checkpoint-30/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 24.0,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 1.7059780359268188,
      "eval_runtime": 3.184,
      "eval_samples_per_second": 0.942,
      "eval_steps_per_second": 0.942,
      "step": 1
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.552927017211914,
      "eval_runtime": 3.1846,
      "eval_samples_per_second": 0.942,
      "eval_steps_per_second": 0.942,
      "step": 2
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.338813304901123,
      "eval_runtime": 3.1854,
      "eval_samples_per_second": 0.942,
      "eval_steps_per_second": 0.942,
      "step": 4
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.2230206727981567,
      "eval_runtime": 3.1854,
      "eval_samples_per_second": 0.942,
      "eval_steps_per_second": 0.942,
      "step": 5
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.1060389280319214,
      "eval_runtime": 3.185,
      "eval_samples_per_second": 0.942,
      "eval_steps_per_second": 0.942,
      "step": 6
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.9127510190010071,
      "eval_runtime": 3.1854,
      "eval_samples_per_second": 0.942,
      "eval_steps_per_second": 0.942,
      "step": 8
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.8066120147705078,
      "eval_runtime": 3.1857,
      "eval_samples_per_second": 0.942,
      "eval_steps_per_second": 0.942,
      "step": 9
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.31343773007392883,
      "learning_rate": 0.0002,
      "loss": 0.3573,
      "step": 10
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.713127076625824,
      "eval_runtime": 3.1868,
      "eval_samples_per_second": 0.941,
      "eval_steps_per_second": 0.941,
      "step": 10
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.6134043335914612,
      "eval_runtime": 3.1858,
      "eval_samples_per_second": 0.942,
      "eval_steps_per_second": 0.942,
      "step": 11
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.5432830452919006,
      "eval_runtime": 3.1857,
      "eval_samples_per_second": 0.942,
      "eval_steps_per_second": 0.942,
      "step": 12
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.5256462693214417,
      "eval_runtime": 3.1867,
      "eval_samples_per_second": 0.941,
      "eval_steps_per_second": 0.941,
      "step": 14
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.4858134686946869,
      "eval_runtime": 3.1872,
      "eval_samples_per_second": 0.941,
      "eval_steps_per_second": 0.941,
      "step": 15
    },
    {
      "epoch": 13.0,
      "eval_loss": 0.4822380840778351,
      "eval_runtime": 3.1868,
      "eval_samples_per_second": 0.941,
      "eval_steps_per_second": 0.941,
      "step": 16
    },
    {
      "epoch": 14.0,
      "eval_loss": 0.4799506664276123,
      "eval_runtime": 3.1861,
      "eval_samples_per_second": 0.942,
      "eval_steps_per_second": 0.942,
      "step": 18
    },
    {
      "epoch": 15.0,
      "eval_loss": 0.46334752440452576,
      "eval_runtime": 3.1859,
      "eval_samples_per_second": 0.942,
      "eval_steps_per_second": 0.942,
      "step": 19
    },
    {
      "epoch": 16.0,
      "grad_norm": 0.19768336415290833,
      "learning_rate": 0.0002,
      "loss": 0.0472,
      "step": 20
    },
    {
      "epoch": 16.0,
      "eval_loss": 0.4545087516307831,
      "eval_runtime": 3.1863,
      "eval_samples_per_second": 0.942,
      "eval_steps_per_second": 0.942,
      "step": 20
    },
    {
      "epoch": 17.0,
      "eval_loss": 0.4524390995502472,
      "eval_runtime": 3.1865,
      "eval_samples_per_second": 0.941,
      "eval_steps_per_second": 0.941,
      "step": 21
    },
    {
      "epoch": 18.0,
      "eval_loss": 0.4537128210067749,
      "eval_runtime": 3.1865,
      "eval_samples_per_second": 0.941,
      "eval_steps_per_second": 0.941,
      "step": 22
    },
    {
      "epoch": 19.0,
      "eval_loss": 0.4678395688533783,
      "eval_runtime": 3.1865,
      "eval_samples_per_second": 0.941,
      "eval_steps_per_second": 0.941,
      "step": 24
    },
    {
      "epoch": 20.0,
      "eval_loss": 0.46853116154670715,
      "eval_runtime": 3.1871,
      "eval_samples_per_second": 0.941,
      "eval_steps_per_second": 0.941,
      "step": 25
    },
    {
      "epoch": 21.0,
      "eval_loss": 0.47128668427467346,
      "eval_runtime": 3.1866,
      "eval_samples_per_second": 0.941,
      "eval_steps_per_second": 0.941,
      "step": 26
    },
    {
      "epoch": 22.0,
      "eval_loss": 0.4789499044418335,
      "eval_runtime": 3.1865,
      "eval_samples_per_second": 0.941,
      "eval_steps_per_second": 0.941,
      "step": 28
    },
    {
      "epoch": 23.0,
      "eval_loss": 0.4797506630420685,
      "eval_runtime": 3.1863,
      "eval_samples_per_second": 0.942,
      "eval_steps_per_second": 0.942,
      "step": 29
    },
    {
      "epoch": 24.0,
      "grad_norm": 0.13670594990253448,
      "learning_rate": 0.0002,
      "loss": 0.0021,
      "step": 30
    },
    {
      "epoch": 24.0,
      "eval_loss": 0.47982195019721985,
      "eval_runtime": 3.1868,
      "eval_samples_per_second": 0.941,
      "eval_steps_per_second": 0.941,
      "step": 30
    }
  ],
  "logging_steps": 10,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 60,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7388616670052352.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}