trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9975812953507122,
  "eval_steps": 500,
  "global_step": 232,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08599838753023381,
      "grad_norm": 1.4894707202911377,
      "learning_rate": 8.333333333333334e-05,
      "loss": 10.952,
      "step": 20
    },
    {
      "epoch": 0.17199677506046762,
      "grad_norm": 0.6050359010696411,
      "learning_rate": 9.85470908713026e-05,
      "loss": 8.8962,
      "step": 40
    },
    {
      "epoch": 0.25799516259070143,
      "grad_norm": 0.25468742847442627,
      "learning_rate": 9.278906361507238e-05,
      "loss": 7.7551,
      "step": 60
    },
    {
      "epoch": 0.34399355012093524,
      "grad_norm": 0.44108685851097107,
      "learning_rate": 8.315613291203976e-05,
      "loss": 7.4342,
      "step": 80
    },
    {
      "epoch": 0.42999193765116905,
      "grad_norm": 0.38378873467445374,
      "learning_rate": 7.052064027263786e-05,
      "loss": 7.2125,
      "step": 100
    },
    {
      "epoch": 0.5159903251814029,
      "grad_norm": 0.7682523131370544,
      "learning_rate": 5.602683401276615e-05,
      "loss": 7.0084,
      "step": 120
    },
    {
      "epoch": 0.6019887127116367,
      "grad_norm": 0.5268513560295105,
      "learning_rate": 4.0987248109304714e-05,
      "loss": 6.817,
      "step": 140
    },
    {
      "epoch": 0.6879871002418705,
      "grad_norm": 0.7004027366638184,
      "learning_rate": 2.6763841397811573e-05,
      "loss": 6.6429,
      "step": 160
    },
    {
      "epoch": 0.7739854877721043,
      "grad_norm": 1.4404789209365845,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 6.4766,
      "step": 180
    },
    {
      "epoch": 0.8599838753023381,
      "grad_norm": 0.3456955552101135,
      "learning_rate": 5.727198717339511e-06,
      "loss": 6.3555,
      "step": 200
    },
    {
      "epoch": 0.9459822628325719,
      "grad_norm": 0.23901048302650452,
      "learning_rate": 8.190046526428242e-07,
      "loss": 6.3162,
      "step": 220
    }
  ],
  "logging_steps": 20,
  "max_steps": 232,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.384639693215236e+18,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}