初始化项目，由ModelHub XC社区提供模型

Model: NastasiaM/mbert-loraxs-qa-vanilla Source: Original Platform
2026-06-10 00:18:47 +08:00
commit d696db249d
795 changed files with 8285474 additions and 0 deletions
--- a/run-4/checkpoint-2536/trainer_state.json
+++ b/run-4/checkpoint-2536/trainer_state.json
@@ -0,0 +1,109 @@
+{
+  "best_global_step": 2536,
+  "best_metric": 26.874869223819044,
+  "best_model_checkpoint": "mbert-loraxs-qa-vanilla/run-4/checkpoint-2536",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 2536,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 11.041559219360352,
+      "learning_rate": 5.605194150710478e-05,
+      "loss": 5.270265597274251,
+      "step": 634
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 2.8,
+      "eval_f1": 8.945758396151355,
+      "eval_loss": 4.365081310272217,
+      "eval_runtime": 7.7244,
+      "eval_samples_per_second": 163.766,
+      "eval_steps_per_second": 10.357,
+      "step": 634
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 18.68657684326172,
+      "learning_rate": 4.204447957746172e-05,
+      "loss": 4.260111811785292,
+      "step": 1268
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 6.56,
+      "eval_f1": 13.990675637585385,
+      "eval_loss": 3.790620803833008,
+      "eval_runtime": 7.6676,
+      "eval_samples_per_second": 164.979,
+      "eval_steps_per_second": 10.433,
+      "step": 1268
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 26.60645866394043,
+      "learning_rate": 2.8037017647818668e-05,
+      "loss": 3.8954057663397084,
+      "step": 1902
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 10.72,
+      "eval_f1": 20.682353135829914,
+      "eval_loss": 3.431551933288574,
+      "eval_runtime": 7.5743,
+      "eval_samples_per_second": 167.013,
+      "eval_steps_per_second": 10.562,
+      "step": 1902
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 39.42831039428711,
+      "learning_rate": 1.4029555718175614e-05,
+      "loss": 3.6393634784108833,
+      "step": 2536
+    },
+    {
+      "epoch": 4.0,
+      "eval_exact_match": 15.92,
+      "eval_f1": 26.874869223819044,
+      "eval_loss": 3.1858983039855957,
+      "eval_runtime": 7.6014,
+      "eval_samples_per_second": 166.418,
+      "eval_steps_per_second": 10.524,
+      "step": 2536
+    }
+  ],
+  "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": 8075628404895744.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.303357868339374e-05,
+    "lora_alpha": 64,
+    "lora_dropout": 0.17883000020205417,
+    "lora_r": 8,
+    "num_train_epochs": 5,
+    "weight_decay": 0.043219314058624864
+  }
+}