Training in progress, step 6000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcb9e249858be8cd1761d787a5eab4c07eeae570ff35e838e331a6da03f1806b
+oid sha256:ce470db20a3b3fa0e4c26072d5eaa59b030c4dd69694ce9ae9f5da06c6e277be
 size 3673690696

trainer_log.jsonl

@@ -10,3 +10,15 @@
 {"current_steps": 2700, "total_steps": 9120, "loss": 0.1797, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.238538385782601e-05, "epoch": 0.2960445163235657, "percentage": 29.61, "elapsed_time": "1:40:55", "remaining_time": "3:59:59"}
 {"current_steps": 3000, "total_steps": 9120, "loss": 0.176, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.032123642522486e-05, "epoch": 0.32893835147062855, "percentage": 32.89, "elapsed_time": "1:51:07", "remaining_time": "3:46:41"}
 {"current_steps": 3000, "total_steps": 9120, "loss": null, "eval_loss": 0.1760552078485489, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.32893835147062855, "percentage": 32.89, "elapsed_time": "1:51:07", "remaining_time": "3:46:41"}
+{"current_steps": 3300, "total_steps": 9120, "loss": 0.1791, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.8074115216771435e-05, "epoch": 0.3618321866176914, "percentage": 36.18, "elapsed_time": "2:04:22", "remaining_time": "3:39:21"}
+{"current_steps": 3600, "total_steps": 9120, "loss": 0.1808, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.567085646427478e-05, "epoch": 0.39472602176475424, "percentage": 39.47, "elapsed_time": "2:14:33", "remaining_time": "3:26:19"}
+{"current_steps": 3900, "total_steps": 9120, "loss": 0.1805, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.3140161071244915e-05, "epoch": 0.4276198569118171, "percentage": 42.76, "elapsed_time": "2:26:25", "remaining_time": "3:15:58"}
+{"current_steps": 4200, "total_steps": 9120, "loss": 0.1738, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.05122518525215e-05, "epoch": 0.46051369205888, "percentage": 46.05, "elapsed_time": "2:36:32", "remaining_time": "3:03:22"}
+{"current_steps": 4500, "total_steps": 9120, "loss": 0.1736, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.781851259848554e-05, "epoch": 0.49340752720594283, "percentage": 49.34, "elapsed_time": "2:48:26", "remaining_time": "2:52:55"}
+{"current_steps": 4500, "total_steps": 9120, "loss": null, "eval_loss": 0.17090687155723572, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.49340752720594283, "percentage": 49.34, "elapsed_time": "2:48:26", "remaining_time": "2:52:55"}
+{"current_steps": 4800, "total_steps": 9120, "loss": 0.1709, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.509111327432736e-05, "epoch": 0.5263013623530056, "percentage": 52.63, "elapsed_time": "2:59:53", "remaining_time": "2:41:53"}
+{"current_steps": 5100, "total_steps": 9120, "loss": 0.1775, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.236262583042668e-05, "epoch": 0.5591951975000685, "percentage": 55.92, "elapsed_time": "3:11:41", "remaining_time": "2:31:05"}
+{"current_steps": 5400, "total_steps": 9120, "loss": 0.1759, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.966563521202681e-05, "epoch": 0.5920890326471314, "percentage": 59.21, "elapsed_time": "3:21:50", "remaining_time": "2:19:02"}
+{"current_steps": 5700, "total_steps": 9120, "loss": 0.1754, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.7032350213717874e-05, "epoch": 0.6249828677941942, "percentage": 62.5, "elapsed_time": "3:33:38", "remaining_time": "2:08:11"}
+{"current_steps": 6000, "total_steps": 9120, "loss": 0.1688, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.4494218826096939e-05, "epoch": 0.6578767029412571, "percentage": 65.79, "elapsed_time": "3:43:45", "remaining_time": "1:56:21"}
+{"current_steps": 6000, "total_steps": 9120, "loss": null, "eval_loss": 0.16823573410511017, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.6578767029412571, "percentage": 65.79, "elapsed_time": "3:43:45", "remaining_time": "1:56:21"}