Training in progress, step 850

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c2d1079cd05e8c36866f0ce14918f9a74fd022fe9e1c3e3f5283318522807f
+oid sha256:89aa50978dd9bb6b676eef7ba40cd4761651038e2f09545246dc32df2b2a9619
 size 25200088

trainer_log.jsonl

@@ -94,3 +94,9 @@
 {"current_steps": 790, "total_steps": 1500, "loss": 0.1764, "accuracy": 1.0, "learning_rate": 2.290805391669212e-06, "epoch": 0.7015985790408525, "percentage": 52.67, "elapsed_time": "1:47:25", "remaining_time": "1:36:33", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 800, "total_steps": 1500, "loss": 0.2429, "accuracy": 0.949999988079071, "learning_rate": 2.238678841830867e-06, "epoch": 0.7104795737122558, "percentage": 53.33, "elapsed_time": "1:48:36", "remaining_time": "1:35:02", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 800, "total_steps": 1500, "eval_loss": 0.2468602955341339, "epoch": 0.7104795737122558, "percentage": 53.33, "elapsed_time": "1:49:02", "remaining_time": "1:35:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 810, "total_steps": 1500, "loss": 0.2277, "accuracy": 0.925000011920929, "learning_rate": 2.186666916089239e-06, "epoch": 0.7193605683836589, "percentage": 54.0, "elapsed_time": "1:50:24", "remaining_time": "1:34:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 820, "total_steps": 1500, "loss": 0.2428, "accuracy": 0.949999988079071, "learning_rate": 2.134792428593971e-06, "epoch": 0.7282415630550622, "percentage": 54.67, "elapsed_time": "1:51:36", "remaining_time": "1:32:33", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 830, "total_steps": 1500, "loss": 0.2288, "accuracy": 0.925000011920929, "learning_rate": 2.0830781332097446e-06, "epoch": 0.7371225577264654, "percentage": 55.33, "elapsed_time": "1:52:52", "remaining_time": "1:31:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 840, "total_steps": 1500, "loss": 0.2384, "accuracy": 0.925000011920929, "learning_rate": 2.031546713535688e-06, "epoch": 0.7460035523978685, "percentage": 56.0, "elapsed_time": "1:54:04", "remaining_time": "1:29:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 850, "total_steps": 1500, "loss": 0.2229, "accuracy": 0.9624999761581421, "learning_rate": 1.9802207729556023e-06, "epoch": 0.7548845470692718, "percentage": 56.67, "elapsed_time": "1:55:25", "remaining_time": "1:28:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 850, "total_steps": 1500, "eval_loss": 0.2361687868833542, "epoch": 0.7548845470692718, "percentage": 56.67, "elapsed_time": "1:55:50", "remaining_time": "1:28:35", "throughput": "0.00", "total_tokens": 0}