Training in progress, step 700

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef816079b89b86f5ac927d541f47d19a26059903a9d30904b7e5318efa79c348
+oid sha256:186cd96a41c3447887c7913bca1d768b158b800658d05f0641f9056a5fcf0f84
 size 25200088

trainer_log.jsonl

@@ -76,3 +76,9 @@
 {"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}
+{"current_steps": 660, "total_steps": 1500, "loss": 0.2678, "accuracy": 0.949999988079071, "learning_rate": 2.9684532864643123e-06, "epoch": 0.6064086367290685, "percentage": 44.0, "elapsed_time": "1:31:39", "remaining_time": "1:56:39", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 670, "total_steps": 1500, "loss": 0.294, "accuracy": 0.925000011920929, "learning_rate": 2.9169218667902562e-06, "epoch": 0.6155966463764787, "percentage": 44.67, "elapsed_time": "1:32:54", "remaining_time": "1:55:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 680, "total_steps": 1500, "loss": 0.23, "accuracy": 0.925000011920929, "learning_rate": 2.8652075714060296e-06, "epoch": 0.6247846560238888, "percentage": 45.33, "elapsed_time": "1:34:11", "remaining_time": "1:53:34", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 690, "total_steps": 1500, "loss": 0.2808, "accuracy": 0.925000011920929, "learning_rate": 2.813333083910761e-06, "epoch": 0.633972665671299, "percentage": 46.0, "elapsed_time": "1:35:27", "remaining_time": "1:52:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 700, "total_steps": 1500, "loss": 0.2808, "accuracy": 0.8999999761581421, "learning_rate": 2.761321158169134e-06, "epoch": 0.6431606753187091, "percentage": 46.67, "elapsed_time": "1:36:46", "remaining_time": "1:50:36", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 700, "total_steps": 1500, "eval_loss": 0.26070258021354675, "epoch": 0.6431606753187091, "percentage": 46.67, "elapsed_time": "1:37:11", "remaining_time": "1:51:04", "throughput": "0.00", "total_tokens": 0}