last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006100971071228837,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00020336570237429458,
      "eval_loss": NaN,
      "eval_runtime": 70.9911,
      "eval_samples_per_second": 29.173,
      "eval_steps_per_second": 14.593,
      "step": 1
    },
    {
      "epoch": 0.0006100971071228837,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.001016828511871473,
      "eval_loss": NaN,
      "eval_runtime": 70.4481,
      "eval_samples_per_second": 29.398,
      "eval_steps_per_second": 14.706,
      "step": 5
    },
    {
      "epoch": 0.0012201942142457674,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0018302913213686513,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.002033657023742946,
      "eval_loss": NaN,
      "eval_runtime": 70.4354,
      "eval_samples_per_second": 29.403,
      "eval_steps_per_second": 14.709,
      "step": 10
    },
    {
      "epoch": 0.0024403884284915347,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0030504855356144186,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0030504855356144186,
      "eval_loss": NaN,
      "eval_runtime": 70.3932,
      "eval_samples_per_second": 29.42,
      "eval_steps_per_second": 14.717,
      "step": 15
    },
    {
      "epoch": 0.0036605826427373025,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.004067314047485892,
      "eval_loss": NaN,
      "eval_runtime": 70.434,
      "eval_samples_per_second": 29.403,
      "eval_steps_per_second": 14.709,
      "step": 20
    },
    {
      "epoch": 0.004270679749860186,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0048807768569830694,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.005084142559357364,
      "eval_loss": NaN,
      "eval_runtime": 70.3954,
      "eval_samples_per_second": 29.42,
      "eval_steps_per_second": 14.717,
      "step": 25
    },
    {
      "epoch": 0.005490873964105953,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.006100971071228837,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.006100971071228837,
      "eval_loss": NaN,
      "eval_runtime": 70.4023,
      "eval_samples_per_second": 29.417,
      "eval_steps_per_second": 14.715,
      "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": 4192264393850880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}