{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 4,
  "global_step": 23,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.043478260869565216,
      "grad_norm": 0.09251802414655685,
      "learning_rate": 0.0,
      "loss": 1.8154,
      "step": 1
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 0.10928324609994888,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.0176,
      "step": 2
    },
    {
      "epoch": 0.13043478260869565,
      "grad_norm": 0.1132240816950798,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.0127,
      "step": 3
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.11549753695726395,
      "learning_rate": 0.0001,
      "loss": 1.9375,
      "step": 4
    },
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 0.10435386747121811,
      "learning_rate": 9.94459753267812e-05,
      "loss": 1.6768,
      "step": 5
    },
    {
      "epoch": 0.2608695652173913,
      "grad_norm": 0.1588195115327835,
      "learning_rate": 9.779754323328192e-05,
      "loss": 2.0381,
      "step": 6
    },
    {
      "epoch": 0.30434782608695654,
      "grad_norm": 0.16324423253536224,
      "learning_rate": 9.509529358847655e-05,
      "loss": 1.897,
      "step": 7
    },
    {
      "epoch": 0.30434782608695654,
      "eval_loss": 1.8427734375,
      "eval_runtime": 4.6653,
      "eval_samples_per_second": 1.072,
      "eval_steps_per_second": 0.214,
      "step": 7
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.17935040593147278,
      "learning_rate": 9.140576474687264e-05,
      "loss": 1.8438,
      "step": 8
    },
    {
      "epoch": 0.391304347826087,
      "grad_norm": 0.18160544335842133,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.7764,
      "step": 9
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 0.2144618034362793,
      "learning_rate": 8.14503363531613e-05,
      "loss": 1.8271,
      "step": 10
    },
    {
      "epoch": 0.4782608695652174,
      "grad_norm": 0.2014264315366745,
      "learning_rate": 7.542957248827961e-05,
      "loss": 1.6982,
      "step": 11
    },
    {
      "epoch": 0.4782608695652174,
      "eval_loss": 1.7138671875,
      "eval_runtime": 4.6849,
      "eval_samples_per_second": 1.067,
      "eval_steps_per_second": 0.213,
      "step": 11
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.2807057797908783,
      "learning_rate": 6.890576474687263e-05,
      "loss": 1.9902,
      "step": 12
    },
    {
      "epoch": 0.5652173913043478,
      "grad_norm": 0.24102626740932465,
      "learning_rate": 6.203955092681039e-05,
      "loss": 1.7295,
      "step": 13
    },
    {
      "epoch": 0.6086956521739131,
      "grad_norm": 0.2287806123495102,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.6768,
      "step": 14
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 0.24968694150447845,
      "learning_rate": 4.7960449073189606e-05,
      "loss": 1.7373,
      "step": 15
    },
    {
      "epoch": 0.6521739130434783,
      "eval_loss": 1.619140625,
      "eval_runtime": 4.6702,
      "eval_samples_per_second": 1.071,
      "eval_steps_per_second": 0.214,
      "step": 15
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.23189352452754974,
      "learning_rate": 4.109423525312738e-05,
      "loss": 1.5874,
      "step": 16
    },
    {
      "epoch": 0.7391304347826086,
      "grad_norm": 0.2342681735754013,
      "learning_rate": 3.45704275117204e-05,
      "loss": 1.6475,
      "step": 17
    },
    {
      "epoch": 0.782608695652174,
      "grad_norm": 0.19619220495224,
      "learning_rate": 2.854966364683872e-05,
      "loss": 1.4912,
      "step": 18
    },
    {
      "epoch": 0.8260869565217391,
      "grad_norm": 0.2293105125427246,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.5801,
      "step": 19
    },
    {
      "epoch": 0.8260869565217391,
      "eval_loss": 1.56494140625,
      "eval_runtime": 4.6788,
      "eval_samples_per_second": 1.069,
      "eval_steps_per_second": 0.214,
      "step": 19
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.22101208567619324,
      "learning_rate": 1.8594235253127375e-05,
      "loss": 1.5908,
      "step": 20
    },
    {
      "epoch": 0.9130434782608695,
      "grad_norm": 0.2261812388896942,
      "learning_rate": 1.490470641152345e-05,
      "loss": 1.5752,
      "step": 21
    },
    {
      "epoch": 0.9565217391304348,
      "grad_norm": 0.2427031248807907,
      "learning_rate": 1.2202456766718093e-05,
      "loss": 1.624,
      "step": 22
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.24397827684879303,
      "learning_rate": 1.0554024673218807e-05,
      "loss": 1.6299,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.5458984375,
      "eval_runtime": 4.6806,
      "eval_samples_per_second": 1.068,
      "eval_steps_per_second": 0.214,
      "step": 23
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 23,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1189353360518021e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}