Training in progress, step 570

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff8085c289919936dfbb91b40a140729c03a107514af206678c9508b0f1c3c08
+oid sha256:0593e895b4ed8f62cb1c5a27948ee91b6542783a9854216f3ffae7d92fc4b5e4
 size 1638528

trainer_log.jsonl

@@ -128,3 +128,7 @@
 {"current_steps": 550, "total_steps": 570, "loss": 4.9823, "lr": 2.064500424599436e-07, "epoch": 9.649122807017545, "percentage": 96.49, "elapsed_time": "0:02:31", "remaining_time": "0:00:05", "throughput": 2346.13, "total_tokens": 355432}
 {"current_steps": 551, "total_steps": 570, "eval_loss": 4.722128391265869, "epoch": 9.666666666666666, "percentage": 96.67, "elapsed_time": "0:02:32", "remaining_time": "0:00:05", "throughput": 2336.19, "total_tokens": 356456}
 {"current_steps": 555, "total_steps": 570, "loss": 4.8414, "lr": 1.1991334092484318e-07, "epoch": 9.736842105263158, "percentage": 97.37, "elapsed_time": "0:02:34", "remaining_time": "0:00:04", "throughput": 2327.26, "total_tokens": 358760}
+{"current_steps": 560, "total_steps": 570, "loss": 4.9607, "lr": 5.6701710711626334e-08, "epoch": 9.824561403508772, "percentage": 98.25, "elapsed_time": "0:02:35", "remaining_time": "0:00:02", "throughput": 2331.83, "total_tokens": 362088}
+{"current_steps": 565, "total_steps": 570, "loss": 4.9469, "lr": 1.6874412698408836e-08, "epoch": 9.912280701754385, "percentage": 99.12, "elapsed_time": "0:02:36", "remaining_time": "0:00:01", "throughput": 2336.81, "total_tokens": 365544}
+{"current_steps": 570, "total_steps": 570, "loss": 4.6089, "lr": 4.687849611939576e-10, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:37", "remaining_time": "0:00:00", "throughput": 2336.99, "total_tokens": 367864}
+{"current_steps": 570, "total_steps": 570, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:02:38", "remaining_time": "0:00:00", "throughput": 2326.4, "total_tokens": 367864}