Training in progress, step 1200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d0a9ad35b163273c24e20b07f258f44868d9db5a4a56a374295104d04c75c0
+oid sha256:dcbe5c60e63a74bda1718c743a5e3df0a742995ea8da64d57c7081a949df9d74
 size 40036488

trainer_log.jsonl

@@ -136,3 +136,9 @@
 {"current_steps": 1140, "total_steps": 1500, "loss": 0.5027, "accuracy": 0.9750000238418579, "learning_rate": 6.775784314464717e-07, "epoch": 0.8263114976895896, "percentage": 76.0, "elapsed_time": "2:37:41", "remaining_time": "0:49:47", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1150, "total_steps": 1500, "loss": 0.7009, "accuracy": 0.987500011920929, "learning_rate": 6.421379363065142e-07, "epoch": 0.8335598441605508, "percentage": 76.67, "elapsed_time": "2:38:55", "remaining_time": "0:48:22", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1150, "total_steps": 1500, "eval_loss": 0.09489800035953522, "epoch": 0.8335598441605508, "percentage": 76.67, "elapsed_time": "2:39:25", "remaining_time": "0:48:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1160, "total_steps": 1500, "loss": 0.9432, "accuracy": 0.9624999761581421, "learning_rate": 6.075123608706093e-07, "epoch": 0.8408081906315121, "percentage": 77.33, "elapsed_time": "2:40:53", "remaining_time": "0:47:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1170, "total_steps": 1500, "loss": 0.5761, "accuracy": 0.987500011920929, "learning_rate": 5.737168930605272e-07, "epoch": 0.8480565371024735, "percentage": 78.0, "elapsed_time": "2:42:06", "remaining_time": "0:45:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1180, "total_steps": 1500, "loss": 0.8883, "accuracy": 0.949999988079071, "learning_rate": 5.407663566854008e-07, "epoch": 0.8553048835734348, "percentage": 78.67, "elapsed_time": "2:43:22", "remaining_time": "0:44:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1190, "total_steps": 1500, "loss": 1.1177, "accuracy": 0.949999988079071, "learning_rate": 5.086752049395094e-07, "epoch": 0.8625532300443961, "percentage": 79.33, "elapsed_time": "2:44:37", "remaining_time": "0:42:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1200, "total_steps": 1500, "loss": 0.4369, "accuracy": 1.0, "learning_rate": 4.774575140626317e-07, "epoch": 0.8698015765153574, "percentage": 80.0, "elapsed_time": "2:45:55", "remaining_time": "0:41:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1200, "total_steps": 1500, "eval_loss": 0.08837977796792984, "epoch": 0.8698015765153574, "percentage": 80.0, "elapsed_time": "2:46:25", "remaining_time": "0:41:36", "throughput": "0.00", "total_tokens": 0}