trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 21,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 8.267570495605469,
      "learning_rate": 3.055555555555556e-05,
      "loss": 1.0915,
      "step": 10
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 9.618600845336914,
      "learning_rate": 2.777777777777778e-06,
      "loss": 1.0665,
      "step": 20
    },
    {
      "epoch": 1.0,
      "step": 21,
      "train_accuracy": 0.5294117647058824,
      "train_f1_score": 0.4002614379084967,
      "train_loss": 1.0142669677734375,
      "train_precision": 0.6444444444444445,
      "train_recall": 0.44285714285714284,
      "train_runtime": 92.9856,
      "train_samples_per_second": 0.914,
      "train_steps_per_second": 0.237
    },
    {
      "epoch": 1.0,
      "step": 21,
      "total_flos": 1.0467035897226854e+17,
      "train_loss": 1.0731309538795835,
      "train_runtime": 209.4786,
      "train_samples_per_second": 0.401,
      "train_steps_per_second": 0.1
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.47619047619047616,
      "eval_f1_score": 0.41111111111111115,
      "eval_loss": 1.0267835855484009,
      "eval_precision": 0.48888888888888893,
      "eval_recall": 0.42116402116402113,
      "eval_runtime": 45.2712,
      "eval_samples_per_second": 0.464,
      "eval_steps_per_second": 0.133,
      "step": 21
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.47619047619047616,
      "eval_f1_score": 0.41111111111111115,
      "eval_loss": 1.0267837047576904,
      "eval_precision": 0.48888888888888893,
      "eval_recall": 0.42116402116402113,
      "eval_runtime": 47.5405,
      "eval_samples_per_second": 0.442,
      "eval_steps_per_second": 0.126,
      "step": 21
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.47619047619047616,
      "eval_f1_score": 0.41111111111111115,
      "eval_loss": 1.0267835855484009,
      "eval_precision": 0.48888888888888893,
      "eval_recall": 0.42116402116402113,
      "eval_runtime": 53.8815,
      "eval_samples_per_second": 0.39,
      "eval_steps_per_second": 0.111,
      "step": 21
    }
  ],
  "logging_steps": 10,
  "max_steps": 21,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "total_flos": 1.0467035897226854e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}