Training in progress, step 250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d673deb3e7741342520f3b84ddf56868f3254207b2c59afb0f6adb0afa6accd0
+oid sha256:20f162ea214e0953700bd73b322d14375f02ad63b80dfd9c31601fbe2b9ff081
 size 40036488

trainer_log.jsonl

@@ -22,3 +22,9 @@
 {"current_steps": 190, "total_steps": 1000, "loss": 7.004, "accuracy": 0.5874999761581421, "learning_rate": 4.567701435686405e-06, "epoch": 0.13771858294826492, "percentage": 19.0, "elapsed_time": "0:25:35", "remaining_time": "1:49:04", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 200, "total_steps": 1000, "loss": 7.0539, "accuracy": 0.6499999761581421, "learning_rate": 4.522542485937369e-06, "epoch": 0.14496692941922623, "percentage": 20.0, "elapsed_time": "0:26:48", "remaining_time": "1:47:15", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 200, "total_steps": 1000, "eval_loss": 0.8565592169761658, "epoch": 0.14496692941922623, "percentage": 20.0, "elapsed_time": "0:27:19", "remaining_time": "1:49:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 210, "total_steps": 1000, "loss": 6.9013, "accuracy": 0.5874999761581421, "learning_rate": 4.475387530939226e-06, "epoch": 0.15221527589018755, "percentage": 21.0, "elapsed_time": "0:28:46", "remaining_time": "1:48:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 220, "total_steps": 1000, "loss": 6.9366, "accuracy": 0.699999988079071, "learning_rate": 4.426283106939474e-06, "epoch": 0.15946362236114886, "percentage": 22.0, "elapsed_time": "0:29:59", "remaining_time": "1:46:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 230, "total_steps": 1000, "loss": 6.8823, "accuracy": 0.699999988079071, "learning_rate": 4.3752776740761495e-06, "epoch": 0.16671196883211017, "percentage": 23.0, "elapsed_time": "0:31:13", "remaining_time": "1:44:32", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 240, "total_steps": 1000, "loss": 6.7139, "accuracy": 0.6625000238418579, "learning_rate": 4.322421568553529e-06, "epoch": 0.1739603153030715, "percentage": 24.0, "elapsed_time": "0:32:29", "remaining_time": "1:42:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 1000, "loss": 6.7737, "accuracy": 0.550000011920929, "learning_rate": 4.267766952966369e-06, "epoch": 0.1812086617740328, "percentage": 25.0, "elapsed_time": "0:33:48", "remaining_time": "1:41:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 1000, "eval_loss": 0.816527247428894, "epoch": 0.1812086617740328, "percentage": 25.0, "elapsed_time": "0:34:18", "remaining_time": "1:42:55", "throughput": "0.00", "total_tokens": 0}