{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 92,
  "global_step": 184,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010899182561307902,
      "grad_norm": 2.1655566692352295,
      "learning_rate": 0.0,
      "loss": 1.2956244945526123,
      "step": 1
    },
    {
      "epoch": 0.10899182561307902,
      "grad_norm": 6.883086681365967,
      "learning_rate": 1.3846153846153844e-06,
      "loss": 1.2135541703965929,
      "step": 10
    },
    {
      "epoch": 0.21798365122615804,
      "grad_norm": 1.6097644567489624,
      "learning_rate": 2e-06,
      "loss": 1.176595687866211,
      "step": 20
    },
    {
      "epoch": 0.32697547683923706,
      "grad_norm": 1.3759019374847412,
      "learning_rate": 2e-06,
      "loss": 1.1085619926452637,
      "step": 30
    },
    {
      "epoch": 0.4359673024523161,
      "grad_norm": 1.9806879758834839,
      "learning_rate": 2e-06,
      "loss": 1.0621185302734375,
      "step": 40
    },
    {
      "epoch": 0.5449591280653951,
      "grad_norm": 1.8080946207046509,
      "learning_rate": 2e-06,
      "loss": 1.0446945190429688,
      "step": 50
    },
    {
      "epoch": 0.6539509536784741,
      "grad_norm": 2.0513596534729004,
      "learning_rate": 2e-06,
      "loss": 1.005961036682129,
      "step": 60
    },
    {
      "epoch": 0.7629427792915532,
      "grad_norm": 1.1626204252243042,
      "learning_rate": 2e-06,
      "loss": 0.991724967956543,
      "step": 70
    },
    {
      "epoch": 0.8719346049046321,
      "grad_norm": 2.2486190795898438,
      "learning_rate": 2e-06,
      "loss": 0.9822382926940918,
      "step": 80
    },
    {
      "epoch": 0.9809264305177112,
      "grad_norm": 1.088089108467102,
      "learning_rate": 2e-06,
      "loss": 0.9526179313659668,
      "step": 90
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.9977306127548218,
      "eval_runtime": 6.4119,
      "eval_samples_per_second": 15.596,
      "eval_steps_per_second": 2.027,
      "step": 92
    },
    {
      "epoch": 1.0871934604904632,
      "grad_norm": 1.646237850189209,
      "learning_rate": 2e-06,
      "loss": 0.8067577362060547,
      "step": 100
    },
    {
      "epoch": 1.1961852861035422,
      "grad_norm": 1.154694676399231,
      "learning_rate": 2e-06,
      "loss": 0.7513428688049316,
      "step": 110
    },
    {
      "epoch": 1.3051771117166213,
      "grad_norm": 1.3161247968673706,
      "learning_rate": 2e-06,
      "loss": 0.7651296615600586,
      "step": 120
    },
    {
      "epoch": 1.4141689373297002,
      "grad_norm": 3.3871452808380127,
      "learning_rate": 2e-06,
      "loss": 0.7529166221618653,
      "step": 130
    },
    {
      "epoch": 1.5231607629427792,
      "grad_norm": 1.1526254415512085,
      "learning_rate": 2e-06,
      "loss": 0.7394458770751953,
      "step": 140
    },
    {
      "epoch": 1.6321525885558583,
      "grad_norm": 1.1925352811813354,
      "learning_rate": 2e-06,
      "loss": 0.7612244606018066,
      "step": 150
    },
    {
      "epoch": 1.7411444141689372,
      "grad_norm": 1.19083833694458,
      "learning_rate": 2e-06,
      "loss": 0.7518976211547852,
      "step": 160
    },
    {
      "epoch": 1.8501362397820165,
      "grad_norm": 1.2023205757141113,
      "learning_rate": 2e-06,
      "loss": 0.7534203052520752,
      "step": 170
    },
    {
      "epoch": 1.9591280653950953,
      "grad_norm": 19.363874435424805,
      "learning_rate": 2e-06,
      "loss": 0.7472377777099609,
      "step": 180
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.9622921943664551,
      "eval_runtime": 6.5494,
      "eval_samples_per_second": 15.269,
      "eval_steps_per_second": 1.985,
      "step": 184
    }
  ],
  "logging_steps": 10,
  "max_steps": 460,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.589825445317837e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}