Training in progress, step 950

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94cd87a4b4528b78adde5d2592e83e2067f8049b083c82ed609a8f1fc79273a4
+oid sha256:e08273ceb712f08a2815122661d2d7d01011b88901c1ac1edf823bc23d8f9040
 size 25200088

trainer_log.jsonl

@@ -106,3 +106,9 @@
 {"current_steps": 890, "total_steps": 1500, "loss": 0.2023, "accuracy": 0.9624999761581421, "learning_rate": 1.7774205076388207e-06, "epoch": 0.7904085257548845, "percentage": 59.33, "elapsed_time": "2:04:26", "remaining_time": "1:25:17", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 900, "total_steps": 1500, "loss": 0.2205, "accuracy": 0.8999999761581421, "learning_rate": 1.7274575140626318e-06, "epoch": 0.7992895204262878, "percentage": 60.0, "elapsed_time": "2:05:41", "remaining_time": "1:23:47", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 900, "total_steps": 1500, "eval_loss": 0.23354515433311462, "epoch": 0.7992895204262878, "percentage": 60.0, "elapsed_time": "2:06:08", "remaining_time": "1:24:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 910, "total_steps": 1500, "loss": 0.1897, "accuracy": 0.9375, "learning_rate": 1.677833383153542e-06, "epoch": 0.8081705150976909, "percentage": 60.67, "elapsed_time": "2:07:36", "remaining_time": "1:22:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 920, "total_steps": 1500, "loss": 0.2111, "accuracy": 0.9375, "learning_rate": 1.6285698816954626e-06, "epoch": 0.8170515097690941, "percentage": 61.33, "elapsed_time": "2:08:55", "remaining_time": "1:21:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 930, "total_steps": 1500, "loss": 0.1988, "accuracy": 0.9624999761581421, "learning_rate": 1.5796886182883053e-06, "epoch": 0.8259325044404974, "percentage": 62.0, "elapsed_time": "2:10:12", "remaining_time": "1:19:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 940, "total_steps": 1500, "loss": 0.2148, "accuracy": 0.887499988079071, "learning_rate": 1.5312110338697427e-06, "epoch": 0.8348134991119005, "percentage": 62.67, "elapsed_time": "2:11:28", "remaining_time": "1:18:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 950, "total_steps": 1500, "loss": 0.191, "accuracy": 0.949999988079071, "learning_rate": 1.4831583923105e-06, "epoch": 0.8436944937833037, "percentage": 63.33, "elapsed_time": "2:12:46", "remaining_time": "1:16:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 950, "total_steps": 1500, "eval_loss": 0.22145631909370422, "epoch": 0.8436944937833037, "percentage": 63.33, "elapsed_time": "2:13:13", "remaining_time": "1:17:07", "throughput": "0.00", "total_tokens": 0}