{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009854644000985464,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009854644000985464,
      "grad_norm": 7.580688953399658,
      "learning_rate": 2e-05,
      "loss": 3.2945,
      "step": 1
    },
    {
      "epoch": 0.0009854644000985464,
      "eval_loss": 2.2907557487487793,
      "eval_runtime": 16.3387,
      "eval_samples_per_second": 26.195,
      "eval_steps_per_second": 13.098,
      "step": 1
    },
    {
      "epoch": 0.001970928800197093,
      "grad_norm": 3.5840377807617188,
      "learning_rate": 4e-05,
      "loss": 1.9572,
      "step": 2
    },
    {
      "epoch": 0.0029563932002956393,
      "grad_norm": 5.3621745109558105,
      "learning_rate": 6e-05,
      "loss": 2.3513,
      "step": 3
    },
    {
      "epoch": 0.0029563932002956393,
      "eval_loss": 2.247276544570923,
      "eval_runtime": 16.3744,
      "eval_samples_per_second": 26.138,
      "eval_steps_per_second": 13.069,
      "step": 3
    },
    {
      "epoch": 0.003941857600394186,
      "grad_norm": 6.783773422241211,
      "learning_rate": 8e-05,
      "loss": 2.5767,
      "step": 4
    },
    {
      "epoch": 0.004927322000492732,
      "grad_norm": 4.403555870056152,
      "learning_rate": 0.0001,
      "loss": 1.6635,
      "step": 5
    },
    {
      "epoch": 0.005912786400591279,
      "grad_norm": 3.2795095443725586,
      "learning_rate": 0.00012,
      "loss": 1.4479,
      "step": 6
    },
    {
      "epoch": 0.005912786400591279,
      "eval_loss": 1.6754177808761597,
      "eval_runtime": 16.3726,
      "eval_samples_per_second": 26.141,
      "eval_steps_per_second": 13.071,
      "step": 6
    },
    {
      "epoch": 0.006898250800689825,
      "grad_norm": 3.435171604156494,
      "learning_rate": 0.00014,
      "loss": 1.6169,
      "step": 7
    },
    {
      "epoch": 0.007883715200788372,
      "grad_norm": 3.7676050662994385,
      "learning_rate": 0.00016,
      "loss": 1.6486,
      "step": 8
    },
    {
      "epoch": 0.008869179600886918,
      "grad_norm": 3.500913143157959,
      "learning_rate": 0.00018,
      "loss": 1.1327,
      "step": 9
    },
    {
      "epoch": 0.008869179600886918,
      "eval_loss": 1.229416012763977,
      "eval_runtime": 16.3672,
      "eval_samples_per_second": 26.15,
      "eval_steps_per_second": 13.075,
      "step": 9
    },
    {
      "epoch": 0.009854644000985464,
      "grad_norm": 4.124852180480957,
      "learning_rate": 0.0002,
      "loss": 1.0295,
      "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": 962687361613824.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}