Training in progress, step 250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b429eff2d94a39ff0cd74e96b721b051c369979584f0853ccb5c79966083fe52
+oid sha256:25d808019198adde16a3d47e4e81a439048b0f35d4c3d396db957eacf7ae0621
 size 25200088

trainer_log.jsonl

@@ -22,3 +22,9 @@
 {"current_steps": 190, "total_steps": 1500, "loss": 0.8425, "accuracy": 0.6875, "learning_rate": 4.804657878971252e-06, "epoch": 0.15338042381432895, "percentage": 12.67, "elapsed_time": "0:26:08", "remaining_time": "3:00:15", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 200, "total_steps": 1500, "loss": 0.8327, "accuracy": 0.612500011920929, "learning_rate": 4.783863644106502e-06, "epoch": 0.16145307769929365, "percentage": 13.33, "elapsed_time": "0:27:31", "remaining_time": "2:58:56", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8103437423706055, "epoch": 0.16145307769929365, "percentage": 13.33, "elapsed_time": "0:28:01", "remaining_time": "3:02:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 210, "total_steps": 1500, "loss": 0.7877, "accuracy": 0.625, "learning_rate": 4.762067631165049e-06, "epoch": 0.16952573158425832, "percentage": 14.0, "elapsed_time": "0:29:27", "remaining_time": "3:00:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 220, "total_steps": 1500, "loss": 0.7816, "accuracy": 0.612500011920929, "learning_rate": 4.7392794005985324e-06, "epoch": 0.17759838546922302, "percentage": 14.67, "elapsed_time": "0:30:44", "remaining_time": "2:58:51", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 230, "total_steps": 1500, "loss": 0.7306, "accuracy": 0.6625000238418579, "learning_rate": 4.715508948078037e-06, "epoch": 0.1856710393541877, "percentage": 15.33, "elapsed_time": "0:32:02", "remaining_time": "2:56:53", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 240, "total_steps": 1500, "loss": 0.7214, "accuracy": 0.625, "learning_rate": 4.690766700109659e-06, "epoch": 0.19374369323915236, "percentage": 16.0, "elapsed_time": "0:33:18", "remaining_time": "2:54:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 1500, "loss": 0.6811, "accuracy": 0.7124999761581421, "learning_rate": 4.665063509461098e-06, "epoch": 0.20181634712411706, "percentage": 16.67, "elapsed_time": "0:34:36", "remaining_time": "2:53:02", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 1500, "eval_loss": 0.6842760443687439, "epoch": 0.20181634712411706, "percentage": 16.67, "elapsed_time": "0:35:06", "remaining_time": "2:55:32", "throughput": "0.00", "total_tokens": 0}