last-checkpoint/trainer_state.json

{
  "best_metric": 3.548567771911621,
  "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": 3.9746313095092773,
      "eval_runtime": 48.7988,
      "eval_samples_per_second": 50.329,
      "eval_steps_per_second": 25.165,
      "step": 1
    },
    {
      "epoch": 0.00051440329218107,
      "grad_norm": 46.01416015625,
      "learning_rate": 6e-05,
      "loss": 15.6898,
      "step": 3
    },
    {
      "epoch": 0.0008573388203017832,
      "eval_loss": 3.9556028842926025,
      "eval_runtime": 48.9909,
      "eval_samples_per_second": 50.132,
      "eval_steps_per_second": 25.066,
      "step": 5
    },
    {
      "epoch": 0.00102880658436214,
      "grad_norm": 45.302635192871094,
      "learning_rate": 0.00012,
      "loss": 16.039,
      "step": 6
    },
    {
      "epoch": 0.0015432098765432098,
      "grad_norm": 57.03993225097656,
      "learning_rate": 0.00018,
      "loss": 17.0235,
      "step": 9
    },
    {
      "epoch": 0.0017146776406035665,
      "eval_loss": 3.8164217472076416,
      "eval_runtime": 49.444,
      "eval_samples_per_second": 49.672,
      "eval_steps_per_second": 24.836,
      "step": 10
    },
    {
      "epoch": 0.00205761316872428,
      "grad_norm": 60.8523063659668,
      "learning_rate": 0.00019510565162951537,
      "loss": 14.8321,
      "step": 12
    },
    {
      "epoch": 0.00257201646090535,
      "grad_norm": 64.35668182373047,
      "learning_rate": 0.00017071067811865476,
      "loss": 14.7542,
      "step": 15
    },
    {
      "epoch": 0.00257201646090535,
      "eval_loss": 3.6742002964019775,
      "eval_runtime": 52.3218,
      "eval_samples_per_second": 46.94,
      "eval_steps_per_second": 23.47,
      "step": 15
    },
    {
      "epoch": 0.0030864197530864196,
      "grad_norm": 63.078304290771484,
      "learning_rate": 0.00013090169943749476,
      "loss": 15.7294,
      "step": 18
    },
    {
      "epoch": 0.003429355281207133,
      "eval_loss": 3.5884788036346436,
      "eval_runtime": 49.8784,
      "eval_samples_per_second": 49.24,
      "eval_steps_per_second": 24.62,
      "step": 20
    },
    {
      "epoch": 0.00360082304526749,
      "grad_norm": 65.02677917480469,
      "learning_rate": 8.435655349597689e-05,
      "loss": 14.097,
      "step": 21
    },
    {
      "epoch": 0.00411522633744856,
      "grad_norm": 76.67129516601562,
      "learning_rate": 4.12214747707527e-05,
      "loss": 13.7619,
      "step": 24
    },
    {
      "epoch": 0.0042866941015089165,
      "eval_loss": 3.5535809993743896,
      "eval_runtime": 48.946,
      "eval_samples_per_second": 50.178,
      "eval_steps_per_second": 25.089,
      "step": 25
    },
    {
      "epoch": 0.004629629629629629,
      "grad_norm": 60.97380447387695,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 13.284,
      "step": 27
    },
    {
      "epoch": 0.0051440329218107,
      "grad_norm": 59.055320739746094,
      "learning_rate": 0.0,
      "loss": 14.099,
      "step": 30
    },
    {
      "epoch": 0.0051440329218107,
      "eval_loss": 3.548567771911621,
      "eval_runtime": 52.3268,
      "eval_samples_per_second": 46.936,
      "eval_steps_per_second": 23.468,
      "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
}