last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02476780185758514,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002476780185758514,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 12.4296,
      "step": 1
    },
    {
      "epoch": 0.002476780185758514,
      "eval_loss": 13.640811920166016,
      "eval_runtime": 17.945,
      "eval_samples_per_second": 18.947,
      "eval_steps_per_second": 4.737,
      "step": 1
    },
    {
      "epoch": 0.004953560371517028,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 12.642,
      "step": 2
    },
    {
      "epoch": 0.007430340557275541,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 12.1927,
      "step": 3
    },
    {
      "epoch": 0.007430340557275541,
      "eval_loss": 13.640811920166016,
      "eval_runtime": 15.7624,
      "eval_samples_per_second": 21.57,
      "eval_steps_per_second": 5.393,
      "step": 3
    },
    {
      "epoch": 0.009907120743034056,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 14.1388,
      "step": 4
    },
    {
      "epoch": 0.01238390092879257,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 12.2371,
      "step": 5
    },
    {
      "epoch": 0.014860681114551083,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 12.8818,
      "step": 6
    },
    {
      "epoch": 0.014860681114551083,
      "eval_loss": 13.640811920166016,
      "eval_runtime": 15.7658,
      "eval_samples_per_second": 21.566,
      "eval_steps_per_second": 5.391,
      "step": 6
    },
    {
      "epoch": 0.0173374613003096,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 13.059,
      "step": 7
    },
    {
      "epoch": 0.019814241486068113,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 13.0242,
      "step": 8
    },
    {
      "epoch": 0.022291021671826627,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 13.058,
      "step": 9
    },
    {
      "epoch": 0.022291021671826627,
      "eval_loss": 13.640811920166016,
      "eval_runtime": 15.8013,
      "eval_samples_per_second": 21.517,
      "eval_steps_per_second": 5.379,
      "step": 9
    },
    {
      "epoch": 0.02476780185758514,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 13.689,
      "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": 1.4847506923913216e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}