{
  "best_metric": 0.9433962264150944,
  "best_model_checkpoint": "./models/tese_classification_llama_long/checkpoint-190",
  "epoch": 7.037383177570093,
  "eval_steps": 10,
  "global_step": 190,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.37383177570093457,
      "eval_accuracy": 0.6981132075471698,
      "eval_loss": 0.8507290482521057,
      "eval_runtime": 5.9153,
      "eval_samples_per_second": 8.96,
      "eval_steps_per_second": 8.96,
      "step": 10
    },
    {
      "epoch": 0.7476635514018691,
      "eval_accuracy": 0.41509433962264153,
      "eval_loss": 2.2180840969085693,
      "eval_runtime": 7.8616,
      "eval_samples_per_second": 6.742,
      "eval_steps_per_second": 6.742,
      "step": 20
    },
    {
      "epoch": 1.1121495327102804,
      "eval_accuracy": 0.6226415094339622,
      "eval_loss": 0.677739679813385,
      "eval_runtime": 8.3022,
      "eval_samples_per_second": 6.384,
      "eval_steps_per_second": 6.384,
      "step": 30
    },
    {
      "epoch": 1.485981308411215,
      "eval_accuracy": 0.6226415094339622,
      "eval_loss": 0.6453462243080139,
      "eval_runtime": 8.0938,
      "eval_samples_per_second": 6.548,
      "eval_steps_per_second": 6.548,
      "step": 40
    },
    {
      "epoch": 1.8598130841121496,
      "eval_accuracy": 0.6226415094339622,
      "eval_loss": 0.6518319845199585,
      "eval_runtime": 8.0342,
      "eval_samples_per_second": 6.597,
      "eval_steps_per_second": 6.597,
      "step": 50
    },
    {
      "epoch": 2.2242990654205608,
      "eval_accuracy": 0.6226415094339622,
      "eval_loss": 0.643576979637146,
      "eval_runtime": 7.9454,
      "eval_samples_per_second": 6.67,
      "eval_steps_per_second": 6.67,
      "step": 60
    },
    {
      "epoch": 2.5981308411214954,
      "eval_accuracy": 0.6226415094339622,
      "eval_loss": 0.6438348293304443,
      "eval_runtime": 7.991,
      "eval_samples_per_second": 6.632,
      "eval_steps_per_second": 6.632,
      "step": 70
    },
    {
      "epoch": 2.97196261682243,
      "eval_accuracy": 0.6226415094339622,
      "eval_loss": 0.6433556079864502,
      "eval_runtime": 8.1158,
      "eval_samples_per_second": 6.53,
      "eval_steps_per_second": 6.53,
      "step": 80
    },
    {
      "epoch": 3.336448598130841,
      "eval_accuracy": 0.6226415094339622,
      "eval_loss": 0.6432814598083496,
      "eval_runtime": 8.0097,
      "eval_samples_per_second": 6.617,
      "eval_steps_per_second": 6.617,
      "step": 90
    },
    {
      "epoch": 3.710280373831776,
      "eval_accuracy": 0.6226415094339622,
      "eval_loss": 0.6522361040115356,
      "eval_runtime": 7.9727,
      "eval_samples_per_second": 6.648,
      "eval_steps_per_second": 6.648,
      "step": 100
    },
    {
      "epoch": 4.074766355140187,
      "eval_accuracy": 0.6226415094339622,
      "eval_loss": 0.6425078511238098,
      "eval_runtime": 8.0939,
      "eval_samples_per_second": 6.548,
      "eval_steps_per_second": 6.548,
      "step": 110
    },
    {
      "epoch": 4.4485981308411215,
      "eval_accuracy": 0.6226415094339622,
      "eval_loss": 0.5939860939979553,
      "eval_runtime": 8.075,
      "eval_samples_per_second": 6.563,
      "eval_steps_per_second": 6.563,
      "step": 120
    },
    {
      "epoch": 4.822429906542056,
      "eval_accuracy": 0.8301886792452831,
      "eval_loss": 0.5158368945121765,
      "eval_runtime": 7.9094,
      "eval_samples_per_second": 6.701,
      "eval_steps_per_second": 6.701,
      "step": 130
    },
    {
      "epoch": 5.186915887850467,
      "eval_accuracy": 0.6792452830188679,
      "eval_loss": 2.4835591316223145,
      "eval_runtime": 7.9712,
      "eval_samples_per_second": 6.649,
      "eval_steps_per_second": 6.649,
      "step": 140
    },
    {
      "epoch": 5.5607476635514015,
      "eval_accuracy": 0.8679245283018868,
      "eval_loss": 0.4775002598762512,
      "eval_runtime": 8.0391,
      "eval_samples_per_second": 6.593,
      "eval_steps_per_second": 6.593,
      "step": 150
    },
    {
      "epoch": 5.934579439252336,
      "eval_accuracy": 0.7169811320754716,
      "eval_loss": 0.9641516208648682,
      "eval_runtime": 7.8863,
      "eval_samples_per_second": 6.72,
      "eval_steps_per_second": 6.72,
      "step": 160
    },
    {
      "epoch": 6.299065420560748,
      "eval_accuracy": 0.8490566037735849,
      "eval_loss": 0.560844361782074,
      "eval_runtime": 7.7803,
      "eval_samples_per_second": 6.812,
      "eval_steps_per_second": 6.812,
      "step": 170
    },
    {
      "epoch": 6.672897196261682,
      "eval_accuracy": 0.7924528301886793,
      "eval_loss": 0.6886337995529175,
      "eval_runtime": 7.7771,
      "eval_samples_per_second": 6.815,
      "eval_steps_per_second": 6.815,
      "step": 180
    },
    {
      "epoch": 7.037383177570093,
      "eval_accuracy": 0.9433962264150944,
      "eval_loss": 0.24409902095794678,
      "eval_runtime": 7.8505,
      "eval_samples_per_second": 6.751,
      "eval_steps_per_second": 6.751,
      "step": 190
    }
  ],
  "logging_steps": 500,
  "max_steps": 2600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 100,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.902763621994496e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}