trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.3455909192562103,
      "learning_rate": 0.00016,
      "loss": 0.7527,
      "step": 5
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.532439649105072,
      "learning_rate": 0.00018545454545454545,
      "loss": 0.426,
      "step": 10
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.3362359404563904,
      "learning_rate": 0.00016727272727272728,
      "loss": 0.2268,
      "step": 15
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.2568519115447998,
      "learning_rate": 0.0001490909090909091,
      "loss": 0.1894,
      "step": 20
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 0.263459712266922,
      "learning_rate": 0.00013090909090909093,
      "loss": 0.1829,
      "step": 25
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.20919214189052582,
      "learning_rate": 0.00011272727272727272,
      "loss": 0.1623,
      "step": 30
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 0.2152024358510971,
      "learning_rate": 9.454545454545455e-05,
      "loss": 0.1638,
      "step": 35
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.2593837082386017,
      "learning_rate": 7.636363636363637e-05,
      "loss": 0.1665,
      "step": 40
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.20896115899085999,
      "learning_rate": 5.818181818181818e-05,
      "loss": 0.1678,
      "step": 45
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.2554057538509369,
      "learning_rate": 4e-05,
      "loss": 0.155,
      "step": 50
    },
    {
      "epoch": 0.9166666666666666,
      "grad_norm": 0.17573142051696777,
      "learning_rate": 2.1818181818181818e-05,
      "loss": 0.1529,
      "step": 55
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.24647420644760132,
      "learning_rate": 3.636363636363636e-06,
      "loss": 0.1557,
      "step": 60
    },
    {
      "epoch": 1.0,
      "step": 60,
      "total_flos": 2717720554039296.0,
      "train_loss": 0.24179711043834687,
      "train_runtime": 32.7348,
      "train_samples_per_second": 1.833,
      "train_steps_per_second": 1.833
    }
  ],
  "logging_steps": 5,
  "max_steps": 60,
  "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": 2717720554039296.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}