last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004167824395665463,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001389274798555154,
      "eval_loss": NaN,
      "eval_runtime": 67.7783,
      "eval_samples_per_second": 44.719,
      "eval_steps_per_second": 22.367,
      "step": 1
    },
    {
      "epoch": 0.0004167824395665463,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0008335648791330926,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0011114198388441233,
      "eval_loss": NaN,
      "eval_runtime": 66.9558,
      "eval_samples_per_second": 45.269,
      "eval_steps_per_second": 22.642,
      "step": 8
    },
    {
      "epoch": 0.0012503473186996387,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0016671297582661851,
      "grad_norm": NaN,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0020839121978327314,
      "grad_norm": NaN,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0022228396776882466,
      "eval_loss": NaN,
      "eval_runtime": 67.0863,
      "eval_samples_per_second": 45.181,
      "eval_steps_per_second": 22.598,
      "step": 16
    },
    {
      "epoch": 0.0025006946373992774,
      "grad_norm": NaN,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.002917477076965824,
      "grad_norm": NaN,
      "learning_rate": 8.435655349597689e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0033342595165323703,
      "grad_norm": NaN,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.0033342595165323703,
      "eval_loss": NaN,
      "eval_runtime": 66.4418,
      "eval_samples_per_second": 45.619,
      "eval_steps_per_second": 22.817,
      "step": 24
    },
    {
      "epoch": 0.0037510419560989163,
      "grad_norm": NaN,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.004167824395665463,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 219772817768448.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}