Training in progress, step 570

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3ce3faec285c2ec1db97889a248e4d2e13ffd43fd474979b93d7c7ba517fbe9
+oid sha256:7002ea32650eb9951e000b7ef9cd092a9bd024701c4ec20577a027165fe70c84
 size 798032

trainer_log.jsonl

@@ -128,3 +128,7 @@
 {"current_steps": 550, "total_steps": 570, "loss": 0.1179, "lr": 2.064500424599436e-07, "epoch": 9.649122807017545, "percentage": 96.49, "elapsed_time": "0:02:26", "remaining_time": "0:00:05", "throughput": 2422.25, "total_tokens": 355432}
 {"current_steps": 551, "total_steps": 570, "eval_loss": 0.15663054585456848, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:02:27", "remaining_time": "0:00:05", "throughput": 2413.84, "total_tokens": 356456}
 {"current_steps": 555, "total_steps": 570, "loss": 0.1534, "lr": 1.1991334092484318e-07, "epoch": 9.736842105263158, "percentage": 97.37, "elapsed_time": "0:02:29", "remaining_time": "0:00:04", "throughput": 2402.06, "total_tokens": 358760}
+{"current_steps": 560, "total_steps": 570, "loss": 0.227, "lr": 5.6701710711626334e-08, "epoch": 9.824561403508772, "percentage": 98.25, "elapsed_time": "0:02:30", "remaining_time": "0:00:02", "throughput": 2406.81, "total_tokens": 362088}
+{"current_steps": 565, "total_steps": 570, "loss": 0.2402, "lr": 1.6874412698408836e-08, "epoch": 9.912280701754385, "percentage": 99.12, "elapsed_time": "0:02:31", "remaining_time": "0:00:01", "throughput": 2411.77, "total_tokens": 365544}
+{"current_steps": 570, "total_steps": 570, "loss": 0.1567, "lr": 4.687849611939576e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:32", "remaining_time": "0:00:00", "throughput": 2411.21, "total_tokens": 367864}
+{"current_steps": 570, "total_steps": 570, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:33", "remaining_time": "0:00:00", "throughput": 2398.83, "total_tokens": 367864}