checkpoint-5082/trainer_state.json

{
  "best_metric": 1.5357526540756226,
  "best_model_checkpoint": "cat_breed_image_detection/checkpoint-5082",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 5082,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19677292404565133,
      "grad_norm": 5.552952289581299,
      "learning_rate": 8.195151033386328e-07,
      "loss": 1.5186,
      "step": 500
    },
    {
      "epoch": 0.39354584809130266,
      "grad_norm": 7.020349025726318,
      "learning_rate": 7.300874403815579e-07,
      "loss": 1.5185,
      "step": 1000
    },
    {
      "epoch": 0.5903187721369539,
      "grad_norm": 7.434261798858643,
      "learning_rate": 6.406597774244833e-07,
      "loss": 1.5257,
      "step": 1500
    },
    {
      "epoch": 0.7870916961826053,
      "grad_norm": 8.402517318725586,
      "learning_rate": 5.512321144674086e-07,
      "loss": 1.5192,
      "step": 2000
    },
    {
      "epoch": 0.9838646202282566,
      "grad_norm": 9.466378211975098,
      "learning_rate": 4.618044515103339e-07,
      "loss": 1.5059,
      "step": 2500
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5991567020962504,
      "eval_loss": 1.54666006565094,
      "eval_model_preparation_time": 0.0055,
      "eval_runtime": 1190.6514,
      "eval_samples_per_second": 91.029,
      "eval_steps_per_second": 2.845,
      "step": 2541
    },
    {
      "epoch": 1.1806375442739079,
      "grad_norm": 7.1390910148620605,
      "learning_rate": 3.7237678855325916e-07,
      "loss": 1.4908,
      "step": 3000
    },
    {
      "epoch": 1.3774104683195592,
      "grad_norm": 7.025146961212158,
      "learning_rate": 2.8294912559618444e-07,
      "loss": 1.5019,
      "step": 3500
    },
    {
      "epoch": 1.5741833923652107,
      "grad_norm": 7.744629383087158,
      "learning_rate": 1.935214626391097e-07,
      "loss": 1.4874,
      "step": 4000
    },
    {
      "epoch": 1.770956316410862,
      "grad_norm": 6.708190441131592,
      "learning_rate": 1.0409379968203497e-07,
      "loss": 1.4976,
      "step": 4500
    },
    {
      "epoch": 1.9677292404565132,
      "grad_norm": 7.407255172729492,
      "learning_rate": 1.4666136724960254e-08,
      "loss": 1.4901,
      "step": 5000
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6043973280188958,
      "eval_loss": 1.5357526540756226,
      "eval_model_preparation_time": 0.0055,
      "eval_runtime": 1207.654,
      "eval_samples_per_second": 89.748,
      "eval_steps_per_second": 2.805,
      "step": 5082
    }
  ],
  "logging_steps": 500,
  "max_steps": 5082,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.5207063579431272e+19,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}