_tokens": 1430592}
653
+ {"current_steps": 3160, "total_steps": 3160, "epoch": 20.0, "percentage": 100.0, "elapsed_time": "0:09:34", "remaining_time": "0:00:00", "throughput": 2488.68, "total_tokens": 1430592}