{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002206896551724138,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.35632183908046e-05,
      "eval_loss": 2.3828835487365723,
      "eval_runtime": 907.8494,
      "eval_samples_per_second": 6.305,
      "eval_steps_per_second": 3.153,
      "step": 1
    },
    {
      "epoch": 0.00022068965517241379,
      "grad_norm": 3.1533737182617188,
      "learning_rate": 6e-05,
      "loss": 2.4211,
      "step": 3
    },
    {
      "epoch": 0.00044137931034482757,
      "grad_norm": 3.350109815597534,
      "learning_rate": 0.00012,
      "loss": 2.045,
      "step": 6
    },
    {
      "epoch": 0.0005885057471264368,
      "eval_loss": 1.6408686637878418,
      "eval_runtime": 912.7595,
      "eval_samples_per_second": 6.271,
      "eval_steps_per_second": 3.136,
      "step": 8
    },
    {
      "epoch": 0.0006620689655172414,
      "grad_norm": 1.667354702949524,
      "learning_rate": 0.00018,
      "loss": 1.6767,
      "step": 9
    },
    {
      "epoch": 0.0008827586206896551,
      "grad_norm": 1.8691641092300415,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.7465,
      "step": 12
    },
    {
      "epoch": 0.001103448275862069,
      "grad_norm": 1.5032830238342285,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.8574,
      "step": 15
    },
    {
      "epoch": 0.0011770114942528736,
      "eval_loss": 1.6107295751571655,
      "eval_runtime": 913.4051,
      "eval_samples_per_second": 6.267,
      "eval_steps_per_second": 3.133,
      "step": 16
    },
    {
      "epoch": 0.0013241379310344828,
      "grad_norm": 1.3698562383651733,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.5757,
      "step": 18
    },
    {
      "epoch": 0.0015448275862068965,
      "grad_norm": 1.4209589958190918,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.5202,
      "step": 21
    },
    {
      "epoch": 0.0017655172413793103,
      "grad_norm": 1.3715722560882568,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.7136,
      "step": 24
    },
    {
      "epoch": 0.0017655172413793103,
      "eval_loss": 1.598349928855896,
      "eval_runtime": 912.9401,
      "eval_samples_per_second": 6.27,
      "eval_steps_per_second": 3.135,
      "step": 24
    },
    {
      "epoch": 0.0019862068965517243,
      "grad_norm": 1.235002040863037,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.6393,
      "step": 27
    },
    {
      "epoch": 0.002206896551724138,
      "grad_norm": 1.50495183467865,
      "learning_rate": 0.0,
      "loss": 1.5971,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.271324882239488e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}