Training in progress, step 900

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:065ea2f87f143869b48d6c38a544bae4a7c1d851c8604f05cf76f8939acfe83f
+oid sha256:db4320c34e69b61e2e6bbe8d869bb335b97ac72926ffaa976aa7eb5a930e0315
 size 25200088

trainer_log.jsonl

@@ -100,3 +100,9 @@
 {"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}
+{"current_steps": 860, "total_steps": 1500, "loss": 0.254, "accuracy": 0.949999988079071, "learning_rate": 1.9291228247233607e-06, "epoch": 0.7901688296772712, "percentage": 57.33, "elapsed_time": "1:59:24", "remaining_time": "1:28:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 870, "total_steps": 1500, "loss": 0.2325, "accuracy": 0.9624999761581421, "learning_rate": 1.8782752820878636e-06, "epoch": 0.7993568393246813, "percentage": 58.0, "elapsed_time": "2:00:40", "remaining_time": "1:27:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 880, "total_steps": 1500, "loss": 0.2427, "accuracy": 0.887499988079071, "learning_rate": 1.827700448461836e-06, "epoch": 0.8085448489720914, "percentage": 58.67, "elapsed_time": "2:01:53", "remaining_time": "1:25:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 890, "total_steps": 1500, "loss": 0.1988, "accuracy": 0.925000011920929, "learning_rate": 1.7774205076388207e-06, "epoch": 0.8177328586195015, "percentage": 59.33, "elapsed_time": "2:03:07", "remaining_time": "1:24:23", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 900, "total_steps": 1500, "loss": 0.2055, "accuracy": 0.9375, "learning_rate": 1.7274575140626318e-06, "epoch": 0.8269208682669117, "percentage": 60.0, "elapsed_time": "2:04:27", "remaining_time": "1:22:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 900, "total_steps": 1500, "eval_loss": 0.2267654538154602, "epoch": 0.8269208682669117, "percentage": 60.0, "elapsed_time": "2:04:52", "remaining_time": "1:23:14", "throughput": "0.00", "total_tokens": 0}