{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8181818181818183,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01818181818181818,
      "eval_loss": 0.8232752680778503,
      "eval_runtime": 1.7017,
      "eval_samples_per_second": 54.651,
      "eval_steps_per_second": 7.052,
      "step": 1
    },
    {
      "epoch": 0.05454545454545454,
      "grad_norm": 1.0431333780288696,
      "learning_rate": 3e-05,
      "loss": 0.9096,
      "step": 3
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 1.381081461906433,
      "learning_rate": 6e-05,
      "loss": 0.7918,
      "step": 6
    },
    {
      "epoch": 0.16363636363636364,
      "grad_norm": 0.8481101393699646,
      "learning_rate": 9e-05,
      "loss": 0.699,
      "step": 9
    },
    {
      "epoch": 0.16363636363636364,
      "eval_loss": 0.5536388158798218,
      "eval_runtime": 1.6975,
      "eval_samples_per_second": 54.787,
      "eval_steps_per_second": 7.069,
      "step": 9
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 0.7306303977966309,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.5831,
      "step": 12
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.8772233128547668,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.4517,
      "step": 15
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 0.8330588936805725,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.463,
      "step": 18
    },
    {
      "epoch": 0.32727272727272727,
      "eval_loss": 0.37208396196365356,
      "eval_runtime": 1.7251,
      "eval_samples_per_second": 53.91,
      "eval_steps_per_second": 6.956,
      "step": 18
    },
    {
      "epoch": 0.38181818181818183,
      "grad_norm": 0.6052883863449097,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.4153,
      "step": 21
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.5696281790733337,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.398,
      "step": 24
    },
    {
      "epoch": 0.4909090909090909,
      "grad_norm": 0.5094695687294006,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.381,
      "step": 27
    },
    {
      "epoch": 0.4909090909090909,
      "eval_loss": 0.3064245879650116,
      "eval_runtime": 1.7094,
      "eval_samples_per_second": 54.404,
      "eval_steps_per_second": 7.02,
      "step": 27
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.47634822130203247,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.3259,
      "step": 30
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.6172341704368591,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.3468,
      "step": 33
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 0.44620198011398315,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.2712,
      "step": 36
    },
    {
      "epoch": 0.6545454545454545,
      "eval_loss": 0.2684729993343353,
      "eval_runtime": 1.7078,
      "eval_samples_per_second": 54.456,
      "eval_steps_per_second": 7.027,
      "step": 36
    },
    {
      "epoch": 0.7090909090909091,
      "grad_norm": 0.5440018177032471,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.36,
      "step": 39
    },
    {
      "epoch": 0.7636363636363637,
      "grad_norm": 0.5840175747871399,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.3477,
      "step": 42
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.4900560677051544,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.3062,
      "step": 45
    },
    {
      "epoch": 0.8181818181818182,
      "eval_loss": 0.2494433969259262,
      "eval_runtime": 1.7163,
      "eval_samples_per_second": 54.187,
      "eval_steps_per_second": 6.992,
      "step": 45
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 0.4461391270160675,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.2657,
      "step": 48
    },
    {
      "epoch": 0.9272727272727272,
      "grad_norm": 0.535493016242981,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.2891,
      "step": 51
    },
    {
      "epoch": 0.9818181818181818,
      "grad_norm": 0.6309211254119873,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.271,
      "step": 54
    },
    {
      "epoch": 0.9818181818181818,
      "eval_loss": 0.23513805866241455,
      "eval_runtime": 1.7162,
      "eval_samples_per_second": 54.189,
      "eval_steps_per_second": 6.992,
      "step": 54
    },
    {
      "epoch": 1.0363636363636364,
      "grad_norm": 0.46374499797821045,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.264,
      "step": 57
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.43277519941329956,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.262,
      "step": 60
    },
    {
      "epoch": 1.1454545454545455,
      "grad_norm": 0.4681129455566406,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.2522,
      "step": 63
    },
    {
      "epoch": 1.1454545454545455,
      "eval_loss": 0.224752277135849,
      "eval_runtime": 1.7139,
      "eval_samples_per_second": 54.261,
      "eval_steps_per_second": 7.001,
      "step": 63
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.4968392252922058,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.206,
      "step": 66
    },
    {
      "epoch": 1.2545454545454544,
      "grad_norm": 0.47857439517974854,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.2197,
      "step": 69
    },
    {
      "epoch": 1.309090909090909,
      "grad_norm": 0.4433331787586212,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.2292,
      "step": 72
    },
    {
      "epoch": 1.309090909090909,
      "eval_loss": 0.21840831637382507,
      "eval_runtime": 1.7104,
      "eval_samples_per_second": 54.372,
      "eval_steps_per_second": 7.016,
      "step": 72
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.5370104908943176,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.2634,
      "step": 75
    },
    {
      "epoch": 1.4181818181818182,
      "grad_norm": 0.5451434254646301,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.2539,
      "step": 78
    },
    {
      "epoch": 1.4727272727272727,
      "grad_norm": 0.5778789520263672,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.2318,
      "step": 81
    },
    {
      "epoch": 1.4727272727272727,
      "eval_loss": 0.21548418700695038,
      "eval_runtime": 1.7211,
      "eval_samples_per_second": 54.034,
      "eval_steps_per_second": 6.972,
      "step": 81
    },
    {
      "epoch": 1.5272727272727273,
      "grad_norm": 0.5370736122131348,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.2867,
      "step": 84
    },
    {
      "epoch": 1.5818181818181818,
      "grad_norm": 0.48193562030792236,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.1957,
      "step": 87
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.4694143533706665,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2136,
      "step": 90
    },
    {
      "epoch": 1.6363636363636362,
      "eval_loss": 0.21406370401382446,
      "eval_runtime": 1.7178,
      "eval_samples_per_second": 54.14,
      "eval_steps_per_second": 6.986,
      "step": 90
    },
    {
      "epoch": 1.690909090909091,
      "grad_norm": 0.5793366432189941,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.24,
      "step": 93
    },
    {
      "epoch": 1.7454545454545456,
      "grad_norm": 0.5438080430030823,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.2427,
      "step": 96
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.49919649958610535,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.2304,
      "step": 99
    },
    {
      "epoch": 1.8,
      "eval_loss": 0.21381090581417084,
      "eval_runtime": 1.7104,
      "eval_samples_per_second": 54.374,
      "eval_steps_per_second": 7.016,
      "step": 99
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.057450833104077e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}