last-checkpoint/trainer_state.json

{
  "best_metric": 0.816862165927887,
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
  "epoch": 0.008989976176563132,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.989976176563132e-05,
      "eval_loss": 1.525974988937378,
      "eval_runtime": 653.7709,
      "eval_samples_per_second": 7.165,
      "eval_steps_per_second": 3.582,
      "step": 1
    },
    {
      "epoch": 0.0008989976176563133,
      "grad_norm": 27.566255569458008,
      "learning_rate": 2.5e-06,
      "loss": 5.9581,
      "step": 10
    },
    {
      "epoch": 0.0017979952353126265,
      "grad_norm": 23.980079650878906,
      "learning_rate": 5e-06,
      "loss": 5.7295,
      "step": 20
    },
    {
      "epoch": 0.0026969928529689395,
      "grad_norm": 22.77297592163086,
      "learning_rate": 7.5e-06,
      "loss": 4.7677,
      "step": 30
    },
    {
      "epoch": 0.003595990470625253,
      "grad_norm": 24.030942916870117,
      "learning_rate": 1e-05,
      "loss": 4.3247,
      "step": 40
    },
    {
      "epoch": 0.004494988088281566,
      "grad_norm": 18.87146759033203,
      "learning_rate": 1.25e-05,
      "loss": 3.8906,
      "step": 50
    },
    {
      "epoch": 0.005393985705937879,
      "grad_norm": 20.442569732666016,
      "learning_rate": 1.5e-05,
      "loss": 3.6275,
      "step": 60
    },
    {
      "epoch": 0.0062929833235941925,
      "grad_norm": 18.778696060180664,
      "learning_rate": 1.75e-05,
      "loss": 3.5476,
      "step": 70
    },
    {
      "epoch": 0.007191980941250506,
      "grad_norm": 17.43655776977539,
      "learning_rate": 2e-05,
      "loss": 3.4289,
      "step": 80
    },
    {
      "epoch": 0.008090978558906819,
      "grad_norm": 21.041603088378906,
      "learning_rate": 2.25e-05,
      "loss": 3.3832,
      "step": 90
    },
    {
      "epoch": 0.008989976176563132,
      "grad_norm": 18.440113067626953,
      "learning_rate": 2.5e-05,
      "loss": 3.3127,
      "step": 100
    },
    {
      "epoch": 0.008989976176563132,
      "eval_loss": 0.816862165927887,
      "eval_runtime": 653.3249,
      "eval_samples_per_second": 7.169,
      "eval_steps_per_second": 3.585,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.066805854470144e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}