Training in progress, step 250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb56273056ec04d3405e95205845f9e1f27c43f83e6eec397d0f6cdc71896bfc
+oid sha256:6baf886cc9db648c0ec9ea06cd29eabd2f452242f0f1dd64d6bd00c42afe8850
 size 25200088

trainer_log.jsonl

@@ -22,3 +22,9 @@
 {"current_steps": 190, "total_steps": 1500, "loss": 0.8776, "accuracy": 0.6499999761581421, "learning_rate": 4.804657878971252e-06, "epoch": 0.16873889875666073, "percentage": 12.67, "elapsed_time": "0:26:22", "remaining_time": "3:01:53", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 200, "total_steps": 1500, "loss": 0.8596, "accuracy": 0.5874999761581421, "learning_rate": 4.783863644106502e-06, "epoch": 0.17761989342806395, "percentage": 13.33, "elapsed_time": "0:27:39", "remaining_time": "2:59:49", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8602121472358704, "epoch": 0.17761989342806395, "percentage": 13.33, "elapsed_time": "0:28:06", "remaining_time": "3:02:44", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 210, "total_steps": 1500, "loss": 0.8553, "accuracy": 0.625, "learning_rate": 4.762067631165049e-06, "epoch": 0.18650088809946713, "percentage": 14.0, "elapsed_time": "0:29:28", "remaining_time": "3:01:01", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 220, "total_steps": 1500, "loss": 0.8204, "accuracy": 0.574999988079071, "learning_rate": 4.7392794005985324e-06, "epoch": 0.19538188277087035, "percentage": 14.67, "elapsed_time": "0:30:46", "remaining_time": "2:59:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 230, "total_steps": 1500, "loss": 0.7884, "accuracy": 0.612500011920929, "learning_rate": 4.715508948078037e-06, "epoch": 0.20426287744227353, "percentage": 15.33, "elapsed_time": "0:32:01", "remaining_time": "2:56:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 240, "total_steps": 1500, "loss": 0.7919, "accuracy": 0.612500011920929, "learning_rate": 4.690766700109659e-06, "epoch": 0.21314387211367672, "percentage": 16.0, "elapsed_time": "0:33:17", "remaining_time": "2:54:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 1500, "loss": 0.7456, "accuracy": 0.675000011920929, "learning_rate": 4.665063509461098e-06, "epoch": 0.22202486678507993, "percentage": 16.67, "elapsed_time": "0:34:33", "remaining_time": "2:52:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7499477863311768, "epoch": 0.22202486678507993, "percentage": 16.67, "elapsed_time": "0:35:00", "remaining_time": "2:55:01", "throughput": "0.00", "total_tokens": 0}