Training in progress, step 1000

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfd440e7fad2202aa5aadeb518f98ac0d3f292864f45e1beccd3794320180905
+oid sha256:877d476d50606e6083f6c78d34e77669367b6c6b165e3fabd4766d94d783d5e9
 size 29034840

trainer_log.jsonl

@@ -208,3 +208,14 @@
 {"current_steps": 945, "total_steps": 6770, "loss": 0.5507, "lr": 9.782502649204512e-05, "epoch": 0.2791728212703102, "percentage": 13.96, "elapsed_time": "4:42:37", "remaining_time": "1 day, 5:02:07", "throughput": 578.61, "total_tokens": 9811880}
 {"current_steps": 950, "total_steps": 6770, "loss": 0.4737, "lr": 9.778925571006495e-05, "epoch": 0.28064992614475626, "percentage": 14.03, "elapsed_time": "4:44:05", "remaining_time": "1 day, 5:00:27", "throughput": 578.63, "total_tokens": 9863168}
 {"current_steps": 950, "total_steps": 6770, "eval_loss": 0.479105681180954, "epoch": 0.28064992614475626, "percentage": 14.03, "elapsed_time": "4:44:24", "remaining_time": "1 day, 5:02:25", "throughput": 577.98, "total_tokens": 9863168}
+{"current_steps": 955, "total_steps": 6770, "loss": 0.4393, "lr": 9.775319981786445e-05, "epoch": 0.2821270310192024, "percentage": 14.11, "elapsed_time": "4:45:57", "remaining_time": "1 day, 5:01:09", "throughput": 577.87, "total_tokens": 9914672}
+{"current_steps": 960, "total_steps": 6770, "loss": 0.4355, "lr": 9.771685903055277e-05, "epoch": 0.28360413589364847, "percentage": 14.18, "elapsed_time": "4:47:25", "remaining_time": "1 day, 4:59:30", "throughput": 577.94, "total_tokens": 9966736}
+{"current_steps": 965, "total_steps": 6770, "loss": 0.4459, "lr": 9.768023356493864e-05, "epoch": 0.28508124076809455, "percentage": 14.25, "elapsed_time": "4:48:53", "remaining_time": "1 day, 4:57:48", "throughput": 577.97, "total_tokens": 10017984}
+{"current_steps": 970, "total_steps": 6770, "loss": 0.4774, "lr": 9.764332363952927e-05, "epoch": 0.2865583456425406, "percentage": 14.33, "elapsed_time": "4:50:21", "remaining_time": "1 day, 4:56:10", "throughput": 577.99, "total_tokens": 10069520}
+{"current_steps": 975, "total_steps": 6770, "loss": 0.413, "lr": 9.760612947452884e-05, "epoch": 0.2880354505169867, "percentage": 14.4, "elapsed_time": "4:51:48", "remaining_time": "1 day, 4:54:21", "throughput": 578.14, "total_tokens": 10122208}
+{"current_steps": 980, "total_steps": 6770, "loss": 0.5433, "lr": 9.756865129183741e-05, "epoch": 0.2895125553914328, "percentage": 14.48, "elapsed_time": "4:53:15", "remaining_time": "1 day, 4:52:39", "throughput": 578.19, "total_tokens": 10173760}
+{"current_steps": 985, "total_steps": 6770, "loss": 0.4096, "lr": 9.753088931504944e-05, "epoch": 0.29098966026587886, "percentage": 14.55, "elapsed_time": "4:54:42", "remaining_time": "1 day, 4:50:51", "throughput": 578.25, "total_tokens": 10224976}
+{"current_steps": 990, "total_steps": 6770, "loss": 0.3916, "lr": 9.749284376945248e-05, "epoch": 0.29246676514032494, "percentage": 14.62, "elapsed_time": "4:56:10", "remaining_time": "1 day, 4:49:08", "throughput": 578.33, "total_tokens": 10276928}
+{"current_steps": 995, "total_steps": 6770, "loss": 0.3899, "lr": 9.74545148820259e-05, "epoch": 0.29394387001477107, "percentage": 14.7, "elapsed_time": "4:57:35", "remaining_time": "1 day, 4:47:15", "throughput": 578.41, "total_tokens": 10328048}
+{"current_steps": 1000, "total_steps": 6770, "loss": 0.4005, "lr": 9.741590288143944e-05, "epoch": 0.29542097488921715, "percentage": 14.77, "elapsed_time": "4:59:02", "remaining_time": "1 day, 4:45:26", "throughput": 578.48, "total_tokens": 10379136}
+{"current_steps": 1000, "total_steps": 6770, "eval_loss": 0.5501028299331665, "epoch": 0.29542097488921715, "percentage": 14.77, "elapsed_time": "4:59:21", "remaining_time": "1 day, 4:47:16", "throughput": 577.86, "total_tokens": 10379136}