Training in progress, step 250

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16ebb238066311e1d044b75ba68510f141fa7dcb784eb182857a664e1c5d33e5
+oid sha256:baf8d899504b31aa88914bfb3f8ef2feb95c0337a42c24e27bf49d3f3935979b
 size 25200088

trainer_log.jsonl

@@ -22,3 +22,9 @@
 {"current_steps": 190, "total_steps": 1500, "loss": 0.8875, "accuracy": 0.625, "learning_rate": 4.804657878971252e-06, "epoch": 0.17457218330079247, "percentage": 12.67, "elapsed_time": "0:26:04", "remaining_time": "2:59:48", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 200, "total_steps": 1500, "loss": 0.8647, "accuracy": 0.6000000238418579, "learning_rate": 4.783863644106502e-06, "epoch": 0.1837601929482026, "percentage": 13.33, "elapsed_time": "0:27:19", "remaining_time": "2:57:37", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 200, "total_steps": 1500, "eval_loss": 0.8702690005302429, "epoch": 0.1837601929482026, "percentage": 13.33, "elapsed_time": "0:27:44", "remaining_time": "3:00:16", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 210, "total_steps": 1500, "loss": 0.8471, "accuracy": 0.612500011920929, "learning_rate": 4.762067631165049e-06, "epoch": 0.19294820259561274, "percentage": 14.0, "elapsed_time": "0:29:03", "remaining_time": "2:58:31", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 220, "total_steps": 1500, "loss": 0.8427, "accuracy": 0.5375000238418579, "learning_rate": 4.7392794005985324e-06, "epoch": 0.20213621224302286, "percentage": 14.67, "elapsed_time": "0:30:21", "remaining_time": "2:56:38", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 230, "total_steps": 1500, "loss": 0.8201, "accuracy": 0.6499999761581421, "learning_rate": 4.715508948078037e-06, "epoch": 0.21132422189043298, "percentage": 15.33, "elapsed_time": "0:31:41", "remaining_time": "2:54:58", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 240, "total_steps": 1500, "loss": 0.7877, "accuracy": 0.675000011920929, "learning_rate": 4.690766700109659e-06, "epoch": 0.2205122315378431, "percentage": 16.0, "elapsed_time": "0:32:56", "remaining_time": "2:52:54", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 1500, "loss": 0.7902, "accuracy": 0.5874999761581421, "learning_rate": 4.665063509461098e-06, "epoch": 0.22970024118525326, "percentage": 16.67, "elapsed_time": "0:34:14", "remaining_time": "2:51:10", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 250, "total_steps": 1500, "eval_loss": 0.7682384252548218, "epoch": 0.22970024118525326, "percentage": 16.67, "elapsed_time": "0:34:38", "remaining_time": "2:53:12", "throughput": "0.00", "total_tokens": 0}