trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.44640427993048687,
      "learning_rate": 8.181818181818183e-05,
      "loss": 1.4231,
      "step": 10
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.2479347381773058,
      "learning_rate": 9.839743506981782e-05,
      "loss": 1.1,
      "step": 20
    },
    {
      "epoch": 1.3764705882352941,
      "grad_norm": 0.1419452663021689,
      "learning_rate": 9.206267664155907e-05,
      "loss": 0.9618,
      "step": 30
    },
    {
      "epoch": 1.8470588235294119,
      "grad_norm": 0.09465575638341574,
      "learning_rate": 8.152763335422613e-05,
      "loss": 0.8825,
      "step": 40
    },
    {
      "epoch": 2.2823529411764705,
      "grad_norm": 0.09101493342482378,
      "learning_rate": 6.784431107959359e-05,
      "loss": 0.8325,
      "step": 50
    },
    {
      "epoch": 2.7529411764705882,
      "grad_norm": 0.07927190008295683,
      "learning_rate": 5.2379095791187124e-05,
      "loss": 0.7955,
      "step": 60
    },
    {
      "epoch": 3.1882352941176473,
      "grad_norm": 0.08055075324006687,
      "learning_rate": 3.6676309315498256e-05,
      "loss": 0.7681,
      "step": 70
    },
    {
      "epoch": 3.6588235294117646,
      "grad_norm": 0.08203555824731702,
      "learning_rate": 2.2303996806694488e-05,
      "loss": 0.7545,
      "step": 80
    },
    {
      "epoch": 4.094117647058823,
      "grad_norm": 0.0791495174182695,
      "learning_rate": 1.0697345262860636e-05,
      "loss": 0.7472,
      "step": 90
    },
    {
      "epoch": 4.564705882352941,
      "grad_norm": 0.07871719761471935,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.739,
      "step": 100
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.07558265429833856,
      "learning_rate": 2.5172880840745873e-08,
      "loss": 0.7362,
      "step": 110
    },
    {
      "epoch": 5.0,
      "step": 110,
      "total_flos": 645336894799872.0,
      "train_loss": 0.8854796322909269,
      "train_runtime": 2346.1665,
      "train_samples_per_second": 11.504,
      "train_steps_per_second": 0.047
    }
  ],
  "logging_steps": 10,
  "max_steps": 110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 645336894799872.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}