{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 169,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029585798816568046,
      "grad_norm": 2.8798646926879883,
      "learning_rate": 0.0002,
      "loss": 0.9728,
      "step": 5
    },
    {
      "epoch": 0.05917159763313609,
      "grad_norm": 0.8563704490661621,
      "learning_rate": 0.0002,
      "loss": 0.4818,
      "step": 10
    },
    {
      "epoch": 0.08875739644970414,
      "grad_norm": 0.6149247288703918,
      "learning_rate": 0.0002,
      "loss": 0.409,
      "step": 15
    },
    {
      "epoch": 0.11834319526627218,
      "grad_norm": 0.6278108954429626,
      "learning_rate": 0.0002,
      "loss": 0.41,
      "step": 20
    },
    {
      "epoch": 0.14792899408284024,
      "grad_norm": 0.6502833962440491,
      "learning_rate": 0.0002,
      "loss": 0.3889,
      "step": 25
    },
    {
      "epoch": 0.17751479289940827,
      "grad_norm": 0.4965257942676544,
      "learning_rate": 0.0002,
      "loss": 0.3566,
      "step": 30
    },
    {
      "epoch": 0.20710059171597633,
      "grad_norm": 0.5162677764892578,
      "learning_rate": 0.0002,
      "loss": 0.3501,
      "step": 35
    },
    {
      "epoch": 0.23668639053254437,
      "grad_norm": 0.5184158682823181,
      "learning_rate": 0.0002,
      "loss": 0.3403,
      "step": 40
    },
    {
      "epoch": 0.26627218934911245,
      "grad_norm": 0.5881743431091309,
      "learning_rate": 0.0002,
      "loss": 0.3298,
      "step": 45
    },
    {
      "epoch": 0.2958579881656805,
      "grad_norm": 0.5391240119934082,
      "learning_rate": 0.0002,
      "loss": 0.3357,
      "step": 50
    },
    {
      "epoch": 0.3254437869822485,
      "grad_norm": 0.5666182637214661,
      "learning_rate": 0.0002,
      "loss": 0.3275,
      "step": 55
    },
    {
      "epoch": 0.35502958579881655,
      "grad_norm": 0.48206210136413574,
      "learning_rate": 0.0002,
      "loss": 0.3305,
      "step": 60
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.5350416302680969,
      "learning_rate": 0.0002,
      "loss": 0.3332,
      "step": 65
    },
    {
      "epoch": 0.41420118343195267,
      "grad_norm": 0.46314942836761475,
      "learning_rate": 0.0002,
      "loss": 0.322,
      "step": 70
    },
    {
      "epoch": 0.4437869822485207,
      "grad_norm": 0.5748676657676697,
      "learning_rate": 0.0002,
      "loss": 0.3155,
      "step": 75
    },
    {
      "epoch": 0.47337278106508873,
      "grad_norm": 0.5200490355491638,
      "learning_rate": 0.0002,
      "loss": 0.3176,
      "step": 80
    },
    {
      "epoch": 0.5029585798816568,
      "grad_norm": 0.9615280628204346,
      "learning_rate": 0.0002,
      "loss": 0.2974,
      "step": 85
    },
    {
      "epoch": 0.5325443786982249,
      "grad_norm": 0.4187004566192627,
      "learning_rate": 0.0002,
      "loss": 0.3195,
      "step": 90
    },
    {
      "epoch": 0.5621301775147929,
      "grad_norm": 6.856645584106445,
      "learning_rate": 0.0002,
      "loss": 0.3072,
      "step": 95
    },
    {
      "epoch": 0.591715976331361,
      "grad_norm": 0.4104371964931488,
      "learning_rate": 0.0002,
      "loss": 0.2993,
      "step": 100
    },
    {
      "epoch": 0.621301775147929,
      "grad_norm": 0.40844306349754333,
      "learning_rate": 0.0002,
      "loss": 0.3151,
      "step": 105
    },
    {
      "epoch": 0.650887573964497,
      "grad_norm": 0.3981234133243561,
      "learning_rate": 0.0002,
      "loss": 0.2849,
      "step": 110
    },
    {
      "epoch": 0.6804733727810651,
      "grad_norm": 0.4282432496547699,
      "learning_rate": 0.0002,
      "loss": 0.3085,
      "step": 115
    },
    {
      "epoch": 0.7100591715976331,
      "grad_norm": 0.43276387453079224,
      "learning_rate": 0.0002,
      "loss": 0.3114,
      "step": 120
    },
    {
      "epoch": 0.7396449704142012,
      "grad_norm": 0.6382061839103699,
      "learning_rate": 0.0002,
      "loss": 0.2861,
      "step": 125
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.37785038352012634,
      "learning_rate": 0.0002,
      "loss": 0.3055,
      "step": 130
    },
    {
      "epoch": 0.7988165680473372,
      "grad_norm": 0.3209759294986725,
      "learning_rate": 0.0002,
      "loss": 0.2811,
      "step": 135
    },
    {
      "epoch": 0.8284023668639053,
      "grad_norm": 0.35694730281829834,
      "learning_rate": 0.0002,
      "loss": 0.2746,
      "step": 140
    },
    {
      "epoch": 0.8579881656804734,
      "grad_norm": 1.352852463722229,
      "learning_rate": 0.0002,
      "loss": 0.3107,
      "step": 145
    },
    {
      "epoch": 0.8875739644970414,
      "grad_norm": 0.3421157896518707,
      "learning_rate": 0.0002,
      "loss": 0.2829,
      "step": 150
    },
    {
      "epoch": 0.9171597633136095,
      "grad_norm": 0.3395731449127197,
      "learning_rate": 0.0002,
      "loss": 0.288,
      "step": 155
    },
    {
      "epoch": 0.9467455621301775,
      "grad_norm": 0.33509358763694763,
      "learning_rate": 0.0002,
      "loss": 0.2894,
      "step": 160
    },
    {
      "epoch": 0.9763313609467456,
      "grad_norm": 0.3939138948917389,
      "learning_rate": 0.0002,
      "loss": 0.2941,
      "step": 165
    },
    {
      "epoch": 1.0,
      "step": 169,
      "total_flos": 1.3410656498535629e+17,
      "train_loss": 0.3432579195711034,
      "train_runtime": 1711.473,
      "train_samples_per_second": 1.58,
      "train_steps_per_second": 0.099
    }
  ],
  "logging_steps": 5,
  "max_steps": 169,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3410656498535629e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}