{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.034597471723220224,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008871146595697493,
      "eval_loss": 1.7183804512023926,
      "eval_runtime": 26.9655,
      "eval_samples_per_second": 17.615,
      "eval_steps_per_second": 8.826,
      "step": 1
    },
    {
      "epoch": 0.004435573297848747,
      "grad_norm": 0.6569576263427734,
      "learning_rate": 5e-05,
      "loss": 1.7603,
      "step": 5
    },
    {
      "epoch": 0.008871146595697495,
      "grad_norm": 1.0358091592788696,
      "learning_rate": 0.0001,
      "loss": 1.7299,
      "step": 10
    },
    {
      "epoch": 0.008871146595697495,
      "eval_loss": 1.4282162189483643,
      "eval_runtime": 27.198,
      "eval_samples_per_second": 17.465,
      "eval_steps_per_second": 8.751,
      "step": 10
    },
    {
      "epoch": 0.01330671989354624,
      "grad_norm": 0.7067835927009583,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.0932,
      "step": 15
    },
    {
      "epoch": 0.01774229319139499,
      "grad_norm": 0.7047272324562073,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7826,
      "step": 20
    },
    {
      "epoch": 0.01774229319139499,
      "eval_loss": 0.7068859338760376,
      "eval_runtime": 27.1822,
      "eval_samples_per_second": 17.475,
      "eval_steps_per_second": 8.756,
      "step": 20
    },
    {
      "epoch": 0.022177866489243733,
      "grad_norm": 0.7644681334495544,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.6047,
      "step": 25
    },
    {
      "epoch": 0.02661343978709248,
      "grad_norm": 0.8028997778892517,
      "learning_rate": 5e-05,
      "loss": 0.5485,
      "step": 30
    },
    {
      "epoch": 0.02661343978709248,
      "eval_loss": 0.5370912551879883,
      "eval_runtime": 27.2669,
      "eval_samples_per_second": 17.42,
      "eval_steps_per_second": 8.729,
      "step": 30
    },
    {
      "epoch": 0.031049013084941228,
      "grad_norm": 0.6788683533668518,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.481,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5063800506286080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}