last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10355987055016182,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025889967637540454,
      "grad_norm": 9.556614875793457,
      "learning_rate": 1e-05,
      "loss": 6.8963,
      "step": 1
    },
    {
      "epoch": 0.025889967637540454,
      "eval_loss": 7.188828468322754,
      "eval_runtime": 96.5266,
      "eval_samples_per_second": 0.684,
      "eval_steps_per_second": 0.342,
      "step": 1
    },
    {
      "epoch": 0.05177993527508091,
      "grad_norm": 9.590712547302246,
      "learning_rate": 2e-05,
      "loss": 7.0956,
      "step": 2
    },
    {
      "epoch": 0.05177993527508091,
      "eval_loss": 7.104136943817139,
      "eval_runtime": 10.7379,
      "eval_samples_per_second": 6.146,
      "eval_steps_per_second": 3.073,
      "step": 2
    },
    {
      "epoch": 0.07766990291262135,
      "grad_norm": 9.618792533874512,
      "learning_rate": 3e-05,
      "loss": 7.1833,
      "step": 3
    },
    {
      "epoch": 0.10355987055016182,
      "grad_norm": 9.063897132873535,
      "learning_rate": 4e-05,
      "loss": 6.7351,
      "step": 4
    },
    {
      "epoch": 0.10355987055016182,
      "eval_loss": 6.6838154792785645,
      "eval_runtime": 10.7563,
      "eval_samples_per_second": 6.136,
      "eval_steps_per_second": 3.068,
      "step": 4
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6567659575443456.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}