Training in progress, step 450

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcb67654b6389680d635590ae7933b91d513c182d5ceef5b313a5d33c6232f3c
+oid sha256:5287152d9213dbfa3c38e13847adf3c7b00c332045ff875824d2b8640619101d
 size 25200088

trainer_log.jsonl

@@ -46,3 +46,9 @@
 {"current_steps": 390, "total_steps": 1500, "loss": 0.6301, "accuracy": 0.8374999761581421, "learning_rate": 4.211367764821722e-06, "epoch": 0.49523809523809526, "percentage": 26.0, "elapsed_time": "0:53:08", "remaining_time": "2:31:16", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 400, "total_steps": 1500, "loss": 0.6274, "accuracy": 0.800000011920929, "learning_rate": 4.172826515897146e-06, "epoch": 0.5079365079365079, "percentage": 26.67, "elapsed_time": "0:54:28", "remaining_time": "2:29:49", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 400, "total_steps": 1500, "eval_loss": 0.590033233165741, "epoch": 0.5079365079365079, "percentage": 26.67, "elapsed_time": "0:54:47", "remaining_time": "2:30:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 410, "total_steps": 1500, "loss": 0.6309, "accuracy": 0.8125, "learning_rate": 4.133551509975264e-06, "epoch": 0.5206349206349207, "percentage": 27.33, "elapsed_time": "0:56:11", "remaining_time": "2:29:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 420, "total_steps": 1500, "loss": 0.5839, "accuracy": 0.824999988079071, "learning_rate": 4.093559974371725e-06, "epoch": 0.5333333333333333, "percentage": 28.0, "elapsed_time": "0:57:29", "remaining_time": "2:27:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 430, "total_steps": 1500, "loss": 0.5266, "accuracy": 0.875, "learning_rate": 4.052869450695776e-06, "epoch": 0.546031746031746, "percentage": 28.67, "elapsed_time": "0:58:45", "remaining_time": "2:26:13", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 440, "total_steps": 1500, "loss": 0.5665, "accuracy": 0.8500000238418579, "learning_rate": 4.011497787155938e-06, "epoch": 0.5587301587301587, "percentage": 29.33, "elapsed_time": "1:00:04", "remaining_time": "2:24:43", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 450, "total_steps": 1500, "loss": 0.5118, "accuracy": 0.824999988079071, "learning_rate": 3.969463130731183e-06, "epoch": 0.5714285714285714, "percentage": 30.0, "elapsed_time": "1:01:23", "remaining_time": "2:23:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 450, "total_steps": 1500, "eval_loss": 0.5201926827430725, "epoch": 0.5714285714285714, "percentage": 30.0, "elapsed_time": "1:01:42", "remaining_time": "2:23:59", "throughput": "0.00", "total_tokens": 0}