checkpoint-168/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0059880239520957,
  "eval_steps": 500,
  "global_step": 168,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.059880239520958084,
      "grad_norm": 6.566332162525977,
      "learning_rate": 7.692307692307694e-06,
      "loss": 4.3864,
      "step": 10
    },
    {
      "epoch": 0.11976047904191617,
      "grad_norm": 2.0437379261117132,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 3.4794,
      "step": 20
    },
    {
      "epoch": 0.17964071856287425,
      "grad_norm": 0.8566260346858398,
      "learning_rate": 1.9996500732179695e-05,
      "loss": 2.5375,
      "step": 30
    },
    {
      "epoch": 0.23952095808383234,
      "grad_norm": 0.6117118904297301,
      "learning_rate": 1.995716208873644e-05,
      "loss": 1.8752,
      "step": 40
    },
    {
      "epoch": 0.2994011976047904,
      "grad_norm": 0.3923875723199884,
      "learning_rate": 1.9874283308955058e-05,
      "loss": 1.4434,
      "step": 50
    },
    {
      "epoch": 0.3592814371257485,
      "grad_norm": 0.2726465509781607,
      "learning_rate": 1.9748226800652062e-05,
      "loss": 1.2232,
      "step": 60
    },
    {
      "epoch": 0.41916167664670656,
      "grad_norm": 0.22048277219015358,
      "learning_rate": 1.957954377686475e-05,
      "loss": 1.1031,
      "step": 70
    },
    {
      "epoch": 0.47904191616766467,
      "grad_norm": 0.19131964365908752,
      "learning_rate": 1.9368971845536844e-05,
      "loss": 1.0318,
      "step": 80
    },
    {
      "epoch": 0.5389221556886228,
      "grad_norm": 0.19325047947069812,
      "learning_rate": 1.911743178414665e-05,
      "loss": 0.9724,
      "step": 90
    },
    {
      "epoch": 0.5988023952095808,
      "grad_norm": 0.18220999359482376,
      "learning_rate": 1.8826023513381372e-05,
      "loss": 0.942,
      "step": 100
    },
    {
      "epoch": 0.6586826347305389,
      "grad_norm": 0.17750272843534337,
      "learning_rate": 1.849602128746387e-05,
      "loss": 0.9106,
      "step": 110
    },
    {
      "epoch": 0.718562874251497,
      "grad_norm": 0.16658108783370879,
      "learning_rate": 1.8128868122163125e-05,
      "loss": 0.8876,
      "step": 120
    },
    {
      "epoch": 0.7784431137724551,
      "grad_norm": 0.1461861518555333,
      "learning_rate": 1.7726169484853438e-05,
      "loss": 0.872,
      "step": 130
    },
    {
      "epoch": 0.8383233532934131,
      "grad_norm": 0.14457472093324725,
      "learning_rate": 1.7289686274214116e-05,
      "loss": 0.8576,
      "step": 140
    },
    {
      "epoch": 0.8982035928143712,
      "grad_norm": 0.1544690749108873,
      "learning_rate": 1.6821327120267567e-05,
      "loss": 0.8467,
      "step": 150
    },
    {
      "epoch": 0.9580838323353293,
      "grad_norm": 0.1429893393640351,
      "learning_rate": 1.6323140038425842e-05,
      "loss": 0.8252,
      "step": 160
    }
  ],
  "logging_steps": 10,
  "max_steps": 501,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 56,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 306299887681536.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}