{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.98876404494382,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.149812734082397,
      "grad_norm": 0.5950071811676025,
      "learning_rate": 0.00016363636363636366,
      "loss": 2.3793,
      "step": 10
    },
    {
      "epoch": 0.299625468164794,
      "grad_norm": 0.6472743153572083,
      "learning_rate": 0.00019912640693269752,
      "loss": 1.9763,
      "step": 20
    },
    {
      "epoch": 0.449438202247191,
      "grad_norm": 0.4513455033302307,
      "learning_rate": 0.00019560357815343577,
      "loss": 1.7276,
      "step": 30
    },
    {
      "epoch": 0.599250936329588,
      "grad_norm": 0.41116923093795776,
      "learning_rate": 0.00018947293298207635,
      "loss": 1.7337,
      "step": 40
    },
    {
      "epoch": 0.7490636704119851,
      "grad_norm": 0.516603410243988,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.5853,
      "step": 50
    },
    {
      "epoch": 0.7490636704119851,
      "eval_loss": 1.577757716178894,
      "eval_runtime": 8.4577,
      "eval_samples_per_second": 6.976,
      "eval_steps_per_second": 1.774,
      "step": 50
    },
    {
      "epoch": 0.898876404494382,
      "grad_norm": 0.534030556678772,
      "learning_rate": 0.00017012367842724887,
      "loss": 1.59,
      "step": 60
    },
    {
      "epoch": 1.0449438202247192,
      "grad_norm": 0.40544188022613525,
      "learning_rate": 0.00015743286626829437,
      "loss": 1.5288,
      "step": 70
    },
    {
      "epoch": 1.1947565543071161,
      "grad_norm": 0.5801761746406555,
      "learning_rate": 0.00014317543523384928,
      "loss": 1.4823,
      "step": 80
    },
    {
      "epoch": 1.344569288389513,
      "grad_norm": 0.5626828670501709,
      "learning_rate": 0.00012774029087618446,
      "loss": 1.4503,
      "step": 90
    },
    {
      "epoch": 1.49438202247191,
      "grad_norm": 0.6915966272354126,
      "learning_rate": 0.00011154846369695863,
      "loss": 1.4354,
      "step": 100
    },
    {
      "epoch": 1.49438202247191,
      "eval_loss": 1.5176668167114258,
      "eval_runtime": 7.8374,
      "eval_samples_per_second": 7.528,
      "eval_steps_per_second": 1.914,
      "step": 100
    },
    {
      "epoch": 1.6441947565543071,
      "grad_norm": 0.6429805159568787,
      "learning_rate": 9.504162453267777e-05,
      "loss": 1.4173,
      "step": 110
    },
    {
      "epoch": 1.7940074906367043,
      "grad_norm": 0.5912101864814758,
      "learning_rate": 7.867003692562534e-05,
      "loss": 1.3651,
      "step": 120
    },
    {
      "epoch": 1.9438202247191012,
      "grad_norm": 0.6238114237785339,
      "learning_rate": 6.28802751081779e-05,
      "loss": 1.4081,
      "step": 130
    },
    {
      "epoch": 2.0898876404494384,
      "grad_norm": 0.5546865463256836,
      "learning_rate": 4.810304262187852e-05,
      "loss": 1.3884,
      "step": 140
    },
    {
      "epoch": 2.2397003745318353,
      "grad_norm": 0.7205243110656738,
      "learning_rate": 3.4741423847583134e-05,
      "loss": 1.1613,
      "step": 150
    },
    {
      "epoch": 2.2397003745318353,
      "eval_loss": 1.5284953117370605,
      "eval_runtime": 7.895,
      "eval_samples_per_second": 7.473,
      "eval_steps_per_second": 1.9,
      "step": 150
    },
    {
      "epoch": 2.3895131086142323,
      "grad_norm": 0.7052301168441772,
      "learning_rate": 2.315988891431412e-05,
      "loss": 1.2287,
      "step": 160
    },
    {
      "epoch": 2.539325842696629,
      "grad_norm": 0.8039580583572388,
      "learning_rate": 1.3674351904242611e-05,
      "loss": 1.2225,
      "step": 170
    },
    {
      "epoch": 2.689138576779026,
      "grad_norm": 0.8460856080055237,
      "learning_rate": 6.543553540053926e-06,
      "loss": 1.2547,
      "step": 180
    },
    {
      "epoch": 2.8389513108614235,
      "grad_norm": 0.869657039642334,
      "learning_rate": 1.9620034125190644e-06,
      "loss": 1.1826,
      "step": 190
    },
    {
      "epoch": 2.98876404494382,
      "grad_norm": 0.7707263827323914,
      "learning_rate": 5.467426590739511e-08,
      "loss": 1.1658,
      "step": 200
    },
    {
      "epoch": 2.98876404494382,
      "eval_loss": 1.527919888496399,
      "eval_runtime": 7.7439,
      "eval_samples_per_second": 7.619,
      "eval_steps_per_second": 1.937,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 201,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 7623466959651840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}