{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0654205607476634,
  "eval_steps": 50,
  "global_step": 41,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 8.780062675476074,
      "learning_rate": 5e-06,
      "loss": 8.2172,
      "step": 1
    },
    {
      "epoch": 0.07476635514018691,
      "eval_loss": 8.38599967956543,
      "eval_runtime": 7.7537,
      "eval_samples_per_second": 5.804,
      "eval_steps_per_second": 1.548,
      "step": 1
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 8.064007759094238,
      "learning_rate": 1e-05,
      "loss": 8.2832,
      "step": 2
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": 8.712315559387207,
      "learning_rate": 1.5e-05,
      "loss": 8.3247,
      "step": 3
    },
    {
      "epoch": 0.29906542056074764,
      "grad_norm": 11.088969230651855,
      "learning_rate": 2e-05,
      "loss": 7.7675,
      "step": 4
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 10.736077308654785,
      "learning_rate": 2.5e-05,
      "loss": 7.8402,
      "step": 5
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": 8.06237506866455,
      "learning_rate": 3e-05,
      "loss": 7.3686,
      "step": 6
    },
    {
      "epoch": 0.5233644859813084,
      "grad_norm": 9.52974796295166,
      "learning_rate": 3.5e-05,
      "loss": 7.2657,
      "step": 7
    },
    {
      "epoch": 0.5981308411214953,
      "grad_norm": 11.75586986541748,
      "learning_rate": 4e-05,
      "loss": 6.6202,
      "step": 8
    },
    {
      "epoch": 0.6728971962616822,
      "grad_norm": 19.383455276489258,
      "learning_rate": 4.5e-05,
      "loss": 5.686,
      "step": 9
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 7.718400478363037,
      "learning_rate": 5e-05,
      "loss": 4.9268,
      "step": 10
    },
    {
      "epoch": 0.822429906542056,
      "grad_norm": 6.534321308135986,
      "learning_rate": 5.500000000000001e-05,
      "loss": 4.5849,
      "step": 11
    },
    {
      "epoch": 0.897196261682243,
      "grad_norm": 6.954132080078125,
      "learning_rate": 6e-05,
      "loss": 4.2024,
      "step": 12
    },
    {
      "epoch": 0.9719626168224299,
      "grad_norm": 7.563628196716309,
      "learning_rate": 6.500000000000001e-05,
      "loss": 4.0909,
      "step": 13
    },
    {
      "epoch": 1.0467289719626167,
      "grad_norm": 8.51435661315918,
      "learning_rate": 7e-05,
      "loss": 6.2748,
      "step": 14
    },
    {
      "epoch": 1.1214953271028036,
      "grad_norm": 6.701977252960205,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.3227,
      "step": 15
    },
    {
      "epoch": 1.1962616822429906,
      "grad_norm": 5.42073917388916,
      "learning_rate": 8e-05,
      "loss": 3.2101,
      "step": 16
    },
    {
      "epoch": 1.2710280373831775,
      "grad_norm": 3.776437282562256,
      "learning_rate": 8.5e-05,
      "loss": 3.0181,
      "step": 17
    },
    {
      "epoch": 1.3457943925233644,
      "grad_norm": 3.1761717796325684,
      "learning_rate": 9e-05,
      "loss": 3.0455,
      "step": 18
    },
    {
      "epoch": 1.4205607476635513,
      "grad_norm": 3.264157295227051,
      "learning_rate": 9.5e-05,
      "loss": 2.9087,
      "step": 19
    },
    {
      "epoch": 1.4953271028037383,
      "grad_norm": 3.1983323097229004,
      "learning_rate": 0.0001,
      "loss": 2.6551,
      "step": 20
    },
    {
      "epoch": 1.5700934579439252,
      "grad_norm": 2.9175479412078857,
      "learning_rate": 9.944154131125642e-05,
      "loss": 2.7306,
      "step": 21
    },
    {
      "epoch": 1.644859813084112,
      "grad_norm": 2.61401629447937,
      "learning_rate": 9.777864028930705e-05,
      "loss": 2.7251,
      "step": 22
    },
    {
      "epoch": 1.719626168224299,
      "grad_norm": 2.9465088844299316,
      "learning_rate": 9.504844339512095e-05,
      "loss": 2.5248,
      "step": 23
    },
    {
      "epoch": 1.794392523364486,
      "grad_norm": 3.1787397861480713,
      "learning_rate": 9.131193871579975e-05,
      "loss": 2.5716,
      "step": 24
    },
    {
      "epoch": 1.8691588785046729,
      "grad_norm": 2.694627285003662,
      "learning_rate": 8.665259359149132e-05,
      "loss": 2.4999,
      "step": 25
    },
    {
      "epoch": 1.9439252336448598,
      "grad_norm": 3.301701784133911,
      "learning_rate": 8.117449009293668e-05,
      "loss": 2.6129,
      "step": 26
    },
    {
      "epoch": 2.0186915887850465,
      "grad_norm": 4.524110794067383,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.0969,
      "step": 27
    },
    {
      "epoch": 2.0934579439252334,
      "grad_norm": 2.5733392238616943,
      "learning_rate": 6.826705121831976e-05,
      "loss": 2.257,
      "step": 28
    },
    {
      "epoch": 2.1682242990654204,
      "grad_norm": 2.506385564804077,
      "learning_rate": 6.112604669781572e-05,
      "loss": 1.9108,
      "step": 29
    },
    {
      "epoch": 2.2429906542056073,
      "grad_norm": 2.7191073894500732,
      "learning_rate": 5.373650467932122e-05,
      "loss": 1.979,
      "step": 30
    },
    {
      "epoch": 2.317757009345794,
      "grad_norm": 2.4766504764556885,
      "learning_rate": 4.626349532067879e-05,
      "loss": 1.8383,
      "step": 31
    },
    {
      "epoch": 2.392523364485981,
      "grad_norm": 2.5209503173828125,
      "learning_rate": 3.887395330218429e-05,
      "loss": 1.7818,
      "step": 32
    },
    {
      "epoch": 2.467289719626168,
      "grad_norm": 2.8152475357055664,
      "learning_rate": 3.173294878168025e-05,
      "loss": 1.9233,
      "step": 33
    },
    {
      "epoch": 2.542056074766355,
      "grad_norm": 2.721890449523926,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.8239,
      "step": 34
    },
    {
      "epoch": 2.616822429906542,
      "grad_norm": 2.8505470752716064,
      "learning_rate": 1.8825509907063327e-05,
      "loss": 1.618,
      "step": 35
    },
    {
      "epoch": 2.691588785046729,
      "grad_norm": 2.6732444763183594,
      "learning_rate": 1.3347406408508695e-05,
      "loss": 1.6795,
      "step": 36
    },
    {
      "epoch": 2.7663551401869158,
      "grad_norm": 3.0492546558380127,
      "learning_rate": 8.688061284200266e-06,
      "loss": 1.8503,
      "step": 37
    },
    {
      "epoch": 2.8411214953271027,
      "grad_norm": 3.09971022605896,
      "learning_rate": 4.951556604879048e-06,
      "loss": 1.7875,
      "step": 38
    },
    {
      "epoch": 2.9158878504672896,
      "grad_norm": 3.247302532196045,
      "learning_rate": 2.221359710692961e-06,
      "loss": 1.9095,
      "step": 39
    },
    {
      "epoch": 2.9906542056074765,
      "grad_norm": 4.865527153015137,
      "learning_rate": 5.584586887435739e-07,
      "loss": 2.507,
      "step": 40
    },
    {
      "epoch": 3.0654205607476634,
      "grad_norm": 3.7722809314727783,
      "learning_rate": 0.0,
      "loss": 1.8176,
      "step": 41
    }
  ],
  "logging_steps": 1,
  "max_steps": 41,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4711338061830554e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}