last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.024125452352231604,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024125452352231603,
      "grad_norm": 23.346899032592773,
      "learning_rate": 2e-05,
      "loss": 36.656,
      "step": 1
    },
    {
      "epoch": 0.0024125452352231603,
      "eval_loss": 9.807143211364746,
      "eval_runtime": 18.9147,
      "eval_samples_per_second": 9.252,
      "eval_steps_per_second": 4.652,
      "step": 1
    },
    {
      "epoch": 0.0048250904704463205,
      "grad_norm": 20.62853240966797,
      "learning_rate": 4e-05,
      "loss": 37.4754,
      "step": 2
    },
    {
      "epoch": 0.007237635705669481,
      "grad_norm": 23.71076011657715,
      "learning_rate": 6e-05,
      "loss": 36.4394,
      "step": 3
    },
    {
      "epoch": 0.007237635705669481,
      "eval_loss": 9.716862678527832,
      "eval_runtime": 18.9231,
      "eval_samples_per_second": 9.248,
      "eval_steps_per_second": 4.65,
      "step": 3
    },
    {
      "epoch": 0.009650180940892641,
      "grad_norm": 22.9996395111084,
      "learning_rate": 8e-05,
      "loss": 37.4163,
      "step": 4
    },
    {
      "epoch": 0.012062726176115802,
      "grad_norm": 29.07944107055664,
      "learning_rate": 0.0001,
      "loss": 39.3024,
      "step": 5
    },
    {
      "epoch": 0.014475271411338963,
      "grad_norm": 33.20098114013672,
      "learning_rate": 0.00012,
      "loss": 34.4348,
      "step": 6
    },
    {
      "epoch": 0.014475271411338963,
      "eval_loss": 8.189959526062012,
      "eval_runtime": 19.1162,
      "eval_samples_per_second": 9.155,
      "eval_steps_per_second": 4.603,
      "step": 6
    },
    {
      "epoch": 0.016887816646562123,
      "grad_norm": 53.515289306640625,
      "learning_rate": 0.00014,
      "loss": 31.9477,
      "step": 7
    },
    {
      "epoch": 0.019300361881785282,
      "grad_norm": 38.597110748291016,
      "learning_rate": 0.00016,
      "loss": 27.3812,
      "step": 8
    },
    {
      "epoch": 0.021712907117008445,
      "grad_norm": 32.72773742675781,
      "learning_rate": 0.00018,
      "loss": 20.9595,
      "step": 9
    },
    {
      "epoch": 0.021712907117008445,
      "eval_loss": 3.9651339054107666,
      "eval_runtime": 19.1412,
      "eval_samples_per_second": 9.143,
      "eval_steps_per_second": 4.597,
      "step": 9
    },
    {
      "epoch": 0.024125452352231604,
      "grad_norm": 21.228473663330078,
      "learning_rate": 0.0002,
      "loss": 16.7548,
      "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": 3166204172697600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}