last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.25,
  "eval_steps": 100,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.25,
      "eval_loss": 0.018973365426063538,
      "eval_runtime": 3.4194,
      "eval_samples_per_second": 9.358,
      "eval_steps_per_second": 0.292,
      "step": 100
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.018465671688318253,
      "eval_runtime": 3.4208,
      "eval_samples_per_second": 9.355,
      "eval_steps_per_second": 0.292,
      "step": 200
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.018071258440613747,
      "eval_runtime": 3.4148,
      "eval_samples_per_second": 9.371,
      "eval_steps_per_second": 0.293,
      "step": 300
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.01745143160223961,
      "eval_runtime": 3.4178,
      "eval_samples_per_second": 9.363,
      "eval_steps_per_second": 0.293,
      "step": 400
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.001775189652107656,
      "learning_rate": 0.00019149810004597903,
      "loss": 0.0747,
      "step": 500
    },
    {
      "epoch": 1.25,
      "eval_loss": 0.01536159124225378,
      "eval_runtime": 3.4147,
      "eval_samples_per_second": 9.371,
      "eval_steps_per_second": 0.293,
      "step": 500
    },
    {
      "epoch": 1.5,
      "eval_loss": 0.01273431722074747,
      "eval_runtime": 3.4158,
      "eval_samples_per_second": 9.368,
      "eval_steps_per_second": 0.293,
      "step": 600
    },
    {
      "epoch": 1.75,
      "eval_loss": 0.012279544025659561,
      "eval_runtime": 3.4156,
      "eval_samples_per_second": 9.369,
      "eval_steps_per_second": 0.293,
      "step": 700
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.012152126990258694,
      "eval_runtime": 3.4211,
      "eval_samples_per_second": 9.354,
      "eval_steps_per_second": 0.292,
      "step": 800
    },
    {
      "epoch": 2.25,
      "eval_loss": 0.012095152400434017,
      "eval_runtime": 3.4203,
      "eval_samples_per_second": 9.356,
      "eval_steps_per_second": 0.292,
      "step": 900
    }
  ],
  "logging_steps": 500,
  "max_steps": 1200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3327995625065677e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}