{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.39800995024875624,
  "eval_steps": 35,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028429282160625444,
      "grad_norm": 6.4533820152282715,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.9693,
      "step": 5
    },
    {
      "epoch": 0.05685856432125089,
      "grad_norm": 4.657992839813232,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.7795,
      "step": 10
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 2.398066997528076,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.4535,
      "step": 15
    },
    {
      "epoch": 0.11371712864250177,
      "grad_norm": 1.7500923871994019,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.4519,
      "step": 20
    },
    {
      "epoch": 0.14214641080312723,
      "grad_norm": 1.989443063735962,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.4128,
      "step": 25
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 1.1362711191177368,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.3446,
      "step": 30
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 1.1770528554916382,
      "learning_rate": 0.0001,
      "loss": 0.3253,
      "step": 35
    },
    {
      "epoch": 0.19900497512437812,
      "eval_loss": 0.28751906752586365,
      "eval_runtime": 239.7962,
      "eval_samples_per_second": 10.426,
      "eval_steps_per_second": 10.426,
      "step": 35
    },
    {
      "epoch": 0.22743425728500355,
      "grad_norm": 1.1288448572158813,
      "learning_rate": 9.993784606094612e-05,
      "loss": 0.3065,
      "step": 40
    },
    {
      "epoch": 0.255863539445629,
      "grad_norm": 1.0276695489883423,
      "learning_rate": 9.975153876827008e-05,
      "loss": 0.302,
      "step": 45
    },
    {
      "epoch": 0.28429282160625446,
      "grad_norm": 1.2982385158538818,
      "learning_rate": 9.944154131125642e-05,
      "loss": 0.307,
      "step": 50
    },
    {
      "epoch": 0.31272210376687987,
      "grad_norm": 1.4258345365524292,
      "learning_rate": 9.900862439242719e-05,
      "loss": 0.2908,
      "step": 55
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 0.7898867726325989,
      "learning_rate": 9.84538643114539e-05,
      "loss": 0.3112,
      "step": 60
    },
    {
      "epoch": 0.3695806680881308,
      "grad_norm": 0.9717791676521301,
      "learning_rate": 9.777864028930705e-05,
      "loss": 0.2596,
      "step": 65
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 1.0619926452636719,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2868,
      "step": 70
    },
    {
      "epoch": 0.39800995024875624,
      "eval_loss": 0.2600123882293701,
      "eval_runtime": 240.5378,
      "eval_samples_per_second": 10.393,
      "eval_steps_per_second": 10.393,
      "step": 70
    }
  ],
  "logging_steps": 5,
  "max_steps": 350,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 35,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.5048879808171213e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}