{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 3528,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002834467120181406,
      "grad_norm": 5.449254512786865,
      "learning_rate": 0.0,
      "loss": 2.6239,
      "step": 1
    },
    {
      "epoch": 0.2834467120181406,
      "grad_norm": 3.8293514251708984,
      "learning_rate": 2.1225212464589238e-05,
      "loss": 2.239,
      "step": 1000
    },
    {
      "epoch": 0.2834467120181406,
      "eval_cosine_accuracy": 0.9631311893463135,
      "eval_loss": 1.070603609085083,
      "eval_runtime": 24.3925,
      "eval_samples_per_second": 388.071,
      "eval_steps_per_second": 1.517,
      "step": 1000
    },
    {
      "epoch": 0.5668934240362812,
      "grad_norm": 3.8862180709838867,
      "learning_rate": 2.8613385826771657e-05,
      "loss": 1.6315,
      "step": 2000
    },
    {
      "epoch": 0.5668934240362812,
      "eval_cosine_accuracy": 0.9705260992050171,
      "eval_loss": 0.9979932308197021,
      "eval_runtime": 23.6004,
      "eval_samples_per_second": 401.094,
      "eval_steps_per_second": 1.568,
      "step": 2000
    },
    {
      "epoch": 0.8503401360544217,
      "grad_norm": 3.756399631500244,
      "learning_rate": 2.6251181102362205e-05,
      "loss": 1.4885,
      "step": 3000
    },
    {
      "epoch": 0.8503401360544217,
      "eval_cosine_accuracy": 0.9735897183418274,
      "eval_loss": 0.8850170373916626,
      "eval_runtime": 23.076,
      "eval_samples_per_second": 410.209,
      "eval_steps_per_second": 1.603,
      "step": 3000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 14112,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 0.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}