checkpoint-1500/trainer_state.json

{
  "best_metric": 0.4501824975013733,
  "best_model_checkpoint": "weather_types_image_detection/checkpoint-1500",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9539184952978056,
      "eval_loss": 0.5098884701728821,
      "eval_runtime": 39.2951,
      "eval_samples_per_second": 81.181,
      "eval_steps_per_second": 2.545,
      "step": 150
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9570532915360501,
      "eval_loss": 0.4949048161506653,
      "eval_runtime": 39.4441,
      "eval_samples_per_second": 80.874,
      "eval_steps_per_second": 2.535,
      "step": 300
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9561128526645768,
      "eval_loss": 0.4842975437641144,
      "eval_runtime": 39.3465,
      "eval_samples_per_second": 81.074,
      "eval_steps_per_second": 2.542,
      "step": 450
    },
    {
      "epoch": 3.33,
      "grad_norm": 1.1265023946762085,
      "learning_rate": 6.896551724137931e-07,
      "loss": 0.4721,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9567398119122257,
      "eval_loss": 0.4747663140296936,
      "eval_runtime": 39.5346,
      "eval_samples_per_second": 80.689,
      "eval_steps_per_second": 2.529,
      "step": 600
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9573667711598746,
      "eval_loss": 0.4668954908847809,
      "eval_runtime": 39.8389,
      "eval_samples_per_second": 80.072,
      "eval_steps_per_second": 2.51,
      "step": 750
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9586206896551724,
      "eval_loss": 0.46064332127571106,
      "eval_runtime": 39.6385,
      "eval_samples_per_second": 80.477,
      "eval_steps_per_second": 2.523,
      "step": 900
    },
    {
      "epoch": 6.67,
      "grad_norm": 1.8112839460372925,
      "learning_rate": 3.4482758620689656e-07,
      "loss": 0.4345,
      "step": 1000
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.958307210031348,
      "eval_loss": 0.45618754625320435,
      "eval_runtime": 40.2114,
      "eval_samples_per_second": 79.331,
      "eval_steps_per_second": 2.487,
      "step": 1050
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9586206896551724,
      "eval_loss": 0.4524807333946228,
      "eval_runtime": 39.5729,
      "eval_samples_per_second": 80.611,
      "eval_steps_per_second": 2.527,
      "step": 1200
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.958307210031348,
      "eval_loss": 0.45089176297187805,
      "eval_runtime": 39.3148,
      "eval_samples_per_second": 81.14,
      "eval_steps_per_second": 2.544,
      "step": 1350
    },
    {
      "epoch": 10.0,
      "grad_norm": 2.30012845993042,
      "learning_rate": 0.0,
      "loss": 0.4159,
      "step": 1500
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.958307210031348,
      "eval_loss": 0.4501824975013733,
      "eval_runtime": 39.2529,
      "eval_samples_per_second": 81.268,
      "eval_steps_per_second": 2.548,
      "step": 1500
    }
  ],
  "logging_steps": 500,
  "max_steps": 1500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 7.416581610138624e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}