Training in progress, step 250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bde5d7f6b153662f6dc1d9e589d04d01e13a0e0b46c0819acb86dbe16368f9b
+oid sha256:77804bb2d0b2a0a39df56c6d937c8651bdd8a732173064e5c9118a2ce00236ec
 size 8388736

trainer_log.jsonl

@@ -54,3 +54,7 @@
 {"current_steps": 225, "total_steps": 250, "eval_loss": 0.21796944737434387, "epoch": 4.5, "percentage": 90.0, "elapsed_time": "0:01:06", "remaining_time": "0:00:07", "throughput": 2126.47, "total_tokens": 141632}
 {"current_steps": 230, "total_steps": 250, "loss": 0.0981, "lr": 2.134025123396638e-07, "epoch": 4.6, "percentage": 92.0, "elapsed_time": "0:01:09", "remaining_time": "0:00:06", "throughput": 2092.4, "total_tokens": 144960}
 {"current_steps": 235, "total_steps": 250, "loss": 0.0963, "lr": 1.2425322847218368e-07, "epoch": 4.7, "percentage": 94.0, "elapsed_time": "0:01:10", "remaining_time": "0:00:04", "throughput": 2109.54, "total_tokens": 147936}
+{"current_steps": 240, "total_steps": 250, "loss": 0.0972, "lr": 5.8858092767236084e-08, "epoch": 4.8, "percentage": 96.0, "elapsed_time": "0:01:11", "remaining_time": "0:00:02", "throughput": 2131.43, "total_tokens": 151392}
+{"current_steps": 245, "total_steps": 250, "loss": 0.15, "lr": 1.753570375247815e-08, "epoch": 4.9, "percentage": 98.0, "elapsed_time": "0:01:11", "remaining_time": "0:00:01", "throughput": 2148.1, "total_tokens": 154624}
+{"current_steps": 250, "total_steps": 250, "loss": 0.1126, "lr": 4.87379953478806e-10, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:01:13", "remaining_time": "0:00:00", "throughput": 2170.84, "total_tokens": 158656}
+{"current_steps": 250, "total_steps": 250, "eval_loss": 0.2241511344909668, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "0:01:14", "remaining_time": "0:00:00", "throughput": 2133.49, "total_tokens": 158656}