trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9933774834437086,
  "eval_steps": 500,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013245033112582781,
      "grad_norm": 0.4943664073944092,
      "learning_rate": 2.5e-05,
      "loss": 1.4272,
      "step": 1
    },
    {
      "epoch": 0.06622516556291391,
      "grad_norm": 0.20984387397766113,
      "learning_rate": 0.000125,
      "loss": 1.3101,
      "step": 5
    },
    {
      "epoch": 0.13245033112582782,
      "grad_norm": 0.2290477156639099,
      "learning_rate": 0.00019956059820218982,
      "loss": 1.2917,
      "step": 10
    },
    {
      "epoch": 0.1986754966887417,
      "grad_norm": 0.15163910388946533,
      "learning_rate": 0.00019466156752904343,
      "loss": 1.2823,
      "step": 15
    },
    {
      "epoch": 0.26490066225165565,
      "grad_norm": 0.1627238243818283,
      "learning_rate": 0.00018458320592590975,
      "loss": 1.1889,
      "step": 20
    },
    {
      "epoch": 0.33112582781456956,
      "grad_norm": 0.15383219718933105,
      "learning_rate": 0.00016987694277788417,
      "loss": 1.198,
      "step": 25
    },
    {
      "epoch": 0.3973509933774834,
      "grad_norm": 0.1501755714416504,
      "learning_rate": 0.0001513474193514842,
      "loss": 1.1762,
      "step": 30
    },
    {
      "epoch": 0.46357615894039733,
      "grad_norm": 0.14539840817451477,
      "learning_rate": 0.0001300084635000341,
      "loss": 1.2176,
      "step": 35
    },
    {
      "epoch": 0.5298013245033113,
      "grad_norm": 0.12844280898571014,
      "learning_rate": 0.0001070276188945293,
      "loss": 1.1942,
      "step": 40
    },
    {
      "epoch": 0.5960264900662252,
      "grad_norm": 0.13806107640266418,
      "learning_rate": 8.366226381814697e-05,
      "loss": 1.2928,
      "step": 45
    },
    {
      "epoch": 0.6622516556291391,
      "grad_norm": 0.13188520073890686,
      "learning_rate": 6.119081473277501e-05,
      "loss": 1.1959,
      "step": 50
    },
    {
      "epoch": 0.7284768211920529,
      "grad_norm": 0.12824179232120514,
      "learning_rate": 4.084277875864776e-05,
      "loss": 1.1188,
      "step": 55
    },
    {
      "epoch": 0.7947019867549668,
      "grad_norm": 0.14250224828720093,
      "learning_rate": 2.3731482188961818e-05,
      "loss": 1.2076,
      "step": 60
    },
    {
      "epoch": 0.8609271523178808,
      "grad_norm": 0.14001749455928802,
      "learning_rate": 1.0793155744261351e-05,
      "loss": 1.1352,
      "step": 65
    },
    {
      "epoch": 0.9271523178807947,
      "grad_norm": 0.15154731273651123,
      "learning_rate": 2.735709467518699e-06,
      "loss": 1.1486,
      "step": 70
    },
    {
      "epoch": 0.9933774834437086,
      "grad_norm": 0.14987458288669586,
      "learning_rate": 0.0,
      "loss": 1.2385,
      "step": 75
    },
    {
      "epoch": 0.9933774834437086,
      "step": 75,
      "total_flos": 5.564154814608179e+16,
      "train_loss": 0.0,
      "train_runtime": 0.9326,
      "train_samples_per_second": 645.502,
      "train_steps_per_second": 80.42
    }
  ],
  "logging_steps": 5,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.564154814608179e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}