初始化项目，由ModelHub XC社区提供模型

Model: JoaoBoer/tofu_Llama-3.1-8B-Instruct_forget05_NPO Source: Original Platform
2026-09-28 03:45:18 +08:00
commit d5c22b118a
25 changed files with 38661 additions and 0 deletions
--- a/trainer_state.json
+++ b/trainer_state.json
@@ -0,0 +1,127 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.64,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "grad_norm": 334.85599352203303,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 54.718,
+      "step": 5
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 202.7554645505365,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 17.2721,
+      "step": 10
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 80.19389428909676,
+      "learning_rate": 1.7037037037037038e-05,
+      "loss": 9.8854,
+      "step": 15
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 70.15487433345591,
+      "learning_rate": 1.5185185185185187e-05,
+      "loss": 9.1224,
+      "step": 20
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 67.74738211665279,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 6.7069,
+      "step": 25
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 59.21687170152334,
+      "learning_rate": 1.1481481481481482e-05,
+      "loss": 5.8678,
+      "step": 30
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 63.030732034440945,
+      "learning_rate": 9.62962962962963e-06,
+      "loss": 4.7996,
+      "step": 35
+    },
+    {
+      "epoch": 5.8,
+      "grad_norm": 60.56173023691404,
+      "learning_rate": 7.77777777777778e-06,
+      "loss": 5.4373,
+      "step": 40
+    },
+    {
+      "epoch": 6.48,
+      "grad_norm": 59.13232869822844,
+      "learning_rate": 5.925925925925926e-06,
+      "loss": 4.6898,
+      "step": 45
+    },
+    {
+      "epoch": 7.16,
+      "grad_norm": 56.71805846317398,
+      "learning_rate": 4.074074074074074e-06,
+      "loss": 3.3341,
+      "step": 50
+    },
+    {
+      "epoch": 7.96,
+      "grad_norm": 76.99880625336664,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 4.3757,
+      "step": 55
+    },
+    {
+      "epoch": 8.64,
+      "grad_norm": 63.78644421102578,
+      "learning_rate": 3.7037037037037036e-07,
+      "loss": 3.545,
+      "step": 60
+    },
+    {
+      "epoch": 8.64,
+      "step": 60,
+      "total_flos": 0.0,
+      "train_loss": 10.812849680582682,
+      "train_runtime": 3254.027,
+      "train_samples_per_second": 0.615,
+      "train_steps_per_second": 0.018
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 60,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}