Training in progress, step 850

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38ba146d5788d7fe33bf5857935bf4517a02c51c58ef76285bba4eb3c1457aa8
+oid sha256:a2564540f0edd96859a04880441118653825d7f2f7c1ddeecaad9ec4d56c6ce5
 size 25200088

trainer_log.jsonl

@@ -94,3 +94,9 @@
 {"current_steps": 790, "total_steps": 1500, "loss": 0.2437, "accuracy": 0.9125000238418579, "learning_rate": 2.290805391669212e-06, "epoch": 0.6789858186506231, "percentage": 52.67, "elapsed_time": "1:45:36", "remaining_time": "1:34:54", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 800, "total_steps": 1500, "loss": 0.213, "accuracy": 0.9125000238418579, "learning_rate": 2.238678841830867e-06, "epoch": 0.6875805758487322, "percentage": 53.33, "elapsed_time": "1:46:45", "remaining_time": "1:33:24", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 800, "total_steps": 1500, "eval_loss": 0.23895224928855896, "epoch": 0.6875805758487322, "percentage": 53.33, "elapsed_time": "1:47:10", "remaining_time": "1:33:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 810, "total_steps": 1500, "loss": 0.2391, "accuracy": 0.925000011920929, "learning_rate": 2.186666916089239e-06, "epoch": 0.6961753330468414, "percentage": 54.0, "elapsed_time": "1:48:32", "remaining_time": "1:32:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 820, "total_steps": 1500, "loss": 0.1972, "accuracy": 0.887499988079071, "learning_rate": 2.134792428593971e-06, "epoch": 0.7047700902449506, "percentage": 54.67, "elapsed_time": "1:49:46", "remaining_time": "1:31:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 830, "total_steps": 1500, "loss": 0.2161, "accuracy": 0.949999988079071, "learning_rate": 2.0830781332097446e-06, "epoch": 0.7133648474430597, "percentage": 55.33, "elapsed_time": "1:51:02", "remaining_time": "1:29:38", "throughput": "0.00", "total_tokens": 0}
+{"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": "1:52:16", "remaining_time": "1:28:13", "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": "1:53:33", "remaining_time": "1:26:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 850, "total_steps": 1500, "eval_loss": 0.23591776192188263, "epoch": 0.730554361839278, "percentage": 56.67, "elapsed_time": "1:53:58", "remaining_time": "1:27:09", "throughput": "0.00", "total_tokens": 0}