Training in progress, step 550

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dac859c7ff908cd4d01ff89bc83ea5fee5cc4658a79bf64ca31885662e69f632
+oid sha256:3d3902fc67755607a7bc38959707775c3622ad89ee0d249e2608e1790b4df48f
 size 25200088

trainer_log.jsonl

@@ -58,3 +58,9 @@
 {"current_steps": 490, "total_steps": 1500, "loss": 0.4437, "accuracy": 0.949999988079071, "learning_rate": 3.795067523432826e-06, "epoch": 0.6222222222222222, "percentage": 32.67, "elapsed_time": "1:07:02", "remaining_time": "2:18:10", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "loss": 0.4411, "accuracy": 0.887499988079071, "learning_rate": 3.7500000000000005e-06, "epoch": 0.6349206349206349, "percentage": 33.33, "elapsed_time": "1:08:17", "remaining_time": "2:16:34", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 500, "total_steps": 1500, "eval_loss": 0.4819534122943878, "epoch": 0.6349206349206349, "percentage": 33.33, "elapsed_time": "1:08:35", "remaining_time": "2:17:11", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 510, "total_steps": 1500, "loss": 0.5284, "accuracy": 0.862500011920929, "learning_rate": 3.7043841852542884e-06, "epoch": 0.6476190476190476, "percentage": 34.0, "elapsed_time": "1:09:59", "remaining_time": "2:15:52", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 520, "total_steps": 1500, "loss": 0.5357, "accuracy": 0.8374999761581421, "learning_rate": 3.658240087799655e-06, "epoch": 0.6603174603174603, "percentage": 34.67, "elapsed_time": "1:11:14", "remaining_time": "2:14:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 530, "total_steps": 1500, "loss": 0.5079, "accuracy": 0.862500011920929, "learning_rate": 3.611587947962319e-06, "epoch": 0.6730158730158731, "percentage": 35.33, "elapsed_time": "1:12:33", "remaining_time": "2:12:48", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 540, "total_steps": 1500, "loss": 0.4713, "accuracy": 0.8999999761581421, "learning_rate": 3.564448228912682e-06, "epoch": 0.6857142857142857, "percentage": 36.0, "elapsed_time": "1:13:50", "remaining_time": "2:11:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "loss": 0.5543, "accuracy": 0.875, "learning_rate": 3.516841607689501e-06, "epoch": 0.6984126984126984, "percentage": 36.67, "elapsed_time": "1:15:07", "remaining_time": "2:09:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 550, "total_steps": 1500, "eval_loss": 0.458388090133667, "epoch": 0.6984126984126984, "percentage": 36.67, "elapsed_time": "1:15:26", "remaining_time": "2:10:17", "throughput": "0.00", "total_tokens": 0}