初始化项目，由ModelHub XC社区提供模型

Model: laion/sera-316__Qwen3-8B
Source: Original Platform

trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 28,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.3,
+      "grad_norm": 2.0453916235489795,
+      "learning_rate": 3.9842294026289565e-05,
+      "loss": 0.4037,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11261754482984543,
+      "step": 5,
+      "valid_targets_mean": 14021.2,
+      "valid_targets_min": 7176
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.39143453741775175,
+      "learning_rate": 3.457937254842823e-05,
+      "loss": 0.3316,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10281488299369812,
+      "step": 10,
+      "valid_targets_mean": 14427.7,
+      "valid_targets_min": 2828
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 0.271429073833134,
+      "learning_rate": 2.37476262917145e-05,
+      "loss": 0.3035,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09832499921321869,
+      "step": 15,
+      "valid_targets_mean": 13976.7,
+      "valid_targets_min": 9420
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.24325074494907922,
+      "learning_rate": 1.1484414168698547e-05,
+      "loss": 0.2798,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.2742854952812195,
+      "step": 20,
+      "valid_targets_mean": 14033.0,
+      "valid_targets_min": 5856
+    },
+    {
+      "epoch": 6.3,
+      "grad_norm": 0.17833827263967014,
+      "learning_rate": 2.473866399122733e-06,
+      "loss": 0.2712,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08983700722455978,
+      "step": 25,
+      "valid_targets_mean": 14145.2,
+      "valid_targets_min": 8865
+    },
+    {
+      "epoch": 7.0,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.27273428440093994,
+      "step": 28,
+      "total_flos": 1.6389573619325338e+17,
+      "train_loss": 0.31328126788139343,
+      "train_runtime": 731.9084,
+      "train_samples_per_second": 3.022,
+      "train_steps_per_second": 0.038,
+      "valid_targets_mean": 13154.9,
+      "valid_targets_min": 5475
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 28,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6389573619325338e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}