Training in progress, step 600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2daa27207255027add5d55739f8f4dcef7caa8c1ea22ed9d5acda29cedb1c303
+oid sha256:47ce24973590893dc7cddf3cc21f59f8f6c67b007ed7b7ead25503fa1e7d8d1e
 size 40036488

trainer_log.jsonl

@@ -64,3 +64,9 @@
 {"current_steps": 540, "total_steps": 1500, "loss": 2.85, "accuracy": 0.8374999761581421, "learning_rate": 3.564448228912682e-06, "epoch": 0.39141070943191086, "percentage": 36.0, "elapsed_time": "1:14:16", "remaining_time": "2:12:02", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 550, "total_steps": 1500, "loss": 2.6406, "accuracy": 0.875, "learning_rate": 3.516841607689501e-06, "epoch": 0.39865905590287215, "percentage": 36.67, "elapsed_time": "1:15:28", "remaining_time": "2:10:21", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.30369508266448975, "epoch": 0.39865905590287215, "percentage": 36.67, "elapsed_time": "1:15:58", "remaining_time": "2:11:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 560, "total_steps": 1500, "loss": 2.1664, "accuracy": 0.949999988079071, "learning_rate": 3.4687889661302577e-06, "epoch": 0.4059074023738335, "percentage": 37.33, "elapsed_time": "1:17:26", "remaining_time": "2:09:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 570, "total_steps": 1500, "loss": 2.2641, "accuracy": 0.949999988079071, "learning_rate": 3.4203113817116955e-06, "epoch": 0.4131557488447948, "percentage": 38.0, "elapsed_time": "1:18:38", "remaining_time": "2:08:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 580, "total_steps": 1500, "loss": 2.3099, "accuracy": 0.887499988079071, "learning_rate": 3.3714301183045382e-06, "epoch": 0.42040409531575607, "percentage": 38.67, "elapsed_time": "1:19:51", "remaining_time": "2:06:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 590, "total_steps": 1500, "loss": 2.0248, "accuracy": 0.949999988079071, "learning_rate": 3.3221666168464584e-06, "epoch": 0.4276524417867174, "percentage": 39.33, "elapsed_time": "1:21:07", "remaining_time": "2:05:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 600, "total_steps": 1500, "loss": 2.0191, "accuracy": 0.949999988079071, "learning_rate": 3.272542485937369e-06, "epoch": 0.4349007882576787, "percentage": 40.0, "elapsed_time": "1:22:21", "remaining_time": "2:03:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 600, "total_steps": 1500, "eval_loss": 0.22690872848033905, "epoch": 0.4349007882576787, "percentage": 40.0, "elapsed_time": "1:22:51", "remaining_time": "2:04:17", "throughput": "0.00", "total_tokens": 0}