trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 8218,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06084205402774397,
      "grad_norm": 9.958785057067871,
      "learning_rate": 4.6957897298612804e-05,
      "loss": 2.8566,
      "step": 500
    },
    {
      "epoch": 0.12168410805548795,
      "grad_norm": 6.4962873458862305,
      "learning_rate": 4.3915794597225605e-05,
      "loss": 2.445,
      "step": 1000
    },
    {
      "epoch": 0.18252616208323194,
      "grad_norm": 6.847861289978027,
      "learning_rate": 4.0873691895838406e-05,
      "loss": 2.2613,
      "step": 1500
    },
    {
      "epoch": 0.2433682161109759,
      "grad_norm": 7.166022300720215,
      "learning_rate": 3.783158919445121e-05,
      "loss": 2.1305,
      "step": 2000
    },
    {
      "epoch": 0.3042102701387199,
      "grad_norm": 7.0767316818237305,
      "learning_rate": 3.4789486493064e-05,
      "loss": 2.0557,
      "step": 2500
    },
    {
      "epoch": 0.3650523241664639,
      "grad_norm": 5.804446220397949,
      "learning_rate": 3.174738379167681e-05,
      "loss": 2.0253,
      "step": 3000
    },
    {
      "epoch": 0.42589437819420783,
      "grad_norm": 4.874488830566406,
      "learning_rate": 2.8705281090289608e-05,
      "loss": 1.9551,
      "step": 3500
    },
    {
      "epoch": 0.4867364322219518,
      "grad_norm": 5.902616024017334,
      "learning_rate": 2.566317838890241e-05,
      "loss": 1.8709,
      "step": 4000
    },
    {
      "epoch": 0.5475784862496957,
      "grad_norm": 6.240393161773682,
      "learning_rate": 2.262107568751521e-05,
      "loss": 1.8769,
      "step": 4500
    },
    {
      "epoch": 0.6084205402774397,
      "grad_norm": 6.906947135925293,
      "learning_rate": 1.9578972986128012e-05,
      "loss": 1.8443,
      "step": 5000
    },
    {
      "epoch": 0.6692625943051838,
      "grad_norm": 5.4539971351623535,
      "learning_rate": 1.6536870284740814e-05,
      "loss": 1.7751,
      "step": 5500
    },
    {
      "epoch": 0.7301046483329278,
      "grad_norm": 5.705854892730713,
      "learning_rate": 1.3494767583353615e-05,
      "loss": 1.7458,
      "step": 6000
    },
    {
      "epoch": 0.7909467023606717,
      "grad_norm": 5.6163649559021,
      "learning_rate": 1.0452664881966416e-05,
      "loss": 1.6901,
      "step": 6500
    },
    {
      "epoch": 0.8517887563884157,
      "grad_norm": 6.5511016845703125,
      "learning_rate": 7.410562180579217e-06,
      "loss": 1.6807,
      "step": 7000
    },
    {
      "epoch": 0.9126308104161597,
      "grad_norm": 5.792708396911621,
      "learning_rate": 4.368459479192018e-06,
      "loss": 1.6844,
      "step": 7500
    },
    {
      "epoch": 0.9734728644439036,
      "grad_norm": 6.069802761077881,
      "learning_rate": 1.3263567778048189e-06,
      "loss": 1.674,
      "step": 8000
    },
    {
      "epoch": 1.0,
      "step": 8218,
      "total_flos": 1.063927729790976e+16,
      "train_loss": 1.9656052448999624,
      "train_runtime": 5505.0716,
      "train_samples_per_second": 14.927,
      "train_steps_per_second": 1.493
    }
  ],
  "logging_steps": 500,
  "max_steps": 8218,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.063927729790976e+16,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}