{
  "best_metric": 2.02008056640625,
  "best_model_checkpoint": "/home/datta0/models/lora_final/Qwen2-7B_pct_default/checkpoint-8",
  "epoch": 0.020611916264090178,
  "eval_steps": 8,
  "global_step": 8,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025764895330112722,
      "grad_norm": 5.605008125305176,
      "learning_rate": 3.75e-05,
      "loss": 2.0287,
      "step": 1
    },
    {
      "epoch": 0.010305958132045089,
      "grad_norm": 3.37660551071167,
      "learning_rate": 0.00015,
      "loss": 2.1017,
      "step": 4
    },
    {
      "epoch": 0.020611916264090178,
      "grad_norm": 3.2211694717407227,
      "learning_rate": 0.0003,
      "loss": 2.1169,
      "step": 8
    },
    {
      "epoch": 0.020611916264090178,
      "eval_loss": 2.02008056640625,
      "eval_runtime": 10.2397,
      "eval_samples_per_second": 23.927,
      "eval_steps_per_second": 3.027,
      "step": 8
    }
  ],
  "logging_steps": 4,
  "max_steps": 388,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 8,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.827044979572736e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}