last-checkpoint/trainer_state.json

{
  "best_metric": 1.478926658630371,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0022282881176536127,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.427627058845375e-05,
      "eval_loss": 2.134462356567383,
      "eval_runtime": 725.5692,
      "eval_samples_per_second": 7.813,
      "eval_steps_per_second": 3.907,
      "step": 1
    },
    {
      "epoch": 0.00022282881176536126,
      "grad_norm": 25.934616088867188,
      "learning_rate": 6e-05,
      "loss": 8.6831,
      "step": 3
    },
    {
      "epoch": 0.0003713813529422688,
      "eval_loss": 1.8423094749450684,
      "eval_runtime": 728.8393,
      "eval_samples_per_second": 7.778,
      "eval_steps_per_second": 3.89,
      "step": 5
    },
    {
      "epoch": 0.0004456576235307225,
      "grad_norm": 17.646089553833008,
      "learning_rate": 0.00012,
      "loss": 7.8916,
      "step": 6
    },
    {
      "epoch": 0.0006684864352960838,
      "grad_norm": 11.403993606567383,
      "learning_rate": 0.00018,
      "loss": 7.1084,
      "step": 9
    },
    {
      "epoch": 0.0007427627058845376,
      "eval_loss": 1.5946590900421143,
      "eval_runtime": 727.8722,
      "eval_samples_per_second": 7.788,
      "eval_steps_per_second": 3.895,
      "step": 10
    },
    {
      "epoch": 0.000891315247061445,
      "grad_norm": 13.892797470092773,
      "learning_rate": 0.00019510565162951537,
      "loss": 6.251,
      "step": 12
    },
    {
      "epoch": 0.0011141440588268063,
      "grad_norm": 7.632380962371826,
      "learning_rate": 0.00017071067811865476,
      "loss": 6.082,
      "step": 15
    },
    {
      "epoch": 0.0011141440588268063,
      "eval_loss": 1.5541844367980957,
      "eval_runtime": 728.0052,
      "eval_samples_per_second": 7.787,
      "eval_steps_per_second": 3.894,
      "step": 15
    },
    {
      "epoch": 0.0013369728705921677,
      "grad_norm": 8.058558464050293,
      "learning_rate": 0.00013090169943749476,
      "loss": 6.2013,
      "step": 18
    },
    {
      "epoch": 0.0014855254117690751,
      "eval_loss": 1.5074851512908936,
      "eval_runtime": 727.2543,
      "eval_samples_per_second": 7.795,
      "eval_steps_per_second": 3.898,
      "step": 20
    },
    {
      "epoch": 0.0015598016823575288,
      "grad_norm": 8.454328536987305,
      "learning_rate": 8.435655349597689e-05,
      "loss": 6.3236,
      "step": 21
    },
    {
      "epoch": 0.00178263049412289,
      "grad_norm": 6.996322154998779,
      "learning_rate": 4.12214747707527e-05,
      "loss": 6.3287,
      "step": 24
    },
    {
      "epoch": 0.001856906764711344,
      "eval_loss": 1.4847581386566162,
      "eval_runtime": 728.1195,
      "eval_samples_per_second": 7.786,
      "eval_steps_per_second": 3.894,
      "step": 25
    },
    {
      "epoch": 0.002005459305888251,
      "grad_norm": 9.126077651977539,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 6.1673,
      "step": 27
    },
    {
      "epoch": 0.0022282881176536127,
      "grad_norm": 8.678947448730469,
      "learning_rate": 0.0,
      "loss": 5.3701,
      "step": 30
    },
    {
      "epoch": 0.0022282881176536127,
      "eval_loss": 1.478926658630371,
      "eval_runtime": 726.7085,
      "eval_samples_per_second": 7.801,
      "eval_steps_per_second": 3.901,
      "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": 1.1074302287806464e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}