checkpoint-1500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 23.076923076923077,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 134.7136688232422,
      "learning_rate": 9.981600000000001e-06,
      "loss": 5.6198,
      "step": 100
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 115.98611450195312,
      "learning_rate": 9.961600000000001e-06,
      "loss": 3.5959,
      "step": 200
    },
    {
      "epoch": 4.615384615384615,
      "grad_norm": 114.23514556884766,
      "learning_rate": 9.941600000000002e-06,
      "loss": 3.3845,
      "step": 300
    },
    {
      "epoch": 6.153846153846154,
      "grad_norm": 140.5648193359375,
      "learning_rate": 9.921600000000002e-06,
      "loss": 3.1494,
      "step": 400
    },
    {
      "epoch": 7.6923076923076925,
      "grad_norm": 117.4485855102539,
      "learning_rate": 9.901600000000002e-06,
      "loss": 3.0773,
      "step": 500
    },
    {
      "epoch": 9.23076923076923,
      "grad_norm": 389.71490478515625,
      "learning_rate": 9.8816e-06,
      "loss": 3.2116,
      "step": 600
    },
    {
      "epoch": 10.76923076923077,
      "grad_norm": 107.11251831054688,
      "learning_rate": 9.8616e-06,
      "loss": 3.0471,
      "step": 700
    },
    {
      "epoch": 12.307692307692308,
      "grad_norm": 85.49571228027344,
      "learning_rate": 9.8416e-06,
      "loss": 3.0201,
      "step": 800
    },
    {
      "epoch": 13.846153846153847,
      "grad_norm": 121.62274932861328,
      "learning_rate": 9.821600000000001e-06,
      "loss": 2.9355,
      "step": 900
    },
    {
      "epoch": 15.384615384615385,
      "grad_norm": 64.66451263427734,
      "learning_rate": 9.801600000000001e-06,
      "loss": 2.9637,
      "step": 1000
    },
    {
      "epoch": 16.923076923076923,
      "grad_norm": 182.4657440185547,
      "learning_rate": 9.781600000000001e-06,
      "loss": 2.9819,
      "step": 1100
    },
    {
      "epoch": 18.46153846153846,
      "grad_norm": 97.80529022216797,
      "learning_rate": 9.761600000000002e-06,
      "loss": 2.9486,
      "step": 1200
    },
    {
      "epoch": 20.0,
      "grad_norm": 220.0562744140625,
      "learning_rate": 9.741600000000002e-06,
      "loss": 2.8608,
      "step": 1300
    },
    {
      "epoch": 21.53846153846154,
      "grad_norm": 95.53397369384766,
      "learning_rate": 9.7216e-06,
      "loss": 2.8322,
      "step": 1400
    },
    {
      "epoch": 23.076923076923077,
      "grad_norm": 67.54853057861328,
      "learning_rate": 9.7016e-06,
      "loss": 2.9429,
      "step": 1500
    }
  ],
  "logging_steps": 100,
  "max_steps": 50000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 770,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.73364749312e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}