last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0031573131265293236,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00031573131265293233,
      "eval_loss": 2.0692930221557617,
      "eval_runtime": 245.433,
      "eval_samples_per_second": 5.435,
      "eval_steps_per_second": 2.718,
      "step": 1
    },
    {
      "epoch": 0.000947193937958797,
      "grad_norm": 1.692325234413147,
      "learning_rate": 6e-05,
      "loss": 7.9621,
      "step": 3
    },
    {
      "epoch": 0.0015786565632646618,
      "eval_loss": 2.026681900024414,
      "eval_runtime": 247.2335,
      "eval_samples_per_second": 5.396,
      "eval_steps_per_second": 2.698,
      "step": 5
    },
    {
      "epoch": 0.001894387875917594,
      "grad_norm": 2.0406484603881836,
      "learning_rate": 0.00012,
      "loss": 7.7044,
      "step": 6
    },
    {
      "epoch": 0.0028415818138763913,
      "grad_norm": 2.049513101577759,
      "learning_rate": 0.00018,
      "loss": 7.7549,
      "step": 9
    },
    {
      "epoch": 0.0031573131265293236,
      "eval_loss": 1.6765570640563965,
      "eval_runtime": 247.086,
      "eval_samples_per_second": 5.399,
      "eval_steps_per_second": 2.699,
      "step": 10
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6347829962342400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}