{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 10,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8,
      "grad_norm": 3.535655975341797,
      "learning_rate": 0.0001,
      "loss": 2.8223,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 4.1554155349731445,
      "learning_rate": 0.0002,
      "loss": 2.8268,
      "step": 2
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.803156852722168,
      "eval_runtime": 0.5136,
      "eval_samples_per_second": 1.947,
      "eval_steps_per_second": 1.947,
      "step": 2
    },
    {
      "epoch": 1.8,
      "grad_norm": 2.6138558387756348,
      "learning_rate": 0.000175,
      "loss": 2.6803,
      "step": 3
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.1446619033813477,
      "learning_rate": 0.00015000000000000001,
      "loss": 2.4443,
      "step": 4
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.5913567543029785,
      "eval_runtime": 0.5175,
      "eval_samples_per_second": 1.932,
      "eval_steps_per_second": 1.932,
      "step": 4
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.7912520170211792,
      "learning_rate": 0.000125,
      "loss": 2.4006,
      "step": 5
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.2134900093078613,
      "learning_rate": 0.0001,
      "loss": 2.3568,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.456364870071411,
      "eval_runtime": 0.5073,
      "eval_samples_per_second": 1.971,
      "eval_steps_per_second": 1.971,
      "step": 6
    },
    {
      "epoch": 3.8,
      "grad_norm": 1.7705835103988647,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.2664,
      "step": 7
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.7635867595672607,
      "learning_rate": 5e-05,
      "loss": 2.1515,
      "step": 8
    },
    {
      "epoch": 4.0,
      "eval_loss": 2.3617074489593506,
      "eval_runtime": 0.5027,
      "eval_samples_per_second": 1.989,
      "eval_steps_per_second": 1.989,
      "step": 8
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.2085267305374146,
      "learning_rate": 2.5e-05,
      "loss": 2.1536,
      "step": 9
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.5746992826461792,
      "learning_rate": 0.0,
      "loss": 2.1324,
      "step": 10
    },
    {
      "epoch": 5.0,
      "eval_loss": 2.3257529735565186,
      "eval_runtime": 0.5048,
      "eval_samples_per_second": 1.981,
      "eval_steps_per_second": 1.981,
      "step": 10
    },
    {
      "epoch": 5.0,
      "step": 10,
      "total_flos": 549306960445440.0,
      "train_loss": 2.4234995365142824,
      "train_runtime": 54.6732,
      "train_samples_per_second": 1.463,
      "train_steps_per_second": 0.183
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 549306960445440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}