Training in progress, step 600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d3902fc67755607a7bc38959707775c3622ad89ee0d249e2608e1790b4df48f
+oid sha256:99309419be30ee097b400fc268cae8878bca121391cf05ebcdabdd1ac4d16198
 size 25200088

trainer_log.jsonl

@@ -64,3 +64,9 @@
 {"current_steps": 540, "total_steps": 1500, "loss": 0.4713, "accuracy": 0.8999999761581421, "learning_rate": 3.564448228912682e-06, "epoch": 0.6857142857142857, "percentage": 36.0, "elapsed_time": "1:13:50", "remaining_time": "2:11:16", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 550, "total_steps": 1500, "loss": 0.5543, "accuracy": 0.875, "learning_rate": 3.516841607689501e-06, "epoch": 0.6984126984126984, "percentage": 36.67, "elapsed_time": "1:15:07", "remaining_time": "2:09:45", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.458388090133667, "epoch": 0.6984126984126984, "percentage": 36.67, "elapsed_time": "1:15:26", "remaining_time": "2:10:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 560, "total_steps": 1500, "loss": 0.4126, "accuracy": 0.8999999761581421, "learning_rate": 3.4687889661302577e-06, "epoch": 0.7111111111111111, "percentage": 37.33, "elapsed_time": "1:16:50", "remaining_time": "2:08:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 570, "total_steps": 1500, "loss": 0.4379, "accuracy": 0.8999999761581421, "learning_rate": 3.4203113817116955e-06, "epoch": 0.7238095238095238, "percentage": 38.0, "elapsed_time": "1:18:11", "remaining_time": "2:07:33", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 580, "total_steps": 1500, "loss": 0.4483, "accuracy": 0.925000011920929, "learning_rate": 3.3714301183045382e-06, "epoch": 0.7365079365079366, "percentage": 38.67, "elapsed_time": "1:19:27", "remaining_time": "2:06:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 590, "total_steps": 1500, "loss": 0.4229, "accuracy": 0.887499988079071, "learning_rate": 3.3221666168464584e-06, "epoch": 0.7492063492063492, "percentage": 39.33, "elapsed_time": "1:20:47", "remaining_time": "2:04:35", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 600, "total_steps": 1500, "loss": 0.4304, "accuracy": 0.887499988079071, "learning_rate": 3.272542485937369e-06, "epoch": 0.7619047619047619, "percentage": 40.0, "elapsed_time": "1:22:05", "remaining_time": "2:03:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 600, "total_steps": 1500, "eval_loss": 0.43386051058769226, "epoch": 0.7619047619047619, "percentage": 40.0, "elapsed_time": "1:22:23", "remaining_time": "2:03:35", "throughput": "0.00", "total_tokens": 0}