checkpoint-500/trainer_state.json

{
  "best_global_step": 500,
  "best_metric": 0.0044,
  "best_model_checkpoint": "./vit-codegpt-cadcoder/checkpoint-500",
  "epoch": 0.9411764705882353,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18823529411764706,
      "grad_norm": 2.2795276641845703,
      "learning_rate": 1.85625e-05,
      "loss": 4.284,
      "step": 100
    },
    {
      "epoch": 0.3764705882352941,
      "grad_norm": 2.0265636444091797,
      "learning_rate": 2.918523676880223e-05,
      "loss": 0.6672,
      "step": 200
    },
    {
      "epoch": 0.5647058823529412,
      "grad_norm": 1.4436606168746948,
      "learning_rate": 2.7096100278551535e-05,
      "loss": 0.5342,
      "step": 300
    },
    {
      "epoch": 0.7529411764705882,
      "grad_norm": 1.2276115417480469,
      "learning_rate": 2.5006963788300836e-05,
      "loss": 0.4912,
      "step": 400
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 1.580186128616333,
      "learning_rate": 2.2917827298050142e-05,
      "loss": 0.4748,
      "step": 500
    },
    {
      "epoch": 0.9411764705882353,
      "eval_loss": 0.41850993037223816,
      "eval_rouge1": 0.085,
      "eval_rouge2": 0.0044,
      "eval_rougeL": 0.0773,
      "eval_runtime": 4240.7834,
      "eval_samples_per_second": 0.354,
      "eval_steps_per_second": 0.088,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 1596,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.443711128961024e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}