trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3032600454890068,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.030326004548900682,
      "grad_norm": 6.78125,
      "learning_rate": 4.5e-05,
      "loss": 0.7592,
      "step": 10
    },
    {
      "epoch": 0.060652009097801364,
      "grad_norm": 3.65625,
      "learning_rate": 9.5e-05,
      "loss": 0.1834,
      "step": 20
    },
    {
      "epoch": 0.09097801364670205,
      "grad_norm": 4.5625,
      "learning_rate": 0.000145,
      "loss": 0.1956,
      "step": 30
    },
    {
      "epoch": 0.12130401819560273,
      "grad_norm": 9.3125,
      "learning_rate": 0.000195,
      "loss": 0.2217,
      "step": 40
    },
    {
      "epoch": 0.1516300227445034,
      "grad_norm": 3.125,
      "learning_rate": 0.00017,
      "loss": 0.2575,
      "step": 50
    },
    {
      "epoch": 0.1819560272934041,
      "grad_norm": 2.375,
      "learning_rate": 0.00013666666666666666,
      "loss": 0.1987,
      "step": 60
    },
    {
      "epoch": 0.21228203184230476,
      "grad_norm": 1.84375,
      "learning_rate": 0.00010333333333333334,
      "loss": 0.1772,
      "step": 70
    },
    {
      "epoch": 0.24260803639120546,
      "grad_norm": 1.875,
      "learning_rate": 7e-05,
      "loss": 0.1505,
      "step": 80
    },
    {
      "epoch": 0.27293404094010615,
      "grad_norm": 1.21875,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 0.1389,
      "step": 90
    },
    {
      "epoch": 0.3032600454890068,
      "grad_norm": 1.5859375,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.1355,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3155076839401728.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}