初始化项目，由ModelHub XC社区提供模型

Model: Itachi-42/loomstack-qwen-4b-sft-terminal Source: Original Platform
2026-05-08 19:29:02 +08:00
commit f3024c3a98
31 changed files with 2399 additions and 0 deletions
--- a/checkpoint-50/trainer_state.json
+++ b/checkpoint-50/trainer_state.json
@@ -0,0 +1,104 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6666666666666665,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.7803187370300293,
+      "learning_rate": 2e-05,
+      "loss": 0.5952795028686524,
+      "step": 5
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.6131587624549866,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5271629810333252,
+      "step": 10
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.48774853348731995,
+      "learning_rate": 4.75e-05,
+      "loss": 0.4307117938995361,
+      "step": 15
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.33142268657684326,
+      "learning_rate": 4.4375e-05,
+      "loss": 0.3310281991958618,
+      "step": 20
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.29702720046043396,
+      "learning_rate": 4.125e-05,
+      "loss": 0.26529295444488527,
+      "step": 25
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2944898307323456,
+      "learning_rate": 3.8125e-05,
+      "loss": 0.22223505973815919,
+      "step": 30
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.30312275886535645,
+      "learning_rate": 3.5e-05,
+      "loss": 0.17875735759735106,
+      "step": 35
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.21360355615615845,
+      "learning_rate": 3.1875e-05,
+      "loss": 0.14450310468673705,
+      "step": 40
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.27876031398773193,
+      "learning_rate": 2.8749999999999997e-05,
+      "loss": 0.10100011825561524,
+      "step": 45
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.2158161848783493,
+      "learning_rate": 2.5625e-05,
+      "loss": 0.08411684036254882,
+      "step": 50
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 90,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 7776581756912640.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}