{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0014602270653086555,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014602270653086554,
      "grad_norm": 1.8261140584945679,
      "learning_rate": 2e-05,
      "loss": 0.5843,
      "step": 1
    },
    {
      "epoch": 0.00014602270653086554,
      "eval_loss": 0.873163640499115,
      "eval_runtime": 252.6936,
      "eval_samples_per_second": 11.413,
      "eval_steps_per_second": 5.707,
      "step": 1
    },
    {
      "epoch": 0.0002920454130617311,
      "grad_norm": 2.2746965885162354,
      "learning_rate": 4e-05,
      "loss": 0.713,
      "step": 2
    },
    {
      "epoch": 0.00043806811959259663,
      "grad_norm": 1.5648266077041626,
      "learning_rate": 6e-05,
      "loss": 0.7557,
      "step": 3
    },
    {
      "epoch": 0.00043806811959259663,
      "eval_loss": 0.8448721766471863,
      "eval_runtime": 251.2539,
      "eval_samples_per_second": 11.478,
      "eval_steps_per_second": 5.739,
      "step": 3
    },
    {
      "epoch": 0.0005840908261234622,
      "grad_norm": 1.9227348566055298,
      "learning_rate": 8e-05,
      "loss": 0.654,
      "step": 4
    },
    {
      "epoch": 0.0007301135326543278,
      "grad_norm": 1.4340338706970215,
      "learning_rate": 0.0001,
      "loss": 0.7473,
      "step": 5
    },
    {
      "epoch": 0.0008761362391851933,
      "grad_norm": 0.9566660523414612,
      "learning_rate": 0.00012,
      "loss": 0.4959,
      "step": 6
    },
    {
      "epoch": 0.0008761362391851933,
      "eval_loss": 0.5102687478065491,
      "eval_runtime": 251.3029,
      "eval_samples_per_second": 11.476,
      "eval_steps_per_second": 5.738,
      "step": 6
    },
    {
      "epoch": 0.0010221589457160589,
      "grad_norm": 1.2135515213012695,
      "learning_rate": 0.00014,
      "loss": 0.2844,
      "step": 7
    },
    {
      "epoch": 0.0011681816522469243,
      "grad_norm": 0.924731969833374,
      "learning_rate": 0.00016,
      "loss": 0.2435,
      "step": 8
    },
    {
      "epoch": 0.00131420435877779,
      "grad_norm": 1.3633891344070435,
      "learning_rate": 0.00018,
      "loss": 0.5135,
      "step": 9
    },
    {
      "epoch": 0.00131420435877779,
      "eval_loss": 0.21175436675548553,
      "eval_runtime": 251.2162,
      "eval_samples_per_second": 11.48,
      "eval_steps_per_second": 5.74,
      "step": 9
    },
    {
      "epoch": 0.0014602270653086555,
      "grad_norm": 1.094745397567749,
      "learning_rate": 0.0002,
      "loss": 0.2249,
      "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": 2543150841200640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}