初始化项目，由ModelHub XC社区提供模型

Model: Henry236/east8b-eg-lora-heuristic Source: Original Platform
2026-08-22 08:49:17 +08:00
commit 4e00a082d0
191 changed files with 14013 additions and 0 deletions
--- a/checkpoint-300/trainer_state.json
+++ b/checkpoint-300/trainer_state.json
@@ -0,0 +1,139 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5208333333333334,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.034722222222222224,
+      "grad_norm": 2.985321283340454,
+      "learning_rate": 1.6379310344827587e-06,
+      "loss": 2.6523,
+      "step": 20
+    },
+    {
+      "epoch": 0.06944444444444445,
+      "grad_norm": 2.353632926940918,
+      "learning_rate": 3.362068965517242e-06,
+      "loss": 2.4359,
+      "step": 40
+    },
+    {
+      "epoch": 0.10416666666666667,
+      "grad_norm": 1.865394115447998,
+      "learning_rate": 5.086206896551724e-06,
+      "loss": 2.2545,
+      "step": 60
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 1.8125933408737183,
+      "learning_rate": 6.810344827586207e-06,
+      "loss": 2.0557,
+      "step": 80
+    },
+    {
+      "epoch": 0.1736111111111111,
+      "grad_norm": 2.3572490215301514,
+      "learning_rate": 8.53448275862069e-06,
+      "loss": 1.9334,
+      "step": 100
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 2.395277261734009,
+      "learning_rate": 9.999793100349294e-06,
+      "loss": 1.9212,
+      "step": 120
+    },
+    {
+      "epoch": 0.24305555555555555,
+      "grad_norm": 2.714841604232788,
+      "learning_rate": 9.987843743451796e-06,
+      "loss": 1.7889,
+      "step": 140
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 2.236692190170288,
+      "learning_rate": 9.957553516178782e-06,
+      "loss": 1.716,
+      "step": 160
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 2.3020412921905518,
+      "learning_rate": 9.909033799150947e-06,
+      "loss": 1.7569,
+      "step": 180
+    },
+    {
+      "epoch": 0.3472222222222222,
+      "grad_norm": 2.5109288692474365,
+      "learning_rate": 9.842463004902127e-06,
+      "loss": 1.6664,
+      "step": 200
+    },
+    {
+      "epoch": 0.3819444444444444,
+      "grad_norm": 2.5140888690948486,
+      "learning_rate": 9.758085921836076e-06,
+      "loss": 1.6544,
+      "step": 220
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 2.666377544403076,
+      "learning_rate": 9.656212814111567e-06,
+      "loss": 1.6608,
+      "step": 240
+    },
+    {
+      "epoch": 0.4513888888888889,
+      "grad_norm": 2.715240955352783,
+      "learning_rate": 9.53721828076571e-06,
+      "loss": 1.6353,
+      "step": 260
+    },
+    {
+      "epoch": 0.4861111111111111,
+      "grad_norm": 2.7697439193725586,
+      "learning_rate": 9.401539878270545e-06,
+      "loss": 1.6352,
+      "step": 280
+    },
+    {
+      "epoch": 0.5208333333333334,
+      "grad_norm": 2.9743459224700928,
+      "learning_rate": 9.249676511588e-06,
+      "loss": 1.6275,
+      "step": 300
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 1152,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.104440425391718e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}