Training in progress, step 800

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89ebfb4ae968cde67bb3f79df0d409b6a37ea77577d094e03ec35146778788a6
+oid sha256:3fc9c3bf696aec981b040faf7fa40379bc826255f7834dc74701cc30ac2ea708
 size 25200088

trainer_log.jsonl

@@ -88,3 +88,9 @@
 {"current_steps": 740, "total_steps": 1500, "loss": 0.223, "accuracy": 0.887499988079071, "learning_rate": 2.5523560497083927e-06, "epoch": 0.6571936056838366, "percentage": 49.33, "elapsed_time": "1:43:31", "remaining_time": "1:46:19", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 750, "total_steps": 1500, "loss": 0.2227, "accuracy": 0.887499988079071, "learning_rate": 2.5e-06, "epoch": 0.6660746003552398, "percentage": 50.0, "elapsed_time": "1:44:50", "remaining_time": "1:44:50", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.25929248332977295, "epoch": 0.6660746003552398, "percentage": 50.0, "elapsed_time": "1:45:17", "remaining_time": "1:45:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 760, "total_steps": 1500, "loss": 0.1991, "accuracy": 0.9624999761581421, "learning_rate": 2.447643950291608e-06, "epoch": 0.6749555950266429, "percentage": 50.67, "elapsed_time": "1:46:41", "remaining_time": "1:43:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 770, "total_steps": 1500, "loss": 0.2301, "accuracy": 0.9750000238418579, "learning_rate": 2.3953108656770018e-06, "epoch": 0.6838365896980462, "percentage": 51.33, "elapsed_time": "1:47:59", "remaining_time": "1:42:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 780, "total_steps": 1500, "loss": 0.2398, "accuracy": 0.949999988079071, "learning_rate": 2.3430237011767166e-06, "epoch": 0.6927175843694494, "percentage": 52.0, "elapsed_time": "1:49:17", "remaining_time": "1:40:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 790, "total_steps": 1500, "loss": 0.184, "accuracy": 1.0, "learning_rate": 2.290805391669212e-06, "epoch": 0.7015985790408525, "percentage": 52.67, "elapsed_time": "1:50:30", "remaining_time": "1:39:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 800, "total_steps": 1500, "loss": 0.2373, "accuracy": 0.9750000238418579, "learning_rate": 2.238678841830867e-06, "epoch": 0.7104795737122558, "percentage": 53.33, "elapsed_time": "1:51:49", "remaining_time": "1:37:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 800, "total_steps": 1500, "eval_loss": 0.24979564547538757, "epoch": 0.7104795737122558, "percentage": 53.33, "elapsed_time": "1:52:16", "remaining_time": "1:38:14", "throughput": "0.00", "total_tokens": 0}