checkpoint-120/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.341463414634146,
  "eval_steps": 500,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 5.21875,
      "learning_rate": 2.5e-06,
      "loss": 6.2944,
      "step": 5
    },
    {
      "epoch": 0.2,
      "grad_norm": 5.75,
      "learning_rate": 2.9968542393565676e-06,
      "loss": 8.1888,
      "step": 10
    },
    {
      "epoch": 0.29,
      "grad_norm": 4.59375,
      "learning_rate": 2.984097196854534e-06,
      "loss": 4.2333,
      "step": 15
    },
    {
      "epoch": 0.39,
      "grad_norm": 4.09375,
      "learning_rate": 2.9616157869703894e-06,
      "loss": 3.6424,
      "step": 20
    },
    {
      "epoch": 0.49,
      "grad_norm": 4.1875,
      "learning_rate": 2.929557316423291e-06,
      "loss": 5.3747,
      "step": 25
    },
    {
      "epoch": 0.59,
      "grad_norm": 3.453125,
      "learning_rate": 2.8881318444640566e-06,
      "loss": 6.7731,
      "step": 30
    },
    {
      "epoch": 0.68,
      "grad_norm": 3.984375,
      "learning_rate": 2.8376108064873215e-06,
      "loss": 6.4852,
      "step": 35
    },
    {
      "epoch": 0.78,
      "grad_norm": 4.1875,
      "learning_rate": 2.778325235483954e-06,
      "loss": 6.5685,
      "step": 40
    },
    {
      "epoch": 0.88,
      "grad_norm": 3.078125,
      "learning_rate": 2.710663592987414e-06,
      "loss": 7.1279,
      "step": 45
    },
    {
      "epoch": 0.98,
      "grad_norm": 3.21875,
      "learning_rate": 2.6350692237265428e-06,
      "loss": 3.2127,
      "step": 50
    },
    {
      "epoch": 1.07,
      "grad_norm": 2.859375,
      "learning_rate": 2.552037450662849e-06,
      "loss": 9.9494,
      "step": 55
    },
    {
      "epoch": 1.17,
      "grad_norm": 3.078125,
      "learning_rate": 2.4621123294467098e-06,
      "loss": 5.1331,
      "step": 60
    },
    {
      "epoch": 1.27,
      "grad_norm": 2.96875,
      "learning_rate": 2.3658830835585295e-06,
      "loss": 5.8588,
      "step": 65
    },
    {
      "epoch": 1.37,
      "grad_norm": 2.953125,
      "learning_rate": 2.2639802434931445e-06,
      "loss": 4.6236,
      "step": 70
    },
    {
      "epoch": 1.46,
      "grad_norm": 3.09375,
      "learning_rate": 2.1570715152850234e-06,
      "loss": 3.4357,
      "step": 75
    },
    {
      "epoch": 1.56,
      "grad_norm": 2.953125,
      "learning_rate": 2.0458574054452316e-06,
      "loss": 5.1455,
      "step": 80
    },
    {
      "epoch": 1.66,
      "grad_norm": 3.1875,
      "learning_rate": 1.9310666309772426e-06,
      "loss": 2.8809,
      "step": 85
    },
    {
      "epoch": 1.76,
      "grad_norm": 3.0625,
      "learning_rate": 1.813451344546913e-06,
      "loss": 8.66,
      "step": 90
    },
    {
      "epoch": 1.85,
      "grad_norm": 3.109375,
      "learning_rate": 1.6937822060931097e-06,
      "loss": 6.1746,
      "step": 95
    },
    {
      "epoch": 1.95,
      "grad_norm": 3.359375,
      "learning_rate": 1.5728433331716726e-06,
      "loss": 7.1489,
      "step": 100
    },
    {
      "epoch": 2.05,
      "grad_norm": 3.453125,
      "learning_rate": 1.4514271631199665e-06,
      "loss": 9.0421,
      "step": 105
    },
    {
      "epoch": 2.15,
      "grad_norm": 3.328125,
      "learning_rate": 1.3303292607070737e-06,
      "loss": 3.6143,
      "step": 110
    },
    {
      "epoch": 2.24,
      "grad_norm": 3.5625,
      "learning_rate": 1.2103431052918681e-06,
      "loss": 5.9441,
      "step": 115
    },
    {
      "epoch": 2.34,
      "grad_norm": 2.875,
      "learning_rate": 1.0922548916454855e-06,
      "loss": 3.1449,
      "step": 120
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 20,
  "total_flos": 4.821291072638976e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}