初始化项目，由ModelHub XC社区提供模型

Model: Xtra-Computing/XtraGPT-1.5B Source: Original Platform
2026-05-16 01:09:39 +08:00
commit 9710a601ef
18 changed files with 152087 additions and 0 deletions
--- a/trainer_state.json
+++ b/trainer_state.json
@@ -0,0 +1,119 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9777777777777779,
+  "eval_steps": 500,
+  "global_step": 112,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 1.1333891966940177,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.7523,
+      "step": 10
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.958010004815403,
+      "learning_rate": 9.842915805643156e-06,
+      "loss": 0.7075,
+      "step": 20
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.7853045645588168,
+      "learning_rate": 9.221639627510076e-06,
+      "loss": 0.6473,
+      "step": 30
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.8825698012004065,
+      "learning_rate": 8.18711994874345e-06,
+      "loss": 0.6078,
+      "step": 40
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.7151740400775302,
+      "learning_rate": 6.840622763423391e-06,
+      "loss": 0.5699,
+      "step": 50
+    },
+    {
+      "epoch": 1.0533333333333332,
+      "grad_norm": 0.7570773917821664,
+      "learning_rate": 5.3139525976465675e-06,
+      "loss": 0.5587,
+      "step": 60
+    },
+    {
+      "epoch": 1.231111111111111,
+      "grad_norm": 0.8230371816683825,
+      "learning_rate": 3.756550564175727e-06,
+      "loss": 0.382,
+      "step": 70
+    },
+    {
+      "epoch": 1.4088888888888889,
+      "grad_norm": 0.6621112845262395,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 0.3424,
+      "step": 80
+    },
+    {
+      "epoch": 1.5866666666666667,
+      "grad_norm": 0.8311851524519195,
+      "learning_rate": 1.1474337861210543e-06,
+      "loss": 0.3815,
+      "step": 90
+    },
+    {
+      "epoch": 1.7644444444444445,
+      "grad_norm": 0.7404603826818766,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 0.3416,
+      "step": 100
+    },
+    {
+      "epoch": 1.942222222222222,
+      "grad_norm": 0.7121753922595842,
+      "learning_rate": 9.866357858642206e-09,
+      "loss": 0.3558,
+      "step": 110
+    },
+    {
+      "epoch": 1.9777777777777779,
+      "step": 112,
+      "total_flos": 15337468788736.0,
+      "train_loss": 0.5112001879939011,
+      "train_runtime": 1525.5061,
+      "train_samples_per_second": 1.18,
+      "train_steps_per_second": 0.073
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 112,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 15337468788736.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}