checkpoint-500/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4667989263624694,
  "eval_steps": 250,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2333994631812347,
      "grad_norm": 3.4083237648010254,
      "learning_rate": 8.996514402527381e-05,
      "loss": 0.2768,
      "step": 250
    },
    {
      "epoch": 0.2333994631812347,
      "eval_loss": 0.15054132044315338,
      "eval_runtime": 39.385,
      "eval_samples_per_second": 2.209,
      "eval_steps_per_second": 2.209,
      "step": 250
    },
    {
      "epoch": 0.4667989263624694,
      "grad_norm": 7.858141899108887,
      "learning_rate": 5.843391598090062e-05,
      "loss": 0.1092,
      "step": 500
    },
    {
      "epoch": 0.4667989263624694,
      "eval_loss": 0.11498060077428818,
      "eval_runtime": 39.2923,
      "eval_samples_per_second": 2.214,
      "eval_steps_per_second": 2.214,
      "step": 500
    }
  ],
  "logging_steps": 250,
  "max_steps": 1071,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.124302026529997e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}