last-checkpoint/trainer_state.json

{
  "best_metric": 2.458465576171875,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.016133369185264857,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005377789728421619,
      "eval_loss": 3.4151339530944824,
      "eval_runtime": 43.9013,
      "eval_samples_per_second": 17.835,
      "eval_steps_per_second": 8.929,
      "step": 1
    },
    {
      "epoch": 0.0016133369185264857,
      "grad_norm": 9.241133689880371,
      "learning_rate": 3e-05,
      "loss": 14.2802,
      "step": 3
    },
    {
      "epoch": 0.0026888948642108095,
      "eval_loss": 3.3437061309814453,
      "eval_runtime": 44.0837,
      "eval_samples_per_second": 17.762,
      "eval_steps_per_second": 8.892,
      "step": 5
    },
    {
      "epoch": 0.0032266738370529714,
      "grad_norm": 9.475666999816895,
      "learning_rate": 6e-05,
      "loss": 14.2606,
      "step": 6
    },
    {
      "epoch": 0.004840010755579457,
      "grad_norm": 8.76632022857666,
      "learning_rate": 9e-05,
      "loss": 13.2169,
      "step": 9
    },
    {
      "epoch": 0.005377789728421619,
      "eval_loss": 2.988180637359619,
      "eval_runtime": 44.2516,
      "eval_samples_per_second": 17.694,
      "eval_steps_per_second": 8.858,
      "step": 10
    },
    {
      "epoch": 0.006453347674105943,
      "grad_norm": 7.595180511474609,
      "learning_rate": 9.755282581475769e-05,
      "loss": 12.3926,
      "step": 12
    },
    {
      "epoch": 0.008066684592632429,
      "grad_norm": 7.204962253570557,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.3131,
      "step": 15
    },
    {
      "epoch": 0.008066684592632429,
      "eval_loss": 2.7008702754974365,
      "eval_runtime": 44.416,
      "eval_samples_per_second": 17.629,
      "eval_steps_per_second": 8.826,
      "step": 15
    },
    {
      "epoch": 0.009680021511158914,
      "grad_norm": 5.720189094543457,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.1332,
      "step": 18
    },
    {
      "epoch": 0.010755579456843238,
      "eval_loss": 2.5447235107421875,
      "eval_runtime": 44.2569,
      "eval_samples_per_second": 17.692,
      "eval_steps_per_second": 8.857,
      "step": 20
    },
    {
      "epoch": 0.0112933584296854,
      "grad_norm": 8.198662757873535,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 10.4708,
      "step": 21
    },
    {
      "epoch": 0.012906695348211886,
      "grad_norm": 6.4804582595825195,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.4489,
      "step": 24
    },
    {
      "epoch": 0.013444474321054048,
      "eval_loss": 2.470919132232666,
      "eval_runtime": 44.4226,
      "eval_samples_per_second": 17.626,
      "eval_steps_per_second": 8.824,
      "step": 25
    },
    {
      "epoch": 0.01452003226673837,
      "grad_norm": 8.004265785217285,
      "learning_rate": 5.449673790581611e-06,
      "loss": 10.1526,
      "step": 27
    },
    {
      "epoch": 0.016133369185264857,
      "grad_norm": 6.694253444671631,
      "learning_rate": 0.0,
      "loss": 9.8513,
      "step": 30
    },
    {
      "epoch": 0.016133369185264857,
      "eval_loss": 2.458465576171875,
      "eval_runtime": 44.2895,
      "eval_samples_per_second": 17.679,
      "eval_steps_per_second": 8.851,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3933157824921600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}