Training in progress, step 850

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cb13bc9535fc4f4947ff92fd0c6104705259a0b6441692798111e563d4f3b7e
+oid sha256:065ea2f87f143869b48d6c38a544bae4a7c1d851c8604f05cf76f8939acfe83f
 size 25200088

trainer_log.jsonl

@@ -94,3 +94,9 @@
 {"current_steps": 790, "total_steps": 1500, "loss": 0.2315, "accuracy": 0.8999999761581421, "learning_rate": 2.290805391669212e-06, "epoch": 0.7258527621454003, "percentage": 52.67, "elapsed_time": "1:49:29", "remaining_time": "1:38:23", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 800, "total_steps": 1500, "loss": 0.2301, "accuracy": 0.887499988079071, "learning_rate": 2.238678841830867e-06, "epoch": 0.7350407717928104, "percentage": 53.33, "elapsed_time": "1:50:45", "remaining_time": "1:36:54", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 800, "total_steps": 1500, "eval_loss": 0.23762211203575134, "epoch": 0.7350407717928104, "percentage": 53.33, "elapsed_time": "1:51:09", "remaining_time": "1:37:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 810, "total_steps": 1500, "loss": 0.2239, "accuracy": 0.9125000238418579, "learning_rate": 2.186666916089239e-06, "epoch": 0.7442287814402205, "percentage": 54.0, "elapsed_time": "1:52:33", "remaining_time": "1:35:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 820, "total_steps": 1500, "loss": 0.2429, "accuracy": 0.949999988079071, "learning_rate": 2.134792428593971e-06, "epoch": 0.7534167910876306, "percentage": 54.67, "elapsed_time": "1:53:48", "remaining_time": "1:34:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 830, "total_steps": 1500, "loss": 0.2213, "accuracy": 0.9624999761581421, "learning_rate": 2.0830781332097446e-06, "epoch": 0.7626048007350408, "percentage": 55.33, "elapsed_time": "1:55:05", "remaining_time": "1:32:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 840, "total_steps": 1500, "loss": 0.2525, "accuracy": 0.925000011920929, "learning_rate": 2.031546713535688e-06, "epoch": 0.771792810382451, "percentage": 56.0, "elapsed_time": "1:56:23", "remaining_time": "1:31:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 850, "total_steps": 1500, "loss": 0.2253, "accuracy": 0.9375, "learning_rate": 1.9802207729556023e-06, "epoch": 0.780980820029861, "percentage": 56.67, "elapsed_time": "1:57:39", "remaining_time": "1:29:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 850, "total_steps": 1500, "eval_loss": 0.23406219482421875, "epoch": 0.780980820029861, "percentage": 56.67, "elapsed_time": "1:58:03", "remaining_time": "1:30:17", "throughput": "0.00", "total_tokens": 0}