Training in progress, step 600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db8ac4c6cf4d1fc5ec15ae4264c8ffff32276db9138e7e7cdfcdc691a90802d7
+oid sha256:7ebed5a6e0e4120e359607874dba662f9213b8c5471c19eb810814b2e5768cc0
 size 25200088

trainer_log.jsonl

@@ -64,3 +64,9 @@
 {"current_steps": 540, "total_steps": 1500, "loss": 0.3565, "accuracy": 0.9125000238418579, "learning_rate": 3.564448228912682e-06, "epoch": 0.4641168886978943, "percentage": 36.0, "elapsed_time": "1:11:05", "remaining_time": "2:06:23", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 550, "total_steps": 1500, "loss": 0.3103, "accuracy": 0.887499988079071, "learning_rate": 3.516841607689501e-06, "epoch": 0.47271164589600345, "percentage": 36.67, "elapsed_time": "1:12:23", "remaining_time": "2:05:02", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.32732319831848145, "epoch": 0.47271164589600345, "percentage": 36.67, "elapsed_time": "1:12:49", "remaining_time": "2:05:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 560, "total_steps": 1500, "loss": 0.3171, "accuracy": 0.887499988079071, "learning_rate": 3.4687889661302577e-06, "epoch": 0.4813064030941126, "percentage": 37.33, "elapsed_time": "1:14:02", "remaining_time": "2:04:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 570, "total_steps": 1500, "loss": 0.331, "accuracy": 0.949999988079071, "learning_rate": 3.4203113817116955e-06, "epoch": 0.48990116029222175, "percentage": 38.0, "elapsed_time": "1:15:13", "remaining_time": "2:02:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 580, "total_steps": 1500, "loss": 0.2557, "accuracy": 0.9750000238418579, "learning_rate": 3.3714301183045382e-06, "epoch": 0.4984959174903309, "percentage": 38.67, "elapsed_time": "1:16:25", "remaining_time": "2:01:14", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 590, "total_steps": 1500, "loss": 0.2921, "accuracy": 0.949999988079071, "learning_rate": 3.3221666168464584e-06, "epoch": 0.50709067468844, "percentage": 39.33, "elapsed_time": "1:17:39", "remaining_time": "1:59:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 600, "total_steps": 1500, "loss": 0.3225, "accuracy": 0.9125000238418579, "learning_rate": 3.272542485937369e-06, "epoch": 0.5156854318865493, "percentage": 40.0, "elapsed_time": "1:18:52", "remaining_time": "1:58:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 600, "total_steps": 1500, "eval_loss": 0.29786577820777893, "epoch": 0.5156854318865493, "percentage": 40.0, "elapsed_time": "1:19:18", "remaining_time": "1:58:57", "throughput": "0.00", "total_tokens": 0}