checkpoint-7968/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 12.0,
  "eval_steps": 500,
  "global_step": 7968,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7530120481927711,
      "grad_norm": 0.2647170126438141,
      "learning_rate": 0.0004811746987951807,
      "loss": 0.3311,
      "step": 500
    },
    {
      "epoch": 1.5060240963855422,
      "grad_norm": 0.22880347073078156,
      "learning_rate": 0.00046234939759036143,
      "loss": 0.0907,
      "step": 1000
    },
    {
      "epoch": 2.2590361445783134,
      "grad_norm": 0.1677163541316986,
      "learning_rate": 0.00044352409638554217,
      "loss": 0.0568,
      "step": 1500
    },
    {
      "epoch": 3.0120481927710845,
      "grad_norm": 0.12338300049304962,
      "learning_rate": 0.0004246987951807229,
      "loss": 0.0451,
      "step": 2000
    },
    {
      "epoch": 3.765060240963855,
      "grad_norm": 0.08597979694604874,
      "learning_rate": 0.0004058734939759036,
      "loss": 0.0386,
      "step": 2500
    },
    {
      "epoch": 4.518072289156627,
      "grad_norm": 0.0988745242357254,
      "learning_rate": 0.00038704819277108433,
      "loss": 0.0352,
      "step": 3000
    },
    {
      "epoch": 5.271084337349397,
      "grad_norm": 0.11785969883203506,
      "learning_rate": 0.00036822289156626507,
      "loss": 0.0331,
      "step": 3500
    },
    {
      "epoch": 6.024096385542169,
      "grad_norm": 0.09906379133462906,
      "learning_rate": 0.0003493975903614458,
      "loss": 0.0315,
      "step": 4000
    },
    {
      "epoch": 6.77710843373494,
      "grad_norm": 0.1129639744758606,
      "learning_rate": 0.0003305722891566265,
      "loss": 0.0301,
      "step": 4500
    },
    {
      "epoch": 7.530120481927711,
      "grad_norm": 0.07321502268314362,
      "learning_rate": 0.00031174698795180723,
      "loss": 0.0292,
      "step": 5000
    },
    {
      "epoch": 8.283132530120483,
      "grad_norm": 0.05083702132105827,
      "learning_rate": 0.0002929216867469879,
      "loss": 0.028,
      "step": 5500
    },
    {
      "epoch": 9.036144578313253,
      "grad_norm": 0.073179692029953,
      "learning_rate": 0.0002740963855421687,
      "loss": 0.0275,
      "step": 6000
    },
    {
      "epoch": 9.789156626506024,
      "grad_norm": 0.060432616621255875,
      "learning_rate": 0.0002552710843373494,
      "loss": 0.0266,
      "step": 6500
    },
    {
      "epoch": 10.542168674698795,
      "grad_norm": 0.05641400068998337,
      "learning_rate": 0.00023644578313253013,
      "loss": 0.0265,
      "step": 7000
    },
    {
      "epoch": 11.295180722891565,
      "grad_norm": 0.055228352546691895,
      "learning_rate": 0.00021762048192771087,
      "loss": 0.0257,
      "step": 7500
    }
  ],
  "logging_steps": 500,
  "max_steps": 13280,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "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": 4308132553555968.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}