trainer_state.json

{
  "best_metric": 1.4213874340057373,
  "best_model_checkpoint": "tam_test_out_drug_data/checkpoint-1011",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 1011,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.46219659629870735,
      "eval_loss": 1.4630001783370972,
      "eval_runtime": 15.2997,
      "eval_samples_per_second": 702.823,
      "eval_steps_per_second": 7.386,
      "step": 337
    },
    {
      "epoch": 1.48,
      "grad_norm": 283691.34375,
      "learning_rate": 5.554896142433234e-05,
      "loss": 1.599,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.4721473077280759,
      "eval_loss": 1.443649411201477,
      "eval_runtime": 15.1007,
      "eval_samples_per_second": 712.086,
      "eval_steps_per_second": 7.483,
      "step": 674
    },
    {
      "epoch": 2.97,
      "grad_norm": 246200.171875,
      "learning_rate": 5.109792284866469e-05,
      "loss": 1.3511,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.471310332000372,
      "eval_loss": 1.4213874340057373,
      "eval_runtime": 14.9491,
      "eval_samples_per_second": 719.309,
      "eval_steps_per_second": 7.559,
      "step": 1011
    }
  ],
  "logging_steps": 500,
  "max_steps": 6740,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "total_flos": 1.32737670494208e+16,
  "train_batch_size": 96,
  "trial_name": null,
  "trial_params": null
}