last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0011431111675610454,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012701235195122725,
      "grad_norm": 10.388257026672363,
      "learning_rate": 2e-05,
      "loss": 14.8575,
      "step": 1
    },
    {
      "epoch": 0.00012701235195122725,
      "eval_loss": 3.7484116554260254,
      "eval_runtime": 170.1025,
      "eval_samples_per_second": 19.488,
      "eval_steps_per_second": 9.747,
      "step": 1
    },
    {
      "epoch": 0.0002540247039024545,
      "grad_norm": 10.19638442993164,
      "learning_rate": 4e-05,
      "loss": 15.0563,
      "step": 2
    },
    {
      "epoch": 0.0003810370558536818,
      "grad_norm": 15.672657012939453,
      "learning_rate": 6e-05,
      "loss": 15.0697,
      "step": 3
    },
    {
      "epoch": 0.0003810370558536818,
      "eval_loss": 3.707470417022705,
      "eval_runtime": 169.9419,
      "eval_samples_per_second": 19.507,
      "eval_steps_per_second": 9.756,
      "step": 3
    },
    {
      "epoch": 0.000508049407804909,
      "grad_norm": 9.822285652160645,
      "learning_rate": 8e-05,
      "loss": 14.5317,
      "step": 4
    },
    {
      "epoch": 0.0006350617597561363,
      "grad_norm": 11.826835632324219,
      "learning_rate": 0.0001,
      "loss": 14.4164,
      "step": 5
    },
    {
      "epoch": 0.0007620741117073636,
      "grad_norm": 17.98814582824707,
      "learning_rate": 0.00012,
      "loss": 13.5485,
      "step": 6
    },
    {
      "epoch": 0.0007620741117073636,
      "eval_loss": 2.997011184692383,
      "eval_runtime": 170.4969,
      "eval_samples_per_second": 19.443,
      "eval_steps_per_second": 9.725,
      "step": 6
    },
    {
      "epoch": 0.0008890864636585908,
      "grad_norm": 25.546321868896484,
      "learning_rate": 0.00014,
      "loss": 11.763,
      "step": 7
    },
    {
      "epoch": 0.001016098815609818,
      "grad_norm": 22.10211181640625,
      "learning_rate": 0.00016,
      "loss": 9.529,
      "step": 8
    },
    {
      "epoch": 0.0011431111675610454,
      "grad_norm": 11.621769905090332,
      "learning_rate": 0.00018,
      "loss": 8.4666,
      "step": 9
    },
    {
      "epoch": 0.0011431111675610454,
      "eval_loss": 1.7756000757217407,
      "eval_runtime": 170.6112,
      "eval_samples_per_second": 19.43,
      "eval_steps_per_second": 9.718,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2849583755427840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}