{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3812636165577342,
  "eval_steps": 500,
  "global_step": 3500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.054466230936819175,
      "grad_norm": 5.168296813964844,
      "learning_rate": 5e-05,
      "loss": 1.747,
      "step": 500
    },
    {
      "epoch": 0.10893246187363835,
      "grad_norm": 0.6366938948631287,
      "learning_rate": 4.711981566820277e-05,
      "loss": 1.3516,
      "step": 1000
    },
    {
      "epoch": 0.16339869281045752,
      "grad_norm": 0.5679114460945129,
      "learning_rate": 4.423963133640553e-05,
      "loss": 1.3809,
      "step": 1500
    },
    {
      "epoch": 0.2178649237472767,
      "grad_norm": 1.4229077100753784,
      "learning_rate": 4.13594470046083e-05,
      "loss": 1.2784,
      "step": 2000
    },
    {
      "epoch": 0.27233115468409586,
      "grad_norm": 1.4274455308914185,
      "learning_rate": 3.847926267281106e-05,
      "loss": 1.2724,
      "step": 2500
    },
    {
      "epoch": 0.32679738562091504,
      "grad_norm": 1.3789653778076172,
      "learning_rate": 3.559907834101383e-05,
      "loss": 1.2497,
      "step": 3000
    },
    {
      "epoch": 0.3812636165577342,
      "grad_norm": 1.8324720859527588,
      "learning_rate": 3.271889400921659e-05,
      "loss": 1.2794,
      "step": 3500
    }
  ],
  "logging_steps": 500,
  "max_steps": 9180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 914522112000000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}