Training in progress, step 600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2e5abf38eb0fdc317c249ba7ccab44d888ceb90c33c41ddd7fc4c0eef213371
+oid sha256:2cd34603d8071b52d0e64052a555cd92ea97b2ee85ad8f3ac695a9024932b6f3
 size 25200088

trainer_log.jsonl

@@ -64,3 +64,9 @@
 {"current_steps": 540, "total_steps": 1500, "loss": 0.2995, "accuracy": 0.9375, "learning_rate": 3.564448228912682e-06, "epoch": 0.496152520960147, "percentage": 36.0, "elapsed_time": "1:14:34", "remaining_time": "2:12:35", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 550, "total_steps": 1500, "loss": 0.3203, "accuracy": 0.887499988079071, "learning_rate": 3.516841607689501e-06, "epoch": 0.5053405306075571, "percentage": 36.67, "elapsed_time": "1:15:53", "remaining_time": "2:11:04", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.304200142621994, "epoch": 0.5053405306075571, "percentage": 36.67, "elapsed_time": "1:16:17", "remaining_time": "2:11:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 560, "total_steps": 1500, "loss": 0.2728, "accuracy": 0.9624999761581421, "learning_rate": 3.4687889661302577e-06, "epoch": 0.5145285402549673, "percentage": 37.33, "elapsed_time": "1:17:41", "remaining_time": "2:10:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 570, "total_steps": 1500, "loss": 0.2833, "accuracy": 0.9375, "learning_rate": 3.4203113817116955e-06, "epoch": 0.5237165499023774, "percentage": 38.0, "elapsed_time": "1:18:57", "remaining_time": "2:08:49", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 580, "total_steps": 1500, "loss": 0.2942, "accuracy": 0.925000011920929, "learning_rate": 3.3714301183045382e-06, "epoch": 0.5329045595497875, "percentage": 38.67, "elapsed_time": "1:20:13", "remaining_time": "2:07:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 590, "total_steps": 1500, "loss": 0.3347, "accuracy": 0.925000011920929, "learning_rate": 3.3221666168464584e-06, "epoch": 0.5420925691971976, "percentage": 39.33, "elapsed_time": "1:21:29", "remaining_time": "2:05:41", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 600, "total_steps": 1500, "loss": 0.2776, "accuracy": 0.875, "learning_rate": 3.272542485937369e-06, "epoch": 0.5512805788446078, "percentage": 40.0, "elapsed_time": "1:22:47", "remaining_time": "2:04:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 600, "total_steps": 1500, "eval_loss": 0.28658536076545715, "epoch": 0.5512805788446078, "percentage": 40.0, "elapsed_time": "1:23:11", "remaining_time": "2:04:47", "throughput": "0.00", "total_tokens": 0}