last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0935672514619883,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01871345029239766,
      "grad_norm": Infinity,
      "learning_rate": 1e-05,
      "loss": 46.7188,
      "step": 1
    },
    {
      "epoch": 0.01871345029239766,
      "eval_loss": 2.9281249046325684,
      "eval_runtime": 25.752,
      "eval_samples_per_second": 3.495,
      "eval_steps_per_second": 1.747,
      "step": 1
    },
    {
      "epoch": 0.03742690058479532,
      "grad_norm": Infinity,
      "learning_rate": 2e-05,
      "loss": 44.5078,
      "step": 2
    },
    {
      "epoch": 0.03742690058479532,
      "eval_loss": 2.9281249046325684,
      "eval_runtime": 0.5079,
      "eval_samples_per_second": 177.184,
      "eval_steps_per_second": 88.592,
      "step": 2
    },
    {
      "epoch": 0.056140350877192984,
      "grad_norm": Infinity,
      "learning_rate": 3e-05,
      "loss": 45.6562,
      "step": 3
    },
    {
      "epoch": 0.07485380116959064,
      "grad_norm": Infinity,
      "learning_rate": 4e-05,
      "loss": 45.4375,
      "step": 4
    },
    {
      "epoch": 0.07485380116959064,
      "eval_loss": 2.9281249046325684,
      "eval_runtime": 0.5128,
      "eval_samples_per_second": 175.5,
      "eval_steps_per_second": 87.75,
      "step": 4
    },
    {
      "epoch": 0.0935672514619883,
      "grad_norm": 17.95364761352539,
      "learning_rate": 5e-05,
      "loss": 47.6562,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 153892788633600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}