last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10948905109489052,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036496350364963502,
      "eval_loss": 11.93726634979248,
      "eval_runtime": 1.02,
      "eval_samples_per_second": 113.726,
      "eval_steps_per_second": 56.863,
      "step": 1
    },
    {
      "epoch": 0.010948905109489052,
      "grad_norm": 0.01600918173789978,
      "learning_rate": 6e-05,
      "loss": 11.9368,
      "step": 3
    },
    {
      "epoch": 0.01824817518248175,
      "eval_loss": 11.937201499938965,
      "eval_runtime": 1.0442,
      "eval_samples_per_second": 111.09,
      "eval_steps_per_second": 55.545,
      "step": 5
    },
    {
      "epoch": 0.021897810218978103,
      "grad_norm": 0.01779448799788952,
      "learning_rate": 0.00012,
      "loss": 11.9374,
      "step": 6
    },
    {
      "epoch": 0.032846715328467155,
      "grad_norm": 0.014816435985267162,
      "learning_rate": 0.00018,
      "loss": 11.936,
      "step": 9
    },
    {
      "epoch": 0.0364963503649635,
      "eval_loss": 11.936994552612305,
      "eval_runtime": 1.0664,
      "eval_samples_per_second": 108.773,
      "eval_steps_per_second": 54.386,
      "step": 10
    },
    {
      "epoch": 0.043795620437956206,
      "grad_norm": 0.02010119892656803,
      "learning_rate": 0.00019510565162951537,
      "loss": 11.9369,
      "step": 12
    },
    {
      "epoch": 0.05474452554744526,
      "grad_norm": 0.017448164522647858,
      "learning_rate": 0.00017071067811865476,
      "loss": 11.9364,
      "step": 15
    },
    {
      "epoch": 0.05474452554744526,
      "eval_loss": 11.936670303344727,
      "eval_runtime": 1.0228,
      "eval_samples_per_second": 113.41,
      "eval_steps_per_second": 56.705,
      "step": 15
    },
    {
      "epoch": 0.06569343065693431,
      "grad_norm": 0.02098945714533329,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.9356,
      "step": 18
    },
    {
      "epoch": 0.072992700729927,
      "eval_loss": 11.936407089233398,
      "eval_runtime": 1.0226,
      "eval_samples_per_second": 113.436,
      "eval_steps_per_second": 56.718,
      "step": 20
    },
    {
      "epoch": 0.07664233576642336,
      "grad_norm": 0.01992957480251789,
      "learning_rate": 8.435655349597689e-05,
      "loss": 11.9353,
      "step": 21
    },
    {
      "epoch": 0.08759124087591241,
      "grad_norm": 0.015452707186341286,
      "learning_rate": 4.12214747707527e-05,
      "loss": 11.9358,
      "step": 24
    },
    {
      "epoch": 0.09124087591240876,
      "eval_loss": 11.936277389526367,
      "eval_runtime": 1.0213,
      "eval_samples_per_second": 113.577,
      "eval_steps_per_second": 56.788,
      "step": 25
    },
    {
      "epoch": 0.09854014598540146,
      "grad_norm": 0.015086108818650246,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 11.9353,
      "step": 27
    },
    {
      "epoch": 0.10948905109489052,
      "grad_norm": 0.018321814015507698,
      "learning_rate": 0.0,
      "loss": 11.936,
      "step": 30
    },
    {
      "epoch": 0.10948905109489052,
      "eval_loss": 11.936249732971191,
      "eval_runtime": 1.074,
      "eval_samples_per_second": 108.012,
      "eval_steps_per_second": 54.006,
      "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": 11242045440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}