{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5970149253731343,
  "eval_steps": 35,
  "global_step": 105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028429282160625444,
      "grad_norm": 2.917722702026367,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 1.3615,
      "step": 5
    },
    {
      "epoch": 0.05685856432125089,
      "grad_norm": 2.65405011177063,
      "learning_rate": 2.857142857142857e-05,
      "loss": 1.2182,
      "step": 10
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 4.0127272605896,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.8944,
      "step": 15
    },
    {
      "epoch": 0.11371712864250177,
      "grad_norm": 0.8177616000175476,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.512,
      "step": 20
    },
    {
      "epoch": 0.14214641080312723,
      "grad_norm": 0.3800067901611328,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.3435,
      "step": 25
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 0.3455258309841156,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.3027,
      "step": 30
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 0.3401183485984802,
      "learning_rate": 0.0001,
      "loss": 0.3045,
      "step": 35
    },
    {
      "epoch": 0.19900497512437812,
      "eval_loss": 0.2556740641593933,
      "eval_runtime": 1374.6693,
      "eval_samples_per_second": 1.819,
      "eval_steps_per_second": 1.819,
      "step": 35
    },
    {
      "epoch": 0.22743425728500355,
      "grad_norm": 0.3088541328907013,
      "learning_rate": 9.993784606094612e-05,
      "loss": 0.2799,
      "step": 40
    },
    {
      "epoch": 0.255863539445629,
      "grad_norm": 0.2526684105396271,
      "learning_rate": 9.975153876827008e-05,
      "loss": 0.2779,
      "step": 45
    },
    {
      "epoch": 0.28429282160625446,
      "grad_norm": 0.3618779182434082,
      "learning_rate": 9.944154131125642e-05,
      "loss": 0.2781,
      "step": 50
    },
    {
      "epoch": 0.31272210376687987,
      "grad_norm": 0.32333430647850037,
      "learning_rate": 9.900862439242719e-05,
      "loss": 0.2595,
      "step": 55
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 0.328197717666626,
      "learning_rate": 9.84538643114539e-05,
      "loss": 0.275,
      "step": 60
    },
    {
      "epoch": 0.3695806680881308,
      "grad_norm": 0.28067663311958313,
      "learning_rate": 9.777864028930705e-05,
      "loss": 0.2333,
      "step": 65
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 0.3941590487957001,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2524,
      "step": 70
    },
    {
      "epoch": 0.39800995024875624,
      "eval_loss": 0.23971079289913177,
      "eval_runtime": 1374.4109,
      "eval_samples_per_second": 1.819,
      "eval_steps_per_second": 1.819,
      "step": 70
    },
    {
      "epoch": 0.42643923240938164,
      "grad_norm": 0.2214515656232834,
      "learning_rate": 9.607381059352038e-05,
      "loss": 0.2585,
      "step": 75
    },
    {
      "epoch": 0.4548685145700071,
      "grad_norm": 0.27422434091567993,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.2122,
      "step": 80
    },
    {
      "epoch": 0.48329779673063256,
      "grad_norm": 0.28153732419013977,
      "learning_rate": 9.391107866851143e-05,
      "loss": 0.2397,
      "step": 85
    },
    {
      "epoch": 0.511727078891258,
      "grad_norm": 0.2967371344566345,
      "learning_rate": 9.266454408160779e-05,
      "loss": 0.2192,
      "step": 90
    },
    {
      "epoch": 0.5401563610518835,
      "grad_norm": 0.29277151823043823,
      "learning_rate": 9.131193871579975e-05,
      "loss": 0.234,
      "step": 95
    },
    {
      "epoch": 0.5685856432125089,
      "grad_norm": 0.30613964796066284,
      "learning_rate": 8.985662536114613e-05,
      "loss": 0.2376,
      "step": 100
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.27135342359542847,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.245,
      "step": 105
    },
    {
      "epoch": 0.5970149253731343,
      "eval_loss": 0.23002392053604126,
      "eval_runtime": 1375.9551,
      "eval_samples_per_second": 1.817,
      "eval_steps_per_second": 1.817,
      "step": 105
    }
  ],
  "logging_steps": 5,
  "max_steps": 350,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 35,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.813255851494605e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}