last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004228776826302992,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004228776826302992,
      "eval_loss": 1.7915385961532593,
      "eval_runtime": 87.7121,
      "eval_samples_per_second": 11.355,
      "eval_steps_per_second": 5.678,
      "step": 1
    },
    {
      "epoch": 0.0012686330478908975,
      "grad_norm": 0.7311314940452576,
      "learning_rate": 6e-05,
      "loss": 1.7856,
      "step": 3
    },
    {
      "epoch": 0.002537266095781795,
      "grad_norm": 0.8283582925796509,
      "learning_rate": 0.00012,
      "loss": 1.8386,
      "step": 6
    },
    {
      "epoch": 0.0033830214610423934,
      "eval_loss": 1.6457921266555786,
      "eval_runtime": 86.6816,
      "eval_samples_per_second": 11.49,
      "eval_steps_per_second": 5.745,
      "step": 8
    },
    {
      "epoch": 0.003805899143672693,
      "grad_norm": 0.7579265832901001,
      "learning_rate": 0.00018,
      "loss": 1.559,
      "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": 5288752935075840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}