Training in progress, step 3400

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b41c1be8b974e693981390b4f8ea3183b990f4c6cbeb85e09c310968df2c797
+oid sha256:d712f05560ef9d87500810ebe4e96f57f0c9005ed8838b0dd018fe564e447831
 size 29034840

trainer_log.jsonl

@@ -738,3 +738,15 @@
 {"current_steps": 3345, "total_steps": 3400, "loss": 0.289, "lr": 7.152477799867719e-08, "epoch": 0.8614473345351532, "percentage": 98.38, "elapsed_time": "4:01:07", "remaining_time": "0:03:57", "throughput": 2427.92, "total_tokens": 35126296}
 {"current_steps": 3350, "total_steps": 3400, "loss": 0.3253, "lr": 5.911383342556143e-08, "epoch": 0.8627349987123358, "percentage": 98.53, "elapsed_time": "4:02:35", "remaining_time": "0:03:37", "throughput": 2416.91, "total_tokens": 35179104}
 {"current_steps": 3350, "total_steps": 3400, "eval_loss": 0.4714648127555847, "epoch": 0.8627349987123358, "percentage": 98.53, "elapsed_time": "4:03:13", "remaining_time": "0:03:37", "throughput": 2410.68, "total_tokens": 35179104}
+{"current_steps": 3355, "total_steps": 3400, "loss": 0.3179, "lr": 4.788399817602929e-08, "epoch": 0.8640226628895185, "percentage": 98.68, "elapsed_time": "4:04:45", "remaining_time": "0:03:16", "throughput": 2399.06, "total_tokens": 35231608}
+{"current_steps": 3360, "total_steps": 3400, "loss": 0.2829, "lr": 3.7835537837338506e-08, "epoch": 0.865310327066701, "percentage": 98.82, "elapsed_time": "4:06:13", "remaining_time": "0:02:55", "throughput": 2388.31, "total_tokens": 35284448}
+{"current_steps": 3365, "total_steps": 3400, "loss": 0.2579, "lr": 2.8968690057051828e-08, "epoch": 0.8665979912438836, "percentage": 98.97, "elapsed_time": "4:07:40", "remaining_time": "0:02:34", "throughput": 2377.94, "total_tokens": 35336520}
+{"current_steps": 3370, "total_steps": 3400, "loss": 0.2862, "lr": 2.128366453743591e-08, "epoch": 0.8678856554210662, "percentage": 99.12, "elapsed_time": "4:09:07", "remaining_time": "0:02:13", "throughput": 2367.46, "total_tokens": 35388728}
+{"current_steps": 3375, "total_steps": 3400, "loss": 0.2812, "lr": 1.4780643030476438e-08, "epoch": 0.8691733195982487, "percentage": 99.26, "elapsed_time": "4:10:34", "remaining_time": "0:01:51", "throughput": 2357.36, "total_tokens": 35441824}
+{"current_steps": 3380, "total_steps": 3400, "loss": 0.3174, "lr": 9.459779333587104e-09, "epoch": 0.8704609837754314, "percentage": 99.41, "elapsed_time": "4:12:02", "remaining_time": "0:01:29", "throughput": 2347.22, "total_tokens": 35495128}
+{"current_steps": 3385, "total_steps": 3400, "loss": 0.3049, "lr": 5.3211992859791835e-09, "epoch": 0.871748647952614, "percentage": 99.56, "elapsed_time": "4:13:28", "remaining_time": "0:01:07", "throughput": 2337.34, "total_tokens": 35548144}
+{"current_steps": 3390, "total_steps": 3400, "loss": 0.2882, "lr": 2.3650007656805806e-09, "epoch": 0.8730363121297966, "percentage": 99.71, "elapsed_time": "4:14:56", "remaining_time": "0:00:45", "throughput": 2327.46, "total_tokens": 35600936}
+{"current_steps": 3395, "total_steps": 3400, "loss": 0.2789, "lr": 5.912536872321184e-10, "epoch": 0.8743239763069791, "percentage": 99.85, "elapsed_time": "4:16:23", "remaining_time": "0:00:22", "throughput": 2317.73, "total_tokens": 35653896}
+{"current_steps": 3400, "total_steps": 3400, "loss": 0.3187, "lr": 0.0, "epoch": 0.8756116404841617, "percentage": 100.0, "elapsed_time": "4:17:50", "remaining_time": "0:00:00", "throughput": 2308.08, "total_tokens": 35706848}
+{"current_steps": 3400, "total_steps": 3400, "eval_loss": 0.4701705873012543, "epoch": 0.8756116404841617, "percentage": 100.0, "elapsed_time": "4:18:27", "remaining_time": "0:00:00", "throughput": 2302.5, "total_tokens": 35706848}
+{"current_steps": 3400, "total_steps": 3400, "epoch": 0.8756116404841617, "percentage": 100.0, "elapsed_time": "4:18:33", "remaining_time": "0:00:00", "throughput": 2301.72, "total_tokens": 35706848}