{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011886013134044512,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.943006567022257e-05,
      "eval_loss": 2.6626617908477783,
      "eval_runtime": 470.5912,
      "eval_samples_per_second": 15.056,
      "eval_steps_per_second": 7.529,
      "step": 1
    },
    {
      "epoch": 0.0005943006567022257,
      "grad_norm": 0.6062536239624023,
      "learning_rate": 0.0002,
      "loss": 2.4368,
      "step": 10
    },
    {
      "epoch": 0.0011886013134044513,
      "grad_norm": 0.45512208342552185,
      "learning_rate": 0.0002,
      "loss": 2.2546,
      "step": 20
    },
    {
      "epoch": 0.001782901970106677,
      "grad_norm": 0.49260321259498596,
      "learning_rate": 0.0002,
      "loss": 2.2256,
      "step": 30
    },
    {
      "epoch": 0.0023772026268089027,
      "grad_norm": 0.48497384786605835,
      "learning_rate": 0.0002,
      "loss": 2.2565,
      "step": 40
    },
    {
      "epoch": 0.002971503283511128,
      "grad_norm": 0.44261446595191956,
      "learning_rate": 0.0002,
      "loss": 2.2375,
      "step": 50
    },
    {
      "epoch": 0.002971503283511128,
      "eval_loss": 2.2133359909057617,
      "eval_runtime": 470.7348,
      "eval_samples_per_second": 15.051,
      "eval_steps_per_second": 7.527,
      "step": 50
    },
    {
      "epoch": 0.003565803940213354,
      "grad_norm": 0.46642744541168213,
      "learning_rate": 0.0002,
      "loss": 2.2245,
      "step": 60
    },
    {
      "epoch": 0.00416010459691558,
      "grad_norm": 0.46836933493614197,
      "learning_rate": 0.0002,
      "loss": 2.1641,
      "step": 70
    },
    {
      "epoch": 0.004754405253617805,
      "grad_norm": 0.5460557341575623,
      "learning_rate": 0.0002,
      "loss": 2.2276,
      "step": 80
    },
    {
      "epoch": 0.005348705910320031,
      "grad_norm": 0.5021308064460754,
      "learning_rate": 0.0002,
      "loss": 2.2139,
      "step": 90
    },
    {
      "epoch": 0.005943006567022256,
      "grad_norm": 0.5295082330703735,
      "learning_rate": 0.0002,
      "loss": 2.1527,
      "step": 100
    },
    {
      "epoch": 0.005943006567022256,
      "eval_loss": 2.18870210647583,
      "eval_runtime": 470.6047,
      "eval_samples_per_second": 15.055,
      "eval_steps_per_second": 7.529,
      "step": 100
    },
    {
      "epoch": 0.0065373072237244825,
      "grad_norm": 0.43450927734375,
      "learning_rate": 0.0002,
      "loss": 2.1958,
      "step": 110
    },
    {
      "epoch": 0.007131607880426708,
      "grad_norm": 0.5573306083679199,
      "learning_rate": 0.0002,
      "loss": 2.1506,
      "step": 120
    },
    {
      "epoch": 0.007725908537128933,
      "grad_norm": 0.7600811123847961,
      "learning_rate": 0.0002,
      "loss": 2.1196,
      "step": 130
    },
    {
      "epoch": 0.00832020919383116,
      "grad_norm": 0.449724942445755,
      "learning_rate": 0.0002,
      "loss": 2.2089,
      "step": 140
    },
    {
      "epoch": 0.008914509850533384,
      "grad_norm": 0.48421597480773926,
      "learning_rate": 0.0002,
      "loss": 2.216,
      "step": 150
    },
    {
      "epoch": 0.008914509850533384,
      "eval_loss": 2.1804769039154053,
      "eval_runtime": 470.7404,
      "eval_samples_per_second": 15.051,
      "eval_steps_per_second": 7.526,
      "step": 150
    },
    {
      "epoch": 0.00950881050723561,
      "grad_norm": 0.5594499707221985,
      "learning_rate": 0.0002,
      "loss": 2.1633,
      "step": 160
    },
    {
      "epoch": 0.010103111163937837,
      "grad_norm": 0.5630470514297485,
      "learning_rate": 0.0002,
      "loss": 2.2145,
      "step": 170
    },
    {
      "epoch": 0.010697411820640062,
      "grad_norm": 0.525554358959198,
      "learning_rate": 0.0002,
      "loss": 2.1271,
      "step": 180
    },
    {
      "epoch": 0.011291712477342288,
      "grad_norm": 0.5869236588478088,
      "learning_rate": 0.0002,
      "loss": 2.1515,
      "step": 190
    },
    {
      "epoch": 0.011886013134044512,
      "grad_norm": 0.5470851063728333,
      "learning_rate": 0.0002,
      "loss": 2.1862,
      "step": 200
    },
    {
      "epoch": 0.011886013134044512,
      "eval_loss": 2.172609567642212,
      "eval_runtime": 470.6463,
      "eval_samples_per_second": 15.054,
      "eval_steps_per_second": 7.528,
      "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": 5.710785240209818e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}