checkpoint-138/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.989247311827957,
  "eval_steps": 500,
  "global_step": 138,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21505376344086022,
      "grad_norm": 0.26460975408554077,
      "learning_rate": 5e-05,
      "loss": 1.4452,
      "step": 10
    },
    {
      "epoch": 0.43010752688172044,
      "grad_norm": 0.22817669808864594,
      "learning_rate": 4.609375e-05,
      "loss": 1.2818,
      "step": 20
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 0.21125641465187073,
      "learning_rate": 4.21875e-05,
      "loss": 1.1376,
      "step": 30
    },
    {
      "epoch": 0.8602150537634409,
      "grad_norm": 0.17619547247886658,
      "learning_rate": 3.828125e-05,
      "loss": 1.0284,
      "step": 40
    },
    {
      "epoch": 1.086021505376344,
      "grad_norm": 0.14218494296073914,
      "learning_rate": 3.4375e-05,
      "loss": 1.0387,
      "step": 50
    },
    {
      "epoch": 1.3010752688172043,
      "grad_norm": 0.17040374875068665,
      "learning_rate": 3.0468750000000002e-05,
      "loss": 0.9208,
      "step": 60
    },
    {
      "epoch": 1.5161290322580645,
      "grad_norm": 0.17605076730251312,
      "learning_rate": 2.6562500000000002e-05,
      "loss": 0.8767,
      "step": 70
    },
    {
      "epoch": 1.7311827956989247,
      "grad_norm": 0.2109171748161316,
      "learning_rate": 2.2656250000000002e-05,
      "loss": 0.8643,
      "step": 80
    },
    {
      "epoch": 1.946236559139785,
      "grad_norm": 0.12548676133155823,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 0.8447,
      "step": 90
    },
    {
      "epoch": 2.172043010752688,
      "grad_norm": 0.09563092142343521,
      "learning_rate": 1.484375e-05,
      "loss": 0.931,
      "step": 100
    },
    {
      "epoch": 2.3870967741935485,
      "grad_norm": 0.0941094309091568,
      "learning_rate": 1.09375e-05,
      "loss": 0.8484,
      "step": 110
    },
    {
      "epoch": 2.6021505376344085,
      "grad_norm": 0.08611814677715302,
      "learning_rate": 7.031250000000001e-06,
      "loss": 0.8253,
      "step": 120
    },
    {
      "epoch": 2.817204301075269,
      "grad_norm": 0.09332480281591415,
      "learning_rate": 3.125e-06,
      "loss": 0.8225,
      "step": 130
    }
  ],
  "logging_steps": 10,
  "max_steps": 138,
  "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": 5.544255608487936e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}