last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0547945205479452,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005479452054794521,
      "grad_norm": 0.023885909467935562,
      "learning_rate": 2e-05,
      "loss": 10.3806,
      "step": 1
    },
    {
      "epoch": 0.005479452054794521,
      "eval_loss": 10.376846313476562,
      "eval_runtime": 0.3174,
      "eval_samples_per_second": 122.881,
      "eval_steps_per_second": 122.881,
      "step": 1
    },
    {
      "epoch": 0.010958904109589041,
      "grad_norm": 0.02708149142563343,
      "learning_rate": 4e-05,
      "loss": 10.3795,
      "step": 2
    },
    {
      "epoch": 0.01643835616438356,
      "grad_norm": 0.016956843435764313,
      "learning_rate": 6e-05,
      "loss": 10.3782,
      "step": 3
    },
    {
      "epoch": 0.01643835616438356,
      "eval_loss": 10.376829147338867,
      "eval_runtime": 0.2781,
      "eval_samples_per_second": 140.23,
      "eval_steps_per_second": 140.23,
      "step": 3
    },
    {
      "epoch": 0.021917808219178082,
      "grad_norm": 0.022694140672683716,
      "learning_rate": 8e-05,
      "loss": 10.3785,
      "step": 4
    },
    {
      "epoch": 0.0273972602739726,
      "grad_norm": 0.023907892405986786,
      "learning_rate": 0.0001,
      "loss": 10.3697,
      "step": 5
    },
    {
      "epoch": 0.03287671232876712,
      "grad_norm": 0.019220907241106033,
      "learning_rate": 0.00012,
      "loss": 10.3829,
      "step": 6
    },
    {
      "epoch": 0.03287671232876712,
      "eval_loss": 10.376757621765137,
      "eval_runtime": 0.2992,
      "eval_samples_per_second": 130.333,
      "eval_steps_per_second": 130.333,
      "step": 6
    },
    {
      "epoch": 0.038356164383561646,
      "grad_norm": 0.02152101695537567,
      "learning_rate": 0.00014,
      "loss": 10.3818,
      "step": 7
    },
    {
      "epoch": 0.043835616438356165,
      "grad_norm": 0.07344566285610199,
      "learning_rate": 0.00016,
      "loss": 10.38,
      "step": 8
    },
    {
      "epoch": 0.049315068493150684,
      "grad_norm": 0.03503725305199623,
      "learning_rate": 0.00018,
      "loss": 10.3829,
      "step": 9
    },
    {
      "epoch": 0.049315068493150684,
      "eval_loss": 10.376622200012207,
      "eval_runtime": 0.3928,
      "eval_samples_per_second": 99.297,
      "eval_steps_per_second": 99.297,
      "step": 9
    },
    {
      "epoch": 0.0547945205479452,
      "grad_norm": 0.03340437635779381,
      "learning_rate": 0.0002,
      "loss": 10.3759,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 129309081600.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}