{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8022053756030324,
  "eval_steps": 291,
  "global_step": 1164,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06891798759476224,
      "grad_norm": 4.408621311187744,
      "learning_rate": 9.92330596776479e-06,
      "loss": 0.6326,
      "step": 100
    },
    {
      "epoch": 0.13783597518952448,
      "grad_norm": 5.029026985168457,
      "learning_rate": 9.62094968320582e-06,
      "loss": 0.5365,
      "step": 200
    },
    {
      "epoch": 0.2005513439007581,
      "eval_accuracy": 0.7271186845182692,
      "eval_loss": 0.5419921875,
      "eval_runtime": 641.9062,
      "eval_samples_per_second": 130.552,
      "eval_steps_per_second": 8.16,
      "step": 291
    },
    {
      "epoch": 0.2067539627842867,
      "grad_norm": 5.613715648651123,
      "learning_rate": 9.102819483545054e-06,
      "loss": 0.4928,
      "step": 300
    },
    {
      "epoch": 0.27567195037904896,
      "grad_norm": 5.0579833984375,
      "learning_rate": 8.39310930928775e-06,
      "loss": 0.4794,
      "step": 400
    },
    {
      "epoch": 0.34458993797381116,
      "grad_norm": 6.232191562652588,
      "learning_rate": 7.524958872697738e-06,
      "loss": 0.4521,
      "step": 500
    },
    {
      "epoch": 0.4011026878015162,
      "eval_accuracy": 0.7484546908188349,
      "eval_loss": 0.50341796875,
      "eval_runtime": 627.5856,
      "eval_samples_per_second": 133.531,
      "eval_steps_per_second": 8.346,
      "step": 582
    },
    {
      "epoch": 0.4135079255685734,
      "grad_norm": 6.169258117675781,
      "learning_rate": 6.5389062084740715e-06,
      "loss": 0.4361,
      "step": 600
    },
    {
      "epoch": 0.4824259131633356,
      "grad_norm": 6.576643466949463,
      "learning_rate": 5.4809947618915035e-06,
      "loss": 0.427,
      "step": 700
    },
    {
      "epoch": 0.5513439007580979,
      "grad_norm": 9.296501159667969,
      "learning_rate": 4.400623403379149e-06,
      "loss": 0.3994,
      "step": 800
    },
    {
      "epoch": 0.6016540317022743,
      "eval_accuracy": 0.7576788143481062,
      "eval_loss": 0.4892578125,
      "eval_runtime": 627.8256,
      "eval_samples_per_second": 133.48,
      "eval_steps_per_second": 8.343,
      "step": 873
    },
    {
      "epoch": 0.6202618883528601,
      "grad_norm": 7.580721378326416,
      "learning_rate": 3.3482397624875462e-06,
      "loss": 0.3907,
      "step": 900
    },
    {
      "epoch": 0.6891798759476223,
      "grad_norm": 7.101686477661133,
      "learning_rate": 2.3729845903505033e-06,
      "loss": 0.37,
      "step": 1000
    },
    {
      "epoch": 0.7580978635423845,
      "grad_norm": 7.940699577331543,
      "learning_rate": 1.5281793713805377e-06,
      "loss": 0.3596,
      "step": 1100
    },
    {
      "epoch": 0.8022053756030324,
      "eval_accuracy": 0.7692656499844872,
      "eval_loss": 0.468505859375,
      "eval_runtime": 628.1575,
      "eval_samples_per_second": 133.409,
      "eval_steps_per_second": 8.339,
      "step": 1164
    }
  ],
  "logging_steps": 100,
  "max_steps": 1451,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 291,
  "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": 4,
  "trial_name": null,
  "trial_params": null
}