last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0020479213598197828,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.82640453273261e-05,
      "eval_loss": 11.5,
      "eval_runtime": 36.6278,
      "eval_samples_per_second": 168.397,
      "eval_steps_per_second": 84.198,
      "step": 1
    },
    {
      "epoch": 0.00020479213598197828,
      "grad_norm": 2.006130489462521e-05,
      "learning_rate": 3e-05,
      "loss": 46.0,
      "step": 3
    },
    {
      "epoch": 0.00040958427196395656,
      "grad_norm": 1.6455342120025307e-05,
      "learning_rate": 6e-05,
      "loss": 46.0,
      "step": 6
    },
    {
      "epoch": 0.0005461123626186088,
      "eval_loss": 11.5,
      "eval_runtime": 36.5661,
      "eval_samples_per_second": 168.681,
      "eval_steps_per_second": 84.34,
      "step": 8
    },
    {
      "epoch": 0.0006143764079459349,
      "grad_norm": 1.869518746389076e-05,
      "learning_rate": 9e-05,
      "loss": 46.0,
      "step": 9
    },
    {
      "epoch": 0.0008191685439279131,
      "grad_norm": 1.7077587472158484e-05,
      "learning_rate": 9.755282581475769e-05,
      "loss": 46.0,
      "step": 12
    },
    {
      "epoch": 0.0010239606799098914,
      "grad_norm": 2.8311023925198242e-05,
      "learning_rate": 8.535533905932738e-05,
      "loss": 46.0,
      "step": 15
    },
    {
      "epoch": 0.0010922247252372176,
      "eval_loss": 11.5,
      "eval_runtime": 36.7465,
      "eval_samples_per_second": 167.853,
      "eval_steps_per_second": 83.926,
      "step": 16
    },
    {
      "epoch": 0.0012287528158918697,
      "grad_norm": 1.9214716303395107e-05,
      "learning_rate": 6.545084971874738e-05,
      "loss": 46.0,
      "step": 18
    },
    {
      "epoch": 0.0014335449518738481,
      "grad_norm": 2.6326768420403823e-05,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 46.0,
      "step": 21
    },
    {
      "epoch": 0.0016383370878558263,
      "grad_norm": 1.5010924471425824e-05,
      "learning_rate": 2.061073738537635e-05,
      "loss": 46.0,
      "step": 24
    },
    {
      "epoch": 0.0016383370878558263,
      "eval_loss": 11.5,
      "eval_runtime": 36.8458,
      "eval_samples_per_second": 167.4,
      "eval_steps_per_second": 83.7,
      "step": 24
    },
    {
      "epoch": 0.0018431292238378046,
      "grad_norm": 2.5682602426968515e-05,
      "learning_rate": 5.449673790581611e-06,
      "loss": 46.0,
      "step": 27
    },
    {
      "epoch": 0.0020479213598197828,
      "grad_norm": 2.1994239432387985e-05,
      "learning_rate": 0.0,
      "loss": 46.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1246752768000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}