Training in progress, step 570

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6362b20c1a4e9fedf22023b0596370d1b832a1e5548418d74ced1c8d4d0b5897
+oid sha256:6603751c7d5563601d61f30fa4097c2db95a1e90fa60fc92f4ad28c915f90e1e
 size 798032

trainer_log.jsonl

@@ -128,3 +128,7 @@
 {"current_steps": 550, "total_steps": 570, "loss": 0.4177, "lr": 2.064500424599436e-07, "epoch": 9.649122807017545, "percentage": 96.49, "elapsed_time": "0:02:26", "remaining_time": "0:00:05", "throughput": 2387.08, "total_tokens": 349376}
 {"current_steps": 551, "total_steps": 570, "eval_loss": 0.11319712549448013, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:02:27", "remaining_time": "0:00:05", "throughput": 2377.76, "total_tokens": 350336}
 {"current_steps": 555, "total_steps": 570, "loss": 0.0854, "lr": 1.1991334092484318e-07, "epoch": 9.736842105263158, "percentage": 97.37, "elapsed_time": "0:02:28", "remaining_time": "0:00:04", "throughput": 2370.41, "total_tokens": 353152}
+{"current_steps": 560, "total_steps": 570, "loss": 0.04, "lr": 5.6701710711626334e-08, "epoch": 9.824561403508772, "percentage": 98.25, "elapsed_time": "0:02:29", "remaining_time": "0:00:02", "throughput": 2373.73, "total_tokens": 355904}
+{"current_steps": 565, "total_steps": 570, "loss": 0.1639, "lr": 1.6874412698408836e-08, "epoch": 9.912280701754385, "percentage": 99.12, "elapsed_time": "0:02:30", "remaining_time": "0:00:01", "throughput": 2377.52, "total_tokens": 358912}
+{"current_steps": 570, "total_steps": 570, "loss": 0.1488, "lr": 4.687849611939576e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:32", "remaining_time": "0:00:00", "throughput": 2379.16, "total_tokens": 361992}
+{"current_steps": 570, "total_steps": 570, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:32", "remaining_time": "0:00:00", "throughput": 2368.0, "total_tokens": 361992}