Training in progress, step 250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b46650585d549db15a88ae31d90e6a5753076a356c350d134669e8e5cfea84e
+oid sha256:731cde73e4b26d6035bdf231c601e7329a579b67ec63a07f1a6946bb019df650
 size 25200088

trainer_log.jsonl

@@ -22,3 +22,9 @@
 {"current_steps": 190, "total_steps": 1500, "loss": 0.8565, "accuracy": 0.675000011920929, "learning_rate": 4.804657878971252e-06, "epoch": 0.15338042381432895, "percentage": 12.67, "elapsed_time": "0:26:10", "remaining_time": "3:00:29", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 200, "total_steps": 1500, "loss": 0.8482, "accuracy": 0.5874999761581421, "learning_rate": 4.783863644106502e-06, "epoch": 0.16145307769929365, "percentage": 13.33, "elapsed_time": "0:27:26", "remaining_time": "2:58:23", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8243693113327026, "epoch": 0.16145307769929365, "percentage": 13.33, "elapsed_time": "0:27:55", "remaining_time": "3:01:32", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 210, "total_steps": 1500, "loss": 0.7988, "accuracy": 0.612500011920929, "learning_rate": 4.762067631165049e-06, "epoch": 0.16952573158425832, "percentage": 14.0, "elapsed_time": "0:29:17", "remaining_time": "2:59:56", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 220, "total_steps": 1500, "loss": 0.796, "accuracy": 0.6000000238418579, "learning_rate": 4.7392794005985324e-06, "epoch": 0.17759838546922302, "percentage": 14.67, "elapsed_time": "0:30:32", "remaining_time": "2:57:42", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 230, "total_steps": 1500, "loss": 0.7457, "accuracy": 0.637499988079071, "learning_rate": 4.715508948078037e-06, "epoch": 0.1856710393541877, "percentage": 15.33, "elapsed_time": "0:31:46", "remaining_time": "2:55:24", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 240, "total_steps": 1500, "loss": 0.7453, "accuracy": 0.550000011920929, "learning_rate": 4.690766700109659e-06, "epoch": 0.19374369323915236, "percentage": 16.0, "elapsed_time": "0:32:58", "remaining_time": "2:53:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 1500, "loss": 0.704, "accuracy": 0.6625000238418579, "learning_rate": 4.665063509461098e-06, "epoch": 0.20181634712411706, "percentage": 16.67, "elapsed_time": "0:34:13", "remaining_time": "2:51:07", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 1500, "eval_loss": 0.6982013583183289, "epoch": 0.20181634712411706, "percentage": 16.67, "elapsed_time": "0:34:42", "remaining_time": "2:53:32", "throughput": "0.00", "total_tokens": 0}