{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0028436018957345,
  "eval_steps": 66,
  "global_step": 264,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0037914691943127963,
      "eval_loss": 2.0063271522521973,
      "eval_runtime": 14.7339,
      "eval_samples_per_second": 7.534,
      "eval_steps_per_second": 3.801,
      "step": 1
    },
    {
      "epoch": 0.018957345971563982,
      "grad_norm": 4.575433254241943,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.316,
      "step": 5
    },
    {
      "epoch": 0.037914691943127965,
      "grad_norm": 1.6114368438720703,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.9077,
      "step": 10
    },
    {
      "epoch": 0.05687203791469194,
      "grad_norm": 1.59214448928833,
      "learning_rate": 5e-05,
      "loss": 1.1933,
      "step": 15
    },
    {
      "epoch": 0.07582938388625593,
      "grad_norm": 1.5013682842254639,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.1184,
      "step": 20
    },
    {
      "epoch": 0.0947867298578199,
      "grad_norm": 2.266918897628784,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.2437,
      "step": 25
    },
    {
      "epoch": 0.11374407582938388,
      "grad_norm": 2.5026302337646484,
      "learning_rate": 0.0001,
      "loss": 1.3318,
      "step": 30
    },
    {
      "epoch": 0.13270142180094788,
      "grad_norm": 4.762207984924316,
      "learning_rate": 9.988738792578126e-05,
      "loss": 1.3961,
      "step": 35
    },
    {
      "epoch": 0.15165876777251186,
      "grad_norm": 5.990009784698486,
      "learning_rate": 9.955005896229543e-05,
      "loss": 1.3369,
      "step": 40
    },
    {
      "epoch": 0.17061611374407584,
      "grad_norm": 13.45676326751709,
      "learning_rate": 9.898953260211338e-05,
      "loss": 1.6573,
      "step": 45
    },
    {
      "epoch": 0.1895734597156398,
      "grad_norm": 20.142257690429688,
      "learning_rate": 9.820833372667812e-05,
      "loss": 2.4071,
      "step": 50
    },
    {
      "epoch": 0.20853080568720378,
      "grad_norm": 2.136573314666748,
      "learning_rate": 9.720998123301923e-05,
      "loss": 1.3441,
      "step": 55
    },
    {
      "epoch": 0.22748815165876776,
      "grad_norm": 1.304834008216858,
      "learning_rate": 9.599897218294122e-05,
      "loss": 3.473,
      "step": 60
    },
    {
      "epoch": 0.24644549763033174,
      "grad_norm": 1.3176236152648926,
      "learning_rate": 9.458076154608515e-05,
      "loss": 1.0091,
      "step": 65
    },
    {
      "epoch": 0.2502369668246445,
      "eval_loss": 1.3693103790283203,
      "eval_runtime": 15.1018,
      "eval_samples_per_second": 7.35,
      "eval_steps_per_second": 3.708,
      "step": 66
    },
    {
      "epoch": 0.26540284360189575,
      "grad_norm": 1.3287938833236694,
      "learning_rate": 9.296173762811085e-05,
      "loss": 0.9501,
      "step": 70
    },
    {
      "epoch": 0.2843601895734597,
      "grad_norm": 2.3178670406341553,
      "learning_rate": 9.114919329468282e-05,
      "loss": 1.1101,
      "step": 75
    },
    {
      "epoch": 0.3033175355450237,
      "grad_norm": 3.3593289852142334,
      "learning_rate": 8.915129312088112e-05,
      "loss": 1.1248,
      "step": 80
    },
    {
      "epoch": 0.3222748815165877,
      "grad_norm": 2.683689832687378,
      "learning_rate": 8.697703661401186e-05,
      "loss": 1.0555,
      "step": 85
    },
    {
      "epoch": 0.3412322274881517,
      "grad_norm": 2.545621871948242,
      "learning_rate": 8.463621767547998e-05,
      "loss": 0.9885,
      "step": 90
    },
    {
      "epoch": 0.36018957345971564,
      "grad_norm": 6.741793155670166,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.3054,
      "step": 95
    },
    {
      "epoch": 0.3791469194312796,
      "grad_norm": 30.347795486450195,
      "learning_rate": 7.949777200115616e-05,
      "loss": 2.2587,
      "step": 100
    },
    {
      "epoch": 0.3981042654028436,
      "grad_norm": 0.6259477138519287,
      "learning_rate": 7.672329130639005e-05,
      "loss": 0.9893,
      "step": 105
    },
    {
      "epoch": 0.41706161137440756,
      "grad_norm": 1.175485372543335,
      "learning_rate": 7.38284360010654e-05,
      "loss": 3.1866,
      "step": 110
    },
    {
      "epoch": 0.43601895734597157,
      "grad_norm": 1.1434948444366455,
      "learning_rate": 7.082624591160201e-05,
      "loss": 1.0689,
      "step": 115
    },
    {
      "epoch": 0.4549763033175355,
      "grad_norm": 2.3580820560455322,
      "learning_rate": 6.773024435212678e-05,
      "loss": 1.1477,
      "step": 120
    },
    {
      "epoch": 0.47393364928909953,
      "grad_norm": 1.5657998323440552,
      "learning_rate": 6.455437720893564e-05,
      "loss": 0.8839,
      "step": 125
    },
    {
      "epoch": 0.4928909952606635,
      "grad_norm": 2.185641288757324,
      "learning_rate": 6.131295012148612e-05,
      "loss": 1.0864,
      "step": 130
    },
    {
      "epoch": 0.500473933649289,
      "eval_loss": 1.240807056427002,
      "eval_runtime": 14.9134,
      "eval_samples_per_second": 7.443,
      "eval_steps_per_second": 3.755,
      "step": 132
    },
    {
      "epoch": 0.5118483412322274,
      "grad_norm": 2.4784717559814453,
      "learning_rate": 5.8020564042888015e-05,
      "loss": 0.9521,
      "step": 135
    },
    {
      "epoch": 0.5308056872037915,
      "grad_norm": 4.177745342254639,
      "learning_rate": 5.469204947015897e-05,
      "loss": 1.1792,
      "step": 140
    },
    {
      "epoch": 0.5497630331753555,
      "grad_norm": 9.582822799682617,
      "learning_rate": 5.134239964050307e-05,
      "loss": 1.4924,
      "step": 145
    },
    {
      "epoch": 0.5687203791469194,
      "grad_norm": 15.12871265411377,
      "learning_rate": 4.798670299452926e-05,
      "loss": 2.0682,
      "step": 150
    },
    {
      "epoch": 0.5876777251184834,
      "grad_norm": 1.2145541906356812,
      "learning_rate": 4.4640075210627615e-05,
      "loss": 0.9506,
      "step": 155
    },
    {
      "epoch": 0.6066350710900474,
      "grad_norm": 0.9340455532073975,
      "learning_rate": 4.131759111665349e-05,
      "loss": 3.1557,
      "step": 160
    },
    {
      "epoch": 0.6255924170616114,
      "grad_norm": 1.0512124300003052,
      "learning_rate": 3.803421678562213e-05,
      "loss": 1.3106,
      "step": 165
    },
    {
      "epoch": 0.6445497630331753,
      "grad_norm": 1.033964991569519,
      "learning_rate": 3.480474212128766e-05,
      "loss": 1.1408,
      "step": 170
    },
    {
      "epoch": 0.6635071090047393,
      "grad_norm": 1.7510710954666138,
      "learning_rate": 3.164371423727362e-05,
      "loss": 0.8601,
      "step": 175
    },
    {
      "epoch": 0.6824644549763034,
      "grad_norm": 1.9360414743423462,
      "learning_rate": 2.8565371929847284e-05,
      "loss": 1.1003,
      "step": 180
    },
    {
      "epoch": 0.7014218009478673,
      "grad_norm": 1.985480785369873,
      "learning_rate": 2.5583581539504464e-05,
      "loss": 0.9948,
      "step": 185
    },
    {
      "epoch": 0.7203791469194313,
      "grad_norm": 3.7504513263702393,
      "learning_rate": 2.2711774490274766e-05,
      "loss": 1.152,
      "step": 190
    },
    {
      "epoch": 0.7393364928909952,
      "grad_norm": 4.799010753631592,
      "learning_rate": 1.996288678810105e-05,
      "loss": 1.4613,
      "step": 195
    },
    {
      "epoch": 0.7507109004739336,
      "eval_loss": 1.1724706888198853,
      "eval_runtime": 15.1001,
      "eval_samples_per_second": 7.351,
      "eval_steps_per_second": 3.709,
      "step": 198
    },
    {
      "epoch": 0.7582938388625592,
      "grad_norm": 36.87416076660156,
      "learning_rate": 1.734930075082076e-05,
      "loss": 1.8898,
      "step": 200
    },
    {
      "epoch": 0.7772511848341233,
      "grad_norm": 0.7642176151275635,
      "learning_rate": 1.4882789232226125e-05,
      "loss": 1.1519,
      "step": 205
    },
    {
      "epoch": 0.7962085308056872,
      "grad_norm": 0.675323486328125,
      "learning_rate": 1.257446259144494e-05,
      "loss": 2.5007,
      "step": 210
    },
    {
      "epoch": 0.8151658767772512,
      "grad_norm": 1.0708622932434082,
      "learning_rate": 1.0434718646516917e-05,
      "loss": 0.8607,
      "step": 215
    },
    {
      "epoch": 0.8341232227488151,
      "grad_norm": 2.112217664718628,
      "learning_rate": 8.473195837599418e-06,
      "loss": 0.9331,
      "step": 220
    },
    {
      "epoch": 0.8530805687203792,
      "grad_norm": 1.9522455930709839,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.1168,
      "step": 225
    },
    {
      "epoch": 0.8720379146919431,
      "grad_norm": 2.002206563949585,
      "learning_rate": 5.1193136180493095e-06,
      "loss": 0.9973,
      "step": 230
    },
    {
      "epoch": 0.8909952606635071,
      "grad_norm": 1.8621110916137695,
      "learning_rate": 3.7420617127538248e-06,
      "loss": 0.9534,
      "step": 235
    },
    {
      "epoch": 0.909952606635071,
      "grad_norm": 3.7210357189178467,
      "learning_rate": 2.573177902642726e-06,
      "loss": 1.2029,
      "step": 240
    },
    {
      "epoch": 0.9289099526066351,
      "grad_norm": 3.859623670578003,
      "learning_rate": 1.6179274049310966e-06,
      "loss": 1.4043,
      "step": 245
    },
    {
      "epoch": 0.9478672985781991,
      "grad_norm": 15.304886817932129,
      "learning_rate": 8.806131292167618e-07,
      "loss": 2.086,
      "step": 250
    },
    {
      "epoch": 0.966824644549763,
      "grad_norm": 1.3227756023406982,
      "learning_rate": 3.6455629509730136e-07,
      "loss": 1.6543,
      "step": 255
    },
    {
      "epoch": 0.985781990521327,
      "grad_norm": 2.1567444801330566,
      "learning_rate": 7.208147179291192e-08,
      "loss": 1.0496,
      "step": 260
    },
    {
      "epoch": 1.0028436018957345,
      "eval_loss": 1.1479114294052124,
      "eval_runtime": 15.1375,
      "eval_samples_per_second": 7.333,
      "eval_steps_per_second": 3.699,
      "step": 264
    }
  ],
  "logging_steps": 5,
  "max_steps": 264,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.631756088414044e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}