Training in progress, step 650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2537418fea2bc52c3dcb900d1cf4847005adef59b18ffee5005283c1d27658c1
+oid sha256:7b4ab14d4ff7fdf2ae1645c041218b89fb8163efd5047ff801575b916faa4bda
 size 25200088

trainer_log.jsonl

@@ -70,3 +70,9 @@
 {"current_steps": 590, "total_steps": 1500, "loss": 0.3666, "accuracy": 0.875, "learning_rate": 3.3221666168464584e-06, "epoch": 0.6289978678038379, "percentage": 39.33, "elapsed_time": "1:19:43", "remaining_time": "2:02:58", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 600, "total_steps": 1500, "loss": 0.3017, "accuracy": 0.862500011920929, "learning_rate": 3.272542485937369e-06, "epoch": 0.6396588486140725, "percentage": 40.0, "elapsed_time": "1:20:54", "remaining_time": "2:01:21", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.3409230411052704, "epoch": 0.6396588486140725, "percentage": 40.0, "elapsed_time": "1:21:16", "remaining_time": "2:01:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 610, "total_steps": 1500, "loss": 0.3429, "accuracy": 0.9375, "learning_rate": 3.222579492361179e-06, "epoch": 0.650319829424307, "percentage": 40.67, "elapsed_time": "1:22:40", "remaining_time": "2:00:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 620, "total_steps": 1500, "loss": 0.3355, "accuracy": 0.925000011920929, "learning_rate": 3.1722995515381644e-06, "epoch": 0.6609808102345416, "percentage": 41.33, "elapsed_time": "1:23:54", "remaining_time": "1:59:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 630, "total_steps": 1500, "loss": 0.3218, "accuracy": 0.925000011920929, "learning_rate": 3.121724717912138e-06, "epoch": 0.6716417910447762, "percentage": 42.0, "elapsed_time": "1:25:12", "remaining_time": "1:57:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 640, "total_steps": 1500, "loss": 0.2868, "accuracy": 0.925000011920929, "learning_rate": 3.0708771752766397e-06, "epoch": 0.6823027718550106, "percentage": 42.67, "elapsed_time": "1:26:27", "remaining_time": "1:56:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1500, "loss": 0.3491, "accuracy": 0.9375, "learning_rate": 3.019779227044398e-06, "epoch": 0.6929637526652452, "percentage": 43.33, "elapsed_time": "1:27:45", "remaining_time": "1:54:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1500, "eval_loss": 0.31618499755859375, "epoch": 0.6929637526652452, "percentage": 43.33, "elapsed_time": "1:28:06", "remaining_time": "1:55:13", "throughput": "0.00", "total_tokens": 0}