{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04498931503767855,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00022494657518839275,
      "eval_loss": 1.3146981000900269,
      "eval_runtime": 67.0104,
      "eval_samples_per_second": 13.968,
      "eval_steps_per_second": 6.984,
      "step": 1
    },
    {
      "epoch": 0.0022494657518839275,
      "grad_norm": 1.1338897943496704,
      "learning_rate": 0.0002,
      "loss": 2.5636,
      "step": 10
    },
    {
      "epoch": 0.004498931503767855,
      "grad_norm": 1.8249558210372925,
      "learning_rate": 0.0002,
      "loss": 2.5914,
      "step": 20
    },
    {
      "epoch": 0.0067483972556517825,
      "grad_norm": 1.2825453281402588,
      "learning_rate": 0.0002,
      "loss": 2.4154,
      "step": 30
    },
    {
      "epoch": 0.00899786300753571,
      "grad_norm": 2.0352253913879395,
      "learning_rate": 0.0002,
      "loss": 2.4877,
      "step": 40
    },
    {
      "epoch": 0.011247328759419637,
      "grad_norm": 0.9270350337028503,
      "learning_rate": 0.0002,
      "loss": 2.0619,
      "step": 50
    },
    {
      "epoch": 0.011247328759419637,
      "eval_loss": 1.2109270095825195,
      "eval_runtime": 67.0303,
      "eval_samples_per_second": 13.964,
      "eval_steps_per_second": 6.982,
      "step": 50
    },
    {
      "epoch": 0.013496794511303565,
      "grad_norm": 1.5693869590759277,
      "learning_rate": 0.0002,
      "loss": 2.3889,
      "step": 60
    },
    {
      "epoch": 0.015746260263187494,
      "grad_norm": 1.03313148021698,
      "learning_rate": 0.0002,
      "loss": 2.2495,
      "step": 70
    },
    {
      "epoch": 0.01799572601507142,
      "grad_norm": 1.0436208248138428,
      "learning_rate": 0.0002,
      "loss": 2.6946,
      "step": 80
    },
    {
      "epoch": 0.02024519176695535,
      "grad_norm": 1.4744815826416016,
      "learning_rate": 0.0002,
      "loss": 2.2621,
      "step": 90
    },
    {
      "epoch": 0.022494657518839275,
      "grad_norm": 2.6527371406555176,
      "learning_rate": 0.0002,
      "loss": 2.5709,
      "step": 100
    },
    {
      "epoch": 0.022494657518839275,
      "eval_loss": 1.192226529121399,
      "eval_runtime": 67.1155,
      "eval_samples_per_second": 13.946,
      "eval_steps_per_second": 6.973,
      "step": 100
    },
    {
      "epoch": 0.024744123270723204,
      "grad_norm": 1.56536066532135,
      "learning_rate": 0.0002,
      "loss": 2.2297,
      "step": 110
    },
    {
      "epoch": 0.02699358902260713,
      "grad_norm": 1.3520946502685547,
      "learning_rate": 0.0002,
      "loss": 2.2107,
      "step": 120
    },
    {
      "epoch": 0.02924305477449106,
      "grad_norm": 0.8982442021369934,
      "learning_rate": 0.0002,
      "loss": 2.5156,
      "step": 130
    },
    {
      "epoch": 0.03149252052637499,
      "grad_norm": 2.5134899616241455,
      "learning_rate": 0.0002,
      "loss": 1.9862,
      "step": 140
    },
    {
      "epoch": 0.03374198627825891,
      "grad_norm": 1.1740270853042603,
      "learning_rate": 0.0002,
      "loss": 2.0565,
      "step": 150
    },
    {
      "epoch": 0.03374198627825891,
      "eval_loss": 1.182604432106018,
      "eval_runtime": 67.1743,
      "eval_samples_per_second": 13.934,
      "eval_steps_per_second": 6.967,
      "step": 150
    },
    {
      "epoch": 0.03599145203014284,
      "grad_norm": 0.9191089272499084,
      "learning_rate": 0.0002,
      "loss": 2.2336,
      "step": 160
    },
    {
      "epoch": 0.03824091778202677,
      "grad_norm": 3.097604274749756,
      "learning_rate": 0.0002,
      "loss": 2.3238,
      "step": 170
    },
    {
      "epoch": 0.0404903835339107,
      "grad_norm": 1.0487302541732788,
      "learning_rate": 0.0002,
      "loss": 2.3465,
      "step": 180
    },
    {
      "epoch": 0.04273984928579462,
      "grad_norm": 1.4951366186141968,
      "learning_rate": 0.0002,
      "loss": 2.3439,
      "step": 190
    },
    {
      "epoch": 0.04498931503767855,
      "grad_norm": 2.0182831287384033,
      "learning_rate": 0.0002,
      "loss": 2.3684,
      "step": 200
    },
    {
      "epoch": 0.04498931503767855,
      "eval_loss": 1.179027795791626,
      "eval_runtime": 67.2842,
      "eval_samples_per_second": 13.911,
      "eval_steps_per_second": 6.956,
      "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": 4.97508017504256e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}