checkpoint-900/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 11.11111111111111,
  "eval_steps": 500,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6172839506172839,
      "grad_norm": 62.88630294799805,
      "learning_rate": 9.916000000000001e-06,
      "loss": 6.6856,
      "step": 50
    },
    {
      "epoch": 1.2345679012345678,
      "grad_norm": 387.6339111328125,
      "learning_rate": 9.818000000000002e-06,
      "loss": 5.5869,
      "step": 100
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 245.18975830078125,
      "learning_rate": 9.718e-06,
      "loss": 5.159,
      "step": 150
    },
    {
      "epoch": 2.4691358024691357,
      "grad_norm": 330.3158264160156,
      "learning_rate": 9.618e-06,
      "loss": 4.0494,
      "step": 200
    },
    {
      "epoch": 3.0864197530864197,
      "grad_norm": 138.14215087890625,
      "learning_rate": 9.518000000000001e-06,
      "loss": 3.6313,
      "step": 250
    },
    {
      "epoch": 3.7037037037037037,
      "grad_norm": 166.69479370117188,
      "learning_rate": 9.418e-06,
      "loss": 3.3391,
      "step": 300
    },
    {
      "epoch": 4.320987654320987,
      "grad_norm": 107.54407501220703,
      "learning_rate": 9.318e-06,
      "loss": 3.3295,
      "step": 350
    },
    {
      "epoch": 4.938271604938271,
      "grad_norm": 293.8923034667969,
      "learning_rate": 9.218e-06,
      "loss": 3.0956,
      "step": 400
    },
    {
      "epoch": 5.555555555555555,
      "grad_norm": 226.05360412597656,
      "learning_rate": 9.118000000000001e-06,
      "loss": 3.0271,
      "step": 450
    },
    {
      "epoch": 6.172839506172839,
      "grad_norm": 352.8487854003906,
      "learning_rate": 9.018e-06,
      "loss": 3.0627,
      "step": 500
    },
    {
      "epoch": 6.790123456790123,
      "grad_norm": 97.6641616821289,
      "learning_rate": 8.918000000000002e-06,
      "loss": 3.0312,
      "step": 550
    },
    {
      "epoch": 7.407407407407407,
      "grad_norm": 90.92312622070312,
      "learning_rate": 8.818000000000001e-06,
      "loss": 3.0228,
      "step": 600
    },
    {
      "epoch": 8.024691358024691,
      "grad_norm": 241.7625732421875,
      "learning_rate": 8.718e-06,
      "loss": 3.0873,
      "step": 650
    },
    {
      "epoch": 8.641975308641975,
      "grad_norm": 162.14071655273438,
      "learning_rate": 8.618000000000001e-06,
      "loss": 2.9582,
      "step": 700
    },
    {
      "epoch": 9.25925925925926,
      "grad_norm": 128.74766540527344,
      "learning_rate": 8.518e-06,
      "loss": 2.9787,
      "step": 750
    },
    {
      "epoch": 9.876543209876543,
      "grad_norm": 164.0232391357422,
      "learning_rate": 8.418000000000001e-06,
      "loss": 2.969,
      "step": 800
    },
    {
      "epoch": 10.493827160493828,
      "grad_norm": 110.58142852783203,
      "learning_rate": 8.318e-06,
      "loss": 2.884,
      "step": 850
    },
    {
      "epoch": 11.11111111111111,
      "grad_norm": 111.70948791503906,
      "learning_rate": 8.218e-06,
      "loss": 2.8216,
      "step": 900
    }
  ],
  "logging_steps": 50,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 62,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.440188495872e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}