last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.016129032258064516,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016129032258064516,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.9049,
      "step": 1
    },
    {
      "epoch": 0.0016129032258064516,
      "eval_loss": 9.502001762390137,
      "eval_runtime": 24.5704,
      "eval_samples_per_second": 42.49,
      "eval_steps_per_second": 5.332,
      "step": 1
    },
    {
      "epoch": 0.0032258064516129032,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.5029,
      "step": 2
    },
    {
      "epoch": 0.004838709677419355,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.5036,
      "step": 3
    },
    {
      "epoch": 0.004838709677419355,
      "eval_loss": 9.502001762390137,
      "eval_runtime": 23.8929,
      "eval_samples_per_second": 43.695,
      "eval_steps_per_second": 5.483,
      "step": 3
    },
    {
      "epoch": 0.0064516129032258064,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.4681,
      "step": 4
    },
    {
      "epoch": 0.008064516129032258,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.3615,
      "step": 5
    },
    {
      "epoch": 0.00967741935483871,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.3141,
      "step": 6
    },
    {
      "epoch": 0.00967741935483871,
      "eval_loss": 9.502001762390137,
      "eval_runtime": 23.8738,
      "eval_samples_per_second": 43.73,
      "eval_steps_per_second": 5.487,
      "step": 6
    },
    {
      "epoch": 0.01129032258064516,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.2474,
      "step": 7
    },
    {
      "epoch": 0.012903225806451613,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.5729,
      "step": 8
    },
    {
      "epoch": 0.014516129032258065,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.5663,
      "step": 9
    },
    {
      "epoch": 0.014516129032258065,
      "eval_loss": 9.502001762390137,
      "eval_runtime": 23.8764,
      "eval_samples_per_second": 43.725,
      "eval_steps_per_second": 5.487,
      "step": 9
    },
    {
      "epoch": 0.016129032258064516,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 9.5635,
      "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": 2.95105726513152e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}