Training in progress, step 100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df09833f347b02053eabab8c51d7622fa800e6547da018ca3b27e743c5422c3d
+oid sha256:1ebaf7af36f71a89a6cdbbc558640bf51c76e1f919a284df5d1ebf0e6335983d
 size 40036488

trainer_log.jsonl

@@ -4,3 +4,9 @@
 {"current_steps": 40, "total_steps": 1500, "loss": 7.3892, "accuracy": 0.6499999761581421, "learning_rate": 4.9912321481237616e-06, "epoch": 0.028993385883845247, "percentage": 2.67, "elapsed_time": "0:05:02", "remaining_time": "3:04:08", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 50, "total_steps": 1500, "loss": 7.5171, "accuracy": 0.512499988079071, "learning_rate": 4.986304738420684e-06, "epoch": 0.03624173235480656, "percentage": 3.33, "elapsed_time": "0:06:19", "remaining_time": "3:03:27", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9120001792907715, "epoch": 0.03624173235480656, "percentage": 3.33, "elapsed_time": "0:06:50", "remaining_time": "3:18:26", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 60, "total_steps": 1500, "loss": 7.3926, "accuracy": 0.5874999761581421, "learning_rate": 4.980286753286196e-06, "epoch": 0.04349007882576787, "percentage": 4.0, "elapsed_time": "0:08:19", "remaining_time": "3:19:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 70, "total_steps": 1500, "loss": 7.185, "accuracy": 0.5874999761581421, "learning_rate": 4.973180832407471e-06, "epoch": 0.05073842529672919, "percentage": 4.67, "elapsed_time": "0:09:33", "remaining_time": "3:15:19", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 80, "total_steps": 1500, "loss": 7.365, "accuracy": 0.5874999761581421, "learning_rate": 4.964990092676263e-06, "epoch": 0.057986771767690494, "percentage": 5.33, "elapsed_time": "0:10:49", "remaining_time": "3:12:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 90, "total_steps": 1500, "loss": 7.2664, "accuracy": 0.6000000238418579, "learning_rate": 4.9557181268217225e-06, "epoch": 0.0652351182386518, "percentage": 6.0, "elapsed_time": "0:12:01", "remaining_time": "3:08:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 100, "total_steps": 1500, "loss": 7.2542, "accuracy": 0.5874999761581421, "learning_rate": 4.9453690018345144e-06, "epoch": 0.07248346470961312, "percentage": 6.67, "elapsed_time": "0:13:15", "remaining_time": "3:05:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 100, "total_steps": 1500, "eval_loss": 0.891861081123352, "epoch": 0.07248346470961312, "percentage": 6.67, "elapsed_time": "0:13:46", "remaining_time": "3:12:45", "throughput": "0.00", "total_tokens": 0}