{
  "best_global_step": null,
  "best_metric": 7.719013214111328,
  "best_model_checkpoint": "/home/haji80as/invariant-LM/Qwen2-1.5B-merged-server-20000-rank-128/checkpoint-4500",
  "epoch": null,
  "eval_steps": 500,
  "global_step": 0,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "eval_loss": 10.818012237548828,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 251.0603,
      "eval_samples_per_second": 24.512,
      "eval_steps_per_second": 3.067,
      "step": 0
    },
    {
      "eval_loss": 10.818012237548828,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 251.0603,
      "eval_samples_per_second": 24.512,
      "eval_steps_per_second": 3.067,
      "step": 0
    },
    {
      "eval_loss": 10.100893020629883,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 250.5086,
      "eval_samples_per_second": 24.566,
      "eval_steps_per_second": 3.074,
      "step": 0
    },
    {
      "eval_loss": 10.100893020629883,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 250.5086,
      "eval_samples_per_second": 24.566,
      "eval_steps_per_second": 3.074,
      "step": 0
    },
    {
      "eval_loss": 9.53693675994873,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 250.8052,
      "eval_samples_per_second": 24.537,
      "eval_steps_per_second": 3.07,
      "step": 0
    },
    {
      "eval_loss": 9.53693675994873,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 250.8052,
      "eval_samples_per_second": 24.537,
      "eval_steps_per_second": 3.07,
      "step": 0
    },
    {
      "eval_loss": 9.094352722167969,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 250.92,
      "eval_samples_per_second": 24.526,
      "eval_steps_per_second": 3.069,
      "step": 0
    },
    {
      "eval_loss": 9.094352722167969,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 250.92,
      "eval_samples_per_second": 24.526,
      "eval_steps_per_second": 3.069,
      "step": 0
    },
    {
      "eval_loss": 8.673422813415527,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 250.8965,
      "eval_samples_per_second": 24.528,
      "eval_steps_per_second": 3.069,
      "step": 0
    },
    {
      "eval_loss": 8.673422813415527,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 250.8965,
      "eval_samples_per_second": 24.528,
      "eval_steps_per_second": 3.069,
      "step": 0
    },
    {
      "eval_loss": 8.244048118591309,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 262.4664,
      "eval_samples_per_second": 23.447,
      "eval_steps_per_second": 2.934,
      "step": 0
    },
    {
      "eval_loss": 8.244048118591309,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 262.4664,
      "eval_samples_per_second": 23.447,
      "eval_steps_per_second": 2.934,
      "step": 0
    },
    {
      "eval_loss": 7.927587985992432,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 250.5702,
      "eval_samples_per_second": 24.56,
      "eval_steps_per_second": 3.073,
      "step": 0
    },
    {
      "eval_loss": 7.927587985992432,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 250.5702,
      "eval_samples_per_second": 24.56,
      "eval_steps_per_second": 3.073,
      "step": 0
    },
    {
      "eval_loss": 7.749431133270264,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 250.1536,
      "eval_samples_per_second": 24.601,
      "eval_steps_per_second": 3.078,
      "step": 0
    },
    {
      "eval_loss": 7.749431133270264,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 250.1536,
      "eval_samples_per_second": 24.601,
      "eval_steps_per_second": 3.078,
      "step": 0
    },
    {
      "eval_loss": 7.719013214111328,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 250.8627,
      "eval_samples_per_second": 24.531,
      "eval_steps_per_second": 3.069,
      "step": 0
    },
    {
      "eval_loss": 7.719013214111328,
      "eval_model_preparation_time": 0.0227,
      "eval_runtime": 250.8627,
      "eval_samples_per_second": 24.531,
      "eval_steps_per_second": 3.069,
      "step": 0
    }
  ],
  "logging_steps": 500,
  "max_steps": 0,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 0,
  "save_steps": 500,
  "stateful_callbacks": {},
  "total_flos": 0,
  "train_batch_size": null,
  "trial_name": null,
  "trial_params": null
}