{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.021586616297895305,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021586616297895305,
      "grad_norm": 0.45577260851860046,
      "learning_rate": 2e-05,
      "loss": 0.6995,
      "step": 1
    },
    {
      "epoch": 0.0021586616297895305,
      "eval_loss": 0.8814611434936523,
      "eval_runtime": 10.5524,
      "eval_samples_per_second": 18.479,
      "eval_steps_per_second": 9.287,
      "step": 1
    },
    {
      "epoch": 0.004317323259579061,
      "grad_norm": 0.6012941002845764,
      "learning_rate": 4e-05,
      "loss": 0.8884,
      "step": 2
    },
    {
      "epoch": 0.0064759848893685915,
      "grad_norm": 0.7979885339736938,
      "learning_rate": 6e-05,
      "loss": 0.8526,
      "step": 3
    },
    {
      "epoch": 0.0064759848893685915,
      "eval_loss": 0.8783421516418457,
      "eval_runtime": 9.361,
      "eval_samples_per_second": 20.831,
      "eval_steps_per_second": 10.469,
      "step": 3
    },
    {
      "epoch": 0.008634646519158122,
      "grad_norm": 0.5008302330970764,
      "learning_rate": 8e-05,
      "loss": 0.6914,
      "step": 4
    },
    {
      "epoch": 0.010793308148947653,
      "grad_norm": 0.7716145515441895,
      "learning_rate": 0.0001,
      "loss": 0.9655,
      "step": 5
    },
    {
      "epoch": 0.012951969778737183,
      "grad_norm": 0.8028150200843811,
      "learning_rate": 0.00012,
      "loss": 0.9571,
      "step": 6
    },
    {
      "epoch": 0.012951969778737183,
      "eval_loss": 0.8267777562141418,
      "eval_runtime": 9.364,
      "eval_samples_per_second": 20.824,
      "eval_steps_per_second": 10.466,
      "step": 6
    },
    {
      "epoch": 0.015110631408526714,
      "grad_norm": 0.613737165927887,
      "learning_rate": 0.00014,
      "loss": 0.6678,
      "step": 7
    },
    {
      "epoch": 0.017269293038316244,
      "grad_norm": 0.8371005058288574,
      "learning_rate": 0.00016,
      "loss": 0.6438,
      "step": 8
    },
    {
      "epoch": 0.019427954668105773,
      "grad_norm": 0.7334175109863281,
      "learning_rate": 0.00018,
      "loss": 0.6108,
      "step": 9
    },
    {
      "epoch": 0.019427954668105773,
      "eval_loss": 0.5494382381439209,
      "eval_runtime": 9.3835,
      "eval_samples_per_second": 20.781,
      "eval_steps_per_second": 10.444,
      "step": 9
    },
    {
      "epoch": 0.021586616297895305,
      "grad_norm": 0.9324132800102234,
      "learning_rate": 0.0002,
      "loss": 0.4765,
      "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": 3166204172697600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}