Training in progress, step 850

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15c7b2025796d1744848ba59ad2f7a8126b5d52b95715f3e418fdc42dbfcb756
+oid sha256:e41f30261e175a753c2fb8158427a4b9c7319c55289f24d9f16c4a92e8efcbdc
 size 40036488

trainer_log.jsonl

@@ -94,3 +94,9 @@
 {"current_steps": 790, "total_steps": 1500, "loss": 0.9819, "accuracy": 0.9750000238418579, "learning_rate": 2.290805391669212e-06, "epoch": 0.5726193712059436, "percentage": 52.67, "elapsed_time": "1:49:01", "remaining_time": "1:37:59", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 800, "total_steps": 1500, "loss": 1.0712, "accuracy": 0.9750000238418579, "learning_rate": 2.238678841830867e-06, "epoch": 0.5798677176769049, "percentage": 53.33, "elapsed_time": "1:50:13", "remaining_time": "1:36:26", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 800, "total_steps": 1500, "eval_loss": 0.12996967136859894, "epoch": 0.5798677176769049, "percentage": 53.33, "elapsed_time": "1:50:44", "remaining_time": "1:36:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 810, "total_steps": 1500, "loss": 1.2619, "accuracy": 0.949999988079071, "learning_rate": 2.186666916089239e-06, "epoch": 0.5871160641478663, "percentage": 54.0, "elapsed_time": "1:52:10", "remaining_time": "1:35:33", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 820, "total_steps": 1500, "loss": 1.0105, "accuracy": 0.987500011920929, "learning_rate": 2.134792428593971e-06, "epoch": 0.5943644106188276, "percentage": 54.67, "elapsed_time": "1:53:24", "remaining_time": "1:34:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 830, "total_steps": 1500, "loss": 0.8295, "accuracy": 0.9375, "learning_rate": 2.0830781332097446e-06, "epoch": 0.6016127570897889, "percentage": 55.33, "elapsed_time": "1:54:40", "remaining_time": "1:32:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 840, "total_steps": 1500, "loss": 0.9398, "accuracy": 0.987500011920929, "learning_rate": 2.031546713535688e-06, "epoch": 0.6088611035607502, "percentage": 56.0, "elapsed_time": "1:55:54", "remaining_time": "1:31:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 850, "total_steps": 1500, "loss": 0.8919, "accuracy": 1.0, "learning_rate": 1.9802207729556023e-06, "epoch": 0.6161094500317115, "percentage": 56.67, "elapsed_time": "1:57:08", "remaining_time": "1:29:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 850, "total_steps": 1500, "eval_loss": 0.11857374012470245, "epoch": 0.6161094500317115, "percentage": 56.67, "elapsed_time": "1:57:38", "remaining_time": "1:29:57", "throughput": "0.00", "total_tokens": 0}