{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9361702127659575,
  "eval_steps": 25,
  "global_step": 105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 0.26462894678115845,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.9378,
      "step": 10
    },
    {
      "epoch": 0.5673758865248227,
      "grad_norm": 0.14169304072856903,
      "learning_rate": 0.00019551024972069126,
      "loss": 0.8496,
      "step": 20
    },
    {
      "epoch": 0.7092198581560284,
      "eval_loss": 0.8489587306976318,
      "eval_runtime": 26.6774,
      "eval_samples_per_second": 18.742,
      "eval_steps_per_second": 1.2,
      "step": 25
    },
    {
      "epoch": 0.851063829787234,
      "grad_norm": 0.127975732088089,
      "learning_rate": 0.0001805070053127563,
      "loss": 0.861,
      "step": 30
    },
    {
      "epoch": 1.1134751773049645,
      "grad_norm": 0.15211418271064758,
      "learning_rate": 0.00015659470943305955,
      "loss": 0.8392,
      "step": 40
    },
    {
      "epoch": 1.397163120567376,
      "grad_norm": 0.1456218957901001,
      "learning_rate": 0.00012641954018712863,
      "loss": 0.784,
      "step": 50
    },
    {
      "epoch": 1.397163120567376,
      "eval_loss": 0.818655252456665,
      "eval_runtime": 26.6767,
      "eval_samples_per_second": 18.743,
      "eval_steps_per_second": 1.2,
      "step": 50
    },
    {
      "epoch": 1.6808510638297873,
      "grad_norm": 0.14745110273361206,
      "learning_rate": 9.332073662548784e-05,
      "loss": 0.7885,
      "step": 60
    },
    {
      "epoch": 1.9645390070921986,
      "grad_norm": 0.15153422951698303,
      "learning_rate": 6.0961072483650526e-05,
      "loss": 0.7773,
      "step": 70
    },
    {
      "epoch": 2.0851063829787235,
      "eval_loss": 0.8111562132835388,
      "eval_runtime": 26.6835,
      "eval_samples_per_second": 18.738,
      "eval_steps_per_second": 1.199,
      "step": 75
    },
    {
      "epoch": 2.226950354609929,
      "grad_norm": 0.1788651943206787,
      "learning_rate": 3.292152698607768e-05,
      "loss": 0.7987,
      "step": 80
    },
    {
      "epoch": 2.5106382978723403,
      "grad_norm": 0.15647704899311066,
      "learning_rate": 1.230500717933285e-05,
      "loss": 0.74,
      "step": 90
    },
    {
      "epoch": 2.794326241134752,
      "grad_norm": 0.1778271496295929,
      "learning_rate": 1.3929746009971433e-06,
      "loss": 0.754,
      "step": 100
    },
    {
      "epoch": 2.794326241134752,
      "eval_loss": 0.8111380338668823,
      "eval_runtime": 26.682,
      "eval_samples_per_second": 18.739,
      "eval_steps_per_second": 1.199,
      "step": 100
    },
    {
      "epoch": 2.9361702127659575,
      "step": 105,
      "total_flos": 8.675771489095516e+17,
      "train_loss": 0.8103648549034482,
      "train_runtime": 2078.8921,
      "train_samples_per_second": 6.494,
      "train_steps_per_second": 0.051
    }
  ],
  "logging_steps": 10,
  "max_steps": 105,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.675771489095516e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}