last-checkpoint/trainer_state.json

{
  "best_metric": 1.4536380767822266,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.023323615160349854,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0023323615160349854,
      "grad_norm": 1.5346574783325195,
      "learning_rate": 2e-05,
      "loss": 2.2105,
      "step": 1
    },
    {
      "epoch": 0.0023323615160349854,
      "eval_loss": 1.6742810010910034,
      "eval_runtime": 36.5226,
      "eval_samples_per_second": 4.956,
      "eval_steps_per_second": 2.492,
      "step": 1
    },
    {
      "epoch": 0.004664723032069971,
      "grad_norm": 1.4139418601989746,
      "learning_rate": 4e-05,
      "loss": 1.4349,
      "step": 2
    },
    {
      "epoch": 0.006997084548104956,
      "grad_norm": 0.9706037044525146,
      "learning_rate": 6e-05,
      "loss": 0.9538,
      "step": 3
    },
    {
      "epoch": 0.009329446064139942,
      "grad_norm": 1.288402795791626,
      "learning_rate": 8e-05,
      "loss": 1.5789,
      "step": 4
    },
    {
      "epoch": 0.011661807580174927,
      "grad_norm": 1.1371190547943115,
      "learning_rate": 0.0001,
      "loss": 1.4299,
      "step": 5
    },
    {
      "epoch": 0.011661807580174927,
      "eval_loss": 1.5869524478912354,
      "eval_runtime": 36.6166,
      "eval_samples_per_second": 4.943,
      "eval_steps_per_second": 2.485,
      "step": 5
    },
    {
      "epoch": 0.013994169096209912,
      "grad_norm": 1.3522026538848877,
      "learning_rate": 0.00012,
      "loss": 2.1149,
      "step": 6
    },
    {
      "epoch": 0.0163265306122449,
      "grad_norm": 0.786292314529419,
      "learning_rate": 0.00014,
      "loss": 1.0683,
      "step": 7
    },
    {
      "epoch": 0.018658892128279883,
      "grad_norm": 0.6935855150222778,
      "learning_rate": 0.00016,
      "loss": 1.747,
      "step": 8
    },
    {
      "epoch": 0.02099125364431487,
      "grad_norm": 0.5766379237174988,
      "learning_rate": 0.00018,
      "loss": 1.4661,
      "step": 9
    },
    {
      "epoch": 0.023323615160349854,
      "grad_norm": 0.5700016021728516,
      "learning_rate": 0.0002,
      "loss": 1.0889,
      "step": 10
    },
    {
      "epoch": 0.023323615160349854,
      "eval_loss": 1.4536380767822266,
      "eval_runtime": 36.7676,
      "eval_samples_per_second": 4.923,
      "eval_steps_per_second": 2.475,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 987692228149248.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}