Training in progress, step 1050

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efcb72e1e5b7b9d9463df7386b2fcebe57303dc7cbbced6fc797215548fb2612
+oid sha256:2009c31a17a5dbd555b673b8da868740eb2a31647fc0b5bab926db6224fe06b7
 size 25200088

trainer_log.jsonl

@@ -118,3 +118,9 @@
 {"current_steps": 990, "total_steps": 1500, "loss": 0.1702, "accuracy": 0.9750000238418579, "learning_rate": 1.2956158147457116e-06, "epoch": 0.7991927346115035, "percentage": 66.0, "elapsed_time": "2:17:58", "remaining_time": "1:11:04", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1000, "total_steps": 1500, "loss": 0.1934, "accuracy": 0.987500011920929, "learning_rate": 1.2500000000000007e-06, "epoch": 0.8072653884964682, "percentage": 66.67, "elapsed_time": "2:19:12", "remaining_time": "1:09:36", "throughput": "0.00", "total_tokens": 0}
 {"current_steps": 1000, "total_steps": 1500, "eval_loss": 0.20982278883457184, "epoch": 0.8072653884964682, "percentage": 66.67, "elapsed_time": "2:19:41", "remaining_time": "1:09:50", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1010, "total_steps": 1500, "loss": 0.1911, "accuracy": 0.9375, "learning_rate": 1.204932476567175e-06, "epoch": 0.8153380423814329, "percentage": 67.33, "elapsed_time": "2:21:19", "remaining_time": "1:08:33", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1020, "total_steps": 1500, "loss": 0.2222, "accuracy": 0.925000011920929, "learning_rate": 1.160433012552508e-06, "epoch": 0.8234106962663976, "percentage": 68.0, "elapsed_time": "2:22:33", "remaining_time": "1:07:05", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1030, "total_steps": 1500, "loss": 0.1768, "accuracy": 0.9750000238418579, "learning_rate": 1.11652112689164e-06, "epoch": 0.8314833501513622, "percentage": 68.67, "elapsed_time": "2:23:49", "remaining_time": "1:05:37", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1040, "total_steps": 1500, "loss": 0.1923, "accuracy": 0.949999988079071, "learning_rate": 1.073216080788921e-06, "epoch": 0.8395560040363269, "percentage": 69.33, "elapsed_time": "2:25:04", "remaining_time": "1:04:09", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1050, "total_steps": 1500, "loss": 0.1525, "accuracy": 0.987500011920929, "learning_rate": 1.0305368692688175e-06, "epoch": 0.8476286579212916, "percentage": 70.0, "elapsed_time": "2:26:18", "remaining_time": "1:02:42", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 1050, "total_steps": 1500, "eval_loss": 0.20868732035160065, "epoch": 0.8476286579212916, "percentage": 70.0, "elapsed_time": "2:26:47", "remaining_time": "1:02:54", "throughput": "0.00", "total_tokens": 0}