last-checkpoint/trainer_state.json

{
  "best_metric": 0.48303693532943726,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.06012024048096192,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002004008016032064,
      "eval_loss": 0.9850762486457825,
      "eval_runtime": 128.4869,
      "eval_samples_per_second": 3.277,
      "eval_steps_per_second": 0.825,
      "step": 1
    },
    {
      "epoch": 0.006012024048096192,
      "grad_norm": 4.1979827880859375,
      "learning_rate": 0.00012,
      "loss": 3.8858,
      "step": 3
    },
    {
      "epoch": 0.01002004008016032,
      "eval_loss": 0.6958473324775696,
      "eval_runtime": 130.0511,
      "eval_samples_per_second": 3.237,
      "eval_steps_per_second": 0.815,
      "step": 5
    },
    {
      "epoch": 0.012024048096192385,
      "grad_norm": 3.8240315914154053,
      "learning_rate": 0.0001992114701314478,
      "loss": 3.0604,
      "step": 6
    },
    {
      "epoch": 0.018036072144288578,
      "grad_norm": 2.5113887786865234,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.4975,
      "step": 9
    },
    {
      "epoch": 0.02004008016032064,
      "eval_loss": 0.5356647372245789,
      "eval_runtime": 130.3435,
      "eval_samples_per_second": 3.23,
      "eval_steps_per_second": 0.813,
      "step": 10
    },
    {
      "epoch": 0.02404809619238477,
      "grad_norm": 1.6339120864868164,
      "learning_rate": 0.000163742398974869,
      "loss": 2.266,
      "step": 12
    },
    {
      "epoch": 0.03006012024048096,
      "grad_norm": 1.4827417135238647,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.1759,
      "step": 15
    },
    {
      "epoch": 0.03006012024048096,
      "eval_loss": 0.5040991306304932,
      "eval_runtime": 130.1615,
      "eval_samples_per_second": 3.234,
      "eval_steps_per_second": 0.814,
      "step": 15
    },
    {
      "epoch": 0.036072144288577156,
      "grad_norm": 1.6338112354278564,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.248,
      "step": 18
    },
    {
      "epoch": 0.04008016032064128,
      "eval_loss": 0.49245163798332214,
      "eval_runtime": 130.2917,
      "eval_samples_per_second": 3.231,
      "eval_steps_per_second": 0.814,
      "step": 20
    },
    {
      "epoch": 0.04208416833667335,
      "grad_norm": 1.6009563207626343,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.0628,
      "step": 21
    },
    {
      "epoch": 0.04809619238476954,
      "grad_norm": 1.474389910697937,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.9829,
      "step": 24
    },
    {
      "epoch": 0.050100200400801605,
      "eval_loss": 0.48446887731552124,
      "eval_runtime": 130.4175,
      "eval_samples_per_second": 3.228,
      "eval_steps_per_second": 0.813,
      "step": 25
    },
    {
      "epoch": 0.05410821643286573,
      "grad_norm": 1.4533580541610718,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.8224,
      "step": 27
    },
    {
      "epoch": 0.06012024048096192,
      "grad_norm": 1.5185352563858032,
      "learning_rate": 0.0,
      "loss": 1.863,
      "step": 30
    },
    {
      "epoch": 0.06012024048096192,
      "eval_loss": 0.48303693532943726,
      "eval_runtime": 130.2143,
      "eval_samples_per_second": 3.233,
      "eval_steps_per_second": 0.814,
      "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": 4.218776992088064e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}