last-checkpoint/trainer_state.json

{
  "best_metric": 2.1252670288085938,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.002137246869823855,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.124156232746183e-05,
      "eval_loss": 3.529541492462158,
      "eval_runtime": 124.3483,
      "eval_samples_per_second": 47.536,
      "eval_steps_per_second": 23.772,
      "step": 1
    },
    {
      "epoch": 0.00021372468698238552,
      "grad_norm": 7.570005893707275,
      "learning_rate": 6e-05,
      "loss": 3.2671,
      "step": 3
    },
    {
      "epoch": 0.0003562078116373092,
      "eval_loss": 3.216201066970825,
      "eval_runtime": 124.4772,
      "eval_samples_per_second": 47.487,
      "eval_steps_per_second": 23.747,
      "step": 5
    },
    {
      "epoch": 0.00042744937396477104,
      "grad_norm": 3.774989604949951,
      "learning_rate": 0.00012,
      "loss": 2.9538,
      "step": 6
    },
    {
      "epoch": 0.0006411740609471566,
      "grad_norm": 3.665858030319214,
      "learning_rate": 0.00018,
      "loss": 2.7992,
      "step": 9
    },
    {
      "epoch": 0.0007124156232746184,
      "eval_loss": 2.4446890354156494,
      "eval_runtime": 123.643,
      "eval_samples_per_second": 47.807,
      "eval_steps_per_second": 23.908,
      "step": 10
    },
    {
      "epoch": 0.0008548987479295421,
      "grad_norm": 4.437066078186035,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.4558,
      "step": 12
    },
    {
      "epoch": 0.0010686234349119275,
      "grad_norm": 6.945307731628418,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.3293,
      "step": 15
    },
    {
      "epoch": 0.0010686234349119275,
      "eval_loss": 2.2446939945220947,
      "eval_runtime": 124.6029,
      "eval_samples_per_second": 47.439,
      "eval_steps_per_second": 23.723,
      "step": 15
    },
    {
      "epoch": 0.0012823481218943132,
      "grad_norm": 3.3825199604034424,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.0153,
      "step": 18
    },
    {
      "epoch": 0.0014248312465492369,
      "eval_loss": 2.165391683578491,
      "eval_runtime": 124.0293,
      "eval_samples_per_second": 47.658,
      "eval_steps_per_second": 23.833,
      "step": 20
    },
    {
      "epoch": 0.0014960728088766987,
      "grad_norm": 1.945841908454895,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.0475,
      "step": 21
    },
    {
      "epoch": 0.0017097974958590841,
      "grad_norm": 2.166755199432373,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.2409,
      "step": 24
    },
    {
      "epoch": 0.001781039058186546,
      "eval_loss": 2.1316721439361572,
      "eval_runtime": 124.1003,
      "eval_samples_per_second": 47.631,
      "eval_steps_per_second": 23.819,
      "step": 25
    },
    {
      "epoch": 0.0019235221828414698,
      "grad_norm": 2.1919233798980713,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.2256,
      "step": 27
    },
    {
      "epoch": 0.002137246869823855,
      "grad_norm": 1.7260620594024658,
      "learning_rate": 0.0,
      "loss": 2.0275,
      "step": 30
    },
    {
      "epoch": 0.002137246869823855,
      "eval_loss": 2.1252670288085938,
      "eval_runtime": 123.7376,
      "eval_samples_per_second": 47.77,
      "eval_steps_per_second": 23.889,
      "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": 540715725619200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}