Training in progress, step 900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd4297aebfd94c1c658683f162b7ca02f1eea775fe99c7ee88c2ef914c2ac511
+oid sha256:db64502678e79237f58f327a12d209c1787dd07811126f4ac215f9ecbb086e40
 size 25200088

trainer_log.jsonl

@@ -100,3 +100,9 @@
 {"current_steps": 840, "total_steps": 1500, "loss": 0.1953, "accuracy": 0.949999988079071, "learning_rate": 2.031546713535688e-06, "epoch": 0.7219596046411689, "percentage": 56.0, "elapsed_time": "1:50:14", "remaining_time": "1:26:37", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 850, "total_steps": 1500, "loss": 0.2395, "accuracy": 0.8999999761581421, "learning_rate": 1.9802207729556023e-06, "epoch": 0.730554361839278, "percentage": 56.67, "elapsed_time": "1:51:31", "remaining_time": "1:25:16", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 850, "total_steps": 1500, "eval_loss": 0.2363433688879013, "epoch": 0.730554361839278, "percentage": 56.67, "elapsed_time": "1:51:56", "remaining_time": "1:25:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 860, "total_steps": 1500, "loss": 0.2234, "accuracy": 0.925000011920929, "learning_rate": 1.9291228247233607e-06, "epoch": 0.7391491190373872, "percentage": 57.33, "elapsed_time": "1:53:18", "remaining_time": "1:24:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 870, "total_steps": 1500, "loss": 0.2045, "accuracy": 0.949999988079071, "learning_rate": 1.8782752820878636e-06, "epoch": 0.7477438762354963, "percentage": 58.0, "elapsed_time": "1:54:28", "remaining_time": "1:22:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 880, "total_steps": 1500, "loss": 0.231, "accuracy": 0.9125000238418579, "learning_rate": 1.827700448461836e-06, "epoch": 0.7563386334336055, "percentage": 58.67, "elapsed_time": "1:55:39", "remaining_time": "1:21:29", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 890, "total_steps": 1500, "loss": 0.2398, "accuracy": 0.8999999761581421, "learning_rate": 1.7774205076388207e-06, "epoch": 0.7649333906317146, "percentage": 59.33, "elapsed_time": "1:56:50", "remaining_time": "1:20:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 900, "total_steps": 1500, "loss": 0.2388, "accuracy": 0.9750000238418579, "learning_rate": 1.7274575140626318e-06, "epoch": 0.7735281478298238, "percentage": 60.0, "elapsed_time": "1:58:00", "remaining_time": "1:18:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 900, "total_steps": 1500, "eval_loss": 0.22793449461460114, "epoch": 0.7735281478298238, "percentage": 60.0, "elapsed_time": "1:58:25", "remaining_time": "1:18:57", "throughput": "0.00", "total_tokens": 0}