Training in progress, step 650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47ce24973590893dc7cddf3cc21f59f8f6c67b007ed7b7ead25503fa1e7d8d1e
+oid sha256:f68ce168241fb3faec874c5a2443c093347e6963fa70c07806dbd311ababcfc9
 size 40036488

trainer_log.jsonl

@@ -70,3 +70,9 @@
 {"current_steps": 590, "total_steps": 1500, "loss": 2.0248, "accuracy": 0.949999988079071, "learning_rate": 3.3221666168464584e-06, "epoch": 0.4276524417867174, "percentage": 39.33, "elapsed_time": "1:21:07", "remaining_time": "2:05:07", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 600, "total_steps": 1500, "loss": 2.0191, "accuracy": 0.949999988079071, "learning_rate": 3.272542485937369e-06, "epoch": 0.4349007882576787, "percentage": 40.0, "elapsed_time": "1:22:21", "remaining_time": "2:03:31", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.22690872848033905, "epoch": 0.4349007882576787, "percentage": 40.0, "elapsed_time": "1:22:51", "remaining_time": "2:04:17", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 610, "total_steps": 1500, "loss": 1.6936, "accuracy": 0.9375, "learning_rate": 3.222579492361179e-06, "epoch": 0.44214913472864004, "percentage": 40.67, "elapsed_time": "1:24:18", "remaining_time": "2:03:01", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 620, "total_steps": 1500, "loss": 1.6215, "accuracy": 0.9750000238418579, "learning_rate": 3.1722995515381644e-06, "epoch": 0.4493974811996013, "percentage": 41.33, "elapsed_time": "1:25:33", "remaining_time": "2:01:25", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 630, "total_steps": 1500, "loss": 1.7936, "accuracy": 0.9125000238418579, "learning_rate": 3.121724717912138e-06, "epoch": 0.45664582767056267, "percentage": 42.0, "elapsed_time": "1:26:52", "remaining_time": "1:59:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 640, "total_steps": 1500, "loss": 1.7631, "accuracy": 0.9750000238418579, "learning_rate": 3.0708771752766397e-06, "epoch": 0.46389417414152395, "percentage": 42.67, "elapsed_time": "1:28:06", "remaining_time": "1:58:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1500, "loss": 1.5531, "accuracy": 0.987500011920929, "learning_rate": 3.019779227044398e-06, "epoch": 0.4711425206124853, "percentage": 43.33, "elapsed_time": "1:29:22", "remaining_time": "1:56:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1500, "eval_loss": 0.21141496300697327, "epoch": 0.4711425206124853, "percentage": 43.33, "elapsed_time": "1:29:52", "remaining_time": "1:57:31", "throughput": "0.00", "total_tokens": 0}