Training in progress, step 1250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab2bc6f15c00a1cee650dbf09cee22a11740e09d0663793081370d2889379ed2
+oid sha256:681ec224b6b72fee61fa5bbd372f12a4787b3d2856ee3deb08d1b60fb93f44ab
 size 40036488

trainer_log.jsonl

@@ -142,3 +142,9 @@
 {"current_steps": 1190, "total_steps": 1500, "loss": 0.3951, "accuracy": 0.987500011920929, "learning_rate": 5.086752049395094e-07, "epoch": 0.9766105867870333, "percentage": 79.33, "elapsed_time": "2:36:00", "remaining_time": "0:40:38", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1200, "total_steps": 1500, "loss": 0.3622, "accuracy": 0.987500011920929, "learning_rate": 4.774575140626317e-07, "epoch": 0.9848173984407058, "percentage": 80.0, "elapsed_time": "2:37:10", "remaining_time": "0:39:17", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.0954374447464943, "epoch": 0.9848173984407058, "percentage": 80.0, "elapsed_time": "2:37:36", "remaining_time": "0:39:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1210, "total_steps": 1500, "loss": 0.6501, "accuracy": 0.9750000238418579, "learning_rate": 4.4712697716573994e-07, "epoch": 0.9930242100943784, "percentage": 80.67, "elapsed_time": "2:38:59", "remaining_time": "0:38:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1220, "total_steps": 1500, "loss": 0.955, "accuracy": 0.9605262875556946, "learning_rate": 4.1769689822475147e-07, "epoch": 1.0008206811653673, "percentage": 81.33, "elapsed_time": "2:40:06", "remaining_time": "0:36:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1230, "total_steps": 1500, "loss": 0.463, "accuracy": 0.987500011920929, "learning_rate": 3.891801862449629e-07, "epoch": 1.0090274928190397, "percentage": 82.0, "elapsed_time": "2:41:14", "remaining_time": "0:35:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1240, "total_steps": 1500, "loss": 0.4026, "accuracy": 1.0, "learning_rate": 3.615893495987335e-07, "epoch": 1.0172343044727123, "percentage": 82.67, "elapsed_time": "2:42:27", "remaining_time": "0:34:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1250, "total_steps": 1500, "loss": 0.6922, "accuracy": 0.9624999761581421, "learning_rate": 3.3493649053890325e-07, "epoch": 1.025441116126385, "percentage": 83.33, "elapsed_time": "2:43:39", "remaining_time": "0:32:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1250, "total_steps": 1500, "eval_loss": 0.09215716272592545, "epoch": 1.025441116126385, "percentage": 83.33, "elapsed_time": "2:44:05", "remaining_time": "0:32:49", "throughput": "0.00", "total_tokens": 0}