初始化项目，由ModelHub XC社区提供模型

Model: laion/swesmith-unified-1000__Qwen3-8B Source: Original Platform
2026-06-05 00:18:03 +08:00
commit d269e63342
23 changed files with 152531 additions and 0 deletions
--- a/trainer_state.json
+++ b/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": 1.25,
+      "grad_norm": 3.0470718459882953,
+      "learning_rate": 3.9842294026289565e-05,
+      "loss": 0.2767,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07398289442062378,
+      "step": 5,
+      "valid_targets_mean": 8350.3,
+      "valid_targets_min": 1930
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.4265330552753635,
+      "learning_rate": 3.457937254842823e-05,
+      "loss": 0.1895,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.057757824659347534,
+      "step": 10,
+      "valid_targets_mean": 6514.5,
+      "valid_targets_min": 436
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.24584648437132672,
+      "learning_rate": 2.37476262917145e-05,
+      "loss": 0.1574,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.04445400834083557,
+      "step": 15,
+      "valid_targets_mean": 5695.4,
+      "valid_targets_min": 436
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.18406060944399552,
+      "learning_rate": 1.1484414168698547e-05,
+      "loss": 0.1391,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.048449307680130005,
+      "step": 20,
+      "valid_targets_mean": 6897.9,
+      "valid_targets_min": 436
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 0.18454693503355088,
+      "learning_rate": 2.473866399122733e-06,
+      "loss": 0.1299,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.03810304030776024,
+      "step": 25,
+      "valid_targets_mean": 6049.1,
+      "valid_targets_min": 510
+    },
+    {
+      "epoch": 7.0,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.04163763299584389,
+      "step": 28,
+      "total_flos": 1.4912561102402355e+17,
+      "train_loss": 0.17323701509407588,
+      "train_runtime": 898.4803,
+      "train_samples_per_second": 2.781,
+      "train_steps_per_second": 0.031,
+      "valid_targets_mean": 7246.0,
+      "valid_targets_min": 1162
+    }
+  ],
+  "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": 1.4912561102402355e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}