last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015594541910331383,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015594541910331384,
      "eval_loss": 1.508385419845581,
      "eval_runtime": 26.969,
      "eval_samples_per_second": 10.049,
      "eval_steps_per_second": 5.043,
      "step": 1
    },
    {
      "epoch": 0.004678362573099415,
      "grad_norm": 0.39213576912879944,
      "learning_rate": 3e-05,
      "loss": 1.5605,
      "step": 3
    },
    {
      "epoch": 0.007797270955165692,
      "eval_loss": 1.4978253841400146,
      "eval_runtime": 26.4506,
      "eval_samples_per_second": 10.246,
      "eval_steps_per_second": 5.142,
      "step": 5
    },
    {
      "epoch": 0.00935672514619883,
      "grad_norm": 0.36995622515678406,
      "learning_rate": 6e-05,
      "loss": 1.4723,
      "step": 6
    },
    {
      "epoch": 0.014035087719298246,
      "grad_norm": 0.3752123713493347,
      "learning_rate": 9e-05,
      "loss": 1.3854,
      "step": 9
    },
    {
      "epoch": 0.015594541910331383,
      "eval_loss": 1.4332730770111084,
      "eval_runtime": 26.4493,
      "eval_samples_per_second": 10.246,
      "eval_steps_per_second": 5.142,
      "step": 10
    }
  ],
  "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": 6044488367603712.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}