Training in progress, step 600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99afd7d1d267e329ca99fcdaf820287cb9c75b965d648b99a019613bf2251394
+oid sha256:e13dcdfac1567edf8d0a35ab9a0e69e13e4d4a2cfa4f7ec4382db67e5ebafc0b
 size 25200088

trainer_log.jsonl

@@ -64,3 +64,9 @@
 {"current_steps": 540, "total_steps": 1500, "loss": 0.2954, "accuracy": 0.8374999761581421, "learning_rate": 3.564448228912682e-06, "epoch": 0.43592330978809285, "percentage": 36.0, "elapsed_time": "1:15:39", "remaining_time": "2:14:30", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 550, "total_steps": 1500, "loss": 0.26, "accuracy": 0.887499988079071, "learning_rate": 3.516841607689501e-06, "epoch": 0.4439959636730575, "percentage": 36.67, "elapsed_time": "1:16:55", "remaining_time": "2:12:52", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.28268176317214966, "epoch": 0.4439959636730575, "percentage": 36.67, "elapsed_time": "1:17:25", "remaining_time": "2:13:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 560, "total_steps": 1500, "loss": 0.2752, "accuracy": 0.925000011920929, "learning_rate": 3.4687889661302577e-06, "epoch": 0.4520686175580222, "percentage": 37.33, "elapsed_time": "1:18:50", "remaining_time": "2:12:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 570, "total_steps": 1500, "loss": 0.2666, "accuracy": 0.862500011920929, "learning_rate": 3.4203113817116955e-06, "epoch": 0.4601412714429869, "percentage": 38.0, "elapsed_time": "1:20:08", "remaining_time": "2:10:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 580, "total_steps": 1500, "loss": 0.2362, "accuracy": 0.9624999761581421, "learning_rate": 3.3714301183045382e-06, "epoch": 0.4682139253279516, "percentage": 38.67, "elapsed_time": "1:21:23", "remaining_time": "2:09:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 590, "total_steps": 1500, "loss": 0.2774, "accuracy": 0.862500011920929, "learning_rate": 3.3221666168464584e-06, "epoch": 0.47628657921291623, "percentage": 39.33, "elapsed_time": "1:22:39", "remaining_time": "2:07:29", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 600, "total_steps": 1500, "loss": 0.3082, "accuracy": 0.9375, "learning_rate": 3.272542485937369e-06, "epoch": 0.4843592330978809, "percentage": 40.0, "elapsed_time": "1:23:54", "remaining_time": "2:05:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 600, "total_steps": 1500, "eval_loss": 0.2698034942150116, "epoch": 0.4843592330978809, "percentage": 40.0, "elapsed_time": "1:24:24", "remaining_time": "2:06:37", "throughput": "0.00", "total_tokens": 0}