Training in progress, step 450

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b30ac6751c045ed92611c88c626e1042849316e294b20a22f67f1ed48479733
+oid sha256:c967e0ab9c1ac62cd6754f5c3051fcae4eb0791623cbbc7b4928f1f7d2be1db4
 size 40036488

trainer_log.jsonl

@@ -46,3 +46,9 @@
 {"current_steps": 390, "total_steps": 1500, "loss": 4.3874, "accuracy": 0.824999988079071, "learning_rate": 4.211367764821722e-06, "epoch": 0.2826855123674912, "percentage": 26.0, "elapsed_time": "0:53:27", "remaining_time": "2:32:09", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 400, "total_steps": 1500, "loss": 4.2388, "accuracy": 0.6875, "learning_rate": 4.172826515897146e-06, "epoch": 0.28993385883845246, "percentage": 26.67, "elapsed_time": "0:54:42", "remaining_time": "2:30:25", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.49557629227638245, "epoch": 0.28993385883845246, "percentage": 26.67, "elapsed_time": "0:55:12", "remaining_time": "2:31:49", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 410, "total_steps": 1500, "loss": 3.9161, "accuracy": 0.7124999761581421, "learning_rate": 4.133551509975264e-06, "epoch": 0.2971822053094138, "percentage": 27.33, "elapsed_time": "0:56:41", "remaining_time": "2:30:42", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 420, "total_steps": 1500, "loss": 3.8304, "accuracy": 0.762499988079071, "learning_rate": 4.093559974371725e-06, "epoch": 0.3044305517803751, "percentage": 28.0, "elapsed_time": "0:57:58", "remaining_time": "2:29:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 430, "total_steps": 1500, "loss": 3.7662, "accuracy": 0.7250000238418579, "learning_rate": 4.052869450695776e-06, "epoch": 0.31167889825133643, "percentage": 28.67, "elapsed_time": "0:59:12", "remaining_time": "2:27:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 440, "total_steps": 1500, "loss": 3.4493, "accuracy": 0.7749999761581421, "learning_rate": 4.011497787155938e-06, "epoch": 0.3189272447222977, "percentage": 29.33, "elapsed_time": "1:00:28", "remaining_time": "2:25:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 450, "total_steps": 1500, "loss": 4.0187, "accuracy": 0.8125, "learning_rate": 3.969463130731183e-06, "epoch": 0.32617559119325906, "percentage": 30.0, "elapsed_time": "1:01:42", "remaining_time": "2:23:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 450, "total_steps": 1500, "eval_loss": 0.45260879397392273, "epoch": 0.32617559119325906, "percentage": 30.0, "elapsed_time": "1:02:13", "remaining_time": "2:25:10", "throughput": "0.00", "total_tokens": 0}