{
  "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": 2.6524465084075928,
      "learning_rate": 0.0002,
      "loss": 0.9777,
      "step": 5
    },
    {
      "epoch": 0.05917159763313609,
      "grad_norm": 0.8162792325019836,
      "learning_rate": 0.0002,
      "loss": 0.4776,
      "step": 10
    },
    {
      "epoch": 0.08875739644970414,
      "grad_norm": 0.6695148348808289,
      "learning_rate": 0.0002,
      "loss": 0.4121,
      "step": 15
    },
    {
      "epoch": 0.11834319526627218,
      "grad_norm": 0.6613922715187073,
      "learning_rate": 0.0002,
      "loss": 0.3996,
      "step": 20
    },
    {
      "epoch": 0.14792899408284024,
      "grad_norm": 0.5690529346466064,
      "learning_rate": 0.0002,
      "loss": 0.3708,
      "step": 25
    },
    {
      "epoch": 0.17751479289940827,
      "grad_norm": 0.6801875233650208,
      "learning_rate": 0.0002,
      "loss": 0.3682,
      "step": 30
    },
    {
      "epoch": 0.20710059171597633,
      "grad_norm": 0.5573334097862244,
      "learning_rate": 0.0002,
      "loss": 0.3578,
      "step": 35
    },
    {
      "epoch": 0.23668639053254437,
      "grad_norm": 0.48602545261383057,
      "learning_rate": 0.0002,
      "loss": 0.3506,
      "step": 40
    },
    {
      "epoch": 0.26627218934911245,
      "grad_norm": 0.5038454532623291,
      "learning_rate": 0.0002,
      "loss": 0.3442,
      "step": 45
    },
    {
      "epoch": 0.2958579881656805,
      "grad_norm": 0.4245965778827667,
      "learning_rate": 0.0002,
      "loss": 0.3278,
      "step": 50
    },
    {
      "epoch": 0.3254437869822485,
      "grad_norm": 0.4995708465576172,
      "learning_rate": 0.0002,
      "loss": 0.3376,
      "step": 55
    },
    {
      "epoch": 0.35502958579881655,
      "grad_norm": 0.44329550862312317,
      "learning_rate": 0.0002,
      "loss": 0.3188,
      "step": 60
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 1.3675458431243896,
      "learning_rate": 0.0002,
      "loss": 0.3306,
      "step": 65
    },
    {
      "epoch": 0.41420118343195267,
      "grad_norm": 0.5217191576957703,
      "learning_rate": 0.0002,
      "loss": 0.3164,
      "step": 70
    },
    {
      "epoch": 0.4437869822485207,
      "grad_norm": 0.46393847465515137,
      "learning_rate": 0.0002,
      "loss": 0.3149,
      "step": 75
    },
    {
      "epoch": 0.47337278106508873,
      "grad_norm": 0.4221293330192566,
      "learning_rate": 0.0002,
      "loss": 0.3086,
      "step": 80
    },
    {
      "epoch": 0.5029585798816568,
      "grad_norm": 0.4734734892845154,
      "learning_rate": 0.0002,
      "loss": 0.3061,
      "step": 85
    },
    {
      "epoch": 0.5325443786982249,
      "grad_norm": 0.40803948044776917,
      "learning_rate": 0.0002,
      "loss": 0.2961,
      "step": 90
    },
    {
      "epoch": 0.5621301775147929,
      "grad_norm": 0.3886331617832184,
      "learning_rate": 0.0002,
      "loss": 0.306,
      "step": 95
    },
    {
      "epoch": 0.591715976331361,
      "grad_norm": 0.36911633610725403,
      "learning_rate": 0.0002,
      "loss": 0.2968,
      "step": 100
    },
    {
      "epoch": 0.621301775147929,
      "grad_norm": 0.42346394062042236,
      "learning_rate": 0.0002,
      "loss": 0.3021,
      "step": 105
    },
    {
      "epoch": 0.650887573964497,
      "grad_norm": 0.39378297328948975,
      "learning_rate": 0.0002,
      "loss": 0.2996,
      "step": 110
    },
    {
      "epoch": 0.6804733727810651,
      "grad_norm": 0.4639412462711334,
      "learning_rate": 0.0002,
      "loss": 0.3017,
      "step": 115
    },
    {
      "epoch": 0.7100591715976331,
      "grad_norm": 0.35044291615486145,
      "learning_rate": 0.0002,
      "loss": 0.2771,
      "step": 120
    },
    {
      "epoch": 0.7396449704142012,
      "grad_norm": 0.3248099386692047,
      "learning_rate": 0.0002,
      "loss": 0.3,
      "step": 125
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.36477237939834595,
      "learning_rate": 0.0002,
      "loss": 0.2783,
      "step": 130
    },
    {
      "epoch": 0.7988165680473372,
      "grad_norm": 0.3327581286430359,
      "learning_rate": 0.0002,
      "loss": 0.2737,
      "step": 135
    },
    {
      "epoch": 0.8284023668639053,
      "grad_norm": 0.3683614134788513,
      "learning_rate": 0.0002,
      "loss": 0.2932,
      "step": 140
    },
    {
      "epoch": 0.8579881656804734,
      "grad_norm": 0.39452311396598816,
      "learning_rate": 0.0002,
      "loss": 0.2822,
      "step": 145
    },
    {
      "epoch": 0.8875739644970414,
      "grad_norm": 0.3625282049179077,
      "learning_rate": 0.0002,
      "loss": 0.2833,
      "step": 150
    },
    {
      "epoch": 0.9171597633136095,
      "grad_norm": 0.3708689212799072,
      "learning_rate": 0.0002,
      "loss": 0.2744,
      "step": 155
    },
    {
      "epoch": 0.9467455621301775,
      "grad_norm": 0.35336822271347046,
      "learning_rate": 0.0002,
      "loss": 0.2804,
      "step": 160
    },
    {
      "epoch": 0.9763313609467456,
      "grad_norm": 0.3205427825450897,
      "learning_rate": 0.0002,
      "loss": 0.2875,
      "step": 165
    },
    {
      "epoch": 1.0,
      "step": 169,
      "total_flos": 1.3375939562333798e+17,
      "train_loss": 0.3392575450197479,
      "train_runtime": 1725.4456,
      "train_samples_per_second": 1.563,
      "train_steps_per_second": 0.098
    }
  ],
  "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": 1.3375939562333798e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}