Training in progress, step 500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c967e0ab9c1ac62cd6754f5c3051fcae4eb0791623cbbc7b4928f1f7d2be1db4
+oid sha256:3a909a43912f10c53467a5af7e8e1ae977d5a341fa984689508ce9ce64da7ccc
 size 40036488

trainer_log.jsonl

@@ -52,3 +52,9 @@
 {"current_steps": 440, "total_steps": 1500, "loss": 3.4493, "accuracy": 0.7749999761581421, "learning_rate": 4.011497787155938e-06, "epoch": 0.3189272447222977, "percentage": 29.33, "elapsed_time": "1:00:28", "remaining_time": "2:25:40", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 450, "total_steps": 1500, "loss": 4.0187, "accuracy": 0.8125, "learning_rate": 3.969463130731183e-06, "epoch": 0.32617559119325906, "percentage": 30.0, "elapsed_time": "1:01:42", "remaining_time": "2:23:59", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.45260879397392273, "epoch": 0.32617559119325906, "percentage": 30.0, "elapsed_time": "1:02:13", "remaining_time": "2:25:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 460, "total_steps": 1500, "loss": 3.5788, "accuracy": 0.7124999761581421, "learning_rate": 3.92678391921108e-06, "epoch": 0.33342393766422035, "percentage": 30.67, "elapsed_time": "1:03:41", "remaining_time": "2:24:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 470, "total_steps": 1500, "loss": 3.5681, "accuracy": 0.75, "learning_rate": 3.88347887310836e-06, "epoch": 0.34067228413518164, "percentage": 31.33, "elapsed_time": "1:04:56", "remaining_time": "2:22:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 480, "total_steps": 1500, "loss": 3.2884, "accuracy": 0.862500011920929, "learning_rate": 3.839566987447492e-06, "epoch": 0.347920630606143, "percentage": 32.0, "elapsed_time": "1:06:13", "remaining_time": "2:20:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 490, "total_steps": 1500, "loss": 3.5505, "accuracy": 0.7749999761581421, "learning_rate": 3.795067523432826e-06, "epoch": 0.35516897707710426, "percentage": 32.67, "elapsed_time": "1:07:28", "remaining_time": "2:19:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 500, "total_steps": 1500, "loss": 3.3992, "accuracy": 0.800000011920929, "learning_rate": 3.7500000000000005e-06, "epoch": 0.3624173235480656, "percentage": 33.33, "elapsed_time": "1:08:42", "remaining_time": "2:17:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 500, "total_steps": 1500, "eval_loss": 0.40332508087158203, "epoch": 0.3624173235480656, "percentage": 33.33, "elapsed_time": "1:09:12", "remaining_time": "2:18:25", "throughput": "0.00", "total_tokens": 0}