Training in progress, step 1900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:715ff69f50f84d39187c1f0fc35de081fab6e8a1a5b66268497bd57f97e40762
+oid sha256:920101966caf9f63708128eacbc2e0f1c2ccd11ad0e5ce041ad3a77fc5419432
 size 29034840

trainer_log.jsonl

@@ -405,3 +405,14 @@
 {"current_steps": 1845, "total_steps": 3882, "loss": 0.3758, "lr": 5.820650559495523e-05, "epoch": 0.950296162760752, "percentage": 47.53, "elapsed_time": "9:24:03", "remaining_time": "10:22:45", "throughput": 637.63, "total_tokens": 21579376}
 {"current_steps": 1850, "total_steps": 3882, "loss": 0.3221, "lr": 5.7996302341738164e-05, "epoch": 0.9528714911151172, "percentage": 47.66, "elapsed_time": "9:25:32", "remaining_time": "10:21:10", "throughput": 637.67, "total_tokens": 21637848}
 {"current_steps": 1850, "total_steps": 3882, "eval_loss": 0.2935050129890442, "epoch": 0.9528714911151172, "percentage": 47.66, "elapsed_time": "9:25:51", "remaining_time": "10:21:32", "throughput": 637.31, "total_tokens": 21637848}
+{"current_steps": 1855, "total_steps": 3882, "loss": 0.4205, "lr": 5.778595395022226e-05, "epoch": 0.9554468194694824, "percentage": 47.78, "elapsed_time": "9:27:26", "remaining_time": "10:20:03", "throughput": 637.26, "total_tokens": 21696328}
+{"current_steps": 1860, "total_steps": 3882, "loss": 0.3075, "lr": 5.757546423837314e-05, "epoch": 0.9580221478238475, "percentage": 47.91, "elapsed_time": "9:28:55", "remaining_time": "10:18:28", "throughput": 637.31, "total_tokens": 21754816}
+{"current_steps": 1865, "total_steps": 3882, "loss": 0.2604, "lr": 5.736483702672155e-05, "epoch": 0.9605974761782127, "percentage": 48.04, "elapsed_time": "9:30:24", "remaining_time": "10:16:53", "throughput": 637.37, "total_tokens": 21813296}
+{"current_steps": 1870, "total_steps": 3882, "loss": 0.342, "lr": 5.7154076138293914e-05, "epoch": 0.9631728045325779, "percentage": 48.17, "elapsed_time": "9:31:52", "remaining_time": "10:15:18", "throughput": 637.42, "total_tokens": 21871800}
+{"current_steps": 1875, "total_steps": 3882, "loss": 0.411, "lr": 5.694318539854297e-05, "epoch": 0.9657481328869431, "percentage": 48.3, "elapsed_time": "9:33:21", "remaining_time": "10:13:43", "throughput": 637.48, "total_tokens": 21930272}
+{"current_steps": 1880, "total_steps": 3882, "loss": 0.2606, "lr": 5.673216863527836e-05, "epoch": 0.9683234612413083, "percentage": 48.43, "elapsed_time": "9:34:50", "remaining_time": "10:12:09", "throughput": 637.52, "total_tokens": 21988736}
+{"current_steps": 1885, "total_steps": 3882, "loss": 0.2647, "lr": 5.652102967859715e-05, "epoch": 0.9708987895956734, "percentage": 48.56, "elapsed_time": "9:36:19", "remaining_time": "10:10:34", "throughput": 637.58, "total_tokens": 22047200}
+{"current_steps": 1890, "total_steps": 3882, "loss": 0.2961, "lr": 5.6309772360814295e-05, "epoch": 0.9734741179500386, "percentage": 48.69, "elapsed_time": "9:37:49", "remaining_time": "10:09:00", "throughput": 637.61, "total_tokens": 22105664}
+{"current_steps": 1895, "total_steps": 3882, "loss": 0.2776, "lr": 5.6098400516393065e-05, "epoch": 0.9760494463044038, "percentage": 48.82, "elapsed_time": "9:39:18", "remaining_time": "10:07:25", "throughput": 637.67, "total_tokens": 22164184}
+{"current_steps": 1900, "total_steps": 3882, "loss": 0.3781, "lr": 5.5886917981875485e-05, "epoch": 0.978624774658769, "percentage": 48.94, "elapsed_time": "9:40:47", "remaining_time": "10:05:51", "throughput": 637.71, "total_tokens": 22222632}
+{"current_steps": 1900, "total_steps": 3882, "eval_loss": 0.297338604927063, "epoch": 0.978624774658769, "percentage": 48.94, "elapsed_time": "9:41:07", "remaining_time": "10:06:11", "throughput": 637.35, "total_tokens": 22222632}