Training in progress, step 700

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:161e891f1f1307c98508eb47e0d7f9774e5eaad7be0bcb986d8f289281fcb5a9
+oid sha256:9e5befebf1017039d1a13a3c3c99e065d865220f99076a124e5bb5e00ad0954c
 size 25200088

trainer_log.jsonl

@@ -76,3 +76,9 @@
 {"current_steps": 640, "total_steps": 1500, "loss": 0.4461, "accuracy": 0.875, "learning_rate": 3.0708771752766397e-06, "epoch": 0.8126984126984127, "percentage": 42.67, "elapsed_time": "1:27:39", "remaining_time": "1:57:47", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 650, "total_steps": 1500, "loss": 0.4231, "accuracy": 0.949999988079071, "learning_rate": 3.019779227044398e-06, "epoch": 0.8253968253968254, "percentage": 43.33, "elapsed_time": "1:28:57", "remaining_time": "1:56:20", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 650, "total_steps": 1500, "eval_loss": 0.4155474007129669, "epoch": 0.8253968253968254, "percentage": 43.33, "elapsed_time": "1:29:16", "remaining_time": "1:56:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 660, "total_steps": 1500, "loss": 0.4137, "accuracy": 0.925000011920929, "learning_rate": 2.9684532864643123e-06, "epoch": 0.8380952380952381, "percentage": 44.0, "elapsed_time": "1:30:40", "remaining_time": "1:55:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 670, "total_steps": 1500, "loss": 0.4138, "accuracy": 0.875, "learning_rate": 2.9169218667902562e-06, "epoch": 0.8507936507936508, "percentage": 44.67, "elapsed_time": "1:31:58", "remaining_time": "1:53:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 680, "total_steps": 1500, "loss": 0.4267, "accuracy": 0.949999988079071, "learning_rate": 2.8652075714060296e-06, "epoch": 0.8634920634920635, "percentage": 45.33, "elapsed_time": "1:33:15", "remaining_time": "1:52:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 690, "total_steps": 1500, "loss": 0.3531, "accuracy": 0.9375, "learning_rate": 2.813333083910761e-06, "epoch": 0.8761904761904762, "percentage": 46.0, "elapsed_time": "1:34:32", "remaining_time": "1:50:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 700, "total_steps": 1500, "loss": 0.4327, "accuracy": 0.8374999761581421, "learning_rate": 2.761321158169134e-06, "epoch": 0.8888888888888888, "percentage": 46.67, "elapsed_time": "1:35:48", "remaining_time": "1:49:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 700, "total_steps": 1500, "eval_loss": 0.40030673146247864, "epoch": 0.8888888888888888, "percentage": 46.67, "elapsed_time": "1:36:07", "remaining_time": "1:49:51", "throughput": "0.00", "total_tokens": 0}