{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.19603038470963,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00098015192354815,
      "eval_loss": 10.373798370361328,
      "eval_runtime": 1.1582,
      "eval_samples_per_second": 371.252,
      "eval_steps_per_second": 185.626,
      "step": 1
    },
    {
      "epoch": 0.0098015192354815,
      "grad_norm": 0.036782316863536835,
      "learning_rate": 0.0002,
      "loss": 10.3749,
      "step": 10
    },
    {
      "epoch": 0.019603038470963,
      "grad_norm": 0.03539657965302467,
      "learning_rate": 0.0002,
      "loss": 10.3727,
      "step": 20
    },
    {
      "epoch": 0.029404557706444498,
      "grad_norm": 0.05783862620592117,
      "learning_rate": 0.0002,
      "loss": 10.3724,
      "step": 30
    },
    {
      "epoch": 0.039206076941926,
      "grad_norm": 0.054115310311317444,
      "learning_rate": 0.0002,
      "loss": 10.3728,
      "step": 40
    },
    {
      "epoch": 0.0490075961774075,
      "grad_norm": 0.07443208992481232,
      "learning_rate": 0.0002,
      "loss": 10.3677,
      "step": 50
    },
    {
      "epoch": 0.0490075961774075,
      "eval_loss": 10.365926742553711,
      "eval_runtime": 1.1706,
      "eval_samples_per_second": 367.33,
      "eval_steps_per_second": 183.665,
      "step": 50
    },
    {
      "epoch": 0.058809115412888996,
      "grad_norm": 0.08249140530824661,
      "learning_rate": 0.0002,
      "loss": 10.366,
      "step": 60
    },
    {
      "epoch": 0.0686106346483705,
      "grad_norm": 0.10592123121023178,
      "learning_rate": 0.0002,
      "loss": 10.3601,
      "step": 70
    },
    {
      "epoch": 0.078412153883852,
      "grad_norm": 0.09555134922266006,
      "learning_rate": 0.0002,
      "loss": 10.3583,
      "step": 80
    },
    {
      "epoch": 0.0882136731193335,
      "grad_norm": 0.10184665769338608,
      "learning_rate": 0.0002,
      "loss": 10.3525,
      "step": 90
    },
    {
      "epoch": 0.098015192354815,
      "grad_norm": 0.11435921490192413,
      "learning_rate": 0.0002,
      "loss": 10.3406,
      "step": 100
    },
    {
      "epoch": 0.098015192354815,
      "eval_loss": 10.337488174438477,
      "eval_runtime": 1.1718,
      "eval_samples_per_second": 366.95,
      "eval_steps_per_second": 183.475,
      "step": 100
    },
    {
      "epoch": 0.1078167115902965,
      "grad_norm": 0.08737977594137192,
      "learning_rate": 0.0002,
      "loss": 10.3371,
      "step": 110
    },
    {
      "epoch": 0.11761823082577799,
      "grad_norm": 0.08922211825847626,
      "learning_rate": 0.0002,
      "loss": 10.3303,
      "step": 120
    },
    {
      "epoch": 0.1274197500612595,
      "grad_norm": 0.05983508378267288,
      "learning_rate": 0.0002,
      "loss": 10.333,
      "step": 130
    },
    {
      "epoch": 0.137221269296741,
      "grad_norm": 0.07052959501743317,
      "learning_rate": 0.0002,
      "loss": 10.3318,
      "step": 140
    },
    {
      "epoch": 0.1470227885322225,
      "grad_norm": 0.08523882925510406,
      "learning_rate": 0.0002,
      "loss": 10.3309,
      "step": 150
    },
    {
      "epoch": 0.1470227885322225,
      "eval_loss": 10.32862663269043,
      "eval_runtime": 1.2288,
      "eval_samples_per_second": 349.922,
      "eval_steps_per_second": 174.961,
      "step": 150
    },
    {
      "epoch": 0.156824307767704,
      "grad_norm": 0.05235796049237251,
      "learning_rate": 0.0002,
      "loss": 10.3316,
      "step": 160
    },
    {
      "epoch": 0.16662582700318548,
      "grad_norm": 0.074577696621418,
      "learning_rate": 0.0002,
      "loss": 10.3277,
      "step": 170
    },
    {
      "epoch": 0.176427346238667,
      "grad_norm": 0.07419592142105103,
      "learning_rate": 0.0002,
      "loss": 10.3274,
      "step": 180
    },
    {
      "epoch": 0.1862288654741485,
      "grad_norm": 0.05108886584639549,
      "learning_rate": 0.0002,
      "loss": 10.3287,
      "step": 190
    },
    {
      "epoch": 0.19603038470963,
      "grad_norm": 0.1003885269165039,
      "learning_rate": 0.0002,
      "loss": 10.3248,
      "step": 200
    },
    {
      "epoch": 0.19603038470963,
      "eval_loss": 10.323884963989258,
      "eval_runtime": 1.2027,
      "eval_samples_per_second": 357.533,
      "eval_steps_per_second": 178.766,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2586181632000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}