{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.037257824143070044,
  "eval_steps": 9,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014903129657228018,
      "grad_norm": 2.0342986583709717,
      "learning_rate": 1e-05,
      "loss": 3.4859,
      "step": 1
    },
    {
      "epoch": 0.0014903129657228018,
      "eval_loss": 3.4842216968536377,
      "eval_runtime": 3.0911,
      "eval_samples_per_second": 182.782,
      "eval_steps_per_second": 22.969,
      "step": 1
    },
    {
      "epoch": 0.0029806259314456036,
      "grad_norm": 1.7465375661849976,
      "learning_rate": 2e-05,
      "loss": 3.4165,
      "step": 2
    },
    {
      "epoch": 0.004470938897168405,
      "grad_norm": 1.9989283084869385,
      "learning_rate": 3e-05,
      "loss": 3.4885,
      "step": 3
    },
    {
      "epoch": 0.005961251862891207,
      "grad_norm": 1.7901273965835571,
      "learning_rate": 4e-05,
      "loss": 3.388,
      "step": 4
    },
    {
      "epoch": 0.007451564828614009,
      "grad_norm": 1.8343313932418823,
      "learning_rate": 5e-05,
      "loss": 3.4413,
      "step": 5
    },
    {
      "epoch": 0.00894187779433681,
      "grad_norm": 1.9110901355743408,
      "learning_rate": 6e-05,
      "loss": 3.4883,
      "step": 6
    },
    {
      "epoch": 0.010432190760059613,
      "grad_norm": 1.8050709962844849,
      "learning_rate": 7e-05,
      "loss": 3.4939,
      "step": 7
    },
    {
      "epoch": 0.011922503725782414,
      "grad_norm": 1.8594285249710083,
      "learning_rate": 8e-05,
      "loss": 3.3683,
      "step": 8
    },
    {
      "epoch": 0.013412816691505217,
      "grad_norm": 2.0457093715667725,
      "learning_rate": 9e-05,
      "loss": 3.4379,
      "step": 9
    },
    {
      "epoch": 0.013412816691505217,
      "eval_loss": 3.1294145584106445,
      "eval_runtime": 2.6674,
      "eval_samples_per_second": 211.814,
      "eval_steps_per_second": 26.617,
      "step": 9
    },
    {
      "epoch": 0.014903129657228018,
      "grad_norm": 1.7745529413223267,
      "learning_rate": 0.0001,
      "loss": 3.1102,
      "step": 10
    },
    {
      "epoch": 0.01639344262295082,
      "grad_norm": 1.6581326723098755,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.9326,
      "step": 11
    },
    {
      "epoch": 0.01788375558867362,
      "grad_norm": 1.645290732383728,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.813,
      "step": 12
    },
    {
      "epoch": 0.019374068554396422,
      "grad_norm": 1.6816961765289307,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.6876,
      "step": 13
    },
    {
      "epoch": 0.020864381520119227,
      "grad_norm": 1.6662911176681519,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.6106,
      "step": 14
    },
    {
      "epoch": 0.022354694485842028,
      "grad_norm": 1.542525053024292,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.5321,
      "step": 15
    },
    {
      "epoch": 0.02384500745156483,
      "grad_norm": 1.4631415605545044,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.3101,
      "step": 16
    },
    {
      "epoch": 0.02533532041728763,
      "grad_norm": 1.5643318891525269,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.2768,
      "step": 17
    },
    {
      "epoch": 0.026825633383010434,
      "grad_norm": 1.6115552186965942,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.1149,
      "step": 18
    },
    {
      "epoch": 0.026825633383010434,
      "eval_loss": 2.07175612449646,
      "eval_runtime": 2.6646,
      "eval_samples_per_second": 212.036,
      "eval_steps_per_second": 26.645,
      "step": 18
    },
    {
      "epoch": 0.028315946348733235,
      "grad_norm": 1.5824073553085327,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.0145,
      "step": 19
    },
    {
      "epoch": 0.029806259314456036,
      "grad_norm": 1.674318790435791,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.047,
      "step": 20
    },
    {
      "epoch": 0.03129657228017884,
      "grad_norm": 1.6824314594268799,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.8464,
      "step": 21
    },
    {
      "epoch": 0.03278688524590164,
      "grad_norm": 1.9013198614120483,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.7421,
      "step": 22
    },
    {
      "epoch": 0.03427719821162444,
      "grad_norm": 1.8643028736114502,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.7526,
      "step": 23
    },
    {
      "epoch": 0.03576751117734724,
      "grad_norm": 1.9997265338897705,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.6996,
      "step": 24
    },
    {
      "epoch": 0.037257824143070044,
      "grad_norm": 2.215336322784424,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.6416,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 347093965209600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}