trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9976689976689976,
  "eval_steps": 500,
  "global_step": 107,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09324009324009325,
      "grad_norm": 0.7132964134216309,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 2.8806,
      "step": 10
    },
    {
      "epoch": 0.1864801864801865,
      "grad_norm": 0.2468750923871994,
      "learning_rate": 4.934692448193334e-05,
      "loss": 2.6386,
      "step": 20
    },
    {
      "epoch": 0.27972027972027974,
      "grad_norm": 0.3147766888141632,
      "learning_rate": 4.6230054538164474e-05,
      "loss": 2.5088,
      "step": 30
    },
    {
      "epoch": 0.372960372960373,
      "grad_norm": 0.3248756229877472,
      "learning_rate": 4.085983210409114e-05,
      "loss": 2.4838,
      "step": 40
    },
    {
      "epoch": 0.4662004662004662,
      "grad_norm": 0.19801785051822662,
      "learning_rate": 3.380625119803084e-05,
      "loss": 2.4479,
      "step": 50
    },
    {
      "epoch": 0.5594405594405595,
      "grad_norm": 0.28579196333885193,
      "learning_rate": 2.5817977070544407e-05,
      "loss": 2.4131,
      "step": 60
    },
    {
      "epoch": 0.6526806526806527,
      "grad_norm": 0.3095599412918091,
      "learning_rate": 1.7742883068638447e-05,
      "loss": 2.3956,
      "step": 70
    },
    {
      "epoch": 0.745920745920746,
      "grad_norm": 0.22690406441688538,
      "learning_rate": 1.043805757830495e-05,
      "loss": 2.3636,
      "step": 80
    },
    {
      "epoch": 0.8391608391608392,
      "grad_norm": 0.30492693185806274,
      "learning_rate": 4.678832885209622e-06,
      "loss": 2.3307,
      "step": 90
    },
    {
      "epoch": 0.9324009324009324,
      "grad_norm": 0.18911170959472656,
      "learning_rate": 1.0764916066947794e-06,
      "loss": 2.3372,
      "step": 100
    },
    {
      "epoch": 0.9976689976689976,
      "step": 107,
      "total_flos": 1.4643175261407805e+18,
      "train_loss": 2.473550457820714,
      "train_runtime": 8966.4187,
      "train_samples_per_second": 0.382,
      "train_steps_per_second": 0.012
    }
  ],
  "logging_steps": 10,
  "max_steps": 107,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4643175261407805e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}