{
  "best_metric": 1.0443669557571411,
  "best_model_checkpoint": "./output/checkpoints/2024-06-10_23-12-21/checkpoint-40",
  "epoch": 1.0,
  "eval_steps": 1,
  "global_step": 43,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023255813953488372,
      "grad_norm": 3.1748037338256836,
      "learning_rate": 8e-05,
      "loss": 5.1513,
      "step": 1
    },
    {
      "epoch": 0.023255813953488372,
      "eval_loss": 5.098567485809326,
      "eval_runtime": 10.4736,
      "eval_samples_per_second": 11.171,
      "eval_steps_per_second": 0.764,
      "step": 1
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 3.149711847305298,
      "learning_rate": 0.00016,
      "loss": 5.1556,
      "step": 2
    },
    {
      "epoch": 0.046511627906976744,
      "eval_loss": 4.689513683319092,
      "eval_runtime": 10.5409,
      "eval_samples_per_second": 11.1,
      "eval_steps_per_second": 0.759,
      "step": 2
    },
    {
      "epoch": 0.06976744186046512,
      "grad_norm": 3.1611013412475586,
      "learning_rate": 0.00024,
      "loss": 4.6255,
      "step": 3
    },
    {
      "epoch": 0.06976744186046512,
      "eval_loss": 3.2834692001342773,
      "eval_runtime": 10.5481,
      "eval_samples_per_second": 11.092,
      "eval_steps_per_second": 0.758,
      "step": 3
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 3.4506750106811523,
      "learning_rate": 0.00032,
      "loss": 3.268,
      "step": 4
    },
    {
      "epoch": 0.09302325581395349,
      "eval_loss": 2.105466604232788,
      "eval_runtime": 10.6124,
      "eval_samples_per_second": 11.025,
      "eval_steps_per_second": 0.754,
      "step": 4
    },
    {
      "epoch": 0.11627906976744186,
      "grad_norm": 2.139575719833374,
      "learning_rate": 0.0004,
      "loss": 2.0627,
      "step": 5
    },
    {
      "epoch": 0.11627906976744186,
      "eval_loss": 1.586738109588623,
      "eval_runtime": 10.5613,
      "eval_samples_per_second": 11.078,
      "eval_steps_per_second": 0.757,
      "step": 5
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 1.1181566715240479,
      "learning_rate": 0.00038947368421052633,
      "loss": 1.5525,
      "step": 6
    },
    {
      "epoch": 0.13953488372093023,
      "eval_loss": 1.442232608795166,
      "eval_runtime": 10.458,
      "eval_samples_per_second": 11.188,
      "eval_steps_per_second": 0.765,
      "step": 6
    },
    {
      "epoch": 0.16279069767441862,
      "grad_norm": 1.6108548641204834,
      "learning_rate": 0.00037894736842105265,
      "loss": 1.4249,
      "step": 7
    },
    {
      "epoch": 0.16279069767441862,
      "eval_loss": 1.2906938791275024,
      "eval_runtime": 10.5694,
      "eval_samples_per_second": 11.07,
      "eval_steps_per_second": 0.757,
      "step": 7
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 0.19699308276176453,
      "learning_rate": 0.00036842105263157896,
      "loss": 1.2713,
      "step": 8
    },
    {
      "epoch": 0.18604651162790697,
      "eval_loss": 1.2516891956329346,
      "eval_runtime": 10.4427,
      "eval_samples_per_second": 11.204,
      "eval_steps_per_second": 0.766,
      "step": 8
    },
    {
      "epoch": 0.20930232558139536,
      "grad_norm": 0.12418746948242188,
      "learning_rate": 0.0003578947368421053,
      "loss": 1.2447,
      "step": 9
    },
    {
      "epoch": 0.20930232558139536,
      "eval_loss": 1.2212988138198853,
      "eval_runtime": 10.4966,
      "eval_samples_per_second": 11.146,
      "eval_steps_per_second": 0.762,
      "step": 9
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 0.10525760799646378,
      "learning_rate": 0.0003473684210526316,
      "loss": 1.2071,
      "step": 10
    },
    {
      "epoch": 0.23255813953488372,
      "eval_loss": 1.1963647603988647,
      "eval_runtime": 10.5914,
      "eval_samples_per_second": 11.047,
      "eval_steps_per_second": 0.755,
      "step": 10
    },
    {
      "epoch": 0.2558139534883721,
      "grad_norm": 0.1781289279460907,
      "learning_rate": 0.0003368421052631579,
      "loss": 1.1832,
      "step": 11
    },
    {
      "epoch": 0.2558139534883721,
      "eval_loss": 1.1730906963348389,
      "eval_runtime": 10.565,
      "eval_samples_per_second": 11.074,
      "eval_steps_per_second": 0.757,
      "step": 11
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 0.16088849306106567,
      "learning_rate": 0.0003263157894736842,
      "loss": 1.1447,
      "step": 12
    },
    {
      "epoch": 0.27906976744186046,
      "eval_loss": 1.1521227359771729,
      "eval_runtime": 10.5741,
      "eval_samples_per_second": 11.065,
      "eval_steps_per_second": 0.757,
      "step": 12
    },
    {
      "epoch": 0.3023255813953488,
      "grad_norm": 0.11435263603925705,
      "learning_rate": 0.00031578947368421053,
      "loss": 1.1098,
      "step": 13
    },
    {
      "epoch": 0.3023255813953488,
      "eval_loss": 1.131661295890808,
      "eval_runtime": 10.5531,
      "eval_samples_per_second": 11.087,
      "eval_steps_per_second": 0.758,
      "step": 13
    },
    {
      "epoch": 0.32558139534883723,
      "grad_norm": 0.0963783711194992,
      "learning_rate": 0.0003052631578947369,
      "loss": 1.1298,
      "step": 14
    },
    {
      "epoch": 0.32558139534883723,
      "eval_loss": 1.115828275680542,
      "eval_runtime": 10.5575,
      "eval_samples_per_second": 11.082,
      "eval_steps_per_second": 0.758,
      "step": 14
    },
    {
      "epoch": 0.3488372093023256,
      "grad_norm": 0.0737914890050888,
      "learning_rate": 0.00029473684210526316,
      "loss": 1.0838,
      "step": 15
    },
    {
      "epoch": 0.3488372093023256,
      "eval_loss": 1.1041659116744995,
      "eval_runtime": 10.4999,
      "eval_samples_per_second": 11.143,
      "eval_steps_per_second": 0.762,
      "step": 15
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 0.06079930067062378,
      "learning_rate": 0.00028421052631578947,
      "loss": 1.0878,
      "step": 16
    },
    {
      "epoch": 0.37209302325581395,
      "eval_loss": 1.0959372520446777,
      "eval_runtime": 10.5731,
      "eval_samples_per_second": 11.066,
      "eval_steps_per_second": 0.757,
      "step": 16
    },
    {
      "epoch": 0.3953488372093023,
      "grad_norm": 0.05798230320215225,
      "learning_rate": 0.0002736842105263158,
      "loss": 1.0726,
      "step": 17
    },
    {
      "epoch": 0.3953488372093023,
      "eval_loss": 1.0892282724380493,
      "eval_runtime": 10.5989,
      "eval_samples_per_second": 11.039,
      "eval_steps_per_second": 0.755,
      "step": 17
    },
    {
      "epoch": 0.4186046511627907,
      "grad_norm": 0.05506344139575958,
      "learning_rate": 0.00026315789473684215,
      "loss": 1.0643,
      "step": 18
    },
    {
      "epoch": 0.4186046511627907,
      "eval_loss": 1.0838031768798828,
      "eval_runtime": 10.583,
      "eval_samples_per_second": 11.055,
      "eval_steps_per_second": 0.756,
      "step": 18
    },
    {
      "epoch": 0.4418604651162791,
      "grad_norm": 0.05198650062084198,
      "learning_rate": 0.0002526315789473684,
      "loss": 1.0661,
      "step": 19
    },
    {
      "epoch": 0.4418604651162791,
      "eval_loss": 1.0791563987731934,
      "eval_runtime": 10.5263,
      "eval_samples_per_second": 11.115,
      "eval_steps_per_second": 0.76,
      "step": 19
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 0.051451779901981354,
      "learning_rate": 0.00024210526315789475,
      "loss": 1.062,
      "step": 20
    },
    {
      "epoch": 0.46511627906976744,
      "eval_loss": 1.0747723579406738,
      "eval_runtime": 10.5633,
      "eval_samples_per_second": 11.076,
      "eval_steps_per_second": 0.757,
      "step": 20
    },
    {
      "epoch": 0.4883720930232558,
      "grad_norm": 0.04886360839009285,
      "learning_rate": 0.00023157894736842107,
      "loss": 1.0482,
      "step": 21
    },
    {
      "epoch": 0.4883720930232558,
      "eval_loss": 1.0707547664642334,
      "eval_runtime": 10.5723,
      "eval_samples_per_second": 11.067,
      "eval_steps_per_second": 0.757,
      "step": 21
    },
    {
      "epoch": 0.5116279069767442,
      "grad_norm": 0.04511698707938194,
      "learning_rate": 0.0002210526315789474,
      "loss": 1.0526,
      "step": 22
    },
    {
      "epoch": 0.5116279069767442,
      "eval_loss": 1.0674015283584595,
      "eval_runtime": 10.5187,
      "eval_samples_per_second": 11.123,
      "eval_steps_per_second": 0.761,
      "step": 22
    },
    {
      "epoch": 0.5348837209302325,
      "grad_norm": 0.049303531646728516,
      "learning_rate": 0.0002105263157894737,
      "loss": 1.0154,
      "step": 23
    },
    {
      "epoch": 0.5348837209302325,
      "eval_loss": 1.0645886659622192,
      "eval_runtime": 10.5824,
      "eval_samples_per_second": 11.056,
      "eval_steps_per_second": 0.756,
      "step": 23
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 0.13970467448234558,
      "learning_rate": 0.0002,
      "loss": 1.0336,
      "step": 24
    },
    {
      "epoch": 0.5581395348837209,
      "eval_loss": 1.0622761249542236,
      "eval_runtime": 10.5378,
      "eval_samples_per_second": 11.103,
      "eval_steps_per_second": 0.759,
      "step": 24
    },
    {
      "epoch": 0.5813953488372093,
      "grad_norm": 0.04498777911067009,
      "learning_rate": 0.00018947368421052632,
      "loss": 1.0727,
      "step": 25
    },
    {
      "epoch": 0.5813953488372093,
      "eval_loss": 1.0603291988372803,
      "eval_runtime": 10.5222,
      "eval_samples_per_second": 11.119,
      "eval_steps_per_second": 0.76,
      "step": 25
    },
    {
      "epoch": 0.6046511627906976,
      "grad_norm": 0.04431827366352081,
      "learning_rate": 0.00017894736842105264,
      "loss": 1.035,
      "step": 26
    },
    {
      "epoch": 0.6046511627906976,
      "eval_loss": 1.0584354400634766,
      "eval_runtime": 10.5855,
      "eval_samples_per_second": 11.053,
      "eval_steps_per_second": 0.756,
      "step": 26
    },
    {
      "epoch": 0.627906976744186,
      "grad_norm": 0.0488644503057003,
      "learning_rate": 0.00016842105263157895,
      "loss": 1.057,
      "step": 27
    },
    {
      "epoch": 0.627906976744186,
      "eval_loss": 1.0564749240875244,
      "eval_runtime": 10.5114,
      "eval_samples_per_second": 11.131,
      "eval_steps_per_second": 0.761,
      "step": 27
    },
    {
      "epoch": 0.6511627906976745,
      "grad_norm": 0.04599970951676369,
      "learning_rate": 0.00015789473684210527,
      "loss": 1.0386,
      "step": 28
    },
    {
      "epoch": 0.6511627906976745,
      "eval_loss": 1.0546391010284424,
      "eval_runtime": 10.536,
      "eval_samples_per_second": 11.105,
      "eval_steps_per_second": 0.759,
      "step": 28
    },
    {
      "epoch": 0.6744186046511628,
      "grad_norm": 0.04661059379577637,
      "learning_rate": 0.00014736842105263158,
      "loss": 1.0552,
      "step": 29
    },
    {
      "epoch": 0.6744186046511628,
      "eval_loss": 1.0529735088348389,
      "eval_runtime": 10.5645,
      "eval_samples_per_second": 11.075,
      "eval_steps_per_second": 0.757,
      "step": 29
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 0.04191095009446144,
      "learning_rate": 0.0001368421052631579,
      "loss": 1.0261,
      "step": 30
    },
    {
      "epoch": 0.6976744186046512,
      "eval_loss": 1.0515702962875366,
      "eval_runtime": 10.5459,
      "eval_samples_per_second": 11.094,
      "eval_steps_per_second": 0.759,
      "step": 30
    },
    {
      "epoch": 0.7209302325581395,
      "grad_norm": 0.04263598471879959,
      "learning_rate": 0.0001263157894736842,
      "loss": 1.0265,
      "step": 31
    },
    {
      "epoch": 0.7209302325581395,
      "eval_loss": 1.0504158735275269,
      "eval_runtime": 10.5618,
      "eval_samples_per_second": 11.078,
      "eval_steps_per_second": 0.757,
      "step": 31
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 0.043207377195358276,
      "learning_rate": 0.00011578947368421053,
      "loss": 1.038,
      "step": 32
    },
    {
      "epoch": 0.7441860465116279,
      "eval_loss": 1.049385905265808,
      "eval_runtime": 10.5765,
      "eval_samples_per_second": 11.062,
      "eval_steps_per_second": 0.756,
      "step": 32
    },
    {
      "epoch": 0.7674418604651163,
      "grad_norm": 0.0437220074236393,
      "learning_rate": 0.00010526315789473685,
      "loss": 1.0456,
      "step": 33
    },
    {
      "epoch": 0.7674418604651163,
      "eval_loss": 1.0484665632247925,
      "eval_runtime": 10.6182,
      "eval_samples_per_second": 11.019,
      "eval_steps_per_second": 0.753,
      "step": 33
    },
    {
      "epoch": 0.7906976744186046,
      "grad_norm": 0.04280296340584755,
      "learning_rate": 9.473684210526316e-05,
      "loss": 1.0339,
      "step": 34
    },
    {
      "epoch": 0.7906976744186046,
      "eval_loss": 1.047668218612671,
      "eval_runtime": 10.5375,
      "eval_samples_per_second": 11.103,
      "eval_steps_per_second": 0.759,
      "step": 34
    },
    {
      "epoch": 0.813953488372093,
      "grad_norm": 0.048476554453372955,
      "learning_rate": 8.421052631578948e-05,
      "loss": 1.0452,
      "step": 35
    },
    {
      "epoch": 0.813953488372093,
      "eval_loss": 1.0469459295272827,
      "eval_runtime": 10.5569,
      "eval_samples_per_second": 11.083,
      "eval_steps_per_second": 0.758,
      "step": 35
    },
    {
      "epoch": 0.8372093023255814,
      "grad_norm": 0.03983575850725174,
      "learning_rate": 7.368421052631579e-05,
      "loss": 1.0112,
      "step": 36
    },
    {
      "epoch": 0.8372093023255814,
      "eval_loss": 1.0462400913238525,
      "eval_runtime": 10.5644,
      "eval_samples_per_second": 11.075,
      "eval_steps_per_second": 0.757,
      "step": 36
    },
    {
      "epoch": 0.8604651162790697,
      "grad_norm": 0.04240667447447777,
      "learning_rate": 6.31578947368421e-05,
      "loss": 1.032,
      "step": 37
    },
    {
      "epoch": 0.8604651162790697,
      "eval_loss": 1.0456737279891968,
      "eval_runtime": 10.5478,
      "eval_samples_per_second": 11.092,
      "eval_steps_per_second": 0.758,
      "step": 37
    },
    {
      "epoch": 0.8837209302325582,
      "grad_norm": 0.04697669297456741,
      "learning_rate": 5.2631578947368424e-05,
      "loss": 1.0216,
      "step": 38
    },
    {
      "epoch": 0.8837209302325582,
      "eval_loss": 1.0451328754425049,
      "eval_runtime": 10.5909,
      "eval_samples_per_second": 11.047,
      "eval_steps_per_second": 0.755,
      "step": 38
    },
    {
      "epoch": 0.9069767441860465,
      "grad_norm": 0.04411022737622261,
      "learning_rate": 4.210526315789474e-05,
      "loss": 1.0367,
      "step": 39
    },
    {
      "epoch": 0.9069767441860465,
      "eval_loss": 1.0447440147399902,
      "eval_runtime": 10.5309,
      "eval_samples_per_second": 11.11,
      "eval_steps_per_second": 0.76,
      "step": 39
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 0.051756396889686584,
      "learning_rate": 3.157894736842105e-05,
      "loss": 1.0144,
      "step": 40
    },
    {
      "epoch": 0.9302325581395349,
      "eval_loss": 1.0443669557571411,
      "eval_runtime": 10.545,
      "eval_samples_per_second": 11.095,
      "eval_steps_per_second": 0.759,
      "step": 40
    },
    {
      "epoch": 0.9534883720930233,
      "grad_norm": 0.05069413781166077,
      "learning_rate": 2.105263157894737e-05,
      "loss": 1.0339,
      "step": 41
    },
    {
      "epoch": 0.9534883720930233,
      "eval_loss": 1.0441150665283203,
      "eval_runtime": 10.5475,
      "eval_samples_per_second": 11.093,
      "eval_steps_per_second": 0.758,
      "step": 41
    },
    {
      "epoch": 0.9767441860465116,
      "grad_norm": 0.03964732587337494,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 1.0046,
      "step": 42
    },
    {
      "epoch": 0.9767441860465116,
      "eval_loss": 1.043948769569397,
      "eval_runtime": 10.5196,
      "eval_samples_per_second": 11.122,
      "eval_steps_per_second": 0.76,
      "step": 42
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.06997141987085342,
      "learning_rate": 0.0,
      "loss": 1.0082,
      "step": 43
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.0438673496246338,
      "eval_runtime": 10.5692,
      "eval_samples_per_second": 11.07,
      "eval_steps_per_second": 0.757,
      "step": 43
    },
    {
      "epoch": 1.0,
      "step": 43,
      "total_flos": 1.5716557095174144e+16,
      "train_loss": 1.4361294785211252,
      "train_runtime": 852.0177,
      "train_samples_per_second": 1.592,
      "train_steps_per_second": 0.05
    }
  ],
  "logging_steps": 1,
  "max_steps": 43,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5716557095174144e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}