Training in progress, step 500

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad5c49e5dbbbb952b0231024ed83dc94f00125f5a9d53a6fbb1962b4bd4aa1c2
+oid sha256:a2e33ab4487c1a06c567516ea6e07b84e961c6141c94d9e716655afade3dc9bb
 size 25200088

trainer_log.jsonl

@@ -52,3 +52,9 @@
 {"current_steps": 440, "total_steps": 1500, "loss": 0.3783, "accuracy": 0.8374999761581421, "learning_rate": 4.011497787155938e-06, "epoch": 0.4042724244860457, "percentage": 29.33, "elapsed_time": "1:00:33", "remaining_time": "2:25:52", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 450, "total_steps": 1500, "loss": 0.347, "accuracy": 0.9375, "learning_rate": 3.969463130731183e-06, "epoch": 0.41346043413345585, "percentage": 30.0, "elapsed_time": "1:01:53", "remaining_time": "2:24:25", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 450, "total_steps": 1500, "eval_loss": 0.36501914262771606, "epoch": 0.41346043413345585, "percentage": 30.0, "elapsed_time": "1:02:18", "remaining_time": "2:25:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 460, "total_steps": 1500, "loss": 0.3689, "accuracy": 0.9125000238418579, "learning_rate": 3.92678391921108e-06, "epoch": 0.42264844378086597, "percentage": 30.67, "elapsed_time": "1:03:41", "remaining_time": "2:24:00", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 470, "total_steps": 1500, "loss": 0.3587, "accuracy": 0.8999999761581421, "learning_rate": 3.88347887310836e-06, "epoch": 0.4318364534282761, "percentage": 31.33, "elapsed_time": "1:04:59", "remaining_time": "2:22:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 480, "total_steps": 1500, "loss": 0.2922, "accuracy": 0.9624999761581421, "learning_rate": 3.839566987447492e-06, "epoch": 0.4410244630756862, "percentage": 32.0, "elapsed_time": "1:06:14", "remaining_time": "2:20:45", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 490, "total_steps": 1500, "loss": 0.3086, "accuracy": 0.9375, "learning_rate": 3.795067523432826e-06, "epoch": 0.45021247272309634, "percentage": 32.67, "elapsed_time": "1:07:36", "remaining_time": "2:19:22", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 500, "total_steps": 1500, "loss": 0.3128, "accuracy": 0.9125000238418579, "learning_rate": 3.7500000000000005e-06, "epoch": 0.4594004823705065, "percentage": 33.33, "elapsed_time": "1:08:51", "remaining_time": "2:17:42", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 500, "total_steps": 1500, "eval_loss": 0.32884541153907776, "epoch": 0.4594004823705065, "percentage": 33.33, "elapsed_time": "1:09:15", "remaining_time": "2:18:31", "throughput": "0.00", "total_tokens": 0}