{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8324661810613944,
  "eval_steps": 25,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002081165452653486,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 1.1218,
      "step": 1
    },
    {
      "epoch": 0.05202913631633715,
      "grad_norm": 112.7115707397461,
      "learning_rate": 1.4201183431952663e-07,
      "loss": 1.0823,
      "step": 25
    },
    {
      "epoch": 0.05202913631633715,
      "eval_loss": 0.7267751097679138,
      "eval_runtime": 17.4992,
      "eval_samples_per_second": 51.374,
      "eval_steps_per_second": 12.858,
      "step": 25
    },
    {
      "epoch": 0.1040582726326743,
      "grad_norm": 58.33771514892578,
      "learning_rate": 2.8994082840236686e-07,
      "loss": 0.8661,
      "step": 50
    },
    {
      "epoch": 0.1040582726326743,
      "eval_loss": 0.6249979734420776,
      "eval_runtime": 17.7916,
      "eval_samples_per_second": 50.529,
      "eval_steps_per_second": 12.646,
      "step": 50
    },
    {
      "epoch": 0.15608740894901144,
      "grad_norm": 141.5440673828125,
      "learning_rate": 4.378698224852071e-07,
      "loss": 0.7323,
      "step": 75
    },
    {
      "epoch": 0.15608740894901144,
      "eval_loss": 0.5851046442985535,
      "eval_runtime": 17.459,
      "eval_samples_per_second": 51.492,
      "eval_steps_per_second": 12.887,
      "step": 75
    },
    {
      "epoch": 0.2081165452653486,
      "grad_norm": 123.83263397216797,
      "learning_rate": 5.857988165680473e-07,
      "loss": 0.5271,
      "step": 100
    },
    {
      "epoch": 0.2081165452653486,
      "eval_loss": 0.605644702911377,
      "eval_runtime": 17.4819,
      "eval_samples_per_second": 51.425,
      "eval_steps_per_second": 12.87,
      "step": 100
    },
    {
      "epoch": 0.2601456815816857,
      "grad_norm": 48.97358703613281,
      "learning_rate": 7.337278106508875e-07,
      "loss": 0.5311,
      "step": 125
    },
    {
      "epoch": 0.2601456815816857,
      "eval_loss": 0.5933497548103333,
      "eval_runtime": 17.4087,
      "eval_samples_per_second": 51.641,
      "eval_steps_per_second": 12.925,
      "step": 125
    },
    {
      "epoch": 0.31217481789802287,
      "grad_norm": 113.67745208740234,
      "learning_rate": 8.816568047337278e-07,
      "loss": 0.5233,
      "step": 150
    },
    {
      "epoch": 0.31217481789802287,
      "eval_loss": 0.6305265426635742,
      "eval_runtime": 17.4649,
      "eval_samples_per_second": 51.475,
      "eval_steps_per_second": 12.883,
      "step": 150
    },
    {
      "epoch": 0.36420395421436,
      "grad_norm": 158.48524475097656,
      "learning_rate": 9.999019112527836e-07,
      "loss": 0.5819,
      "step": 175
    },
    {
      "epoch": 0.36420395421436,
      "eval_loss": 0.6344813108444214,
      "eval_runtime": 17.558,
      "eval_samples_per_second": 51.202,
      "eval_steps_per_second": 12.815,
      "step": 175
    },
    {
      "epoch": 0.4162330905306972,
      "grad_norm": 65.56009674072266,
      "learning_rate": 9.9647284439831e-07,
      "loss": 0.7013,
      "step": 200
    },
    {
      "epoch": 0.4162330905306972,
      "eval_loss": 0.5766075253486633,
      "eval_runtime": 17.4518,
      "eval_samples_per_second": 51.513,
      "eval_steps_per_second": 12.893,
      "step": 200
    },
    {
      "epoch": 0.46826222684703434,
      "grad_norm": 59.14521789550781,
      "learning_rate": 9.881777579730005e-07,
      "loss": 0.6697,
      "step": 225
    },
    {
      "epoch": 0.46826222684703434,
      "eval_loss": 0.5534063577651978,
      "eval_runtime": 17.4744,
      "eval_samples_per_second": 51.447,
      "eval_steps_per_second": 12.876,
      "step": 225
    },
    {
      "epoch": 0.5202913631633714,
      "grad_norm": 29.80727195739746,
      "learning_rate": 9.750979536096495e-07,
      "loss": 0.5794,
      "step": 250
    },
    {
      "epoch": 0.5202913631633714,
      "eval_loss": 0.5618265867233276,
      "eval_runtime": 17.4679,
      "eval_samples_per_second": 51.466,
      "eval_steps_per_second": 12.881,
      "step": 250
    },
    {
      "epoch": 0.5723204994797086,
      "grad_norm": 138.9149627685547,
      "learning_rate": 9.573616288214395e-07,
      "loss": 0.5292,
      "step": 275
    },
    {
      "epoch": 0.5723204994797086,
      "eval_loss": 0.621860682964325,
      "eval_runtime": 17.4394,
      "eval_samples_per_second": 51.55,
      "eval_steps_per_second": 12.902,
      "step": 275
    },
    {
      "epoch": 0.6243496357960457,
      "grad_norm": 67.80418395996094,
      "learning_rate": 9.351426205150776e-07,
      "loss": 0.704,
      "step": 300
    },
    {
      "epoch": 0.6243496357960457,
      "eval_loss": 0.5616322755813599,
      "eval_runtime": 17.4043,
      "eval_samples_per_second": 51.654,
      "eval_steps_per_second": 12.928,
      "step": 300
    },
    {
      "epoch": 0.676378772112383,
      "grad_norm": 126.93467712402344,
      "learning_rate": 9.086587011840308e-07,
      "loss": 0.5832,
      "step": 325
    },
    {
      "epoch": 0.676378772112383,
      "eval_loss": 0.5842172503471375,
      "eval_runtime": 17.3785,
      "eval_samples_per_second": 51.731,
      "eval_steps_per_second": 12.947,
      "step": 325
    },
    {
      "epoch": 0.72840790842872,
      "grad_norm": 173.32260131835938,
      "learning_rate": 8.781694444811812e-07,
      "loss": 0.5968,
      "step": 350
    },
    {
      "epoch": 0.72840790842872,
      "eval_loss": 0.5498592257499695,
      "eval_runtime": 17.3993,
      "eval_samples_per_second": 51.669,
      "eval_steps_per_second": 12.932,
      "step": 350
    },
    {
      "epoch": 0.7804370447450573,
      "grad_norm": 76.53514862060547,
      "learning_rate": 8.439736810908056e-07,
      "loss": 0.4945,
      "step": 375
    },
    {
      "epoch": 0.7804370447450573,
      "eval_loss": 0.5408959984779358,
      "eval_runtime": 17.4427,
      "eval_samples_per_second": 51.54,
      "eval_steps_per_second": 12.899,
      "step": 375
    },
    {
      "epoch": 0.8324661810613944,
      "grad_norm": 154.95327758789062,
      "learning_rate": 8.064065698353344e-07,
      "loss": 0.4931,
      "step": 400
    },
    {
      "epoch": 0.8324661810613944,
      "eval_loss": 0.5708575248718262,
      "eval_runtime": 17.4803,
      "eval_samples_per_second": 51.429,
      "eval_steps_per_second": 12.872,
      "step": 400
    }
  ],
  "logging_steps": 25,
  "max_steps": 962,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4329971279462400.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}