{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 14436,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10390689941812137,
      "grad_norm": 3.488266944885254,
      "learning_rate": 1.9311443613189252e-05,
      "loss": 0.8436,
      "step": 500
    },
    {
      "epoch": 0.20781379883624274,
      "grad_norm": 0.8393851518630981,
      "learning_rate": 1.8618730950401776e-05,
      "loss": 0.5316,
      "step": 1000
    },
    {
      "epoch": 0.3117206982543641,
      "grad_norm": 1.4351526498794556,
      "learning_rate": 1.79260182876143e-05,
      "loss": 0.483,
      "step": 1500
    },
    {
      "epoch": 0.41562759767248547,
      "grad_norm": 1.4630037546157837,
      "learning_rate": 1.7233305624826823e-05,
      "loss": 0.4516,
      "step": 2000
    },
    {
      "epoch": 0.5195344970906068,
      "grad_norm": 0.854028046131134,
      "learning_rate": 1.6540592962039347e-05,
      "loss": 0.4387,
      "step": 2500
    },
    {
      "epoch": 0.6234413965087282,
      "grad_norm": 0.8339985013008118,
      "learning_rate": 1.584788029925187e-05,
      "loss": 0.4192,
      "step": 3000
    },
    {
      "epoch": 0.7273482959268496,
      "grad_norm": 1.0237222909927368,
      "learning_rate": 1.5155167636464397e-05,
      "loss": 0.422,
      "step": 3500
    },
    {
      "epoch": 0.8312551953449709,
      "grad_norm": 1.0825960636138916,
      "learning_rate": 1.446245497367692e-05,
      "loss": 0.4065,
      "step": 4000
    },
    {
      "epoch": 0.9351620947630923,
      "grad_norm": 1.4909119606018066,
      "learning_rate": 1.3769742310889445e-05,
      "loss": 0.4031,
      "step": 4500
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.3220335841178894,
      "eval_runtime": 31.3207,
      "eval_samples_per_second": 15.772,
      "eval_steps_per_second": 7.886,
      "step": 4812
    },
    {
      "epoch": 1.0390689941812137,
      "grad_norm": 0.6415828466415405,
      "learning_rate": 1.3077029648101969e-05,
      "loss": 0.4064,
      "step": 5000
    },
    {
      "epoch": 1.142975893599335,
      "grad_norm": 0.6136273741722107,
      "learning_rate": 1.2384316985314493e-05,
      "loss": 0.3599,
      "step": 5500
    },
    {
      "epoch": 1.2468827930174564,
      "grad_norm": 0.49429360032081604,
      "learning_rate": 1.1692989747852592e-05,
      "loss": 0.3737,
      "step": 6000
    },
    {
      "epoch": 1.3507896924355778,
      "grad_norm": 1.103445053100586,
      "learning_rate": 1.1000277085065116e-05,
      "loss": 0.3626,
      "step": 6500
    },
    {
      "epoch": 1.4546965918536992,
      "grad_norm": 0.35276883840560913,
      "learning_rate": 1.030756442227764e-05,
      "loss": 0.352,
      "step": 7000
    },
    {
      "epoch": 1.5586034912718203,
      "grad_norm": 2.3900763988494873,
      "learning_rate": 9.614851759490165e-06,
      "loss": 0.3564,
      "step": 7500
    },
    {
      "epoch": 1.6625103906899419,
      "grad_norm": 0.7738548517227173,
      "learning_rate": 8.92213909670269e-06,
      "loss": 0.3639,
      "step": 8000
    },
    {
      "epoch": 1.766417290108063,
      "grad_norm": 0.8235663771629333,
      "learning_rate": 8.229426433915213e-06,
      "loss": 0.355,
      "step": 8500
    },
    {
      "epoch": 1.8703241895261846,
      "grad_norm": 0.8178287148475647,
      "learning_rate": 7.536713771127737e-06,
      "loss": 0.3492,
      "step": 9000
    },
    {
      "epoch": 1.9742310889443058,
      "grad_norm": 1.3331661224365234,
      "learning_rate": 6.844001108340261e-06,
      "loss": 0.3386,
      "step": 9500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.29590198397636414,
      "eval_runtime": 31.3938,
      "eval_samples_per_second": 15.736,
      "eval_steps_per_second": 7.868,
      "step": 9624
    },
    {
      "epoch": 2.0781379883624274,
      "grad_norm": 0.6089585423469543,
      "learning_rate": 6.151288445552786e-06,
      "loss": 0.3294,
      "step": 10000
    },
    {
      "epoch": 2.1820448877805485,
      "grad_norm": 1.1987346410751343,
      "learning_rate": 5.459961208090885e-06,
      "loss": 0.3377,
      "step": 10500
    },
    {
      "epoch": 2.28595178719867,
      "grad_norm": 0.7879965901374817,
      "learning_rate": 4.767248545303408e-06,
      "loss": 0.3383,
      "step": 11000
    },
    {
      "epoch": 2.3898586866167912,
      "grad_norm": 1.5681509971618652,
      "learning_rate": 4.074535882515933e-06,
      "loss": 0.3412,
      "step": 11500
    },
    {
      "epoch": 2.493765586034913,
      "grad_norm": 0.8355275988578796,
      "learning_rate": 3.381823219728457e-06,
      "loss": 0.3168,
      "step": 12000
    },
    {
      "epoch": 2.597672485453034,
      "grad_norm": 1.3090420961380005,
      "learning_rate": 2.6891105569409807e-06,
      "loss": 0.3176,
      "step": 12500
    },
    {
      "epoch": 2.7015793848711556,
      "grad_norm": 1.0440038442611694,
      "learning_rate": 1.99778331947908e-06,
      "loss": 0.3391,
      "step": 13000
    },
    {
      "epoch": 2.8054862842892767,
      "grad_norm": 1.7209734916687012,
      "learning_rate": 1.3050706566916044e-06,
      "loss": 0.3164,
      "step": 13500
    },
    {
      "epoch": 2.9093931837073983,
      "grad_norm": 0.7560927867889404,
      "learning_rate": 6.123579939041286e-07,
      "loss": 0.3268,
      "step": 14000
    }
  ],
  "logging_steps": 500,
  "max_steps": 14436,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.758000534257664e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}