初始化项目，由ModelHub XC社区提供模型

Model: Cisco1963/llmplasticity-en_zh_linear_0.125_1-seed42 Source: Original Platform
2026-05-01 06:20:27 +08:00
commit ee5e46d8ff
158 changed files with 4508267 additions and 0 deletions
--- a/checkpoint-1/trainer_state.json
+++ b/checkpoint-1/trainer_state.json
@@ -0,0 +1,50 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0001873909326212478,
+  "eval_steps": 99999999,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0001873909326212478,
+      "grad_norm": 245.6398468017578,
+      "learning_rate": 5e-05,
+      "loss": 175.7636,
+      "step": 1
+    },
+    {
+      "epoch": 0.0001873909326212478,
+      "eval_accuracy": 0.015452299171252725,
+      "eval_loss": 10.732580184936523,
+      "eval_runtime": 219.7551,
+      "eval_samples_per_second": 35.922,
+      "eval_steps_per_second": 4.491,
+      "step": 1
+    }
+  ],
+  "logging_steps": 99999999,
+  "max_steps": 5337,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 99999999,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 66890760192000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}