Training in progress, step 208

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dab4fce552b6ff2c1acb4383594a95bdc755cc25c4f1adeed440c620d11651e
+oid sha256:997774bf8b11eca81554198a1869b51edceac75e57ee798aee8c37dc441eeafe
 size 312947112

trainer_log.jsonl

@@ -54,3 +54,7 @@
 {"current_steps": 195, "total_steps": 249, "eval_loss": 0.5061560273170471, "epoch": 0.7831325301204819, "percentage": 78.31, "elapsed_time": "0:00:51", "remaining_time": "0:00:14", "throughput": 659.28, "total_tokens": 34176}
 {"current_steps": 200, "total_steps": 249, "loss": 0.4622, "lr": 5.899065604459814e-06, "epoch": 0.8032128514056225, "percentage": 80.32, "elapsed_time": "0:00:53", "remaining_time": "0:00:13", "throughput": 651.59, "total_tokens": 34992}
 {"current_steps": 205, "total_steps": 249, "loss": 0.6246, "lr": 4.81587299765594e-06, "epoch": 0.8232931726907631, "percentage": 82.33, "elapsed_time": "0:00:54", "remaining_time": "0:00:11", "throughput": 662.37, "total_tokens": 35888}
+{"current_steps": 208, "total_steps": 249, "eval_loss": 0.5011698007583618, "epoch": 0.8353413654618473, "percentage": 83.53, "elapsed_time": "0:00:55", "remaining_time": "0:00:10", "throughput": 657.28, "total_tokens": 36512}
+{"current_steps": 210, "total_steps": 249, "loss": 0.553, "lr": 3.831895019292897e-06, "epoch": 0.8433734939759037, "percentage": 84.34, "elapsed_time": "0:00:57", "remaining_time": "0:00:10", "throughput": 643.63, "total_tokens": 36848}
+{"current_steps": 215, "total_steps": 249, "loss": 0.5892, "lr": 2.9519683912911266e-06, "epoch": 0.8634538152610441, "percentage": 86.35, "elapsed_time": "0:00:57", "remaining_time": "0:00:09", "throughput": 655.44, "total_tokens": 37888}
+{"current_steps": 220, "total_steps": 249, "loss": 0.5174, "lr": 2.1804183734670277e-06, "epoch": 0.8835341365461847, "percentage": 88.35, "elapsed_time": "0:00:58", "remaining_time": "0:00:07", "throughput": 664.72, "total_tokens": 38768}