{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.97442143727162,
  "eval_steps": 300.0,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11693057247259439,
      "grad_norm": 3.9375,
      "learning_rate": 9.953429730181653e-06,
      "loss": 1.9912,
      "num_input_tokens_seen": 1966080,
      "step": 3
    },
    {
      "epoch": 0.23386114494518878,
      "grad_norm": 4.40625,
      "learning_rate": 9.272097022732444e-06,
      "loss": 2.0628,
      "num_input_tokens_seen": 3932160,
      "step": 6
    },
    {
      "epoch": 0.3507917174177832,
      "grad_norm": 3.328125,
      "learning_rate": 7.883401610574338e-06,
      "loss": 1.9881,
      "num_input_tokens_seen": 5898240,
      "step": 9
    },
    {
      "epoch": 0.46772228989037756,
      "grad_norm": 2.640625,
      "learning_rate": 6.0172800652631706e-06,
      "loss": 2.0124,
      "num_input_tokens_seen": 7864320,
      "step": 12
    },
    {
      "epoch": 0.584652862362972,
      "grad_norm": 2.046875,
      "learning_rate": 3.982719934736832e-06,
      "loss": 1.9821,
      "num_input_tokens_seen": 9830400,
      "step": 15
    },
    {
      "epoch": 0.7015834348355664,
      "grad_norm": 1.8359375,
      "learning_rate": 2.1165983894256647e-06,
      "loss": 1.9827,
      "num_input_tokens_seen": 11796480,
      "step": 18
    },
    {
      "epoch": 0.8185140073081608,
      "grad_norm": 1.828125,
      "learning_rate": 7.279029772675572e-07,
      "loss": 2.0028,
      "num_input_tokens_seen": 13762560,
      "step": 21
    },
    {
      "epoch": 0.9354445797807551,
      "grad_norm": 1.765625,
      "learning_rate": 4.657026981834623e-08,
      "loss": 1.9667,
      "num_input_tokens_seen": 15728640,
      "step": 24
    },
    {
      "epoch": 0.97442143727162,
      "eval_accuracy": 0.5395915960884954,
      "eval_loss": 2.0784361362457275,
      "eval_runtime": 47.2625,
      "eval_samples_per_second": 0.571,
      "eval_steps_per_second": 0.571,
      "num_input_tokens_seen": 16384000,
      "step": 25
    },
    {
      "epoch": 0.97442143727162,
      "num_input_tokens_seen": 16384000,
      "step": 25,
      "total_flos": 6.99315567722496e+17,
      "train_loss": 1.9963084888458251,
      "train_runtime": 7134.0129,
      "train_samples_per_second": 0.115,
      "train_steps_per_second": 0.004
    }
  ],
  "logging_steps": 3,
  "max_steps": 25,
  "num_input_tokens_seen": 16384000,
  "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": 6.99315567722496e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}