last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03759398496240601,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018796992481203006,
      "eval_loss": 2.188689947128296,
      "eval_runtime": 15.8759,
      "eval_samples_per_second": 28.219,
      "eval_steps_per_second": 7.055,
      "step": 1
    },
    {
      "epoch": 0.005639097744360902,
      "grad_norm": 2.3131868839263916,
      "learning_rate": 3e-05,
      "loss": 2.1981,
      "step": 3
    },
    {
      "epoch": 0.009398496240601503,
      "eval_loss": 2.0904104709625244,
      "eval_runtime": 15.9911,
      "eval_samples_per_second": 28.016,
      "eval_steps_per_second": 7.004,
      "step": 5
    },
    {
      "epoch": 0.011278195488721804,
      "grad_norm": 1.1980903148651123,
      "learning_rate": 6e-05,
      "loss": 2.1063,
      "step": 6
    },
    {
      "epoch": 0.016917293233082706,
      "grad_norm": 1.9292231798171997,
      "learning_rate": 9e-05,
      "loss": 2.0794,
      "step": 9
    },
    {
      "epoch": 0.018796992481203006,
      "eval_loss": 1.9134695529937744,
      "eval_runtime": 16.0172,
      "eval_samples_per_second": 27.97,
      "eval_steps_per_second": 6.992,
      "step": 10
    },
    {
      "epoch": 0.022556390977443608,
      "grad_norm": 1.6164668798446655,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.9332,
      "step": 12
    },
    {
      "epoch": 0.02819548872180451,
      "grad_norm": 1.1573011875152588,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.7655,
      "step": 15
    },
    {
      "epoch": 0.02819548872180451,
      "eval_loss": 1.7978755235671997,
      "eval_runtime": 16.0385,
      "eval_samples_per_second": 27.933,
      "eval_steps_per_second": 6.983,
      "step": 15
    },
    {
      "epoch": 0.03383458646616541,
      "grad_norm": 1.463262677192688,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.7978,
      "step": 18
    },
    {
      "epoch": 0.03759398496240601,
      "eval_loss": 1.7174512147903442,
      "eval_runtime": 16.0423,
      "eval_samples_per_second": 27.926,
      "eval_steps_per_second": 6.982,
      "step": 20
    }
  ],
  "logging_steps": 3,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3973659450408960.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}