Training in progress, step 650

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd34603d8071b52d0e64052a555cd92ea97b2ee85ad8f3ac695a9024932b6f3
+oid sha256:ef816079b89b86f5ac927d541f47d19a26059903a9d30904b7e5318efa79c348
 size 25200088

trainer_log.jsonl

@@ -70,3 +70,9 @@
 {"current_steps": 590, "total_steps": 1500, "loss": 0.3347, "accuracy": 0.925000011920929, "learning_rate": 3.3221666168464584e-06, "epoch": 0.5420925691971976, "percentage": 39.33, "elapsed_time": "1:21:29", "remaining_time": "2:05:41", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 600, "total_steps": 1500, "loss": 0.2776, "accuracy": 0.875, "learning_rate": 3.272542485937369e-06, "epoch": 0.5512805788446078, "percentage": 40.0, "elapsed_time": "1:22:47", "remaining_time": "2:04:10", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 600, "total_steps": 1500, "eval_loss": 0.28658536076545715, "epoch": 0.5512805788446078, "percentage": 40.0, "elapsed_time": "1:23:11", "remaining_time": "2:04:47", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 610, "total_steps": 1500, "loss": 0.3243, "accuracy": 0.8999999761581421, "learning_rate": 3.222579492361179e-06, "epoch": 0.560468588492018, "percentage": 40.67, "elapsed_time": "1:24:38", "remaining_time": "2:03:29", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 620, "total_steps": 1500, "loss": 0.2615, "accuracy": 0.862500011920929, "learning_rate": 3.1722995515381644e-06, "epoch": 0.569656598139428, "percentage": 41.33, "elapsed_time": "1:25:54", "remaining_time": "2:01:55", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 630, "total_steps": 1500, "loss": 0.2649, "accuracy": 0.862500011920929, "learning_rate": 3.121724717912138e-06, "epoch": 0.5788446077868382, "percentage": 42.0, "elapsed_time": "1:27:15", "remaining_time": "2:00:30", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 640, "total_steps": 1500, "loss": 0.2761, "accuracy": 0.9125000238418579, "learning_rate": 3.0708771752766397e-06, "epoch": 0.5880326174342483, "percentage": 42.67, "elapsed_time": "1:28:32", "remaining_time": "1:58:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1500, "loss": 0.2739, "accuracy": 0.925000011920929, "learning_rate": 3.019779227044398e-06, "epoch": 0.5972206270816585, "percentage": 43.33, "elapsed_time": "1:29:52", "remaining_time": "1:57:32", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 650, "total_steps": 1500, "eval_loss": 0.27443525195121765, "epoch": 0.5972206270816585, "percentage": 43.33, "elapsed_time": "1:30:17", "remaining_time": "1:58:04", "throughput": "0.00", "total_tokens": 0}