last-checkpoint/trainer_state.json

{
  "best_metric": 3.5863263607025146,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0051440329218107,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017146776406035664,
      "eval_loss": 3.9735350608825684,
      "eval_runtime": 31.8257,
      "eval_samples_per_second": 77.17,
      "eval_steps_per_second": 38.585,
      "step": 1
    },
    {
      "epoch": 0.00051440329218107,
      "grad_norm": 57.646759033203125,
      "learning_rate": 6e-05,
      "loss": 15.6695,
      "step": 3
    },
    {
      "epoch": 0.0008573388203017832,
      "eval_loss": 3.944896936416626,
      "eval_runtime": 31.6407,
      "eval_samples_per_second": 77.621,
      "eval_steps_per_second": 38.811,
      "step": 5
    },
    {
      "epoch": 0.00102880658436214,
      "grad_norm": 47.253658294677734,
      "learning_rate": 0.00012,
      "loss": 15.961,
      "step": 6
    },
    {
      "epoch": 0.0015432098765432098,
      "grad_norm": 54.7822380065918,
      "learning_rate": 0.00018,
      "loss": 16.9551,
      "step": 9
    },
    {
      "epoch": 0.0017146776406035665,
      "eval_loss": 3.788233757019043,
      "eval_runtime": 31.5873,
      "eval_samples_per_second": 77.753,
      "eval_steps_per_second": 38.876,
      "step": 10
    },
    {
      "epoch": 0.00205761316872428,
      "grad_norm": 79.7057876586914,
      "learning_rate": 0.00019510565162951537,
      "loss": 14.7597,
      "step": 12
    },
    {
      "epoch": 0.00257201646090535,
      "grad_norm": 70.68734741210938,
      "learning_rate": 0.00017071067811865476,
      "loss": 14.6524,
      "step": 15
    },
    {
      "epoch": 0.00257201646090535,
      "eval_loss": 3.66300630569458,
      "eval_runtime": 32.4865,
      "eval_samples_per_second": 75.601,
      "eval_steps_per_second": 37.8,
      "step": 15
    },
    {
      "epoch": 0.0030864197530864196,
      "grad_norm": 99.36012268066406,
      "learning_rate": 0.00013090169943749476,
      "loss": 15.8241,
      "step": 18
    },
    {
      "epoch": 0.003429355281207133,
      "eval_loss": 3.6078875064849854,
      "eval_runtime": 31.6607,
      "eval_samples_per_second": 77.572,
      "eval_steps_per_second": 38.786,
      "step": 20
    },
    {
      "epoch": 0.00360082304526749,
      "grad_norm": 75.07467651367188,
      "learning_rate": 8.435655349597689e-05,
      "loss": 14.2807,
      "step": 21
    },
    {
      "epoch": 0.00411522633744856,
      "grad_norm": 96.82402038574219,
      "learning_rate": 4.12214747707527e-05,
      "loss": 14.0723,
      "step": 24
    },
    {
      "epoch": 0.0042866941015089165,
      "eval_loss": 3.58929705619812,
      "eval_runtime": 31.6823,
      "eval_samples_per_second": 77.52,
      "eval_steps_per_second": 38.76,
      "step": 25
    },
    {
      "epoch": 0.004629629629629629,
      "grad_norm": 67.07957458496094,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 13.2909,
      "step": 27
    },
    {
      "epoch": 0.0051440329218107,
      "grad_norm": 66.56720733642578,
      "learning_rate": 0.0,
      "loss": 14.2312,
      "step": 30
    },
    {
      "epoch": 0.0051440329218107,
      "eval_loss": 3.5863263607025146,
      "eval_runtime": 31.6317,
      "eval_samples_per_second": 77.644,
      "eval_steps_per_second": 38.822,
      "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": 531009959362560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}