Training in progress, step 900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2564540f0edd96859a04880441118653825d7f2f7c1ddeecaad9ec4d56c6ce5
+oid sha256:d54e201710ea295096c36b8c50c8aa3738b0826b03e29f602dd4b3a161ecd67d
 size 25200088

trainer_log.jsonl

@@ -100,3 +100,9 @@
 {"current_steps": 840, "total_steps": 1500, "loss": 0.1895, "accuracy": 0.9375, "learning_rate": 2.031546713535688e-06, "epoch": 0.7219596046411689, "percentage": 56.0, "elapsed_time": "1:51:23", "remaining_time": "1:27:31", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 850, "total_steps": 1500, "loss": 0.2239, "accuracy": 0.925000011920929, "learning_rate": 1.9802207729556023e-06, "epoch": 0.730554361839278, "percentage": 56.67, "elapsed_time": "1:52:39", "remaining_time": "1:26:09", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 850, "total_steps": 1500, "eval_loss": 0.23591776192188263, "epoch": 0.730554361839278, "percentage": 56.67, "elapsed_time": "1:53:05", "remaining_time": "1:26:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 860, "total_steps": 1500, "loss": 0.2268, "accuracy": 0.9125000238418579, "learning_rate": 1.9291228247233607e-06, "epoch": 0.7391491190373872, "percentage": 57.33, "elapsed_time": "1:54:26", "remaining_time": "1:25:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 870, "total_steps": 1500, "loss": 0.2001, "accuracy": 0.9750000238418579, "learning_rate": 1.8782752820878636e-06, "epoch": 0.7477438762354963, "percentage": 58.0, "elapsed_time": "1:55:37", "remaining_time": "1:23:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 880, "total_steps": 1500, "loss": 0.2257, "accuracy": 0.9125000238418579, "learning_rate": 1.827700448461836e-06, "epoch": 0.7563386334336055, "percentage": 58.67, "elapsed_time": "1:56:49", "remaining_time": "1:22:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 890, "total_steps": 1500, "loss": 0.2123, "accuracy": 0.9375, "learning_rate": 1.7774205076388207e-06, "epoch": 0.7649333906317146, "percentage": 59.33, "elapsed_time": "1:58:02", "remaining_time": "1:20:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 900, "total_steps": 1500, "loss": 0.2345, "accuracy": 0.9624999761581421, "learning_rate": 1.7274575140626318e-06, "epoch": 0.7735281478298238, "percentage": 60.0, "elapsed_time": "1:59:15", "remaining_time": "1:19:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 900, "total_steps": 1500, "eval_loss": 0.23031750321388245, "epoch": 0.7735281478298238, "percentage": 60.0, "elapsed_time": "1:59:40", "remaining_time": "1:19:46", "throughput": "0.00", "total_tokens": 0}