{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 3084,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19455252918287938,
      "grad_norm": 5.050010681152344,
      "learning_rate": 1.926070038910506e-05,
      "loss": 8.5926,
      "step": 100
    },
    {
      "epoch": 0.38910505836575876,
      "grad_norm": 1.6030714511871338,
      "learning_rate": 3.8715953307393e-05,
      "loss": 6.6577,
      "step": 200
    },
    {
      "epoch": 0.5836575875486382,
      "grad_norm": 1.002219557762146,
      "learning_rate": 5.8171206225680944e-05,
      "loss": 5.4884,
      "step": 300
    },
    {
      "epoch": 0.7782101167315175,
      "grad_norm": 1.1130906343460083,
      "learning_rate": 7.762645914396888e-05,
      "loss": 5.1208,
      "step": 400
    },
    {
      "epoch": 0.9727626459143969,
      "grad_norm": 1.2561383247375488,
      "learning_rate": 9.708171206225682e-05,
      "loss": 5.0439,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_loss": 4.548050403594971,
      "eval_runtime": 0.386,
      "eval_samples_per_second": 593.336,
      "eval_steps_per_second": 75.139,
      "step": 514
    },
    {
      "epoch": 1.1673151750972763,
      "grad_norm": 1.0363208055496216,
      "learning_rate": 9.816255944660613e-05,
      "loss": 4.8297,
      "step": 600
    },
    {
      "epoch": 1.3618677042801557,
      "grad_norm": 1.2391234636306763,
      "learning_rate": 9.600086467790748e-05,
      "loss": 4.6257,
      "step": 700
    },
    {
      "epoch": 1.556420233463035,
      "grad_norm": 1.268858551979065,
      "learning_rate": 9.383916990920882e-05,
      "loss": 4.5661,
      "step": 800
    },
    {
      "epoch": 1.7509727626459144,
      "grad_norm": 1.4311838150024414,
      "learning_rate": 9.167747514051016e-05,
      "loss": 4.5078,
      "step": 900
    },
    {
      "epoch": 1.9455252918287937,
      "grad_norm": 1.9428343772888184,
      "learning_rate": 8.951578037181151e-05,
      "loss": 4.4511,
      "step": 1000
    },
    {
      "epoch": 2.0,
      "eval_loss": 4.148034572601318,
      "eval_runtime": 0.3881,
      "eval_samples_per_second": 590.008,
      "eval_steps_per_second": 74.717,
      "step": 1028
    },
    {
      "epoch": 2.140077821011673,
      "grad_norm": 1.367798924446106,
      "learning_rate": 8.735408560311285e-05,
      "loss": 4.2833,
      "step": 1100
    },
    {
      "epoch": 2.3346303501945527,
      "grad_norm": 1.3669586181640625,
      "learning_rate": 8.519239083441418e-05,
      "loss": 4.4121,
      "step": 1200
    },
    {
      "epoch": 2.529182879377432,
      "grad_norm": 1.2630293369293213,
      "learning_rate": 8.303069606571553e-05,
      "loss": 4.189,
      "step": 1300
    },
    {
      "epoch": 2.7237354085603114,
      "grad_norm": 1.7325519323349,
      "learning_rate": 8.086900129701687e-05,
      "loss": 4.2001,
      "step": 1400
    },
    {
      "epoch": 2.9182879377431905,
      "grad_norm": 1.5118368864059448,
      "learning_rate": 7.870730652831821e-05,
      "loss": 4.1732,
      "step": 1500
    },
    {
      "epoch": 3.0,
      "eval_loss": 3.9841933250427246,
      "eval_runtime": 0.3918,
      "eval_samples_per_second": 584.494,
      "eval_steps_per_second": 74.019,
      "step": 1542
    },
    {
      "epoch": 3.11284046692607,
      "grad_norm": 1.5012787580490112,
      "learning_rate": 7.654561175961954e-05,
      "loss": 4.236,
      "step": 1600
    },
    {
      "epoch": 3.307392996108949,
      "grad_norm": 1.6979159116744995,
      "learning_rate": 7.438391699092088e-05,
      "loss": 4.0165,
      "step": 1700
    },
    {
      "epoch": 3.501945525291829,
      "grad_norm": 2.076409339904785,
      "learning_rate": 7.222222222222222e-05,
      "loss": 4.0474,
      "step": 1800
    },
    {
      "epoch": 3.6964980544747084,
      "grad_norm": 1.3077492713928223,
      "learning_rate": 7.006052745352356e-05,
      "loss": 3.9559,
      "step": 1900
    },
    {
      "epoch": 3.8910505836575875,
      "grad_norm": 1.3804798126220703,
      "learning_rate": 6.78988326848249e-05,
      "loss": 4.0048,
      "step": 2000
    },
    {
      "epoch": 4.0,
      "eval_loss": 3.8890349864959717,
      "eval_runtime": 0.3928,
      "eval_samples_per_second": 583.009,
      "eval_steps_per_second": 73.831,
      "step": 2056
    },
    {
      "epoch": 4.085603112840467,
      "grad_norm": 1.4003207683563232,
      "learning_rate": 6.573713791612624e-05,
      "loss": 3.9389,
      "step": 2100
    },
    {
      "epoch": 4.280155642023346,
      "grad_norm": 1.5252618789672852,
      "learning_rate": 6.357544314742758e-05,
      "loss": 3.7979,
      "step": 2200
    },
    {
      "epoch": 4.474708171206226,
      "grad_norm": 1.5208264589309692,
      "learning_rate": 6.141374837872893e-05,
      "loss": 3.9687,
      "step": 2300
    },
    {
      "epoch": 4.669260700389105,
      "grad_norm": 1.471234679222107,
      "learning_rate": 5.925205361003027e-05,
      "loss": 3.8509,
      "step": 2400
    },
    {
      "epoch": 4.863813229571985,
      "grad_norm": 1.653549313545227,
      "learning_rate": 5.7090358841331606e-05,
      "loss": 3.8276,
      "step": 2500
    },
    {
      "epoch": 5.0,
      "eval_loss": 3.829970359802246,
      "eval_runtime": 0.3885,
      "eval_samples_per_second": 589.446,
      "eval_steps_per_second": 74.646,
      "step": 2570
    },
    {
      "epoch": 5.058365758754864,
      "grad_norm": 1.6126755475997925,
      "learning_rate": 5.492866407263295e-05,
      "loss": 3.9095,
      "step": 2600
    },
    {
      "epoch": 5.252918287937743,
      "grad_norm": 1.7814581394195557,
      "learning_rate": 5.2766969303934287e-05,
      "loss": 3.7747,
      "step": 2700
    },
    {
      "epoch": 5.447470817120623,
      "grad_norm": 1.5165146589279175,
      "learning_rate": 5.0605274535235624e-05,
      "loss": 3.6927,
      "step": 2800
    },
    {
      "epoch": 5.642023346303502,
      "grad_norm": 1.8930598497390747,
      "learning_rate": 4.844357976653697e-05,
      "loss": 3.7231,
      "step": 2900
    },
    {
      "epoch": 5.836575875486381,
      "grad_norm": 1.8033453226089478,
      "learning_rate": 4.628188499783831e-05,
      "loss": 3.7334,
      "step": 3000
    },
    {
      "epoch": 6.0,
      "eval_loss": 3.7915844917297363,
      "eval_runtime": 0.3882,
      "eval_samples_per_second": 589.903,
      "eval_steps_per_second": 74.704,
      "step": 3084
    }
  ],
  "logging_steps": 100,
  "max_steps": 5140,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 462648759828480.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}