初始化项目，由ModelHub XC社区提供模型

Model: edbeeching/Qwen3-0.6B-SFT-Eval-Smoke Source: Original Platform
2026-07-12 04:04:09 +08:00
commit 7facb2f25e
13 changed files with 365 additions and 0 deletions
--- a/trainer_state.json
+++ b/trainer_state.json
@@ -0,0 +1,52 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.008849557522123894,
+  "eval_steps": 10,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008849557522123894,
+      "grad_norm": 8.375,
+      "learning_rate": 0.0,
+      "loss": 1.0641121864318848,
+      "mean_token_accuracy": 0.730694055557251,
+      "num_tokens": 8192.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.008849557522123894,
+      "step": 1,
+      "total_flos": 21649856397312.0,
+      "train_loss": 1.0641121864318848,
+      "train_runtime": 10.9027,
+      "train_samples_per_second": 0.734,
+      "train_steps_per_second": 0.092
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 21649856397312.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}