trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9957081545064378,
  "eval_steps": 1000,
  "global_step": 174,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05722460658082976,
      "grad_norm": 2.8843040386286187,
      "learning_rate": 1e-05,
      "loss": 1.2427,
      "step": 10
    },
    {
      "epoch": 0.11444921316165951,
      "grad_norm": 0.9017664305111632,
      "learning_rate": 9.909643486313533e-06,
      "loss": 0.5328,
      "step": 20
    },
    {
      "epoch": 0.17167381974248927,
      "grad_norm": 0.797068637259448,
      "learning_rate": 9.641839665080363e-06,
      "loss": 0.4447,
      "step": 30
    },
    {
      "epoch": 0.22889842632331903,
      "grad_norm": 0.6941745476559829,
      "learning_rate": 9.206267664155906e-06,
      "loss": 0.4017,
      "step": 40
    },
    {
      "epoch": 0.2861230329041488,
      "grad_norm": 0.6250591769825486,
      "learning_rate": 8.61867019052535e-06,
      "loss": 0.3776,
      "step": 50
    },
    {
      "epoch": 0.34334763948497854,
      "grad_norm": 0.6177949791797019,
      "learning_rate": 7.900284547855992e-06,
      "loss": 0.3662,
      "step": 60
    },
    {
      "epoch": 0.4005722460658083,
      "grad_norm": 0.6776944915753278,
      "learning_rate": 7.0770750650094335e-06,
      "loss": 0.3658,
      "step": 70
    },
    {
      "epoch": 0.45779685264663805,
      "grad_norm": 0.7027875485112575,
      "learning_rate": 6.178794677547138e-06,
      "loss": 0.3553,
      "step": 80
    },
    {
      "epoch": 0.5150214592274678,
      "grad_norm": 0.6301404025031555,
      "learning_rate": 5.237909579118713e-06,
      "loss": 0.3317,
      "step": 90
    },
    {
      "epoch": 0.5722460658082976,
      "grad_norm": 0.6840316408079424,
      "learning_rate": 4.2884258086335755e-06,
      "loss": 0.3428,
      "step": 100
    },
    {
      "epoch": 0.6294706723891274,
      "grad_norm": 0.6028809547153681,
      "learning_rate": 3.3646601834128924e-06,
      "loss": 0.331,
      "step": 110
    },
    {
      "epoch": 0.6866952789699571,
      "grad_norm": 0.6463003155720976,
      "learning_rate": 2.5000000000000015e-06,
      "loss": 0.3252,
      "step": 120
    },
    {
      "epoch": 0.7439198855507868,
      "grad_norm": 0.5511586120399353,
      "learning_rate": 1.7256963302735752e-06,
      "loss": 0.3167,
      "step": 130
    },
    {
      "epoch": 0.8011444921316166,
      "grad_norm": 0.6770595845177203,
      "learning_rate": 1.0697345262860638e-06,
      "loss": 0.326,
      "step": 140
    },
    {
      "epoch": 0.8583690987124464,
      "grad_norm": 0.5474842641924246,
      "learning_rate": 5.558227567253832e-07,
      "loss": 0.3133,
      "step": 150
    },
    {
      "epoch": 0.9155937052932761,
      "grad_norm": 0.5872523545390601,
      "learning_rate": 2.0253513192751374e-07,
      "loss": 0.3195,
      "step": 160
    },
    {
      "epoch": 0.9728183118741058,
      "grad_norm": 0.5924289357218945,
      "learning_rate": 2.264038713457706e-08,
      "loss": 0.3216,
      "step": 170
    },
    {
      "epoch": 0.9957081545064378,
      "step": 174,
      "total_flos": 599683779002368.0,
      "train_loss": 0.40995535357245083,
      "train_runtime": 10019.3178,
      "train_samples_per_second": 2.232,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 174,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 599683779002368.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}