last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04085801838610827,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008171603677221655,
      "grad_norm": 2.0513486862182617,
      "learning_rate": 1e-05,
      "loss": 2.6675,
      "step": 1
    },
    {
      "epoch": 0.008171603677221655,
      "eval_loss": 2.9138283729553223,
      "eval_runtime": 78.8303,
      "eval_samples_per_second": 2.626,
      "eval_steps_per_second": 1.319,
      "step": 1
    },
    {
      "epoch": 0.01634320735444331,
      "grad_norm": 2.482210636138916,
      "learning_rate": 2e-05,
      "loss": 3.1408,
      "step": 2
    },
    {
      "epoch": 0.01634320735444331,
      "eval_loss": 2.8457190990448,
      "eval_runtime": 1.9977,
      "eval_samples_per_second": 103.619,
      "eval_steps_per_second": 52.06,
      "step": 2
    },
    {
      "epoch": 0.024514811031664963,
      "grad_norm": 2.1288490295410156,
      "learning_rate": 3e-05,
      "loss": 2.7252,
      "step": 3
    },
    {
      "epoch": 0.03268641470888662,
      "grad_norm": 2.3600332736968994,
      "learning_rate": 4e-05,
      "loss": 2.9044,
      "step": 4
    },
    {
      "epoch": 0.03268641470888662,
      "eval_loss": 2.7578065395355225,
      "eval_runtime": 2.0631,
      "eval_samples_per_second": 100.333,
      "eval_steps_per_second": 50.409,
      "step": 4
    },
    {
      "epoch": 0.04085801838610827,
      "grad_norm": 2.2336041927337646,
      "learning_rate": 5e-05,
      "loss": 2.7225,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 753578520084480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}