Training in progress, step 570

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f86665918a72675a58107847743245ec595b0d9740912473ee5d67bdfdfe9ad5
+oid sha256:1a3222ea54d095574663e24ecbdce6c9a5217ba3ad0a3709c37ece056b806429
 size 819328

trainer_log.jsonl

@@ -128,3 +128,7 @@
 {"current_steps": 550, "total_steps": 570, "loss": 0.08, "lr": 2.064500424599436e-07, "epoch": 9.649122807017545, "percentage": 96.49, "elapsed_time": "0:02:33", "remaining_time": "0:00:05", "throughput": 2221.23, "total_tokens": 340480}
 {"current_steps": 551, "total_steps": 570, "eval_loss": 0.41571494936943054, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:02:34", "remaining_time": "0:00:05", "throughput": 2208.34, "total_tokens": 340960}
 {"current_steps": 555, "total_steps": 570, "loss": 0.0687, "lr": 1.1991334092484318e-07, "epoch": 9.736842105263158, "percentage": 97.37, "elapsed_time": "0:02:35", "remaining_time": "0:00:04", "throughput": 2200.93, "total_tokens": 343328}
+{"current_steps": 560, "total_steps": 570, "loss": 0.3369, "lr": 5.6701710711626334e-08, "epoch": 9.824561403508772, "percentage": 98.25, "elapsed_time": "0:02:37", "remaining_time": "0:00:02", "throughput": 2203.31, "total_tokens": 345984}
+{"current_steps": 565, "total_steps": 570, "loss": 0.1646, "lr": 1.6874412698408836e-08, "epoch": 9.912280701754385, "percentage": 99.12, "elapsed_time": "0:02:38", "remaining_time": "0:00:01", "throughput": 2208.47, "total_tokens": 349280}
+{"current_steps": 570, "total_steps": 570, "loss": 0.0533, "lr": 4.687849611939576e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:39", "remaining_time": "0:00:00", "throughput": 2212.18, "total_tokens": 352296}
+{"current_steps": 570, "total_steps": 570, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:39", "remaining_time": "0:00:00", "throughput": 2202.52, "total_tokens": 352296}