Training in progress, step 200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:442e84a82ef60b1292f867c9009c32f0ca5781c8c3d3860899926f4c6b5af50e
+oid sha256:581366060782e938b86d372e3ac57ee947923597892403136e60025f2ce70a3c
 size 40036488

trainer_log.jsonl

@@ -16,3 +16,9 @@
 {"current_steps": 140, "total_steps": 1500, "loss": 7.2892, "accuracy": 0.550000011920929, "learning_rate": 4.893298743830168e-06, "epoch": 0.11489536315141567, "percentage": 9.33, "elapsed_time": "0:18:10", "remaining_time": "2:56:35", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "loss": 7.26, "accuracy": 0.5874999761581421, "learning_rate": 4.8776412907378845e-06, "epoch": 0.12310217480508823, "percentage": 10.0, "elapsed_time": "0:19:21", "remaining_time": "2:54:15", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 150, "total_steps": 1500, "eval_loss": 0.8929102420806885, "epoch": 0.12310217480508823, "percentage": 10.0, "elapsed_time": "0:19:47", "remaining_time": "2:58:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 160, "total_steps": 1500, "loss": 7.1947, "accuracy": 0.550000011920929, "learning_rate": 4.860940925593703e-06, "epoch": 0.13130898645876077, "percentage": 10.67, "elapsed_time": "0:21:13", "remaining_time": "2:57:46", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 170, "total_steps": 1500, "loss": 7.1774, "accuracy": 0.612500011920929, "learning_rate": 4.84320497372973e-06, "epoch": 0.1395157981124333, "percentage": 11.33, "elapsed_time": "0:22:25", "remaining_time": "2:55:29", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 180, "total_steps": 1500, "loss": 7.1722, "accuracy": 0.512499988079071, "learning_rate": 4.824441214720629e-06, "epoch": 0.14772260976610588, "percentage": 12.0, "elapsed_time": "0:23:38", "remaining_time": "2:53:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 190, "total_steps": 1500, "loss": 7.1186, "accuracy": 0.5249999761581421, "learning_rate": 4.804657878971252e-06, "epoch": 0.15592942141977842, "percentage": 12.67, "elapsed_time": "0:24:52", "remaining_time": "2:51:28", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1500, "loss": 7.082, "accuracy": 0.574999988079071, "learning_rate": 4.783863644106502e-06, "epoch": 0.16413623307345096, "percentage": 13.33, "elapsed_time": "0:26:03", "remaining_time": "2:49:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8775798678398132, "epoch": 0.16413623307345096, "percentage": 13.33, "elapsed_time": "0:26:29", "remaining_time": "2:52:09", "throughput": "0.00", "total_tokens": 0}