checkpoint-500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.001779061865097297,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.895309325486485e-05,
      "grad_norm": 0.5721328258514404,
      "learning_rate": 2.5e-05,
      "loss": 2.8022,
      "step": 25
    },
    {
      "epoch": 0.0001779061865097297,
      "grad_norm": 0.8923015594482422,
      "learning_rate": 2.5e-05,
      "loss": 2.7907,
      "step": 50
    },
    {
      "epoch": 0.0002668592797645945,
      "grad_norm": 0.4010128676891327,
      "learning_rate": 2.5e-05,
      "loss": 2.2071,
      "step": 75
    },
    {
      "epoch": 0.0003558123730194594,
      "grad_norm": 1.1923198699951172,
      "learning_rate": 2.5e-05,
      "loss": 2.0296,
      "step": 100
    },
    {
      "epoch": 0.00044476546627432423,
      "grad_norm": 0.44945457577705383,
      "learning_rate": 2.5e-05,
      "loss": 1.6782,
      "step": 125
    },
    {
      "epoch": 0.000533718559529189,
      "grad_norm": 1.238482117652893,
      "learning_rate": 2.5e-05,
      "loss": 1.3948,
      "step": 150
    },
    {
      "epoch": 0.0006226716527840539,
      "grad_norm": 1.2721318006515503,
      "learning_rate": 2.5e-05,
      "loss": 1.4995,
      "step": 175
    },
    {
      "epoch": 0.0007116247460389188,
      "grad_norm": 0.647321343421936,
      "learning_rate": 2.5e-05,
      "loss": 1.5624,
      "step": 200
    },
    {
      "epoch": 0.0008005778392937836,
      "grad_norm": 2.433274984359741,
      "learning_rate": 2.5e-05,
      "loss": 1.6035,
      "step": 225
    },
    {
      "epoch": 0.0008895309325486485,
      "grad_norm": 0.5926241278648376,
      "learning_rate": 2.5e-05,
      "loss": 1.4234,
      "step": 250
    },
    {
      "epoch": 0.0009784840258035134,
      "grad_norm": 1.6820074319839478,
      "learning_rate": 2.5e-05,
      "loss": 1.1803,
      "step": 275
    },
    {
      "epoch": 0.001067437119058378,
      "grad_norm": 1.5319762229919434,
      "learning_rate": 2.5e-05,
      "loss": 1.3767,
      "step": 300
    },
    {
      "epoch": 0.001156390212313243,
      "grad_norm": 0.5725632309913635,
      "learning_rate": 2.5e-05,
      "loss": 1.245,
      "step": 325
    },
    {
      "epoch": 0.0012453433055681078,
      "grad_norm": 0.7384375929832458,
      "learning_rate": 2.5e-05,
      "loss": 1.2259,
      "step": 350
    },
    {
      "epoch": 0.0013342963988229727,
      "grad_norm": 0.5739320516586304,
      "learning_rate": 2.5e-05,
      "loss": 1.2383,
      "step": 375
    },
    {
      "epoch": 0.0014232494920778376,
      "grad_norm": 0.962674617767334,
      "learning_rate": 2.5e-05,
      "loss": 1.2162,
      "step": 400
    },
    {
      "epoch": 0.0015122025853327023,
      "grad_norm": 1.2786195278167725,
      "learning_rate": 2.5e-05,
      "loss": 1.224,
      "step": 425
    },
    {
      "epoch": 0.0016011556785875672,
      "grad_norm": 1.3110697269439697,
      "learning_rate": 2.5e-05,
      "loss": 1.3172,
      "step": 450
    },
    {
      "epoch": 0.001690108771842432,
      "grad_norm": 0.6006544828414917,
      "learning_rate": 2.5e-05,
      "loss": 1.3636,
      "step": 475
    },
    {
      "epoch": 0.001779061865097297,
      "grad_norm": 0.6102003455162048,
      "learning_rate": 2.5e-05,
      "loss": 1.1117,
      "step": 500
    }
  ],
  "logging_steps": 25,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0200419401728e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}