{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9655172413793105,
  "eval_steps": 500,
  "global_step": 72,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.027586206896551724,
      "grad_norm": 0.11144802174556881,
      "learning_rate": 1.25e-06,
      "loss": 0.5051,
      "step": 1
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": 0.09698752219012007,
      "learning_rate": 6.25e-06,
      "loss": 0.4632,
      "step": 5
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": 0.13519388776130348,
      "learning_rate": 9.975923633360985e-06,
      "loss": 0.469,
      "step": 10
    },
    {
      "epoch": 0.41379310344827586,
      "grad_norm": 0.1106782389090889,
      "learning_rate": 9.707720325915105e-06,
      "loss": 0.4652,
      "step": 15
    },
    {
      "epoch": 0.5517241379310345,
      "grad_norm": 0.06857565054861327,
      "learning_rate": 9.157348061512728e-06,
      "loss": 0.43,
      "step": 20
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.06552544372541018,
      "learning_rate": 8.357794774235094e-06,
      "loss": 0.427,
      "step": 25
    },
    {
      "epoch": 0.8275862068965517,
      "grad_norm": 0.060081588920205875,
      "learning_rate": 7.3569836841299905e-06,
      "loss": 0.4102,
      "step": 30
    },
    {
      "epoch": 0.9655172413793104,
      "grad_norm": 0.05602335659496659,
      "learning_rate": 6.21490089951632e-06,
      "loss": 0.4186,
      "step": 35
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.42343464493751526,
      "eval_runtime": 28.7921,
      "eval_samples_per_second": 18.929,
      "eval_steps_per_second": 4.758,
      "step": 37
    },
    {
      "epoch": 1.0827586206896551,
      "grad_norm": 0.05373545774087006,
      "learning_rate": 5e-06,
      "loss": 0.4036,
      "step": 40
    },
    {
      "epoch": 1.2206896551724138,
      "grad_norm": 0.053670223651931796,
      "learning_rate": 3.7850991004836813e-06,
      "loss": 0.3594,
      "step": 45
    },
    {
      "epoch": 1.3586206896551725,
      "grad_norm": 0.05692045100097061,
      "learning_rate": 2.6430163158700116e-06,
      "loss": 0.3676,
      "step": 50
    },
    {
      "epoch": 1.4965517241379311,
      "grad_norm": 0.050380887654109356,
      "learning_rate": 1.642205225764908e-06,
      "loss": 0.3407,
      "step": 55
    },
    {
      "epoch": 1.6344827586206896,
      "grad_norm": 0.048983382324476604,
      "learning_rate": 8.426519384872733e-07,
      "loss": 0.3724,
      "step": 60
    },
    {
      "epoch": 1.7724137931034483,
      "grad_norm": 0.048686689507392925,
      "learning_rate": 2.9227967408489653e-07,
      "loss": 0.3631,
      "step": 65
    },
    {
      "epoch": 1.910344827586207,
      "grad_norm": 0.049007540032715985,
      "learning_rate": 2.4076366639015914e-08,
      "loss": 0.35,
      "step": 70
    },
    {
      "epoch": 1.9655172413793105,
      "eval_loss": 0.4222530722618103,
      "eval_runtime": 28.7555,
      "eval_samples_per_second": 18.953,
      "eval_steps_per_second": 4.764,
      "step": 72
    },
    {
      "epoch": 1.9655172413793105,
      "step": 72,
      "total_flos": 1.8383991907496755e+17,
      "train_loss": 0.40288073900673127,
      "train_runtime": 1028.5542,
      "train_samples_per_second": 3.383,
      "train_steps_per_second": 0.07
    }
  ],
  "logging_steps": 5,
  "max_steps": 72,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.8383991907496755e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}