Training in progress, step 600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:add143543c39f322e4d3f1cbbfc33056da1d86262daa3a59f99362191c70de30
+oid sha256:2c971089b0dbb7f1fd7233b86ee4eab0e4320b6c6bbffc37c6fa55466e3172a9
 size 25200088

trainer_log.jsonl

@@ -64,3 +64,9 @@
 {"current_steps": 540, "total_steps": 1500, "loss": 0.2684, "accuracy": 0.9125000238418579, "learning_rate": 3.564448228912682e-06, "epoch": 0.47957371225577267, "percentage": 36.0, "elapsed_time": "1:13:11", "remaining_time": "2:10:07", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 550, "total_steps": 1500, "loss": 0.3159, "accuracy": 0.9375, "learning_rate": 3.516841607689501e-06, "epoch": 0.48845470692717585, "percentage": 36.67, "elapsed_time": "1:14:27", "remaining_time": "2:08:36", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.30747923254966736, "epoch": 0.48845470692717585, "percentage": 36.67, "elapsed_time": "1:14:52", "remaining_time": "2:09:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 560, "total_steps": 1500, "loss": 0.2912, "accuracy": 0.9125000238418579, "learning_rate": 3.4687889661302577e-06, "epoch": 0.49733570159857904, "percentage": 37.33, "elapsed_time": "1:16:12", "remaining_time": "2:07:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 570, "total_steps": 1500, "loss": 0.3284, "accuracy": 0.862500011920929, "learning_rate": 3.4203113817116955e-06, "epoch": 0.5062166962699822, "percentage": 38.0, "elapsed_time": "1:17:23", "remaining_time": "2:06:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 580, "total_steps": 1500, "loss": 0.2728, "accuracy": 0.9125000238418579, "learning_rate": 3.3714301183045382e-06, "epoch": 0.5150976909413855, "percentage": 38.67, "elapsed_time": "1:18:38", "remaining_time": "2:04:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 590, "total_steps": 1500, "loss": 0.2568, "accuracy": 0.9375, "learning_rate": 3.3221666168464584e-06, "epoch": 0.5239786856127886, "percentage": 39.33, "elapsed_time": "1:19:54", "remaining_time": "2:03:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 600, "total_steps": 1500, "loss": 0.2639, "accuracy": 0.925000011920929, "learning_rate": 3.272542485937369e-06, "epoch": 0.5328596802841918, "percentage": 40.0, "elapsed_time": "1:21:11", "remaining_time": "2:01:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 600, "total_steps": 1500, "eval_loss": 0.28853774070739746, "epoch": 0.5328596802841918, "percentage": 40.0, "elapsed_time": "1:21:36", "remaining_time": "2:02:24", "throughput": "0.00", "total_tokens": 0}