{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.038427167113494,
  "eval_steps": 200,
  "global_step": 3400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17873100983020554,
      "grad_norm": 0.8090553879737854,
      "learning_rate": 9.999142157322298e-05,
      "loss": 0.5369,
      "step": 200
    },
    {
      "epoch": 0.17873100983020554,
      "eval_loss": 0.18719753623008728,
      "eval_runtime": 42.7752,
      "eval_samples_per_second": 4.231,
      "eval_steps_per_second": 2.127,
      "step": 200
    },
    {
      "epoch": 0.3574620196604111,
      "grad_norm": 0.41231265664100647,
      "learning_rate": 9.95497608932715e-05,
      "loss": 0.1347,
      "step": 400
    },
    {
      "epoch": 0.3574620196604111,
      "eval_loss": 0.1247013583779335,
      "eval_runtime": 42.7006,
      "eval_samples_per_second": 4.239,
      "eval_steps_per_second": 2.131,
      "step": 400
    },
    {
      "epoch": 0.5361930294906166,
      "grad_norm": 0.23166905343532562,
      "learning_rate": 9.844466810070319e-05,
      "loss": 0.1059,
      "step": 600
    },
    {
      "epoch": 0.5361930294906166,
      "eval_loss": 0.1143762394785881,
      "eval_runtime": 42.7658,
      "eval_samples_per_second": 4.232,
      "eval_steps_per_second": 2.128,
      "step": 600
    },
    {
      "epoch": 0.7149240393208222,
      "grad_norm": 0.2017158418893814,
      "learning_rate": 9.669093951406317e-05,
      "loss": 0.0996,
      "step": 800
    },
    {
      "epoch": 0.7149240393208222,
      "eval_loss": 0.1081576719880104,
      "eval_runtime": 42.705,
      "eval_samples_per_second": 4.238,
      "eval_steps_per_second": 2.131,
      "step": 800
    },
    {
      "epoch": 0.8936550491510277,
      "grad_norm": 0.1813146024942398,
      "learning_rate": 9.431205617221452e-05,
      "loss": 0.0946,
      "step": 1000
    },
    {
      "epoch": 0.8936550491510277,
      "eval_loss": 0.10373637080192566,
      "eval_runtime": 43.753,
      "eval_samples_per_second": 4.137,
      "eval_steps_per_second": 2.08,
      "step": 1000
    },
    {
      "epoch": 1.0723860589812333,
      "grad_norm": 0.2062540054321289,
      "learning_rate": 9.133986944179754e-05,
      "loss": 0.0893,
      "step": 1200
    },
    {
      "epoch": 1.0723860589812333,
      "eval_loss": 0.10310747474431992,
      "eval_runtime": 43.7372,
      "eval_samples_per_second": 4.138,
      "eval_steps_per_second": 2.081,
      "step": 1200
    },
    {
      "epoch": 1.2511170688114388,
      "grad_norm": 0.16564616560935974,
      "learning_rate": 8.781417455261971e-05,
      "loss": 0.0797,
      "step": 1400
    },
    {
      "epoch": 1.2511170688114388,
      "eval_loss": 0.09981610625982285,
      "eval_runtime": 43.6375,
      "eval_samples_per_second": 4.148,
      "eval_steps_per_second": 2.085,
      "step": 1400
    },
    {
      "epoch": 1.4298480786416443,
      "grad_norm": 0.16782471537590027,
      "learning_rate": 8.378217777099999e-05,
      "loss": 0.0781,
      "step": 1600
    },
    {
      "epoch": 1.4298480786416443,
      "eval_loss": 0.09819332510232925,
      "eval_runtime": 43.6747,
      "eval_samples_per_second": 4.144,
      "eval_steps_per_second": 2.084,
      "step": 1600
    },
    {
      "epoch": 1.6085790884718498,
      "grad_norm": 0.11610674858093262,
      "learning_rate": 7.929786434519532e-05,
      "loss": 0.0778,
      "step": 1800
    },
    {
      "epoch": 1.6085790884718498,
      "eval_loss": 0.09649965912103653,
      "eval_runtime": 44.4289,
      "eval_samples_per_second": 4.074,
      "eval_steps_per_second": 2.048,
      "step": 1800
    },
    {
      "epoch": 1.7873100983020556,
      "grad_norm": 0.18362917006015778,
      "learning_rate": 7.442127568561985e-05,
      "loss": 0.0763,
      "step": 2000
    },
    {
      "epoch": 1.7873100983020556,
      "eval_loss": 0.09756463766098022,
      "eval_runtime": 44.3378,
      "eval_samples_per_second": 4.082,
      "eval_steps_per_second": 2.052,
      "step": 2000
    },
    {
      "epoch": 1.966041108132261,
      "grad_norm": 0.19114775955677032,
      "learning_rate": 6.921770545784254e-05,
      "loss": 0.0769,
      "step": 2200
    },
    {
      "epoch": 1.966041108132261,
      "eval_loss": 0.09357864409685135,
      "eval_runtime": 44.4008,
      "eval_samples_per_second": 4.077,
      "eval_steps_per_second": 2.05,
      "step": 2200
    },
    {
      "epoch": 2.1447721179624666,
      "grad_norm": 0.13772954046726227,
      "learning_rate": 6.375682535204167e-05,
      "loss": 0.0643,
      "step": 2400
    },
    {
      "epoch": 2.1447721179624666,
      "eval_loss": 0.09684193134307861,
      "eval_runtime": 44.3802,
      "eval_samples_per_second": 4.078,
      "eval_steps_per_second": 2.05,
      "step": 2400
    },
    {
      "epoch": 2.323503127792672,
      "grad_norm": 0.2045222818851471,
      "learning_rate": 5.81117522341723e-05,
      "loss": 0.0625,
      "step": 2600
    },
    {
      "epoch": 2.323503127792672,
      "eval_loss": 0.09473162144422531,
      "eval_runtime": 42.1741,
      "eval_samples_per_second": 4.292,
      "eval_steps_per_second": 2.158,
      "step": 2600
    },
    {
      "epoch": 2.5022341376228776,
      "grad_norm": 0.14082834124565125,
      "learning_rate": 5.2358069168954583e-05,
      "loss": 0.0623,
      "step": 2800
    },
    {
      "epoch": 2.5022341376228776,
      "eval_loss": 0.09577099233865738,
      "eval_runtime": 42.2132,
      "eval_samples_per_second": 4.288,
      "eval_steps_per_second": 2.156,
      "step": 2800
    },
    {
      "epoch": 2.680965147453083,
      "grad_norm": 0.11483576148748398,
      "learning_rate": 4.657281342241101e-05,
      "loss": 0.0614,
      "step": 3000
    },
    {
      "epoch": 2.680965147453083,
      "eval_loss": 0.09490402787923813,
      "eval_runtime": 42.1999,
      "eval_samples_per_second": 4.289,
      "eval_steps_per_second": 2.156,
      "step": 3000
    },
    {
      "epoch": 2.8596961572832886,
      "grad_norm": 0.20240356028079987,
      "learning_rate": 4.083344499379815e-05,
      "loss": 0.0615,
      "step": 3200
    },
    {
      "epoch": 2.8596961572832886,
      "eval_loss": 0.09255937486886978,
      "eval_runtime": 42.1787,
      "eval_samples_per_second": 4.291,
      "eval_steps_per_second": 2.157,
      "step": 3200
    },
    {
      "epoch": 3.038427167113494,
      "grad_norm": 0.1670568436384201,
      "learning_rate": 3.521680948747494e-05,
      "loss": 0.0583,
      "step": 3400
    },
    {
      "epoch": 3.038427167113494,
      "eval_loss": 0.09762674570083618,
      "eval_runtime": 42.2338,
      "eval_samples_per_second": 4.286,
      "eval_steps_per_second": 2.155,
      "step": 3400
    }
  ],
  "logging_steps": 200,
  "max_steps": 5595,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.8663461756174336e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}