last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013647219379051518,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001364721937905152,
      "eval_loss": 11.113584518432617,
      "eval_runtime": 2.2913,
      "eval_samples_per_second": 134.857,
      "eval_steps_per_second": 67.647,
      "step": 1
    },
    {
      "epoch": 0.0040941658137154556,
      "grad_norm": 1.9208190441131592,
      "learning_rate": 6e-05,
      "loss": 44.4814,
      "step": 3
    },
    {
      "epoch": 0.008188331627430911,
      "grad_norm": 1.8466147184371948,
      "learning_rate": 0.00012,
      "loss": 44.4149,
      "step": 6
    },
    {
      "epoch": 0.010917775503241215,
      "eval_loss": 11.091691017150879,
      "eval_runtime": 1.1447,
      "eval_samples_per_second": 269.934,
      "eval_steps_per_second": 135.404,
      "step": 8
    },
    {
      "epoch": 0.012282497441146366,
      "grad_norm": 1.8949085474014282,
      "learning_rate": 0.00018,
      "loss": 44.3801,
      "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": 207995535360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}