Training in progress, step 208

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b88be18cb72b9882ca5f661464f62b04dc167734f9f990c1a045cc611c21e55
+oid sha256:d3450a265f20d658447e91f7b1233ffb786dc84527f788f9dcbe3ccadbb87f0c
 size 335717200

trainer_log.jsonl

@@ -52,3 +52,10 @@
 {"current_steps": 190, "total_steps": 249, "loss": 0.4085, "lr": 8.341335551199902e-06, "epoch": 0.7630522088353414, "percentage": 76.31, "elapsed_time": "0:00:44", "remaining_time": "0:00:13", "throughput": 756.08, "total_tokens": 33360}
 {"current_steps": 195, "total_steps": 249, "loss": 0.3745, "lr": 7.076148430479321e-06, "epoch": 0.7831325301204819, "percentage": 78.31, "elapsed_time": "0:00:44", "remaining_time": "0:00:12", "throughput": 768.47, "total_tokens": 34176}
 {"current_steps": 195, "total_steps": 249, "eval_loss": 0.3510403037071228, "epoch": 0.7831325301204819, "percentage": 78.31, "elapsed_time": "0:00:45", "remaining_time": "0:00:12", "throughput": 756.02, "total_tokens": 34176}
+{"current_steps": 200, "total_steps": 249, "loss": 0.3619, "lr": 5.899065604459814e-06, "epoch": 0.8032128514056225, "percentage": 80.32, "elapsed_time": "0:00:46", "remaining_time": "0:00:11", "throughput": 749.1, "total_tokens": 34992}
+{"current_steps": 205, "total_steps": 249, "loss": 0.3715, "lr": 4.81587299765594e-06, "epoch": 0.8232931726907631, "percentage": 82.33, "elapsed_time": "0:00:47", "remaining_time": "0:00:10", "throughput": 762.9, "total_tokens": 35888}
+{"current_steps": 208, "total_steps": 249, "eval_loss": 0.3522191047668457, "epoch": 0.8353413654618473, "percentage": 83.53, "elapsed_time": "0:00:48", "remaining_time": "0:00:09", "throughput": 758.49, "total_tokens": 36512}
+{"current_steps": 210, "total_steps": 249, "loss": 0.3618, "lr": 3.831895019292897e-06, "epoch": 0.8433734939759037, "percentage": 84.34, "elapsed_time": "0:00:49", "remaining_time": "0:00:09", "throughput": 737.9, "total_tokens": 36848}
+{"current_steps": 215, "total_steps": 249, "loss": 0.3692, "lr": 2.9519683912911266e-06, "epoch": 0.8634538152610441, "percentage": 86.35, "elapsed_time": "0:00:50", "remaining_time": "0:00:07", "throughput": 753.12, "total_tokens": 37888}
+{"current_steps": 220, "total_steps": 249, "loss": 0.3653, "lr": 2.1804183734670277e-06, "epoch": 0.8835341365461847, "percentage": 88.35, "elapsed_time": "0:00:50", "remaining_time": "0:00:06", "throughput": 765.54, "total_tokens": 38768}
+{"current_steps": 221, "total_steps": 249, "eval_loss": 0.35432901978492737, "epoch": 0.8875502008032129, "percentage": 88.76, "elapsed_time": "0:00:51", "remaining_time": "0:00:06", "throughput": 754.99, "total_tokens": 38912}