{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.859813084112149,
  "eval_steps": 200,
  "global_step": 130,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 0.753517210483551,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.7119,
      "step": 10
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 0.7775868773460388,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.7214,
      "step": 20
    },
    {
      "epoch": 1.1214953271028036,
      "grad_norm": 0.8182362914085388,
      "learning_rate": 6e-06,
      "loss": 2.7061,
      "step": 30
    },
    {
      "epoch": 1.4953271028037383,
      "grad_norm": 0.8709849715232849,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.6934,
      "step": 40
    },
    {
      "epoch": 1.8691588785046729,
      "grad_norm": 0.9852027893066406,
      "learning_rate": 1e-05,
      "loss": 2.6624,
      "step": 50
    },
    {
      "epoch": 2.2429906542056073,
      "grad_norm": 1.1304007768630981,
      "learning_rate": 1.2e-05,
      "loss": 2.6057,
      "step": 60
    },
    {
      "epoch": 2.616822429906542,
      "grad_norm": 1.2537626028060913,
      "learning_rate": 1.4e-05,
      "loss": 2.5097,
      "step": 70
    },
    {
      "epoch": 2.9906542056074765,
      "grad_norm": 1.4190107583999634,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.379,
      "step": 80
    },
    {
      "epoch": 3.364485981308411,
      "grad_norm": 1.7936476469039917,
      "learning_rate": 1.8e-05,
      "loss": 2.181,
      "step": 90
    },
    {
      "epoch": 3.7383177570093458,
      "grad_norm": 2.099269151687622,
      "learning_rate": 2e-05,
      "loss": 1.9225,
      "step": 100
    },
    {
      "epoch": 4.11214953271028,
      "grad_norm": 2.4976556301116943,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 1.6019,
      "step": 110
    },
    {
      "epoch": 4.485981308411215,
      "grad_norm": 2.6975057125091553,
      "learning_rate": 5.000000000000003e-06,
      "loss": 1.3183,
      "step": 120
    },
    {
      "epoch": 4.859813084112149,
      "grad_norm": 2.489922046661377,
      "learning_rate": 0.0,
      "loss": 1.2013,
      "step": 130
    }
  ],
  "logging_steps": 10,
  "max_steps": 130,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.485914631212892e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}