初始化项目，由ModelHub XC社区提供模型

Model: Henry236/east8b-eg-lora-chunk-llama Source: Original Platform
2026-08-24 01:37:17 +08:00
commit 70234cd1db
207 changed files with 15041 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": 2.4759202003479004,
+      "learning_rate": 1.6379310344827587e-06,
+      "loss": 2.5561,
+      "step": 20
+    },
+    {
+      "epoch": 0.06944444444444445,
+      "grad_norm": 2.5604989528656006,
+      "learning_rate": 3.362068965517242e-06,
+      "loss": 2.3957,
+      "step": 40
+    },
+    {
+      "epoch": 0.10416666666666667,
+      "grad_norm": 1.9377268552780151,
+      "learning_rate": 5.086206896551724e-06,
+      "loss": 2.217,
+      "step": 60
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 1.7941242456436157,
+      "learning_rate": 6.810344827586207e-06,
+      "loss": 2.0366,
+      "step": 80
+    },
+    {
+      "epoch": 0.1736111111111111,
+      "grad_norm": 2.2135872840881348,
+      "learning_rate": 8.53448275862069e-06,
+      "loss": 1.9154,
+      "step": 100
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 2.290032148361206,
+      "learning_rate": 9.999793100349294e-06,
+      "loss": 1.8946,
+      "step": 120
+    },
+    {
+      "epoch": 0.24305555555555555,
+      "grad_norm": 2.4187541007995605,
+      "learning_rate": 9.987843743451796e-06,
+      "loss": 1.7858,
+      "step": 140
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 2.115030288696289,
+      "learning_rate": 9.957553516178782e-06,
+      "loss": 1.7133,
+      "step": 160
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 2.290724754333496,
+      "learning_rate": 9.909033799150947e-06,
+      "loss": 1.7567,
+      "step": 180
+    },
+    {
+      "epoch": 0.3472222222222222,
+      "grad_norm": 2.318016767501831,
+      "learning_rate": 9.842463004902127e-06,
+      "loss": 1.6653,
+      "step": 200
+    },
+    {
+      "epoch": 0.3819444444444444,
+      "grad_norm": 2.37850284576416,
+      "learning_rate": 9.758085921836076e-06,
+      "loss": 1.6518,
+      "step": 220
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 2.5013656616210938,
+      "learning_rate": 9.656212814111567e-06,
+      "loss": 1.669,
+      "step": 240
+    },
+    {
+      "epoch": 0.4513888888888889,
+      "grad_norm": 3.0407257080078125,
+      "learning_rate": 9.53721828076571e-06,
+      "loss": 1.6393,
+      "step": 260
+    },
+    {
+      "epoch": 0.4861111111111111,
+      "grad_norm": 2.709101915359497,
+      "learning_rate": 9.401539878270545e-06,
+      "loss": 1.6274,
+      "step": 280
+    },
+    {
+      "epoch": 0.5208333333333334,
+      "grad_norm": 2.9556779861450195,
+      "learning_rate": 9.249676511588e-06,
+      "loss": 1.6256,
+      "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": 6.016103183292826e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}