Training in progress, step 570

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b84f414d9f84ca2b76451bf738a01dde88d5cb352c4f7a24469600dcb951939
+oid sha256:76926841e6d8f727812f03746cafce3668e1f1d1ea68390af00f40748d7989b4
 size 1638528

trainer_log.jsonl

@@ -128,3 +128,7 @@
 {"current_steps": 550, "total_steps": 570, "loss": 0.0003, "lr": 2.064500424599436e-07, "epoch": 9.649122807017545, "percentage": 96.49, "elapsed_time": "0:02:52", "remaining_time": "0:00:06", "throughput": 2002.59, "total_tokens": 346240}
 {"current_steps": 551, "total_steps": 570, "eval_loss": 0.04711783304810524, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:02:54", "remaining_time": "0:00:06", "throughput": 1993.41, "total_tokens": 346944}
 {"current_steps": 555, "total_steps": 570, "loss": 0.0021, "lr": 1.1991334092484318e-07, "epoch": 9.736842105263158, "percentage": 97.37, "elapsed_time": "0:02:56", "remaining_time": "0:00:04", "throughput": 1980.65, "total_tokens": 349472}
+{"current_steps": 560, "total_steps": 570, "loss": 0.0008, "lr": 5.6701710711626334e-08, "epoch": 9.824561403508772, "percentage": 98.25, "elapsed_time": "0:02:57", "remaining_time": "0:00:03", "throughput": 1986.91, "total_tokens": 353088}
+{"current_steps": 565, "total_steps": 570, "loss": 0.0003, "lr": 1.6874412698408836e-08, "epoch": 9.912280701754385, "percentage": 99.12, "elapsed_time": "0:02:59", "remaining_time": "0:00:01", "throughput": 1994.54, "total_tokens": 357088}
+{"current_steps": 570, "total_steps": 570, "loss": 0.0003, "lr": 4.687849611939576e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:03:00", "remaining_time": "0:00:00", "throughput": 1996.88, "total_tokens": 359824}
+{"current_steps": 570, "total_steps": 570, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:03:01", "remaining_time": "0:00:00", "throughput": 1981.47, "total_tokens": 359824}