last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007454342154304882,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007454342154304882,
      "eval_loss": 3.5526232719421387,
      "eval_runtime": 9.0217,
      "eval_samples_per_second": 62.627,
      "eval_steps_per_second": 31.369,
      "step": 1
    },
    {
      "epoch": 0.0022363026462914647,
      "grad_norm": 1.7465190887451172,
      "learning_rate": 6e-05,
      "loss": 3.4371,
      "step": 3
    },
    {
      "epoch": 0.004472605292582929,
      "grad_norm": 1.784867525100708,
      "learning_rate": 0.00012,
      "loss": 3.419,
      "step": 6
    },
    {
      "epoch": 0.005963473723443906,
      "eval_loss": 2.901203155517578,
      "eval_runtime": 7.8582,
      "eval_samples_per_second": 71.9,
      "eval_steps_per_second": 36.013,
      "step": 8
    },
    {
      "epoch": 0.006708907938874394,
      "grad_norm": 1.8665266036987305,
      "learning_rate": 0.00018,
      "loss": 3.0066,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 69418793041920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}