Training in progress, step 2100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4709ac7890db563cedfc9593a73be6ffe73b6111dd9fd8fdc9d8017c84f30b92
+oid sha256:a24a4c37b80664a17b4612dbf43f560521041adc8bc0cc8d0182857100b9274e
 size 29034840

trainer_log.jsonl

@@ -461,3 +461,14 @@
 {"current_steps": 2045, "total_steps": 6770, "loss": 0.295, "lr": 8.361836548299045e-05, "epoch": 0.604135893648449, "percentage": 30.21, "elapsed_time": "1:59:28", "remaining_time": "4:36:03", "throughput": 2962.91, "total_tokens": 21240184}
 {"current_steps": 2050, "total_steps": 6770, "loss": 0.2931, "lr": 8.352786479194288e-05, "epoch": 0.6056129985228951, "percentage": 30.28, "elapsed_time": "2:00:56", "remaining_time": "4:38:27", "throughput": 2934.23, "total_tokens": 21291664}
 {"current_steps": 2050, "total_steps": 6770, "eval_loss": 0.33863261342048645, "epoch": 0.6056129985228951, "percentage": 30.28, "elapsed_time": "2:01:15", "remaining_time": "4:39:11", "throughput": 2926.43, "total_tokens": 21291664}
+{"current_steps": 2055, "total_steps": 6770, "loss": 0.2338, "lr": 8.343716407399019e-05, "epoch": 0.6070901033973413, "percentage": 30.35, "elapsed_time": "2:02:48", "remaining_time": "4:41:46", "throughput": 2896.61, "total_tokens": 21344232}
+{"current_steps": 2060, "total_steps": 6770, "loss": 0.3026, "lr": 8.334626387025197e-05, "epoch": 0.6085672082717873, "percentage": 30.43, "elapsed_time": "2:04:16", "remaining_time": "4:44:09", "throughput": 2869.36, "total_tokens": 21396160}
+{"current_steps": 2065, "total_steps": 6770, "loss": 0.2898, "lr": 8.325516472303792e-05, "epoch": 0.6100443131462334, "percentage": 30.5, "elapsed_time": "2:05:45", "remaining_time": "4:46:31", "throughput": 2842.58, "total_tokens": 21448032}
+{"current_steps": 2070, "total_steps": 6770, "loss": 0.3265, "lr": 8.316386717584463e-05, "epoch": 0.6115214180206795, "percentage": 30.58, "elapsed_time": "2:07:13", "remaining_time": "4:48:52", "throughput": 2816.35, "total_tokens": 21499144}
+{"current_steps": 2075, "total_steps": 6770, "loss": 0.2513, "lr": 8.307237177335239e-05, "epoch": 0.6129985228951256, "percentage": 30.65, "elapsed_time": "2:08:40", "remaining_time": "4:51:09", "throughput": 2791.39, "total_tokens": 21551328}
+{"current_steps": 2080, "total_steps": 6770, "loss": 0.2864, "lr": 8.298067906142182e-05, "epoch": 0.6144756277695717, "percentage": 30.72, "elapsed_time": "2:10:08", "remaining_time": "4:53:26", "throughput": 2766.8, "total_tokens": 21603800}
+{"current_steps": 2085, "total_steps": 6770, "loss": 0.243, "lr": 8.288878958709072e-05, "epoch": 0.6159527326440177, "percentage": 30.8, "elapsed_time": "2:11:35", "remaining_time": "4:55:40", "throughput": 2742.95, "total_tokens": 21656480}
+{"current_steps": 2090, "total_steps": 6770, "loss": 0.2711, "lr": 8.279670389857079e-05, "epoch": 0.6174298375184638, "percentage": 30.87, "elapsed_time": "2:13:02", "remaining_time": "4:57:55", "throughput": 2719.43, "total_tokens": 21708824}
+{"current_steps": 2095, "total_steps": 6770, "loss": 0.2475, "lr": 8.27044225452443e-05, "epoch": 0.6189069423929099, "percentage": 30.95, "elapsed_time": "2:14:29", "remaining_time": "5:00:06", "throughput": 2696.8, "total_tokens": 21760744}
+{"current_steps": 2100, "total_steps": 6770, "loss": 0.1826, "lr": 8.26119460776609e-05, "epoch": 0.620384047267356, "percentage": 31.02, "elapsed_time": "2:15:56", "remaining_time": "5:02:19", "throughput": 2674.27, "total_tokens": 21813984}
+{"current_steps": 2100, "total_steps": 6770, "eval_loss": 0.5386325716972351, "epoch": 0.620384047267356, "percentage": 31.02, "elapsed_time": "2:16:16", "remaining_time": "5:03:02", "throughput": 2667.96, "total_tokens": 21813984}