last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.050452781371280724,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00129366106080207,
      "eval_loss": 10.37984848022461,
      "eval_runtime": 2.2235,
      "eval_samples_per_second": 146.616,
      "eval_steps_per_second": 73.308,
      "step": 1
    },
    {
      "epoch": 0.00646830530401035,
      "grad_norm": 0.014315527863800526,
      "learning_rate": 5e-05,
      "loss": 10.379,
      "step": 5
    },
    {
      "epoch": 0.0129366106080207,
      "grad_norm": 0.012453961186110973,
      "learning_rate": 0.0001,
      "loss": 10.3812,
      "step": 10
    },
    {
      "epoch": 0.0129366106080207,
      "eval_loss": 10.379765510559082,
      "eval_runtime": 2.2571,
      "eval_samples_per_second": 144.431,
      "eval_steps_per_second": 72.215,
      "step": 10
    },
    {
      "epoch": 0.019404915912031046,
      "grad_norm": 0.009488558396697044,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.3807,
      "step": 15
    },
    {
      "epoch": 0.0258732212160414,
      "grad_norm": 0.012411398813128471,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3786,
      "step": 20
    },
    {
      "epoch": 0.0258732212160414,
      "eval_loss": 10.37958812713623,
      "eval_runtime": 2.2895,
      "eval_samples_per_second": 142.39,
      "eval_steps_per_second": 71.195,
      "step": 20
    },
    {
      "epoch": 0.03234152652005175,
      "grad_norm": 0.011458181776106358,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.3788,
      "step": 25
    },
    {
      "epoch": 0.03880983182406209,
      "grad_norm": 0.010108263231813908,
      "learning_rate": 5e-05,
      "loss": 10.3786,
      "step": 30
    },
    {
      "epoch": 0.03880983182406209,
      "eval_loss": 10.37945556640625,
      "eval_runtime": 2.3114,
      "eval_samples_per_second": 141.038,
      "eval_steps_per_second": 70.519,
      "step": 30
    },
    {
      "epoch": 0.045278137128072445,
      "grad_norm": 0.009184284135699272,
      "learning_rate": 3.086582838174551e-05,
      "loss": 10.3809,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1008610836480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}