Training in progress, step 800

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09d2c89b623a0bac2650e986b11ebeefe08ead2d78de6bbef304fb1dc41de899
+oid sha256:3cb13bc9535fc4f4947ff92fd0c6104705259a0b6441692798111e563d4f3b7e
 size 25200088

trainer_log.jsonl

@@ -88,3 +88,9 @@
 {"current_steps": 740, "total_steps": 1500, "loss": 0.2603, "accuracy": 0.9375, "learning_rate": 2.5523560497083927e-06, "epoch": 0.6799127139083496, "percentage": 49.33, "elapsed_time": "1:42:34", "remaining_time": "1:45:20", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 750, "total_steps": 1500, "loss": 0.2348, "accuracy": 0.862500011920929, "learning_rate": 2.5e-06, "epoch": 0.6891007235557597, "percentage": 50.0, "elapsed_time": "1:43:52", "remaining_time": "1:43:52", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 750, "total_steps": 1500, "eval_loss": 0.25226154923439026, "epoch": 0.6891007235557597, "percentage": 50.0, "elapsed_time": "1:44:16", "remaining_time": "1:44:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 760, "total_steps": 1500, "loss": 0.2412, "accuracy": 0.887499988079071, "learning_rate": 2.447643950291608e-06, "epoch": 0.6982887332031699, "percentage": 50.67, "elapsed_time": "1:45:33", "remaining_time": "1:42:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 770, "total_steps": 1500, "loss": 0.2528, "accuracy": 0.9624999761581421, "learning_rate": 2.3953108656770018e-06, "epoch": 0.70747674285058, "percentage": 51.33, "elapsed_time": "1:46:50", "remaining_time": "1:41:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 780, "total_steps": 1500, "loss": 0.2672, "accuracy": 0.8999999761581421, "learning_rate": 2.3430237011767166e-06, "epoch": 0.7166647524979901, "percentage": 52.0, "elapsed_time": "1:48:09", "remaining_time": "1:39:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 790, "total_steps": 1500, "loss": 0.2315, "accuracy": 0.8999999761581421, "learning_rate": 2.290805391669212e-06, "epoch": 0.7258527621454003, "percentage": 52.67, "elapsed_time": "1:49:29", "remaining_time": "1:38:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 800, "total_steps": 1500, "loss": 0.2301, "accuracy": 0.887499988079071, "learning_rate": 2.238678841830867e-06, "epoch": 0.7350407717928104, "percentage": 53.33, "elapsed_time": "1:50:45", "remaining_time": "1:36:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 800, "total_steps": 1500, "eval_loss": 0.23762211203575134, "epoch": 0.7350407717928104, "percentage": 53.33, "elapsed_time": "1:51:09", "remaining_time": "1:37:15", "throughput": "0.00", "total_tokens": 0}