{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008,
      "grad_norm": 0.6091650128364563,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 1.7915,
      "mean_token_accuracy": 0.6200876832008362,
      "step": 1
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.536028265953064,
      "learning_rate": 7.692307692307693e-05,
      "loss": 1.7044,
      "mean_token_accuracy": 0.6384097561240196,
      "step": 5
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.3632589876651764,
      "learning_rate": 0.00015384615384615385,
      "loss": 1.5683,
      "mean_token_accuracy": 0.6574486196041107,
      "step": 10
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.38857078552246094,
      "learning_rate": 0.00019984268150178167,
      "loss": 1.3468,
      "mean_token_accuracy": 0.6951748728752136,
      "step": 15
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.5654380321502686,
      "learning_rate": 0.00019807852804032305,
      "loss": 1.1075,
      "mean_token_accuracy": 0.7350626409053802,
      "step": 20
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.5035667419433594,
      "learning_rate": 0.00019438833303083678,
      "loss": 0.8489,
      "mean_token_accuracy": 0.8006348431110382,
      "step": 25
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.28405892848968506,
      "learning_rate": 0.00018884456359788724,
      "loss": 0.8182,
      "mean_token_accuracy": 0.8062106907367707,
      "step": 30
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.20907118916511536,
      "learning_rate": 0.00018155608689592604,
      "loss": 0.7165,
      "mean_token_accuracy": 0.8268509089946747,
      "step": 35
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.22087477147579193,
      "learning_rate": 0.0001726660322034027,
      "loss": 0.7139,
      "mean_token_accuracy": 0.8272643625736237,
      "step": 40
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.23085324466228485,
      "learning_rate": 0.00016234898018587337,
      "loss": 0.6703,
      "mean_token_accuracy": 0.8364481091499328,
      "step": 45
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.20583884418010712,
      "learning_rate": 0.00015080753452465296,
      "loss": 0.6077,
      "mean_token_accuracy": 0.8467150866985321,
      "step": 50
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.20109635591506958,
      "learning_rate": 0.000138268343236509,
      "loss": 0.6485,
      "mean_token_accuracy": 0.8379231691360474,
      "step": 55
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.19621974229812622,
      "learning_rate": 0.0001249776478167227,
      "loss": 0.661,
      "mean_token_accuracy": 0.8345841407775879,
      "step": 60
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.2204616218805313,
      "learning_rate": 0.00011119644761033078,
      "loss": 0.6226,
      "mean_token_accuracy": 0.8435723900794982,
      "step": 65
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.18189997971057892,
      "learning_rate": 9.719537437241312e-05,
      "loss": 0.5835,
      "mean_token_accuracy": 0.8532270193099976,
      "step": 70
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.2008037269115448,
      "learning_rate": 8.324937766952638e-05,
      "loss": 0.6159,
      "mean_token_accuracy": 0.8451593399047852,
      "step": 75
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.19920995831489563,
      "learning_rate": 6.963232548903853e-05,
      "loss": 0.6134,
      "mean_token_accuracy": 0.844947737455368,
      "step": 80
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.21071140468120575,
      "learning_rate": 5.6611626088244194e-05,
      "loss": 0.6287,
      "mean_token_accuracy": 0.8413995563983917,
      "step": 85
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.2002287358045578,
      "learning_rate": 4.444297669803981e-05,
      "loss": 0.5997,
      "mean_token_accuracy": 0.8461678445339202,
      "step": 90
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.2541356086730957,
      "learning_rate": 3.336534220479961e-05,
      "loss": 0.6379,
      "mean_token_accuracy": 0.8375702917575836,
      "step": 95
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.20431411266326904,
      "learning_rate": 2.3596262417839255e-05,
      "loss": 0.5859,
      "mean_token_accuracy": 0.8490248620510101,
      "step": 100
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.2237038016319275,
      "learning_rate": 1.5327580077171587e-05,
      "loss": 0.6047,
      "mean_token_accuracy": 0.8456766724586486,
      "step": 105
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.22031715512275696,
      "learning_rate": 8.72167349386811e-06,
      "loss": 0.5933,
      "mean_token_accuracy": 0.848451578617096,
      "step": 110
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.21197955310344696,
      "learning_rate": 3.908267805490051e-06,
      "loss": 0.6018,
      "mean_token_accuracy": 0.8468173623085022,
      "step": 115
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.20556138455867767,
      "learning_rate": 9.818874663554357e-07,
      "loss": 0.6277,
      "mean_token_accuracy": 0.8388452410697937,
      "step": 120
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2163011133670807,
      "learning_rate": 0.0,
      "loss": 0.6224,
      "mean_token_accuracy": 0.8408988118171692,
      "step": 125
    },
    {
      "epoch": 1.0,
      "step": 125,
      "total_flos": 4503614496178176.0,
      "train_loss": 0.7746698780059814,
      "train_runtime": 1219.5612,
      "train_samples_per_second": 0.82,
      "train_steps_per_second": 0.102
    }
  ],
  "logging_steps": 5,
  "max_steps": 125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4503614496178176.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}