Training in progress, step 600

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b885b20c1c312d2cba718c440b75145db55e1a6f6d11eaa5559bbc187fc57dc
+oid sha256:2537418fea2bc52c3dcb900d1cf4847005adef59b18ffee5005283c1d27658c1
 size 25200088

trainer_log.jsonl

@@ -64,3 +64,9 @@
 {"current_steps": 540, "total_steps": 1500, "loss": 0.3675, "accuracy": 0.925000011920929, "learning_rate": 3.564448228912682e-06, "epoch": 0.5756929637526652, "percentage": 36.0, "elapsed_time": "1:12:59", "remaining_time": "2:09:45", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 550, "total_steps": 1500, "loss": 0.3921, "accuracy": 0.862500011920929, "learning_rate": 3.516841607689501e-06, "epoch": 0.5863539445628998, "percentage": 36.67, "elapsed_time": "1:14:16", "remaining_time": "2:08:17", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 550, "total_steps": 1500, "eval_loss": 0.35785165429115295, "epoch": 0.5863539445628998, "percentage": 36.67, "elapsed_time": "1:14:38", "remaining_time": "2:08:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 560, "total_steps": 1500, "loss": 0.3701, "accuracy": 0.887499988079071, "learning_rate": 3.4687889661302577e-06, "epoch": 0.5970149253731343, "percentage": 37.33, "elapsed_time": "1:15:56", "remaining_time": "2:07:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 570, "total_steps": 1500, "loss": 0.3481, "accuracy": 0.8999999761581421, "learning_rate": 3.4203113817116955e-06, "epoch": 0.6076759061833689, "percentage": 38.0, "elapsed_time": "1:17:14", "remaining_time": "2:06:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 580, "total_steps": 1500, "loss": 0.3571, "accuracy": 0.9125000238418579, "learning_rate": 3.3714301183045382e-06, "epoch": 0.6183368869936035, "percentage": 38.67, "elapsed_time": "1:18:27", "remaining_time": "2:04:27", "throughput": "0.00", "total_tokens": 0}
+{"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}