last-checkpoint/trainer_state.json

{
  "best_metric": 1.0782692432403564,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0021325371861171828,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.108457287057277e-05,
      "eval_loss": 1.8576879501342773,
      "eval_runtime": 1802.2994,
      "eval_samples_per_second": 3.287,
      "eval_steps_per_second": 1.643,
      "step": 1
    },
    {
      "epoch": 0.00021325371861171828,
      "grad_norm": 3.8153765201568604,
      "learning_rate": 6e-05,
      "loss": 7.5545,
      "step": 3
    },
    {
      "epoch": 0.00035542286435286385,
      "eval_loss": 1.744638442993164,
      "eval_runtime": 1837.2156,
      "eval_samples_per_second": 3.224,
      "eval_steps_per_second": 1.612,
      "step": 5
    },
    {
      "epoch": 0.00042650743722343656,
      "grad_norm": 4.091126441955566,
      "learning_rate": 9.96057350657239e-05,
      "loss": 7.4738,
      "step": 6
    },
    {
      "epoch": 0.0006397611558351549,
      "grad_norm": 3.555290937423706,
      "learning_rate": 9.381533400219318e-05,
      "loss": 6.5046,
      "step": 9
    },
    {
      "epoch": 0.0007108457287057277,
      "eval_loss": 1.4176307916641235,
      "eval_runtime": 1840.5896,
      "eval_samples_per_second": 3.219,
      "eval_steps_per_second": 1.609,
      "step": 10
    },
    {
      "epoch": 0.0008530148744468731,
      "grad_norm": 2.932966947555542,
      "learning_rate": 8.18711994874345e-05,
      "loss": 5.9641,
      "step": 12
    },
    {
      "epoch": 0.0010662685930585914,
      "grad_norm": 2.8447232246398926,
      "learning_rate": 6.545084971874738e-05,
      "loss": 5.2347,
      "step": 15
    },
    {
      "epoch": 0.0010662685930585914,
      "eval_loss": 1.2026777267456055,
      "eval_runtime": 1839.866,
      "eval_samples_per_second": 3.22,
      "eval_steps_per_second": 1.61,
      "step": 15
    },
    {
      "epoch": 0.0012795223116703097,
      "grad_norm": 3.2762951850891113,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 4.6009,
      "step": 18
    },
    {
      "epoch": 0.0014216914574114554,
      "eval_loss": 1.1148810386657715,
      "eval_runtime": 1839.4766,
      "eval_samples_per_second": 3.22,
      "eval_steps_per_second": 1.61,
      "step": 20
    },
    {
      "epoch": 0.001492776030282028,
      "grad_norm": 2.7787132263183594,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 4.6107,
      "step": 21
    },
    {
      "epoch": 0.0017060297488937462,
      "grad_norm": 3.437938690185547,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 4.4289,
      "step": 24
    },
    {
      "epoch": 0.0017771143217643192,
      "eval_loss": 1.0836812257766724,
      "eval_runtime": 1842.4959,
      "eval_samples_per_second": 3.215,
      "eval_steps_per_second": 1.608,
      "step": 25
    },
    {
      "epoch": 0.0019192834675054646,
      "grad_norm": 2.346892833709717,
      "learning_rate": 3.511175705587433e-06,
      "loss": 4.3868,
      "step": 27
    },
    {
      "epoch": 0.0021325371861171828,
      "grad_norm": 2.5171074867248535,
      "learning_rate": 0.0,
      "loss": 4.3477,
      "step": 30
    },
    {
      "epoch": 0.0021325371861171828,
      "eval_loss": 1.0782692432403564,
      "eval_runtime": 1839.9719,
      "eval_samples_per_second": 3.22,
      "eval_steps_per_second": 1.61,
      "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": 1.9043369091072e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}