checkpoint-57180/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 48.0,
  "eval_steps": 500,
  "global_step": 57180,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6,
      "learning_rate": 0.0002399244332493703,
      "loss": 1.697,
      "step": 1906
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0004798488664987406,
      "loss": 1.6518,
      "step": 3812
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.0007192695214105793,
      "loss": 1.6587,
      "step": 5718
    },
    {
      "epoch": 6.4,
      "learning_rate": 0.0009591939546599496,
      "loss": 1.7073,
      "step": 7624
    },
    {
      "epoch": 8.0,
      "learning_rate": 0.001198866498740554,
      "loss": 1.7625,
      "step": 9530
    },
    {
      "epoch": 9.6,
      "learning_rate": 0.0014389168765743072,
      "loss": 1.8284,
      "step": 11436
    },
    {
      "epoch": 11.2,
      "learning_rate": 0.001480142737195634,
      "loss": 1.8887,
      "step": 13342
    },
    {
      "epoch": 12.8,
      "learning_rate": 0.0014534844668345928,
      "loss": 1.9438,
      "step": 15248
    },
    {
      "epoch": 14.4,
      "learning_rate": 0.0014268122026308424,
      "loss": 1.9359,
      "step": 17154
    },
    {
      "epoch": 16.0,
      "learning_rate": 0.0014001679261125106,
      "loss": 2.0,
      "step": 19060
    },
    {
      "epoch": 17.6,
      "learning_rate": 0.0013735236495941786,
      "loss": 2.5228,
      "step": 20966
    },
    {
      "epoch": 19.2,
      "learning_rate": 0.0013571228659389869,
      "loss": 33.1374,
      "step": 22872
    },
    {
      "epoch": 20.8,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 24778
    },
    {
      "epoch": 22.4,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 26684
    },
    {
      "epoch": 24.0,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 28590
    },
    {
      "epoch": 25.6,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 30496
    },
    {
      "epoch": 27.2,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 32402
    },
    {
      "epoch": 28.8,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 34308
    },
    {
      "epoch": 30.4,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 36214
    },
    {
      "epoch": 32.0,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 38120
    },
    {
      "epoch": 33.6,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 40026
    },
    {
      "epoch": 35.2,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 41932
    },
    {
      "epoch": 36.8,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 43838
    },
    {
      "epoch": 38.4,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 45744
    },
    {
      "epoch": 40.0,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 47650
    },
    {
      "epoch": 41.6,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 49556
    },
    {
      "epoch": 43.2,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 51462
    },
    {
      "epoch": 44.8,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 53368
    },
    {
      "epoch": 46.4,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 55274
    },
    {
      "epoch": 48.0,
      "learning_rate": 0.0013571228659389869,
      "loss": 0.0,
      "step": 57180
    }
  ],
  "logging_steps": 1906,
  "max_steps": 119100,
  "num_train_epochs": 100,
  "save_steps": 500,
  "total_flos": 2.0003746684323496e+19,
  "trial_name": null,
  "trial_params": null
}