{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14519056261343014,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014519056261343012,
      "eval_loss": 5.956166744232178,
      "eval_runtime": 10.0522,
      "eval_samples_per_second": 28.849,
      "eval_steps_per_second": 14.425,
      "step": 1
    },
    {
      "epoch": 0.014519056261343012,
      "grad_norm": 1.2935727834701538,
      "learning_rate": 0.00019967573081342103,
      "loss": 5.8948,
      "step": 10
    },
    {
      "epoch": 0.029038112522686024,
      "grad_norm": 0.9941825270652771,
      "learning_rate": 0.0001970941817426052,
      "loss": 5.9223,
      "step": 20
    },
    {
      "epoch": 0.043557168784029036,
      "grad_norm": 1.121877908706665,
      "learning_rate": 0.00019199794436588243,
      "loss": 5.027,
      "step": 30
    },
    {
      "epoch": 0.05807622504537205,
      "grad_norm": 1.5708129405975342,
      "learning_rate": 0.0001845190085543795,
      "loss": 5.5017,
      "step": 40
    },
    {
      "epoch": 0.07259528130671507,
      "grad_norm": 1.9266424179077148,
      "learning_rate": 0.00017485107481711012,
      "loss": 5.2512,
      "step": 50
    },
    {
      "epoch": 0.07259528130671507,
      "eval_loss": 4.811445236206055,
      "eval_runtime": 9.4627,
      "eval_samples_per_second": 30.647,
      "eval_steps_per_second": 15.323,
      "step": 50
    },
    {
      "epoch": 0.08711433756805807,
      "grad_norm": 3.0178332328796387,
      "learning_rate": 0.00016324453755953773,
      "loss": 5.0281,
      "step": 60
    },
    {
      "epoch": 0.10163339382940109,
      "grad_norm": 5.907054901123047,
      "learning_rate": 0.00015000000000000001,
      "loss": 4.7945,
      "step": 70
    },
    {
      "epoch": 0.1161524500907441,
      "grad_norm": 4.798269748687744,
      "learning_rate": 0.00013546048870425356,
      "loss": 3.874,
      "step": 80
    },
    {
      "epoch": 0.1306715063520871,
      "grad_norm": 6.5533576011657715,
      "learning_rate": 0.00012000256937760445,
      "loss": 3.6984,
      "step": 90
    },
    {
      "epoch": 0.14519056261343014,
      "grad_norm": 4.253799915313721,
      "learning_rate": 0.00010402659401094152,
      "loss": 3.6303,
      "step": 100
    },
    {
      "epoch": 0.14519056261343014,
      "eval_loss": 3.2204811573028564,
      "eval_runtime": 9.459,
      "eval_samples_per_second": 30.659,
      "eval_steps_per_second": 15.329,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.84956424814592e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}