初始化项目，由ModelHub XC社区提供模型

Model: NastasiaM/mbert-loraxs-qa-vanilla
Source: Original Platform

run-25/checkpoint-1268/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_global_step": 1268,
+  "best_metric": 74.09763567767044,
+  "best_model_checkpoint": "mbert-loraxs-qa-vanilla/run-25/checkpoint-1268",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1268,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.842517852783203,
+      "learning_rate": 0.0003656668954411681,
+      "loss": 2.791566674265576,
+      "step": 634
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 56.4,
+      "eval_f1": 71.1872177007869,
+      "eval_loss": 1.3755041360855103,
+      "eval_runtime": 7.7747,
+      "eval_samples_per_second": 162.708,
+      "eval_steps_per_second": 10.29,
+      "step": 634
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.100051403045654,
+      "learning_rate": 0.0002742862049761699,
+      "loss": 1.3657944736420544,
+      "step": 1268
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 59.76,
+      "eval_f1": 74.09763567767044,
+      "eval_loss": 1.310166358947754,
+      "eval_runtime": 7.8278,
+      "eval_samples_per_second": 161.604,
+      "eval_steps_per_second": 10.22,
+      "step": 1268
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3170,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6180991462324224.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 0.00041121310709249216,
+    "lora_alpha": 64,
+    "lora_dropout": 0.135671188271432,
+    "lora_r": 256,
+    "num_train_epochs": 5,
+    "weight_decay": 0.023037713272994215
+  }
+}