checkpoint-1876/trainer_state.json

{
  "best_global_step": 1876,
  "best_metric": 0.15963459014892578,
  "best_model_checkpoint": "metaclip-2-image-classification/checkpoint-1876",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 1876,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5330490405117271,
      "grad_norm": 104.10272979736328,
      "learning_rate": 1.7574284170718533e-05,
      "loss": 0.8655,
      "step": 500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.92635,
      "eval_loss": 0.2205629199743271,
      "eval_model_preparation_time": 0.0039,
      "eval_runtime": 90.292,
      "eval_samples_per_second": 221.503,
      "eval_steps_per_second": 27.688,
      "step": 938
    },
    {
      "epoch": 1.0660980810234542,
      "grad_norm": 53.17558670043945,
      "learning_rate": 1.4873041599135603e-05,
      "loss": 0.4234,
      "step": 1000
    },
    {
      "epoch": 1.5991471215351813,
      "grad_norm": 17.705827713012695,
      "learning_rate": 1.2171799027552675e-05,
      "loss": 0.3154,
      "step": 1500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9459,
      "eval_loss": 0.15963459014892578,
      "eval_model_preparation_time": 0.0039,
      "eval_runtime": 87.0564,
      "eval_samples_per_second": 229.736,
      "eval_steps_per_second": 28.717,
      "step": 1876
    }
  ],
  "logging_steps": 500,
  "max_steps": 3752,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 1.17019413504e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}