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-0/checkpoint-2536/trainer_state.json
+++ b/run-0/checkpoint-2536/trainer_state.json
@@ -0,0 +1,109 @@
+{
+  "best_global_step": 2536,
+  "best_metric": 11.5259012819182,
+  "best_model_checkpoint": "mbert-loraxs-qa-vanilla/run-0/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": 5.70946741104126,
+      "learning_rate": 2.0882182104159667e-05,
+      "loss": 5.564044170199132,
+      "step": 634
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 1.2,
+      "eval_f1": 6.921369607966623,
+      "eval_loss": 4.845778942108154,
+      "eval_runtime": 7.7235,
+      "eval_samples_per_second": 163.786,
+      "eval_steps_per_second": 10.358,
+      "step": 634
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.910016059875488,
+      "learning_rate": 1.3925112501407575e-05,
+      "loss": 4.648683566024251,
+      "step": 1268
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 3.44,
+      "eval_f1": 9.779211605145168,
+      "eval_loss": 4.270840644836426,
+      "eval_runtime": 7.7608,
+      "eval_samples_per_second": 162.999,
+      "eval_steps_per_second": 10.308,
+      "step": 1268
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.720287322998047,
+      "learning_rate": 6.968042898655485e-06,
+      "loss": 4.320517362480284,
+      "step": 1902
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 4.32,
+      "eval_f1": 10.835813703423298,
+      "eval_loss": 4.045061111450195,
+      "eval_runtime": 7.7213,
+      "eval_samples_per_second": 163.833,
+      "eval_steps_per_second": 10.361,
+      "step": 1902
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 12.9658784866333,
+      "learning_rate": 1.0973295903394465e-08,
+      "loss": 4.1913481029426265,
+      "step": 2536
+    },
+    {
+      "epoch": 4.0,
+      "eval_exact_match": 4.56,
+      "eval_f1": 11.5259012819182,
+      "eval_loss": 3.976346254348755,
+      "eval_runtime": 7.6892,
+      "eval_samples_per_second": 164.516,
+      "eval_steps_per_second": 10.404,
+      "step": 2536
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2536,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8200975522295808.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.504106125154617e-05,
+    "lora_alpha": 64,
+    "lora_dropout": 0.06066093898873501,
+    "lora_r": 16,
+    "num_train_epochs": 4,
+    "weight_decay": 0.025681530243658136
+  }
+}