checkpoint-102/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 102,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09950248756218906,
      "grad_norm": 0.6564624905586243,
      "learning_rate": 0.00019215686274509807,
      "loss": 3.0078,
      "step": 5
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 0.6871398091316223,
      "learning_rate": 0.0001823529411764706,
      "loss": 2.8242,
      "step": 10
    },
    {
      "epoch": 0.29850746268656714,
      "grad_norm": 0.8124077320098877,
      "learning_rate": 0.00017254901960784316,
      "loss": 2.5151,
      "step": 15
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 1.6018518209457397,
      "learning_rate": 0.0001627450980392157,
      "loss": 2.1472,
      "step": 20
    },
    {
      "epoch": 0.4975124378109453,
      "grad_norm": 0.9264693856239319,
      "learning_rate": 0.00015294117647058822,
      "loss": 1.8993,
      "step": 25
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.8736022114753723,
      "learning_rate": 0.00014313725490196078,
      "loss": 1.8384,
      "step": 30
    },
    {
      "epoch": 0.6965174129353234,
      "grad_norm": 1.6786866188049316,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.4841,
      "step": 35
    },
    {
      "epoch": 0.7960199004975125,
      "grad_norm": 2.2415640354156494,
      "learning_rate": 0.0001235294117647059,
      "loss": 1.3095,
      "step": 40
    },
    {
      "epoch": 0.8955223880597015,
      "grad_norm": 0.7268061637878418,
      "learning_rate": 0.00011372549019607843,
      "loss": 1.5891,
      "step": 45
    },
    {
      "epoch": 0.9950248756218906,
      "grad_norm": 0.6739829778671265,
      "learning_rate": 0.00010392156862745099,
      "loss": 1.5697,
      "step": 50
    },
    {
      "epoch": 1.0796019900497513,
      "grad_norm": 0.8251414895057678,
      "learning_rate": 9.411764705882353e-05,
      "loss": 1.4902,
      "step": 55
    },
    {
      "epoch": 1.1791044776119404,
      "grad_norm": 0.6778109073638916,
      "learning_rate": 8.431372549019608e-05,
      "loss": 1.3125,
      "step": 60
    },
    {
      "epoch": 1.2786069651741294,
      "grad_norm": 0.7273361682891846,
      "learning_rate": 7.450980392156864e-05,
      "loss": 1.1912,
      "step": 65
    },
    {
      "epoch": 1.3781094527363185,
      "grad_norm": 0.7228267788887024,
      "learning_rate": 6.470588235294118e-05,
      "loss": 1.4244,
      "step": 70
    },
    {
      "epoch": 1.4776119402985075,
      "grad_norm": 3.164576768875122,
      "learning_rate": 5.490196078431373e-05,
      "loss": 1.4583,
      "step": 75
    },
    {
      "epoch": 1.5771144278606966,
      "grad_norm": 0.7823672294616699,
      "learning_rate": 4.5098039215686275e-05,
      "loss": 1.4158,
      "step": 80
    },
    {
      "epoch": 1.6766169154228856,
      "grad_norm": 0.7993632555007935,
      "learning_rate": 3.529411764705883e-05,
      "loss": 1.2409,
      "step": 85
    },
    {
      "epoch": 1.7761194029850746,
      "grad_norm": 0.7184426188468933,
      "learning_rate": 2.5490196078431373e-05,
      "loss": 1.2346,
      "step": 90
    },
    {
      "epoch": 1.8756218905472637,
      "grad_norm": 0.8258879780769348,
      "learning_rate": 1.568627450980392e-05,
      "loss": 1.3385,
      "step": 95
    },
    {
      "epoch": 1.9751243781094527,
      "grad_norm": 0.727968692779541,
      "learning_rate": 5.882352941176471e-06,
      "loss": 1.5243,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 102,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3275743297536000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}