{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07366071428571429,
  "eval_steps": 9,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000744047619047619,
      "eval_loss": 8.732146263122559,
      "eval_runtime": 160.772,
      "eval_samples_per_second": 14.082,
      "eval_steps_per_second": 1.76,
      "step": 1
    },
    {
      "epoch": 0.002232142857142857,
      "grad_norm": 3.8600971698760986,
      "learning_rate": 1.5e-05,
      "loss": 8.6341,
      "step": 3
    },
    {
      "epoch": 0.004464285714285714,
      "grad_norm": 3.3618743419647217,
      "learning_rate": 3e-05,
      "loss": 8.6814,
      "step": 6
    },
    {
      "epoch": 0.006696428571428571,
      "grad_norm": 4.365889072418213,
      "learning_rate": 4.5e-05,
      "loss": 8.5392,
      "step": 9
    },
    {
      "epoch": 0.006696428571428571,
      "eval_loss": 8.285680770874023,
      "eval_runtime": 162.175,
      "eval_samples_per_second": 13.96,
      "eval_steps_per_second": 1.745,
      "step": 9
    },
    {
      "epoch": 0.008928571428571428,
      "grad_norm": 4.4500579833984375,
      "learning_rate": 4.993910125649561e-05,
      "loss": 7.668,
      "step": 12
    },
    {
      "epoch": 0.011160714285714286,
      "grad_norm": 5.069802284240723,
      "learning_rate": 4.962019382530521e-05,
      "loss": 7.129,
      "step": 15
    },
    {
      "epoch": 0.013392857142857142,
      "grad_norm": 6.467036724090576,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 6.7975,
      "step": 18
    },
    {
      "epoch": 0.013392857142857142,
      "eval_loss": 6.488559246063232,
      "eval_runtime": 162.089,
      "eval_samples_per_second": 13.968,
      "eval_steps_per_second": 1.746,
      "step": 18
    },
    {
      "epoch": 0.015625,
      "grad_norm": 6.155084609985352,
      "learning_rate": 4.817959636416969e-05,
      "loss": 6.0534,
      "step": 21
    },
    {
      "epoch": 0.017857142857142856,
      "grad_norm": 5.953625202178955,
      "learning_rate": 4.707368982147318e-05,
      "loss": 5.5173,
      "step": 24
    },
    {
      "epoch": 0.020089285714285716,
      "grad_norm": 7.119878768920898,
      "learning_rate": 4.572593931387604e-05,
      "loss": 5.561,
      "step": 27
    },
    {
      "epoch": 0.020089285714285716,
      "eval_loss": 5.080662250518799,
      "eval_runtime": 161.9742,
      "eval_samples_per_second": 13.978,
      "eval_steps_per_second": 1.747,
      "step": 27
    },
    {
      "epoch": 0.022321428571428572,
      "grad_norm": 7.226921558380127,
      "learning_rate": 4.415111107797445e-05,
      "loss": 4.8955,
      "step": 30
    },
    {
      "epoch": 0.024553571428571428,
      "grad_norm": 5.604612350463867,
      "learning_rate": 4.2366459261474933e-05,
      "loss": 4.8425,
      "step": 33
    },
    {
      "epoch": 0.026785714285714284,
      "grad_norm": 4.74511194229126,
      "learning_rate": 4.039153688314145e-05,
      "loss": 4.5303,
      "step": 36
    },
    {
      "epoch": 0.026785714285714284,
      "eval_loss": 4.585251808166504,
      "eval_runtime": 162.1038,
      "eval_samples_per_second": 13.966,
      "eval_steps_per_second": 1.746,
      "step": 36
    },
    {
      "epoch": 0.029017857142857144,
      "grad_norm": 5.430819034576416,
      "learning_rate": 3.824798160583012e-05,
      "loss": 4.5037,
      "step": 39
    },
    {
      "epoch": 0.03125,
      "grad_norm": 5.575501918792725,
      "learning_rate": 3.5959278669726935e-05,
      "loss": 4.0812,
      "step": 42
    },
    {
      "epoch": 0.033482142857142856,
      "grad_norm": 4.442610263824463,
      "learning_rate": 3.355050358314172e-05,
      "loss": 4.2544,
      "step": 45
    },
    {
      "epoch": 0.033482142857142856,
      "eval_loss": 4.347012042999268,
      "eval_runtime": 162.1463,
      "eval_samples_per_second": 13.963,
      "eval_steps_per_second": 1.745,
      "step": 45
    },
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 6.01466703414917,
      "learning_rate": 3.104804738999169e-05,
      "loss": 4.1686,
      "step": 48
    },
    {
      "epoch": 0.03794642857142857,
      "grad_norm": 5.682656288146973,
      "learning_rate": 2.8479327524001636e-05,
      "loss": 4.1502,
      "step": 51
    },
    {
      "epoch": 0.04017857142857143,
      "grad_norm": 5.908854007720947,
      "learning_rate": 2.587248741756253e-05,
      "loss": 3.8599,
      "step": 54
    },
    {
      "epoch": 0.04017857142857143,
      "eval_loss": 4.212040901184082,
      "eval_runtime": 162.0123,
      "eval_samples_per_second": 13.974,
      "eval_steps_per_second": 1.747,
      "step": 54
    },
    {
      "epoch": 0.04241071428571429,
      "grad_norm": 6.2745361328125,
      "learning_rate": 2.3256088156396868e-05,
      "loss": 4.1838,
      "step": 57
    },
    {
      "epoch": 0.044642857142857144,
      "grad_norm": 8.133929252624512,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 4.2924,
      "step": 60
    },
    {
      "epoch": 0.046875,
      "grad_norm": 6.33773946762085,
      "learning_rate": 1.8109066104575023e-05,
      "loss": 4.0613,
      "step": 63
    },
    {
      "epoch": 0.046875,
      "eval_loss": 4.139092922210693,
      "eval_runtime": 162.0637,
      "eval_samples_per_second": 13.97,
      "eval_steps_per_second": 1.746,
      "step": 63
    },
    {
      "epoch": 0.049107142857142856,
      "grad_norm": 6.2956647872924805,
      "learning_rate": 1.56348351646022e-05,
      "loss": 3.9737,
      "step": 66
    },
    {
      "epoch": 0.05133928571428571,
      "grad_norm": 5.961831569671631,
      "learning_rate": 1.3263210930352737e-05,
      "loss": 4.0038,
      "step": 69
    },
    {
      "epoch": 0.05357142857142857,
      "grad_norm": 5.295280456542969,
      "learning_rate": 1.1020177413231334e-05,
      "loss": 4.0164,
      "step": 72
    },
    {
      "epoch": 0.05357142857142857,
      "eval_loss": 4.0898942947387695,
      "eval_runtime": 162.1293,
      "eval_samples_per_second": 13.964,
      "eval_steps_per_second": 1.746,
      "step": 72
    },
    {
      "epoch": 0.05580357142857143,
      "grad_norm": 6.002346038818359,
      "learning_rate": 8.930309757836517e-06,
      "loss": 3.9557,
      "step": 75
    },
    {
      "epoch": 0.05803571428571429,
      "grad_norm": 4.917716026306152,
      "learning_rate": 7.016504991533726e-06,
      "loss": 3.8531,
      "step": 78
    },
    {
      "epoch": 0.060267857142857144,
      "grad_norm": 5.237407207489014,
      "learning_rate": 5.299731159831953e-06,
      "loss": 3.87,
      "step": 81
    },
    {
      "epoch": 0.060267857142857144,
      "eval_loss": 4.061166286468506,
      "eval_runtime": 162.1269,
      "eval_samples_per_second": 13.964,
      "eval_steps_per_second": 1.746,
      "step": 81
    },
    {
      "epoch": 0.0625,
      "grad_norm": 6.281444072723389,
      "learning_rate": 3.798797596089351e-06,
      "loss": 4.232,
      "step": 84
    },
    {
      "epoch": 0.06473214285714286,
      "grad_norm": 5.385371208190918,
      "learning_rate": 2.5301488425208296e-06,
      "loss": 4.1866,
      "step": 87
    },
    {
      "epoch": 0.06696428571428571,
      "grad_norm": 5.542201042175293,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 3.9092,
      "step": 90
    },
    {
      "epoch": 0.06696428571428571,
      "eval_loss": 4.046029567718506,
      "eval_runtime": 162.0655,
      "eval_samples_per_second": 13.97,
      "eval_steps_per_second": 1.746,
      "step": 90
    },
    {
      "epoch": 0.06919642857142858,
      "grad_norm": 5.934990406036377,
      "learning_rate": 7.426068431000882e-07,
      "loss": 4.0361,
      "step": 93
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 6.241161823272705,
      "learning_rate": 2.4329828146074095e-07,
      "loss": 3.8126,
      "step": 96
    },
    {
      "epoch": 0.07366071428571429,
      "grad_norm": 5.458847522735596,
      "learning_rate": 1.522932452260595e-08,
      "loss": 3.8699,
      "step": 99
    },
    {
      "epoch": 0.07366071428571429,
      "eval_loss": 4.043781280517578,
      "eval_runtime": 162.0655,
      "eval_samples_per_second": 13.97,
      "eval_steps_per_second": 1.746,
      "step": 99
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.468936821449687e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}