Training in progress, step 1350

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a58f228bd505214dc3dd6604e8f062c0981998cf7833146d9ec90da5cc2d121f
+oid sha256:b1c834e857d811c66077e5fa4e40ac729017cbc9cc68b5ae7e1b473afac18961
 size 25200088

trainer_log.jsonl

@@ -154,3 +154,9 @@
 {"current_steps": 1290, "total_steps": 1500, "loss": 0.1965, "accuracy": 0.949999988079071, "learning_rate": 2.3793236883495164e-07, "epoch": 1.1456483126110124, "percentage": 86.0, "elapsed_time": "2:55:26", "remaining_time": "0:28:33", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1300, "total_steps": 1500, "loss": 0.174, "accuracy": 0.987500011920929, "learning_rate": 2.1613635589349756e-07, "epoch": 1.1545293072824157, "percentage": 86.67, "elapsed_time": "2:56:45", "remaining_time": "0:27:11", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1300, "total_steps": 1500, "eval_loss": 0.20604319870471954, "epoch": 1.1545293072824157, "percentage": 86.67, "elapsed_time": "2:57:10", "remaining_time": "0:27:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1310, "total_steps": 1500, "loss": 0.1857, "accuracy": 0.925000011920929, "learning_rate": 1.95342121028749e-07, "epoch": 1.163410301953819, "percentage": 87.33, "elapsed_time": "2:58:34", "remaining_time": "0:25:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1320, "total_steps": 1500, "loss": 0.1816, "accuracy": 0.8999999761581421, "learning_rate": 1.7555878527937164e-07, "epoch": 1.1722912966252221, "percentage": 88.0, "elapsed_time": "2:59:54", "remaining_time": "0:24:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1330, "total_steps": 1500, "loss": 0.1965, "accuracy": 0.887499988079071, "learning_rate": 1.567950262702714e-07, "epoch": 1.1811722912966252, "percentage": 88.67, "elapsed_time": "3:01:13", "remaining_time": "0:23:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1340, "total_steps": 1500, "loss": 0.182, "accuracy": 0.949999988079071, "learning_rate": 1.3905907440629752e-07, "epoch": 1.1900532859680284, "percentage": 89.33, "elapsed_time": "3:02:29", "remaining_time": "0:21:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1350, "total_steps": 1500, "loss": 0.2274, "accuracy": 0.9375, "learning_rate": 1.223587092621162e-07, "epoch": 1.1989342806394316, "percentage": 90.0, "elapsed_time": "3:03:43", "remaining_time": "0:20:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1350, "total_steps": 1500, "eval_loss": 0.20770707726478577, "epoch": 1.1989342806394316, "percentage": 90.0, "elapsed_time": "3:04:08", "remaining_time": "0:20:27", "throughput": "0.00", "total_tokens": 0}