checkpoint-1000/trainer_state.json

{
  "best_metric": 0.8976572133168927,
  "best_model_checkpoint": "AAmeni/LILT-checkpoints/checkpoint-600",
  "epoch": 12.195121951219512,
  "eval_steps": 200,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.4390243902439024,
      "eval_accuracy": 0.9208400646203554,
      "eval_f1": 0.8652657601977751,
      "eval_loss": 0.29326215386390686,
      "eval_precision": 0.875,
      "eval_recall": 0.8557457212713936,
      "eval_runtime": 10.0837,
      "eval_samples_per_second": 4.165,
      "eval_steps_per_second": 1.091,
      "step": 200
    },
    {
      "epoch": 4.878048780487805,
      "eval_accuracy": 0.925686591276252,
      "eval_f1": 0.8767123287671232,
      "eval_loss": 0.3650479018688202,
      "eval_precision": 0.8934010152284264,
      "eval_recall": 0.8606356968215159,
      "eval_runtime": 10.3053,
      "eval_samples_per_second": 4.076,
      "eval_steps_per_second": 1.067,
      "step": 400
    },
    {
      "epoch": 6.097560975609756,
      "grad_norm": 15.58462905883789,
      "learning_rate": 3.989837398373984e-05,
      "loss": 0.3014,
      "step": 500
    },
    {
      "epoch": 7.317073170731708,
      "eval_accuracy": 0.938610662358643,
      "eval_f1": 0.8976572133168927,
      "eval_loss": 0.382191926240921,
      "eval_precision": 0.9054726368159204,
      "eval_recall": 0.8899755501222494,
      "eval_runtime": 9.3762,
      "eval_samples_per_second": 4.479,
      "eval_steps_per_second": 1.173,
      "step": 600
    },
    {
      "epoch": 9.75609756097561,
      "eval_accuracy": 0.938610662358643,
      "eval_f1": 0.8902589395807645,
      "eval_loss": 0.4051755368709564,
      "eval_precision": 0.8980099502487562,
      "eval_recall": 0.882640586797066,
      "eval_runtime": 8.2706,
      "eval_samples_per_second": 5.078,
      "eval_steps_per_second": 1.33,
      "step": 800
    },
    {
      "epoch": 12.195121951219512,
      "grad_norm": 0.035131603479385376,
      "learning_rate": 2.973577235772358e-05,
      "loss": 0.0365,
      "step": 1000
    },
    {
      "epoch": 12.195121951219512,
      "eval_accuracy": 0.938610662358643,
      "eval_f1": 0.8932515337423313,
      "eval_loss": 0.4668120741844177,
      "eval_precision": 0.896551724137931,
      "eval_recall": 0.8899755501222494,
      "eval_runtime": 10.5119,
      "eval_samples_per_second": 3.995,
      "eval_steps_per_second": 1.046,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2460,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 556320854016000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}