last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16580310880829016,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04145077720207254,
      "grad_norm": 2.2325406074523926,
      "learning_rate": 1e-05,
      "loss": 3.5141,
      "step": 1
    },
    {
      "epoch": 0.04145077720207254,
      "eval_loss": 3.6483120918273926,
      "eval_runtime": 44.5168,
      "eval_samples_per_second": 0.921,
      "eval_steps_per_second": 0.472,
      "step": 1
    },
    {
      "epoch": 0.08290155440414508,
      "grad_norm": 2.42509126663208,
      "learning_rate": 2e-05,
      "loss": 3.5278,
      "step": 2
    },
    {
      "epoch": 0.08290155440414508,
      "eval_loss": 3.618788242340088,
      "eval_runtime": 0.4535,
      "eval_samples_per_second": 90.41,
      "eval_steps_per_second": 46.308,
      "step": 2
    },
    {
      "epoch": 0.12435233160621761,
      "grad_norm": 2.4377353191375732,
      "learning_rate": 3e-05,
      "loss": 3.531,
      "step": 3
    },
    {
      "epoch": 0.16580310880829016,
      "grad_norm": 2.3675472736358643,
      "learning_rate": 4e-05,
      "loss": 3.6395,
      "step": 4
    },
    {
      "epoch": 0.16580310880829016,
      "eval_loss": 3.585569143295288,
      "eval_runtime": 0.4516,
      "eval_samples_per_second": 90.781,
      "eval_steps_per_second": 46.498,
      "step": 4
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 54868240760832.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}