checkpoint-159/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 159,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1902497027348395,
      "grad_norm": 1.049843430519104,
      "learning_rate": 1.8e-05,
      "loss": 3.6094,
      "step": 10
    },
    {
      "epoch": 0.380499405469679,
      "grad_norm": 1.4530141353607178,
      "learning_rate": 3.8e-05,
      "loss": 3.3156,
      "step": 20
    },
    {
      "epoch": 0.5707491082045184,
      "grad_norm": 1.1667392253875732,
      "learning_rate": 5.8e-05,
      "loss": 2.6267,
      "step": 30
    },
    {
      "epoch": 0.760998810939358,
      "grad_norm": 1.4776651859283447,
      "learning_rate": 7.800000000000001e-05,
      "loss": 2.1165,
      "step": 40
    },
    {
      "epoch": 0.9512485136741974,
      "grad_norm": 1.4660998582839966,
      "learning_rate": 9.8e-05,
      "loss": 1.804,
      "step": 50
    },
    {
      "epoch": 1.1331747919143877,
      "grad_norm": 1.163648247718811,
      "learning_rate": 0.000118,
      "loss": 1.5531,
      "step": 60
    },
    {
      "epoch": 1.323424494649227,
      "grad_norm": 1.323768973350525,
      "learning_rate": 0.000138,
      "loss": 1.4815,
      "step": 70
    },
    {
      "epoch": 1.5136741973840666,
      "grad_norm": 1.6716187000274658,
      "learning_rate": 0.00015800000000000002,
      "loss": 1.3993,
      "step": 80
    },
    {
      "epoch": 1.7039239001189062,
      "grad_norm": 1.709359049797058,
      "learning_rate": 0.00017800000000000002,
      "loss": 1.3135,
      "step": 90
    },
    {
      "epoch": 1.8941736028537455,
      "grad_norm": 1.735700249671936,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.2533,
      "step": 100
    },
    {
      "epoch": 2.0760998810939357,
      "grad_norm": 1.7600226402282715,
      "learning_rate": 0.00018873520750565718,
      "loss": 1.1572,
      "step": 110
    },
    {
      "epoch": 2.2663495838287755,
      "grad_norm": 2.0459885597229004,
      "learning_rate": 0.00015304209081197425,
      "loss": 0.9394,
      "step": 120
    },
    {
      "epoch": 2.456599286563615,
      "grad_norm": 1.884280800819397,
      "learning_rate": 0.00010266205214377748,
      "loss": 0.9113,
      "step": 130
    },
    {
      "epoch": 2.646848989298454,
      "grad_norm": 2.249265432357788,
      "learning_rate": 5.1544912966734994e-05,
      "loss": 0.8832,
      "step": 140
    },
    {
      "epoch": 2.837098692033294,
      "grad_norm": 2.0327601432800293,
      "learning_rate": 1.3844591860619383e-05,
      "loss": 0.9004,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 159,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 6.123192092794552e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}