{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.6,
  "eval_steps": 13,
  "global_step": 143,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01818181818181818,
      "eval_loss": 0.7239479422569275,
      "eval_runtime": 9.6694,
      "eval_samples_per_second": 9.618,
      "eval_steps_per_second": 1.241,
      "step": 1
    },
    {
      "epoch": 0.05454545454545454,
      "grad_norm": 1.006616234779358,
      "learning_rate": 3e-05,
      "loss": 0.7497,
      "step": 3
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 0.7354311347007751,
      "learning_rate": 6e-05,
      "loss": 0.6608,
      "step": 6
    },
    {
      "epoch": 0.16363636363636364,
      "grad_norm": 0.5442305207252502,
      "learning_rate": 9e-05,
      "loss": 0.5711,
      "step": 9
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 0.4888646900653839,
      "learning_rate": 9.994965332706573e-05,
      "loss": 0.6065,
      "step": 12
    },
    {
      "epoch": 0.23636363636363636,
      "eval_loss": 0.5811941027641296,
      "eval_runtime": 9.3174,
      "eval_samples_per_second": 9.981,
      "eval_steps_per_second": 1.288,
      "step": 13
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 0.43622222542762756,
      "learning_rate": 9.968561049466214e-05,
      "loss": 0.545,
      "step": 15
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 0.4785720407962799,
      "learning_rate": 9.919647942993148e-05,
      "loss": 0.552,
      "step": 18
    },
    {
      "epoch": 0.38181818181818183,
      "grad_norm": 0.5042471289634705,
      "learning_rate": 9.848447601883435e-05,
      "loss": 0.5068,
      "step": 21
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.5013201832771301,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.5388,
      "step": 24
    },
    {
      "epoch": 0.4727272727272727,
      "eval_loss": 0.4993453621864319,
      "eval_runtime": 9.3279,
      "eval_samples_per_second": 9.97,
      "eval_steps_per_second": 1.286,
      "step": 26
    },
    {
      "epoch": 0.4909090909090909,
      "grad_norm": 0.45883774757385254,
      "learning_rate": 9.640574942595196e-05,
      "loss": 0.4867,
      "step": 27
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.546485185623169,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.4773,
      "step": 30
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.5516665577888489,
      "learning_rate": 9.348705665778478e-05,
      "loss": 0.4846,
      "step": 33
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 0.5257235765457153,
      "learning_rate": 9.172866268606513e-05,
      "loss": 0.4445,
      "step": 36
    },
    {
      "epoch": 0.7090909090909091,
      "grad_norm": 0.5515545010566711,
      "learning_rate": 8.978122744408906e-05,
      "loss": 0.4303,
      "step": 39
    },
    {
      "epoch": 0.7090909090909091,
      "eval_loss": 0.41172003746032715,
      "eval_runtime": 9.3482,
      "eval_samples_per_second": 9.948,
      "eval_steps_per_second": 1.284,
      "step": 39
    },
    {
      "epoch": 0.7636363636363637,
      "grad_norm": 0.6002129912376404,
      "learning_rate": 8.765357330018056e-05,
      "loss": 0.4047,
      "step": 42
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 0.6026033163070679,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.3728,
      "step": 45
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 0.7240566611289978,
      "learning_rate": 8.289693629698564e-05,
      "loss": 0.3553,
      "step": 48
    },
    {
      "epoch": 0.9272727272727272,
      "grad_norm": 0.6206062436103821,
      "learning_rate": 8.0289502192041e-05,
      "loss": 0.3555,
      "step": 51
    },
    {
      "epoch": 0.9454545454545454,
      "eval_loss": 0.33931291103363037,
      "eval_runtime": 9.3313,
      "eval_samples_per_second": 9.966,
      "eval_steps_per_second": 1.286,
      "step": 52
    },
    {
      "epoch": 0.9818181818181818,
      "grad_norm": 0.6793412566184998,
      "learning_rate": 7.754484907260513e-05,
      "loss": 0.3225,
      "step": 54
    },
    {
      "epoch": 1.0363636363636364,
      "grad_norm": 0.653759777545929,
      "learning_rate": 7.467541090321735e-05,
      "loss": 0.2436,
      "step": 57
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 0.8996871113777161,
      "learning_rate": 7.169418695587791e-05,
      "loss": 0.2055,
      "step": 60
    },
    {
      "epoch": 1.1454545454545455,
      "grad_norm": 0.5913653373718262,
      "learning_rate": 6.861468292009727e-05,
      "loss": 0.1856,
      "step": 63
    },
    {
      "epoch": 1.1818181818181819,
      "eval_loss": 0.2821066677570343,
      "eval_runtime": 9.338,
      "eval_samples_per_second": 9.959,
      "eval_steps_per_second": 1.285,
      "step": 65
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.6527738571166992,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.179,
      "step": 66
    },
    {
      "epoch": 1.2545454545454544,
      "grad_norm": 0.7428808808326721,
      "learning_rate": 6.22170203068947e-05,
      "loss": 0.174,
      "step": 69
    },
    {
      "epoch": 1.309090909090909,
      "grad_norm": 0.6538995504379272,
      "learning_rate": 5.8927844739931834e-05,
      "loss": 0.16,
      "step": 72
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 0.6126785278320312,
      "learning_rate": 5.559822380516539e-05,
      "loss": 0.1336,
      "step": 75
    },
    {
      "epoch": 1.4181818181818182,
      "grad_norm": 0.718612551689148,
      "learning_rate": 5.2243241517525754e-05,
      "loss": 0.132,
      "step": 78
    },
    {
      "epoch": 1.4181818181818182,
      "eval_loss": 0.23752006888389587,
      "eval_runtime": 9.3452,
      "eval_samples_per_second": 9.952,
      "eval_steps_per_second": 1.284,
      "step": 78
    },
    {
      "epoch": 1.4727272727272727,
      "grad_norm": 0.659690260887146,
      "learning_rate": 4.887809678520976e-05,
      "loss": 0.1273,
      "step": 81
    },
    {
      "epoch": 1.5272727272727273,
      "grad_norm": 0.5911349654197693,
      "learning_rate": 4.551803455482833e-05,
      "loss": 0.1286,
      "step": 84
    },
    {
      "epoch": 1.5818181818181818,
      "grad_norm": 0.6244898438453674,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.1135,
      "step": 87
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.6658645272254944,
      "learning_rate": 3.887395330218429e-05,
      "loss": 0.1021,
      "step": 90
    },
    {
      "epoch": 1.6545454545454545,
      "eval_loss": 0.19473232328891754,
      "eval_runtime": 9.334,
      "eval_samples_per_second": 9.964,
      "eval_steps_per_second": 1.286,
      "step": 91
    },
    {
      "epoch": 1.690909090909091,
      "grad_norm": 0.5781804323196411,
      "learning_rate": 3.562003362839914e-05,
      "loss": 0.1118,
      "step": 93
    },
    {
      "epoch": 1.7454545454545456,
      "grad_norm": 0.557227373123169,
      "learning_rate": 3.243125879593286e-05,
      "loss": 0.0887,
      "step": 96
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.6238749623298645,
      "learning_rate": 2.932207475167398e-05,
      "loss": 0.0828,
      "step": 99
    },
    {
      "epoch": 1.8545454545454545,
      "grad_norm": 0.6486019492149353,
      "learning_rate": 2.630656687635007e-05,
      "loss": 0.1015,
      "step": 102
    },
    {
      "epoch": 1.8909090909090909,
      "eval_loss": 0.15355004370212555,
      "eval_runtime": 9.3338,
      "eval_samples_per_second": 9.964,
      "eval_steps_per_second": 1.286,
      "step": 104
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 0.5612895488739014,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 0.0825,
      "step": 105
    },
    {
      "epoch": 1.9636363636363636,
      "grad_norm": 0.5168143510818481,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0798,
      "step": 108
    },
    {
      "epoch": 2.018181818181818,
      "grad_norm": 0.3419465124607086,
      "learning_rate": 1.7956219300748793e-05,
      "loss": 0.0638,
      "step": 111
    },
    {
      "epoch": 2.0727272727272728,
      "grad_norm": 0.3355216085910797,
      "learning_rate": 1.544686755065677e-05,
      "loss": 0.0374,
      "step": 114
    },
    {
      "epoch": 2.1272727272727274,
      "grad_norm": 0.513612687587738,
      "learning_rate": 1.3094050125632972e-05,
      "loss": 0.0367,
      "step": 117
    },
    {
      "epoch": 2.1272727272727274,
      "eval_loss": 0.1390739530324936,
      "eval_runtime": 9.3397,
      "eval_samples_per_second": 9.958,
      "eval_steps_per_second": 1.285,
      "step": 117
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 0.3988870680332184,
      "learning_rate": 1.090842587659851e-05,
      "loss": 0.0385,
      "step": 120
    },
    {
      "epoch": 2.2363636363636363,
      "grad_norm": 0.3185819983482361,
      "learning_rate": 8.899896227604509e-06,
      "loss": 0.0351,
      "step": 123
    },
    {
      "epoch": 2.290909090909091,
      "grad_norm": 0.3625490665435791,
      "learning_rate": 7.077560319906695e-06,
      "loss": 0.0318,
      "step": 126
    },
    {
      "epoch": 2.3454545454545457,
      "grad_norm": 0.31989988684654236,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0339,
      "step": 129
    },
    {
      "epoch": 2.3636363636363638,
      "eval_loss": 0.13768097758293152,
      "eval_runtime": 9.3375,
      "eval_samples_per_second": 9.96,
      "eval_steps_per_second": 1.285,
      "step": 130
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.3828240931034088,
      "learning_rate": 4.023611372427471e-06,
      "loss": 0.0376,
      "step": 132
    },
    {
      "epoch": 2.4545454545454546,
      "grad_norm": 0.315852552652359,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 0.0392,
      "step": 135
    },
    {
      "epoch": 2.509090909090909,
      "grad_norm": 0.43011197447776794,
      "learning_rate": 1.8018569652073381e-06,
      "loss": 0.0369,
      "step": 138
    },
    {
      "epoch": 2.5636363636363635,
      "grad_norm": 0.5211729407310486,
      "learning_rate": 1.016230078838226e-06,
      "loss": 0.0382,
      "step": 141
    },
    {
      "epoch": 2.6,
      "eval_loss": 0.13515090942382812,
      "eval_runtime": 9.3396,
      "eval_samples_per_second": 9.958,
      "eval_steps_per_second": 1.285,
      "step": 143
    }
  ],
  "logging_steps": 3,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.234818805423145e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}