{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.935483870967742,
  "eval_steps": 500,
  "global_step": 138,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.43010752688172044,
      "grad_norm": 2.765007972717285,
      "learning_rate": 1.785714285714286e-05,
      "loss": 3.3581,
      "step": 10
    },
    {
      "epoch": 0.8602150537634409,
      "grad_norm": 1.702070713043213,
      "learning_rate": 3.571428571428572e-05,
      "loss": 1.5448,
      "step": 20
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 1.2462737560272217,
      "learning_rate": 4.995922759815339e-05,
      "loss": 0.8959,
      "step": 30
    },
    {
      "epoch": 1.7204301075268817,
      "grad_norm": 0.8611997365951538,
      "learning_rate": 4.854610909098812e-05,
      "loss": 0.7328,
      "step": 40
    },
    {
      "epoch": 2.150537634408602,
      "grad_norm": 0.799420177936554,
      "learning_rate": 4.522542485937369e-05,
      "loss": 0.5115,
      "step": 50
    },
    {
      "epoch": 2.5806451612903225,
      "grad_norm": 1.2618942260742188,
      "learning_rate": 4.0266196990885955e-05,
      "loss": 0.326,
      "step": 60
    },
    {
      "epoch": 3.010752688172043,
      "grad_norm": 0.8298829197883606,
      "learning_rate": 3.4070192633766025e-05,
      "loss": 0.3035,
      "step": 70
    },
    {
      "epoch": 3.4408602150537635,
      "grad_norm": 1.2379834651947021,
      "learning_rate": 2.7139375211970996e-05,
      "loss": 0.1585,
      "step": 80
    },
    {
      "epoch": 3.870967741935484,
      "grad_norm": 0.8900007009506226,
      "learning_rate": 2.003523833385637e-05,
      "loss": 0.1343,
      "step": 90
    },
    {
      "epoch": 4.301075268817204,
      "grad_norm": 0.3209846019744873,
      "learning_rate": 1.3333316919358157e-05,
      "loss": 0.0785,
      "step": 100
    },
    {
      "epoch": 4.731182795698925,
      "grad_norm": 0.6245219111442566,
      "learning_rate": 7.576560783617668e-06,
      "loss": 0.0657,
      "step": 110
    },
    {
      "epoch": 5.161290322580645,
      "grad_norm": 0.9348724484443665,
      "learning_rate": 3.2313480720055745e-06,
      "loss": 0.0631,
      "step": 120
    },
    {
      "epoch": 5.591397849462366,
      "grad_norm": 0.2755952775478363,
      "learning_rate": 6.497020764416633e-07,
      "loss": 0.0341,
      "step": 130
    },
    {
      "epoch": 5.935483870967742,
      "step": 138,
      "total_flos": 3871080172486656.0,
      "train_loss": 0.597086531744487,
      "train_runtime": 849.7455,
      "train_samples_per_second": 1.313,
      "train_steps_per_second": 0.162
    }
  ],
  "logging_steps": 10,
  "max_steps": 138,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3871080172486656.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}