{
  "best_metric": 1.6923751831054688,
  "best_model_checkpoint": "/root/autodl-tmp/output/Qwen2.5-7B-lora/checkpoint-150",
  "epoch": 2.96,
  "eval_steps": 50,
  "global_step": 168,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.34655386209487915,
      "learning_rate": 4.5099928259173516e-05,
      "loss": 1.9239,
      "step": 50
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 1.7332603931427002,
      "eval_runtime": 5.1621,
      "eval_samples_per_second": 19.372,
      "eval_steps_per_second": 19.372,
      "step": 50
    },
    {
      "epoch": 1.7644444444444445,
      "grad_norm": 0.5022056102752686,
      "learning_rate": 2.182455450632803e-05,
      "loss": 1.702,
      "step": 100
    },
    {
      "epoch": 1.7644444444444445,
      "eval_loss": 1.6984269618988037,
      "eval_runtime": 5.142,
      "eval_samples_per_second": 19.448,
      "eval_steps_per_second": 19.448,
      "step": 100
    },
    {
      "epoch": 2.64,
      "grad_norm": 0.4542456269264221,
      "learning_rate": 1.8027743175872664e-06,
      "loss": 1.6651,
      "step": 150
    },
    {
      "epoch": 2.64,
      "eval_loss": 1.6923751831054688,
      "eval_runtime": 5.2183,
      "eval_samples_per_second": 19.163,
      "eval_steps_per_second": 19.163,
      "step": 150
    },
    {
      "epoch": 2.96,
      "step": 168,
      "total_flos": 2.182399960301568e+16,
      "train_loss": 1.7539968490600586,
      "train_runtime": 301.6989,
      "train_samples_per_second": 8.949,
      "train_steps_per_second": 0.557
    }
  ],
  "logging_steps": 50,
  "max_steps": 168,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.182399960301568e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}