Training in progress, step 1100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f641bb6c1d03cc16fe88932fa5211835a04dfafecb1bbb2938247c4b28bf7e3f
+oid sha256:fd23206a6a0c16946f58e071ddb10743e3ca261a4165bdd2b55c0fbfbba5a665
 size 40036488

trainer_log.jsonl

@@ -124,3 +124,9 @@
 {"current_steps": 1040, "total_steps": 1500, "loss": 0.7519, "accuracy": 0.987500011920929, "learning_rate": 1.073216080788921e-06, "epoch": 0.7538280329799765, "percentage": 69.33, "elapsed_time": "2:23:38", "remaining_time": "1:03:32", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1050, "total_steps": 1500, "loss": 0.5528, "accuracy": 0.9750000238418579, "learning_rate": 1.0305368692688175e-06, "epoch": 0.7610763794509378, "percentage": 70.0, "elapsed_time": "2:24:52", "remaining_time": "1:02:05", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1050, "total_steps": 1500, "eval_loss": 0.1007753536105156, "epoch": 0.7610763794509378, "percentage": 70.0, "elapsed_time": "2:25:22", "remaining_time": "1:02:18", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1060, "total_steps": 1500, "loss": 0.792, "accuracy": 0.987500011920929, "learning_rate": 9.88502212844063e-07, "epoch": 0.768324725921899, "percentage": 70.67, "elapsed_time": "2:26:52", "remaining_time": "1:00:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1070, "total_steps": 1500, "loss": 0.5324, "accuracy": 0.987500011920929, "learning_rate": 9.471305493042243e-07, "epoch": 0.7755730723928603, "percentage": 71.33, "elapsed_time": "2:28:10", "remaining_time": "0:59:32", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1080, "total_steps": 1500, "loss": 0.5667, "accuracy": 1.0, "learning_rate": 9.064400256282757e-07, "epoch": 0.7828214188638217, "percentage": 72.0, "elapsed_time": "2:29:26", "remaining_time": "0:58:06", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1090, "total_steps": 1500, "loss": 0.6379, "accuracy": 0.9750000238418579, "learning_rate": 8.664484900247363e-07, "epoch": 0.790069765334783, "percentage": 72.67, "elapsed_time": "2:30:40", "remaining_time": "0:56:40", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1100, "total_steps": 1500, "loss": 0.6618, "accuracy": 0.987500011920929, "learning_rate": 8.271734841028553e-07, "epoch": 0.7973181118057443, "percentage": 73.33, "elapsed_time": "2:31:57", "remaining_time": "0:55:15", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1100, "total_steps": 1500, "eval_loss": 0.0923290029168129, "epoch": 0.7973181118057443, "percentage": 73.33, "elapsed_time": "2:32:27", "remaining_time": "0:55:26", "throughput": "0.00", "total_tokens": 0}