Training in progress, step 500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ba3c34a6bda432b4b808645d40278644ecab1b8c2d0af4ef4a00234847ed01
+oid sha256:26b71f0067960532c2814f1e4642d5cb656eaf3eec65f685946328cacd674237
 size 25200088

trainer_log.jsonl

@@ -52,3 +52,9 @@
 {"current_steps": 440, "total_steps": 1500, "loss": 0.4132, "accuracy": 0.75, "learning_rate": 4.011497787155938e-06, "epoch": 0.37816931671680276, "percentage": 29.33, "elapsed_time": "0:57:57", "remaining_time": "2:19:37", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 450, "total_steps": 1500, "loss": 0.4266, "accuracy": 0.7749999761581421, "learning_rate": 3.969463130731183e-06, "epoch": 0.3867640739149119, "percentage": 30.0, "elapsed_time": "0:59:09", "remaining_time": "2:18:02", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.4397798478603363, "epoch": 0.3867640739149119, "percentage": 30.0, "elapsed_time": "0:59:35", "remaining_time": "2:19:03", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 460, "total_steps": 1500, "loss": 0.367, "accuracy": 0.762499988079071, "learning_rate": 3.92678391921108e-06, "epoch": 0.39535883111302106, "percentage": 30.67, "elapsed_time": "1:00:53", "remaining_time": "2:17:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 470, "total_steps": 1500, "loss": 0.3957, "accuracy": 0.8374999761581421, "learning_rate": 3.88347887310836e-06, "epoch": 0.4039535883111302, "percentage": 31.33, "elapsed_time": "1:02:05", "remaining_time": "2:16:04", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 480, "total_steps": 1500, "loss": 0.3808, "accuracy": 0.824999988079071, "learning_rate": 3.839566987447492e-06, "epoch": 0.41254834550923936, "percentage": 32.0, "elapsed_time": "1:03:13", "remaining_time": "2:14:20", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 490, "total_steps": 1500, "loss": 0.3555, "accuracy": 0.875, "learning_rate": 3.795067523432826e-06, "epoch": 0.4211431027073485, "percentage": 32.67, "elapsed_time": "1:04:26", "remaining_time": "2:12:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 500, "total_steps": 1500, "loss": 0.3211, "accuracy": 0.824999988079071, "learning_rate": 3.7500000000000005e-06, "epoch": 0.42973785990545765, "percentage": 33.33, "elapsed_time": "1:05:37", "remaining_time": "2:11:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 500, "total_steps": 1500, "eval_loss": 0.37026864290237427, "epoch": 0.42973785990545765, "percentage": 33.33, "elapsed_time": "1:06:03", "remaining_time": "2:12:07", "throughput": "0.00", "total_tokens": 0}