checkpoint-677/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 677,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.29542097488921715,
      "grad_norm": 48.92063522338867,
      "learning_rate": 2.45e-05,
      "loss": 352758333.44,
      "step": 50
    },
    {
      "epoch": 0.5908419497784343,
      "grad_norm": 6.408321380615234,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 178610135.04,
      "step": 100
    },
    {
      "epoch": 0.8862629246676514,
      "grad_norm": 1.5189077854156494,
      "learning_rate": 4.731947483588622e-05,
      "loss": 0.4129,
      "step": 150
    },
    {
      "epoch": 1.1816838995568686,
      "grad_norm": 2.1191959381103516,
      "learning_rate": 4.458424507658643e-05,
      "loss": 0.2667,
      "step": 200
    },
    {
      "epoch": 1.4771048744460857,
      "grad_norm": 4.9505510330200195,
      "learning_rate": 4.201312910284464e-05,
      "loss": 27.1689,
      "step": 250
    },
    {
      "epoch": 1.7725258493353029,
      "grad_norm": 0.197406604886055,
      "learning_rate": 3.9332603938730855e-05,
      "loss": 4.521,
      "step": 300
    },
    {
      "epoch": 2.06794682422452,
      "grad_norm": 0.035883717238903046,
      "learning_rate": 3.6597374179431074e-05,
      "loss": 0.0013,
      "step": 350
    },
    {
      "epoch": 2.363367799113737,
      "grad_norm": 0.02112976275384426,
      "learning_rate": 3.386214442013129e-05,
      "loss": 0.0006,
      "step": 400
    },
    {
      "epoch": 2.658788774002954,
      "grad_norm": 0.005675207823514938,
      "learning_rate": 3.112691466083151e-05,
      "loss": 0.0003,
      "step": 450
    },
    {
      "epoch": 2.9542097488921715,
      "grad_norm": 0.004977445118129253,
      "learning_rate": 2.839168490153173e-05,
      "loss": 0.0003,
      "step": 500
    },
    {
      "epoch": 3.2496307237813884,
      "grad_norm": 0.0056141638197004795,
      "learning_rate": 2.565645514223195e-05,
      "loss": 0.0002,
      "step": 550
    },
    {
      "epoch": 3.5450516986706058,
      "grad_norm": 0.0035467667039483786,
      "learning_rate": 2.292122538293217e-05,
      "loss": 0.0002,
      "step": 600
    },
    {
      "epoch": 3.8404726735598227,
      "grad_norm": 0.0036520687863230705,
      "learning_rate": 2.0185995623632387e-05,
      "loss": 0.0001,
      "step": 650
    }
  ],
  "logging_steps": 50,
  "max_steps": 1014,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "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": 1.0693069955923968e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}