{
  "best_metric": 0.5362756848335266,
  "best_model_checkpoint": "/kaggle/working/results/checkpoint-13500",
  "epoch": 0.977340186780569,
  "eval_steps": 500,
  "global_step": 13500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03619778469557663,
      "grad_norm": 8.067161560058594,
      "learning_rate": 9.638022153044234e-05,
      "loss": 0.873,
      "step": 500
    },
    {
      "epoch": 0.03619778469557663,
      "eval_loss": 1.0014784336090088,
      "eval_runtime": 122.228,
      "eval_samples_per_second": 63.815,
      "eval_steps_per_second": 0.499,
      "step": 500
    },
    {
      "epoch": 0.07239556939115326,
      "grad_norm": 8.213248252868652,
      "learning_rate": 9.276044306088468e-05,
      "loss": 0.8261,
      "step": 1000
    },
    {
      "epoch": 0.07239556939115326,
      "eval_loss": 0.8797920346260071,
      "eval_runtime": 121.4743,
      "eval_samples_per_second": 64.211,
      "eval_steps_per_second": 0.502,
      "step": 1000
    },
    {
      "epoch": 0.10859335408672989,
      "grad_norm": 8.027277946472168,
      "learning_rate": 8.914066459132702e-05,
      "loss": 0.8686,
      "step": 1500
    },
    {
      "epoch": 0.10859335408672989,
      "eval_loss": 0.8256328105926514,
      "eval_runtime": 121.6337,
      "eval_samples_per_second": 64.127,
      "eval_steps_per_second": 0.502,
      "step": 1500
    },
    {
      "epoch": 0.1447911387823065,
      "grad_norm": 5.501945972442627,
      "learning_rate": 8.552088612176935e-05,
      "loss": 0.8266,
      "step": 2000
    },
    {
      "epoch": 0.1447911387823065,
      "eval_loss": 0.7719565033912659,
      "eval_runtime": 121.8754,
      "eval_samples_per_second": 64.0,
      "eval_steps_per_second": 0.501,
      "step": 2000
    },
    {
      "epoch": 0.18098892347788315,
      "grad_norm": 7.218145370483398,
      "learning_rate": 8.190110765221169e-05,
      "loss": 0.801,
      "step": 2500
    },
    {
      "epoch": 0.18098892347788315,
      "eval_loss": 0.766424834728241,
      "eval_runtime": 121.9461,
      "eval_samples_per_second": 63.963,
      "eval_steps_per_second": 0.5,
      "step": 2500
    },
    {
      "epoch": 0.21718670817345978,
      "grad_norm": 9.288457870483398,
      "learning_rate": 7.828132918265403e-05,
      "loss": 0.7709,
      "step": 3000
    },
    {
      "epoch": 0.21718670817345978,
      "eval_loss": 0.7332597970962524,
      "eval_runtime": 121.8362,
      "eval_samples_per_second": 64.02,
      "eval_steps_per_second": 0.501,
      "step": 3000
    },
    {
      "epoch": 0.2533844928690364,
      "grad_norm": 9.63444709777832,
      "learning_rate": 7.466155071309636e-05,
      "loss": 0.7401,
      "step": 3500
    },
    {
      "epoch": 0.2533844928690364,
      "eval_loss": 0.6940492987632751,
      "eval_runtime": 122.025,
      "eval_samples_per_second": 63.921,
      "eval_steps_per_second": 0.5,
      "step": 3500
    },
    {
      "epoch": 0.289582277564613,
      "grad_norm": 4.352470874786377,
      "learning_rate": 7.10417722435387e-05,
      "loss": 0.7217,
      "step": 4000
    },
    {
      "epoch": 0.289582277564613,
      "eval_loss": 0.7044554948806763,
      "eval_runtime": 122.039,
      "eval_samples_per_second": 63.914,
      "eval_steps_per_second": 0.5,
      "step": 4000
    },
    {
      "epoch": 0.3257800622601897,
      "grad_norm": 8.299939155578613,
      "learning_rate": 6.742199377398104e-05,
      "loss": 0.7149,
      "step": 4500
    },
    {
      "epoch": 0.3257800622601897,
      "eval_loss": 0.684947669506073,
      "eval_runtime": 122.0541,
      "eval_samples_per_second": 63.906,
      "eval_steps_per_second": 0.5,
      "step": 4500
    },
    {
      "epoch": 0.3619778469557663,
      "grad_norm": 5.032785415649414,
      "learning_rate": 6.380221530442338e-05,
      "loss": 0.6913,
      "step": 5000
    },
    {
      "epoch": 0.3619778469557663,
      "eval_loss": 0.6848333477973938,
      "eval_runtime": 122.0073,
      "eval_samples_per_second": 63.931,
      "eval_steps_per_second": 0.5,
      "step": 5000
    },
    {
      "epoch": 0.39817563165134295,
      "grad_norm": 7.25339412689209,
      "learning_rate": 6.0182436834865705e-05,
      "loss": 0.6769,
      "step": 5500
    },
    {
      "epoch": 0.39817563165134295,
      "eval_loss": 0.681818425655365,
      "eval_runtime": 121.9878,
      "eval_samples_per_second": 63.941,
      "eval_steps_per_second": 0.5,
      "step": 5500
    },
    {
      "epoch": 0.43437341634691956,
      "grad_norm": 4.095344066619873,
      "learning_rate": 5.656265836530804e-05,
      "loss": 0.6542,
      "step": 6000
    },
    {
      "epoch": 0.43437341634691956,
      "eval_loss": 0.647565484046936,
      "eval_runtime": 122.0947,
      "eval_samples_per_second": 63.885,
      "eval_steps_per_second": 0.5,
      "step": 6000
    },
    {
      "epoch": 0.4705712010424962,
      "grad_norm": 8.288174629211426,
      "learning_rate": 5.2942879895750386e-05,
      "loss": 0.6545,
      "step": 6500
    },
    {
      "epoch": 0.4705712010424962,
      "eval_loss": 0.6471512913703918,
      "eval_runtime": 122.0703,
      "eval_samples_per_second": 63.898,
      "eval_steps_per_second": 0.5,
      "step": 6500
    },
    {
      "epoch": 0.5067689857380728,
      "grad_norm": 5.419597625732422,
      "learning_rate": 4.9323101426192716e-05,
      "loss": 0.6421,
      "step": 7000
    },
    {
      "epoch": 0.5067689857380728,
      "eval_loss": 0.6336092948913574,
      "eval_runtime": 121.8453,
      "eval_samples_per_second": 64.016,
      "eval_steps_per_second": 0.501,
      "step": 7000
    },
    {
      "epoch": 0.5429667704336495,
      "grad_norm": 4.020125865936279,
      "learning_rate": 4.570332295663506e-05,
      "loss": 0.6354,
      "step": 7500
    },
    {
      "epoch": 0.5429667704336495,
      "eval_loss": 0.6177634596824646,
      "eval_runtime": 122.0498,
      "eval_samples_per_second": 63.908,
      "eval_steps_per_second": 0.5,
      "step": 7500
    },
    {
      "epoch": 0.579164555129226,
      "grad_norm": 11.914624214172363,
      "learning_rate": 4.208354448707739e-05,
      "loss": 0.637,
      "step": 8000
    },
    {
      "epoch": 0.579164555129226,
      "eval_loss": 0.60080486536026,
      "eval_runtime": 122.3284,
      "eval_samples_per_second": 63.763,
      "eval_steps_per_second": 0.499,
      "step": 8000
    },
    {
      "epoch": 0.6153623398248027,
      "grad_norm": 6.125587463378906,
      "learning_rate": 3.8463766017519734e-05,
      "loss": 0.6093,
      "step": 8500
    },
    {
      "epoch": 0.6153623398248027,
      "eval_loss": 0.6066346168518066,
      "eval_runtime": 122.3759,
      "eval_samples_per_second": 63.738,
      "eval_steps_per_second": 0.498,
      "step": 8500
    },
    {
      "epoch": 0.6515601245203794,
      "grad_norm": 6.668566703796387,
      "learning_rate": 3.4843987547962065e-05,
      "loss": 0.6107,
      "step": 9000
    },
    {
      "epoch": 0.6515601245203794,
      "eval_loss": 0.5826736688613892,
      "eval_runtime": 121.7463,
      "eval_samples_per_second": 64.068,
      "eval_steps_per_second": 0.501,
      "step": 9000
    },
    {
      "epoch": 0.687757909215956,
      "grad_norm": 5.720597267150879,
      "learning_rate": 3.12242090784044e-05,
      "loss": 0.5869,
      "step": 9500
    },
    {
      "epoch": 0.687757909215956,
      "eval_loss": 0.5872470736503601,
      "eval_runtime": 122.3512,
      "eval_samples_per_second": 63.751,
      "eval_steps_per_second": 0.499,
      "step": 9500
    },
    {
      "epoch": 0.7239556939115326,
      "grad_norm": 12.91817855834961,
      "learning_rate": 2.760443060884674e-05,
      "loss": 0.5907,
      "step": 10000
    },
    {
      "epoch": 0.7239556939115326,
      "eval_loss": 0.5741276741027832,
      "eval_runtime": 122.0844,
      "eval_samples_per_second": 63.89,
      "eval_steps_per_second": 0.5,
      "step": 10000
    },
    {
      "epoch": 0.7601534786071092,
      "grad_norm": 4.865262031555176,
      "learning_rate": 2.3984652139289076e-05,
      "loss": 0.591,
      "step": 10500
    },
    {
      "epoch": 0.7601534786071092,
      "eval_loss": 0.5652084350585938,
      "eval_runtime": 122.5281,
      "eval_samples_per_second": 63.659,
      "eval_steps_per_second": 0.498,
      "step": 10500
    },
    {
      "epoch": 0.7963512633026859,
      "grad_norm": 3.508721351623535,
      "learning_rate": 2.0364873669731413e-05,
      "loss": 0.5786,
      "step": 11000
    },
    {
      "epoch": 0.7963512633026859,
      "eval_loss": 0.5722984075546265,
      "eval_runtime": 122.2178,
      "eval_samples_per_second": 63.82,
      "eval_steps_per_second": 0.499,
      "step": 11000
    },
    {
      "epoch": 0.8325490479982625,
      "grad_norm": 5.5506272315979,
      "learning_rate": 1.674509520017375e-05,
      "loss": 0.5777,
      "step": 11500
    },
    {
      "epoch": 0.8325490479982625,
      "eval_loss": 0.5580069422721863,
      "eval_runtime": 122.1376,
      "eval_samples_per_second": 63.862,
      "eval_steps_per_second": 0.499,
      "step": 11500
    },
    {
      "epoch": 0.8687468326938391,
      "grad_norm": 5.747720241546631,
      "learning_rate": 1.3125316730616085e-05,
      "loss": 0.5837,
      "step": 12000
    },
    {
      "epoch": 0.8687468326938391,
      "eval_loss": 0.5526942014694214,
      "eval_runtime": 122.4022,
      "eval_samples_per_second": 63.724,
      "eval_steps_per_second": 0.498,
      "step": 12000
    },
    {
      "epoch": 0.9049446173894158,
      "grad_norm": 5.70701265335083,
      "learning_rate": 9.505538261058424e-06,
      "loss": 0.5565,
      "step": 12500
    },
    {
      "epoch": 0.9049446173894158,
      "eval_loss": 0.5394288301467896,
      "eval_runtime": 122.3157,
      "eval_samples_per_second": 63.769,
      "eval_steps_per_second": 0.499,
      "step": 12500
    },
    {
      "epoch": 0.9411424020849924,
      "grad_norm": 3.8808445930480957,
      "learning_rate": 5.885759791500761e-06,
      "loss": 0.5645,
      "step": 13000
    },
    {
      "epoch": 0.9411424020849924,
      "eval_loss": 0.5413234233856201,
      "eval_runtime": 122.1305,
      "eval_samples_per_second": 63.866,
      "eval_steps_per_second": 0.499,
      "step": 13000
    },
    {
      "epoch": 0.977340186780569,
      "grad_norm": 7.781164169311523,
      "learning_rate": 2.2659813219430974e-06,
      "loss": 0.5288,
      "step": 13500
    },
    {
      "epoch": 0.977340186780569,
      "eval_loss": 0.5362756848335266,
      "eval_runtime": 122.2122,
      "eval_samples_per_second": 63.823,
      "eval_steps_per_second": 0.499,
      "step": 13500
    }
  ],
  "logging_steps": 500,
  "max_steps": 13813,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.13688468946944e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}