trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00228310502283105,
  "eval_steps": 0,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00022831050228310502,
      "grad_norm": 61.761863708496094,
      "learning_rate": 0.0,
      "loss": 10.6752,
      "step": 1
    },
    {
      "epoch": 0.00045662100456621003,
      "grad_norm": 14.540397644042969,
      "learning_rate": 0.001,
      "loss": 0.4893,
      "step": 2
    },
    {
      "epoch": 0.0006849315068493151,
      "grad_norm": 15.115448951721191,
      "learning_rate": 0.001,
      "loss": 0.533,
      "step": 3
    },
    {
      "epoch": 0.0009132420091324201,
      "grad_norm": 0.1035713478922844,
      "learning_rate": 0.001,
      "loss": 0.0327,
      "step": 4
    },
    {
      "epoch": 0.001141552511415525,
      "grad_norm": 0.1258726716041565,
      "learning_rate": 0.001,
      "loss": 0.0315,
      "step": 5
    },
    {
      "epoch": 0.0013698630136986301,
      "grad_norm": 0.13812150061130524,
      "learning_rate": 0.001,
      "loss": 0.0314,
      "step": 6
    },
    {
      "epoch": 0.0015981735159817352,
      "grad_norm": 0.14780189096927643,
      "learning_rate": 0.001,
      "loss": 0.0321,
      "step": 7
    },
    {
      "epoch": 0.0018264840182648401,
      "grad_norm": 0.18661947548389435,
      "learning_rate": 0.001,
      "loss": 0.0352,
      "step": 8
    },
    {
      "epoch": 0.002054794520547945,
      "grad_norm": 0.2705967426300049,
      "learning_rate": 0.001,
      "loss": 0.0417,
      "step": 9
    },
    {
      "epoch": 0.00228310502283105,
      "grad_norm": 0.24941541254520416,
      "learning_rate": 0.001,
      "loss": 0.0397,
      "step": 10
    },
    {
      "epoch": 0.00228310502283105,
      "step": 10,
      "total_flos": 2405455154380800.0,
      "train_loss": 1.1941861145198345,
      "train_runtime": 71.1991,
      "train_samples_per_second": 2.809,
      "train_steps_per_second": 0.14
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2405455154380800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}