Training in progress, step 450

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec7f69e153f116930da638c31c3747fe4604c97403c4bfc918c0ba168ad207f0
+oid sha256:40839e624e306eeed5406dcbbdc9be3b5fc4b2ca860cededc0848ea0d7d71472
 size 25200088

trainer_log.jsonl

@@ -46,3 +46,9 @@
 {"current_steps": 390, "total_steps": 1500, "loss": 0.4776, "accuracy": 0.625, "learning_rate": 4.211367764821722e-06, "epoch": 0.33519553072625696, "percentage": 26.0, "elapsed_time": "0:52:21", "remaining_time": "2:29:00", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 400, "total_steps": 1500, "loss": 0.4686, "accuracy": 0.6875, "learning_rate": 4.172826515897146e-06, "epoch": 0.3437902879243661, "percentage": 26.67, "elapsed_time": "0:53:32", "remaining_time": "2:27:15", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.46578800678253174, "epoch": 0.3437902879243661, "percentage": 26.67, "elapsed_time": "0:53:58", "remaining_time": "2:28:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 410, "total_steps": 1500, "loss": 0.4335, "accuracy": 0.6625000238418579, "learning_rate": 4.133551509975264e-06, "epoch": 0.3523850451224753, "percentage": 27.33, "elapsed_time": "0:55:22", "remaining_time": "2:27:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 420, "total_steps": 1500, "loss": 0.4543, "accuracy": 0.7124999761581421, "learning_rate": 4.093559974371725e-06, "epoch": 0.36097980232058446, "percentage": 28.0, "elapsed_time": "0:56:37", "remaining_time": "2:25:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 430, "total_steps": 1500, "loss": 0.4091, "accuracy": 0.7749999761581421, "learning_rate": 4.052869450695776e-06, "epoch": 0.3695745595186936, "percentage": 28.67, "elapsed_time": "0:57:53", "remaining_time": "2:24:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 440, "total_steps": 1500, "loss": 0.3995, "accuracy": 0.862500011920929, "learning_rate": 4.011497787155938e-06, "epoch": 0.37816931671680276, "percentage": 29.33, "elapsed_time": "0:59:06", "remaining_time": "2:22:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 450, "total_steps": 1500, "loss": 0.3671, "accuracy": 0.887499988079071, "learning_rate": 3.969463130731183e-06, "epoch": 0.3867640739149119, "percentage": 30.0, "elapsed_time": "1:00:20", "remaining_time": "2:20:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 450, "total_steps": 1500, "eval_loss": 0.3965117633342743, "epoch": 0.3867640739149119, "percentage": 30.0, "elapsed_time": "1:00:45", "remaining_time": "2:21:46", "throughput": "0.00", "total_tokens": 0}