Training in progress, step 650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ebed5a6e0e4120e359607874dba662f9213b8c5471c19eb810814b2e5768cc0
+oid sha256:732a2243927bf2af2581f097fb5738d32b08be5ca129058c60d1f268e965320d
 size 25200088

trainer_log.jsonl

@@ -70,3 +70,9 @@
 {"current_steps": 590, "total_steps": 1500, "loss": 0.2921, "accuracy": 0.949999988079071, "learning_rate": 3.3221666168464584e-06, "epoch": 0.50709067468844, "percentage": 39.33, "elapsed_time": "1:17:39", "remaining_time": "1:59:46", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 600, "total_steps": 1500, "loss": 0.3225, "accuracy": 0.9125000238418579, "learning_rate": 3.272542485937369e-06, "epoch": 0.5156854318865493, "percentage": 40.0, "elapsed_time": "1:18:52", "remaining_time": "1:58:18", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.29786577820777893, "epoch": 0.5156854318865493, "percentage": 40.0, "elapsed_time": "1:19:18", "remaining_time": "1:58:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 610, "total_steps": 1500, "loss": 0.2516, "accuracy": 0.9125000238418579, "learning_rate": 3.222579492361179e-06, "epoch": 0.5242801890846583, "percentage": 40.67, "elapsed_time": "1:20:34", "remaining_time": "1:57:33", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 620, "total_steps": 1500, "loss": 0.3062, "accuracy": 0.925000011920929, "learning_rate": 3.1722995515381644e-06, "epoch": 0.5328749462827675, "percentage": 41.33, "elapsed_time": "1:21:46", "remaining_time": "1:56:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 630, "total_steps": 1500, "loss": 0.2726, "accuracy": 0.9125000238418579, "learning_rate": 3.121724717912138e-06, "epoch": 0.5414697034808766, "percentage": 42.0, "elapsed_time": "1:22:57", "remaining_time": "1:54:33", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 640, "total_steps": 1500, "loss": 0.2861, "accuracy": 0.9125000238418579, "learning_rate": 3.0708771752766397e-06, "epoch": 0.5500644606789858, "percentage": 42.67, "elapsed_time": "1:24:09", "remaining_time": "1:53:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1500, "loss": 0.2507, "accuracy": 0.9125000238418579, "learning_rate": 3.019779227044398e-06, "epoch": 0.5586592178770949, "percentage": 43.33, "elapsed_time": "1:25:20", "remaining_time": "1:51:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1500, "eval_loss": 0.28581172227859497, "epoch": 0.5586592178770949, "percentage": 43.33, "elapsed_time": "1:25:46", "remaining_time": "1:52:10", "throughput": "0.00", "total_tokens": 0}