初始化项目，由ModelHub XC社区提供模型

Model: lldois/v47_v29_clean_world_guard_lr35e7_ep035
Source: Original Platform

trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3623693379790941,
+  "eval_steps": 500,
+  "global_step": 26,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13937282229965156,
+      "grad_norm": 6.75,
+      "learning_rate": 2.6876968912132437e-07,
+      "loss": 1.9448482513427734,
+      "step": 10
+    },
+    {
+      "epoch": 0.2787456445993031,
+      "grad_norm": 6.15625,
+      "learning_rate": 6.345080179397929e-08,
+      "loss": 1.843338394165039,
+      "step": 20
+    },
+    {
+      "epoch": 0.3623693379790941,
+      "step": 26,
+      "total_flos": 1.2298497723426816e+16,
+      "train_loss": 1.9200461094196026,
+      "train_runtime": 208.2018,
+      "train_samples_per_second": 0.482,
+      "train_steps_per_second": 0.125
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 26,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2298497723426816e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}