{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.043769662152920254,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002188483107646013,
      "grad_norm": 130.20263671875,
      "learning_rate": 1e-05,
      "loss": 66.2306,
      "step": 1
    },
    {
      "epoch": 0.002188483107646013,
      "eval_loss": 4.2193779945373535,
      "eval_runtime": 159.7973,
      "eval_samples_per_second": 4.819,
      "eval_steps_per_second": 2.409,
      "step": 1
    },
    {
      "epoch": 0.004376966215292026,
      "grad_norm": 135.54823303222656,
      "learning_rate": 2e-05,
      "loss": 62.8564,
      "step": 2
    },
    {
      "epoch": 0.006565449322938038,
      "grad_norm": 199.6575164794922,
      "learning_rate": 3e-05,
      "loss": 81.161,
      "step": 3
    },
    {
      "epoch": 0.008753932430584052,
      "grad_norm": 124.79432678222656,
      "learning_rate": 4e-05,
      "loss": 54.0789,
      "step": 4
    },
    {
      "epoch": 0.010942415538230063,
      "grad_norm": 124.08785247802734,
      "learning_rate": 5e-05,
      "loss": 62.7002,
      "step": 5
    },
    {
      "epoch": 0.010942415538230063,
      "eval_loss": 3.8745884895324707,
      "eval_runtime": 18.5266,
      "eval_samples_per_second": 41.562,
      "eval_steps_per_second": 20.781,
      "step": 5
    },
    {
      "epoch": 0.013130898645876077,
      "grad_norm": 216.4264373779297,
      "learning_rate": 6e-05,
      "loss": 66.0287,
      "step": 6
    },
    {
      "epoch": 0.01531938175352209,
      "grad_norm": 113.75241088867188,
      "learning_rate": 7e-05,
      "loss": 55.1702,
      "step": 7
    },
    {
      "epoch": 0.017507864861168104,
      "grad_norm": 123.24091339111328,
      "learning_rate": 8e-05,
      "loss": 55.7571,
      "step": 8
    },
    {
      "epoch": 0.019696347968814115,
      "grad_norm": 100.2707290649414,
      "learning_rate": 9e-05,
      "loss": 48.4649,
      "step": 9
    },
    {
      "epoch": 0.021884831076460127,
      "grad_norm": 110.84855651855469,
      "learning_rate": 0.0001,
      "loss": 45.9472,
      "step": 10
    },
    {
      "epoch": 0.021884831076460127,
      "eval_loss": 2.87365460395813,
      "eval_runtime": 18.5458,
      "eval_samples_per_second": 41.519,
      "eval_steps_per_second": 20.759,
      "step": 10
    },
    {
      "epoch": 0.024073314184106142,
      "grad_norm": 105.50072479248047,
      "learning_rate": 9.755282581475769e-05,
      "loss": 42.6006,
      "step": 11
    },
    {
      "epoch": 0.026261797291752154,
      "grad_norm": 92.7238998413086,
      "learning_rate": 9.045084971874738e-05,
      "loss": 44.6438,
      "step": 12
    },
    {
      "epoch": 0.02845028039939817,
      "grad_norm": 93.75603485107422,
      "learning_rate": 7.938926261462366e-05,
      "loss": 48.332,
      "step": 13
    },
    {
      "epoch": 0.03063876350704418,
      "grad_norm": 81.0333023071289,
      "learning_rate": 6.545084971874738e-05,
      "loss": 41.1181,
      "step": 14
    },
    {
      "epoch": 0.03282724661469019,
      "grad_norm": 87.53114318847656,
      "learning_rate": 5e-05,
      "loss": 44.1653,
      "step": 15
    },
    {
      "epoch": 0.03282724661469019,
      "eval_loss": 2.6141836643218994,
      "eval_runtime": 18.5532,
      "eval_samples_per_second": 41.502,
      "eval_steps_per_second": 20.751,
      "step": 15
    },
    {
      "epoch": 0.03501572972233621,
      "grad_norm": 102.71365356445312,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 41.4068,
      "step": 16
    },
    {
      "epoch": 0.037204212829982215,
      "grad_norm": 106.65156555175781,
      "learning_rate": 2.061073738537635e-05,
      "loss": 42.4503,
      "step": 17
    },
    {
      "epoch": 0.03939269593762823,
      "grad_norm": 100.37320709228516,
      "learning_rate": 9.549150281252633e-06,
      "loss": 40.8951,
      "step": 18
    },
    {
      "epoch": 0.041581179045274246,
      "grad_norm": 89.86517333984375,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 41.3933,
      "step": 19
    },
    {
      "epoch": 0.043769662152920254,
      "grad_norm": 79.76675415039062,
      "learning_rate": 0.0,
      "loss": 43.4802,
      "step": 20
    },
    {
      "epoch": 0.043769662152920254,
      "eval_loss": 2.5566649436950684,
      "eval_runtime": 18.5439,
      "eval_samples_per_second": 41.523,
      "eval_steps_per_second": 20.762,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4853884967124992e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}