Training in progress, step 570

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:750eb8a9299167e816154006b95edc792878be3155f2d2ce52716534ef8875b9
+oid sha256:398bc0dc5aa32bcde6d4cd5ab24c211c823cf68390e3fb579e6216e6aab24531
 size 1074144

trainer_log.jsonl

@@ -128,3 +128,7 @@
 {"current_steps": 550, "total_steps": 570, "loss": 0.0381, "lr": 2.064500424599436e-07, "epoch": 9.649122807017545, "percentage": 96.49, "elapsed_time": "0:02:25", "remaining_time": "0:00:05", "throughput": 2340.78, "total_tokens": 340480}
 {"current_steps": 551, "total_steps": 570, "eval_loss": 0.19899024069309235, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:02:26", "remaining_time": "0:00:05", "throughput": 2329.58, "total_tokens": 340960}
 {"current_steps": 555, "total_steps": 570, "loss": 0.1419, "lr": 1.1991334092484318e-07, "epoch": 9.736842105263158, "percentage": 97.37, "elapsed_time": "0:02:27", "remaining_time": "0:00:03", "throughput": 2320.91, "total_tokens": 343328}
+{"current_steps": 560, "total_steps": 570, "loss": 0.2539, "lr": 5.6701710711626334e-08, "epoch": 9.824561403508772, "percentage": 98.25, "elapsed_time": "0:02:28", "remaining_time": "0:00:02", "throughput": 2324.11, "total_tokens": 345984}
+{"current_steps": 565, "total_steps": 570, "loss": 0.1029, "lr": 1.6874412698408836e-08, "epoch": 9.912280701754385, "percentage": 99.12, "elapsed_time": "0:02:29", "remaining_time": "0:00:01", "throughput": 2328.93, "total_tokens": 349280}
+{"current_steps": 570, "total_steps": 570, "loss": 0.0478, "lr": 4.687849611939576e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:31", "remaining_time": "0:00:00", "throughput": 2331.08, "total_tokens": 352296}
+{"current_steps": 570, "total_steps": 570, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:32", "remaining_time": "0:00:00", "throughput": 2308.93, "total_tokens": 352296}