checkpoint-1966/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 1000,
  "global_step": 1966,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000508646998982706,
      "grad_norm": 4.802672863006592,
      "learning_rate": 0.0,
      "loss": 3.5148,
      "step": 1
    },
    {
      "epoch": 0.508646998982706,
      "grad_norm": 4.325772285461426,
      "learning_rate": 2.994574432010851e-05,
      "loss": 2.3332,
      "step": 1000
    },
    {
      "epoch": 0.508646998982706,
      "eval_cosine_accuracy": 0.9514144659042358,
      "eval_loss": 0.4182649254798889,
      "eval_runtime": 40.3586,
      "eval_samples_per_second": 235.613,
      "eval_steps_per_second": 0.942,
      "step": 1000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 9830,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}