{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.936936936936937,
  "eval_steps": 500,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 110.8848,
      "step": 1
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.377,
      "step": 2
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 110.6699,
      "step": 3
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.3672,
      "step": 4
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 110.9941,
      "step": 5
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.1211,
      "step": 6
    },
    {
      "epoch": 0.5045045045045045,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.4082,
      "step": 7
    },
    {
      "epoch": 0.5765765765765766,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.418,
      "step": 8
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 110.4473,
      "step": 9
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.0137,
      "step": 10
    },
    {
      "epoch": 0.7927927927927928,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.3359,
      "step": 11
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.1465,
      "step": 12
    },
    {
      "epoch": 0.9369369369369369,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 110.6699,
      "step": 13
    },
    {
      "epoch": 1.072072072072072,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 138.8008,
      "step": 14
    },
    {
      "epoch": 1.1441441441441442,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.1465,
      "step": 15
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 110.8516,
      "step": 16
    },
    {
      "epoch": 1.2882882882882882,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.6328,
      "step": 17
    },
    {
      "epoch": 1.3603603603603602,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 111.127,
      "step": 18
    },
    {
      "epoch": 1.4324324324324325,
      "grad_norm": 123.0553207397461,
      "learning_rate": 0.0001,
      "loss": 111.041,
      "step": 19
    },
    {
      "epoch": 1.5045045045045045,
      "grad_norm": 121.99684143066406,
      "learning_rate": 9.96057350657239e-05,
      "loss": 92.9346,
      "step": 20
    },
    {
      "epoch": 1.5765765765765765,
      "grad_norm": 44.45335006713867,
      "learning_rate": 9.842915805643155e-05,
      "loss": 36.5908,
      "step": 21
    },
    {
      "epoch": 1.6486486486486487,
      "grad_norm": 44.45335006713867,
      "learning_rate": 9.842915805643155e-05,
      "loss": 26.5054,
      "step": 22
    },
    {
      "epoch": 1.7207207207207207,
      "grad_norm": 44.45335006713867,
      "learning_rate": 9.842915805643155e-05,
      "loss": 26.6528,
      "step": 23
    },
    {
      "epoch": 1.7927927927927927,
      "grad_norm": 71.70808410644531,
      "learning_rate": 9.648882429441257e-05,
      "loss": 25.5659,
      "step": 24
    },
    {
      "epoch": 1.864864864864865,
      "grad_norm": 45.514339447021484,
      "learning_rate": 9.381533400219318e-05,
      "loss": 25.1484,
      "step": 25
    },
    {
      "epoch": 1.936936936936937,
      "grad_norm": 45.514339447021484,
      "learning_rate": 9.381533400219318e-05,
      "loss": 31.6045,
      "step": 26
    },
    {
      "epoch": 1.936936936936937,
      "step": 26,
      "total_flos": 3.909058176221184e+16,
      "train_loss": 92.4405987079327,
      "train_runtime": 5129.5954,
      "train_samples_per_second": 0.344,
      "train_steps_per_second": 0.005
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 26,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.909058176221184e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}