{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 3247,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003079765937788728,
      "grad_norm": 5.474523544311523,
      "learning_rate": 0.0,
      "loss": 2.8435,
      "step": 1
    },
    {
      "epoch": 0.3079765937788728,
      "grad_norm": 3.9317052364349365,
      "learning_rate": 2.991786447638604e-05,
      "loss": 2.0411,
      "step": 1000
    },
    {
      "epoch": 0.3079765937788728,
      "eval_cosine_accuracy": 0.9618675112724304,
      "eval_loss": 0.6112217903137207,
      "eval_runtime": 27.1137,
      "eval_samples_per_second": 349.16,
      "eval_steps_per_second": 1.365,
      "step": 1000
    },
    {
      "epoch": 0.6159531875577456,
      "grad_norm": 3.60844087600708,
      "learning_rate": 2.649555099247091e-05,
      "loss": 1.4493,
      "step": 2000
    },
    {
      "epoch": 0.6159531875577456,
      "eval_cosine_accuracy": 0.9678884744644165,
      "eval_loss": 0.5245885848999023,
      "eval_runtime": 25.7333,
      "eval_samples_per_second": 367.889,
      "eval_steps_per_second": 1.438,
      "step": 2000
    },
    {
      "epoch": 0.9239297813366184,
      "grad_norm": 5.359713554382324,
      "learning_rate": 2.3073237508555782e-05,
      "loss": 1.1061,
      "step": 3000
    },
    {
      "epoch": 0.9239297813366184,
      "eval_cosine_accuracy": 0.9701066613197327,
      "eval_loss": 0.501575231552124,
      "eval_runtime": 26.3777,
      "eval_samples_per_second": 358.902,
      "eval_steps_per_second": 1.403,
      "step": 3000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 9741,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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
}