{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04830917874396135,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004830917874396135,
      "grad_norm": 4.699305534362793,
      "learning_rate": 2e-05,
      "loss": 44.3766,
      "step": 1
    },
    {
      "epoch": 0.004830917874396135,
      "eval_loss": 11.088024139404297,
      "eval_runtime": 1.9009,
      "eval_samples_per_second": 46.294,
      "eval_steps_per_second": 23.147,
      "step": 1
    },
    {
      "epoch": 0.00966183574879227,
      "grad_norm": 4.3816046714782715,
      "learning_rate": 4e-05,
      "loss": 44.3588,
      "step": 2
    },
    {
      "epoch": 0.014492753623188406,
      "grad_norm": 5.163635730743408,
      "learning_rate": 6e-05,
      "loss": 44.4378,
      "step": 3
    },
    {
      "epoch": 0.014492753623188406,
      "eval_loss": 11.081073760986328,
      "eval_runtime": 1.5264,
      "eval_samples_per_second": 57.653,
      "eval_steps_per_second": 28.826,
      "step": 3
    },
    {
      "epoch": 0.01932367149758454,
      "grad_norm": 4.113152980804443,
      "learning_rate": 8e-05,
      "loss": 44.326,
      "step": 4
    },
    {
      "epoch": 0.024154589371980676,
      "grad_norm": 4.332220554351807,
      "learning_rate": 0.0001,
      "loss": 44.307,
      "step": 5
    },
    {
      "epoch": 0.028985507246376812,
      "grad_norm": 4.020875453948975,
      "learning_rate": 0.00012,
      "loss": 44.2553,
      "step": 6
    },
    {
      "epoch": 0.028985507246376812,
      "eval_loss": 11.053601264953613,
      "eval_runtime": 1.5572,
      "eval_samples_per_second": 56.513,
      "eval_steps_per_second": 28.256,
      "step": 6
    },
    {
      "epoch": 0.033816425120772944,
      "grad_norm": 4.814146518707275,
      "learning_rate": 0.00014,
      "loss": 44.2293,
      "step": 7
    },
    {
      "epoch": 0.03864734299516908,
      "grad_norm": 4.547501087188721,
      "learning_rate": 0.00016,
      "loss": 44.1166,
      "step": 8
    },
    {
      "epoch": 0.043478260869565216,
      "grad_norm": 4.67207145690918,
      "learning_rate": 0.00018,
      "loss": 44.1135,
      "step": 9
    },
    {
      "epoch": 0.043478260869565216,
      "eval_loss": 11.005003929138184,
      "eval_runtime": 1.5478,
      "eval_samples_per_second": 56.855,
      "eval_steps_per_second": 28.428,
      "step": 9
    },
    {
      "epoch": 0.04830917874396135,
      "grad_norm": 4.50685977935791,
      "learning_rate": 0.0002,
      "loss": 44.0248,
      "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": 831982141440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}