Training in progress, step 9000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce470db20a3b3fa0e4c26072d5eaa59b030c4dd69694ce9ae9f5da06c6e277be
+oid sha256:d613b956dffb6a6d72f54d2dd6c79e5d199d4d921edd66b8caa8271b95665145
 size 3673690696

trainer_log.jsonl

@@ -22,3 +22,15 @@
 {"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"}
+{"current_steps": 6300, "total_steps": 9120, "loss": 0.1707, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.2081552668325321e-05, "epoch": 0.6907705380883199, "percentage": 69.08, "elapsed_time": "3:57:06", "remaining_time": "1:46:08"}
+{"current_steps": 6600, "total_steps": 9120, "loss": 0.171, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 9.82316499179518e-06, "epoch": 0.7236643732353828, "percentage": 72.37, "elapsed_time": "4:07:12", "remaining_time": "1:34:23"}
+{"current_steps": 6900, "total_steps": 9120, "loss": 0.1702, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 7.74602657804425e-06, "epoch": 0.7565582083824457, "percentage": 75.66, "elapsed_time": "4:19:03", "remaining_time": "1:23:21"}
+{"current_steps": 7200, "total_steps": 9120, "loss": 0.1718, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 5.874943640356082e-06, "epoch": 0.7894520435295085, "percentage": 78.95, "elapsed_time": "4:29:14", "remaining_time": "1:11:47"}
+{"current_steps": 7500, "total_steps": 9120, "loss": 0.1689, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.232261575703861e-06, "epoch": 0.8223458786765714, "percentage": 82.24, "elapsed_time": "4:41:05", "remaining_time": "1:00:42"}
+{"current_steps": 7500, "total_steps": 9120, "loss": null, "eval_loss": 0.16773280501365662, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.8223458786765714, "percentage": 82.24, "elapsed_time": "4:41:05", "remaining_time": "1:00:42"}
+{"current_steps": 7800, "total_steps": 9120, "loss": 0.1692, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.83759810497852e-06, "epoch": 0.8552397138236342, "percentage": 85.53, "elapsed_time": "4:52:30", "remaining_time": "0:49:30"}
+{"current_steps": 8100, "total_steps": 9120, "loss": 0.1787, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 1.70760898847247e-06, "epoch": 0.8881335489706971, "percentage": 88.82, "elapsed_time": "5:04:20", "remaining_time": "0:38:19"}
+{"current_steps": 8400, "total_steps": 9120, "loss": 0.1733, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 8.557891145603042e-07, "epoch": 0.92102738411776, "percentage": 92.11, "elapsed_time": "5:14:28", "remaining_time": "0:26:57"}
+{"current_steps": 8700, "total_steps": 9120, "loss": 0.1741, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.923113370737779e-07, "epoch": 0.9539212192648228, "percentage": 95.39, "elapsed_time": "5:26:22", "remaining_time": "0:15:45"}
+{"current_steps": 9000, "total_steps": 9120, "loss": 0.168, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.3904986054812396e-08, "epoch": 0.9868150544118857, "percentage": 98.68, "elapsed_time": "5:36:30", "remaining_time": "0:04:29"}
+{"current_steps": 9000, "total_steps": 9120, "loss": null, "eval_loss": 0.1676628440618515, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.9868150544118857, "percentage": 98.68, "elapsed_time": "5:36:30", "remaining_time": "0:04:29"}