{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00831255195344971,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008312551953449709,
      "grad_norm": 3.0996017456054688,
      "learning_rate": 2e-05,
      "loss": 10.8636,
      "step": 1
    },
    {
      "epoch": 0.0008312551953449709,
      "eval_loss": 2.586120128631592,
      "eval_runtime": 31.4531,
      "eval_samples_per_second": 16.119,
      "eval_steps_per_second": 8.076,
      "step": 1
    },
    {
      "epoch": 0.0016625103906899418,
      "grad_norm": 1.1362569332122803,
      "learning_rate": 4e-05,
      "loss": 9.5429,
      "step": 2
    },
    {
      "epoch": 0.0024937655860349127,
      "grad_norm": 1.2610175609588623,
      "learning_rate": 6e-05,
      "loss": 8.02,
      "step": 3
    },
    {
      "epoch": 0.0024937655860349127,
      "eval_loss": 2.5848870277404785,
      "eval_runtime": 31.4411,
      "eval_samples_per_second": 16.125,
      "eval_steps_per_second": 8.079,
      "step": 3
    },
    {
      "epoch": 0.0033250207813798837,
      "grad_norm": 0.9110913276672363,
      "learning_rate": 8e-05,
      "loss": 7.8592,
      "step": 4
    },
    {
      "epoch": 0.004156275976724855,
      "grad_norm": 1.345411777496338,
      "learning_rate": 0.0001,
      "loss": 7.6662,
      "step": 5
    },
    {
      "epoch": 0.004987531172069825,
      "grad_norm": 1.016042709350586,
      "learning_rate": 0.00012,
      "loss": 6.5311,
      "step": 6
    },
    {
      "epoch": 0.004987531172069825,
      "eval_loss": 2.5600686073303223,
      "eval_runtime": 31.46,
      "eval_samples_per_second": 16.116,
      "eval_steps_per_second": 8.074,
      "step": 6
    },
    {
      "epoch": 0.005818786367414797,
      "grad_norm": 1.233384609222412,
      "learning_rate": 0.00014,
      "loss": 9.9636,
      "step": 7
    },
    {
      "epoch": 0.006650041562759767,
      "grad_norm": 1.6117174625396729,
      "learning_rate": 0.00016,
      "loss": 10.1133,
      "step": 8
    },
    {
      "epoch": 0.007481296758104738,
      "grad_norm": 1.2704540491104126,
      "learning_rate": 0.00018,
      "loss": 7.8248,
      "step": 9
    },
    {
      "epoch": 0.007481296758104738,
      "eval_loss": 2.4326798915863037,
      "eval_runtime": 31.4929,
      "eval_samples_per_second": 16.099,
      "eval_steps_per_second": 8.065,
      "step": 9
    },
    {
      "epoch": 0.00831255195344971,
      "grad_norm": 2.3734917640686035,
      "learning_rate": 0.0002,
      "loss": 8.5162,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3562002343526400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}