last-checkpoint/trainer_state.json

{
  "best_metric": 2.349764585494995,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.0004452597645466365,
  "eval_steps": 5,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.781039058186546e-05,
      "eval_loss": 4.000479698181152,
      "eval_runtime": 663.8195,
      "eval_samples_per_second": 8.905,
      "eval_steps_per_second": 4.453,
      "step": 1
    },
    {
      "epoch": 5.343117174559638e-05,
      "grad_norm": 6.259640216827393,
      "learning_rate": 6e-05,
      "loss": 3.69,
      "step": 3
    },
    {
      "epoch": 8.90519529093273e-05,
      "eval_loss": 3.7225074768066406,
      "eval_runtime": 655.7424,
      "eval_samples_per_second": 9.014,
      "eval_steps_per_second": 4.508,
      "step": 5
    },
    {
      "epoch": 0.00010686234349119276,
      "grad_norm": 5.012327194213867,
      "learning_rate": 0.00012,
      "loss": 3.5799,
      "step": 6
    },
    {
      "epoch": 0.00016029351523678915,
      "grad_norm": 6.506889820098877,
      "learning_rate": 0.00018,
      "loss": 3.1326,
      "step": 9
    },
    {
      "epoch": 0.0001781039058186546,
      "eval_loss": 2.8797872066497803,
      "eval_runtime": 652.5436,
      "eval_samples_per_second": 9.058,
      "eval_steps_per_second": 4.53,
      "step": 10
    },
    {
      "epoch": 0.00021372468698238552,
      "grad_norm": 5.294992923736572,
      "learning_rate": 0.0001913545457642601,
      "loss": 2.8922,
      "step": 12
    },
    {
      "epoch": 0.0002671558587279819,
      "grad_norm": 7.777354717254639,
      "learning_rate": 0.00015000000000000001,
      "loss": 2.4119,
      "step": 15
    },
    {
      "epoch": 0.0002671558587279819,
      "eval_loss": 2.4778892993927,
      "eval_runtime": 659.4412,
      "eval_samples_per_second": 8.964,
      "eval_steps_per_second": 4.483,
      "step": 15
    },
    {
      "epoch": 0.0003205870304735783,
      "grad_norm": 5.830846309661865,
      "learning_rate": 8.954715367323468e-05,
      "loss": 2.501,
      "step": 18
    },
    {
      "epoch": 0.0003562078116373092,
      "eval_loss": 2.372363805770874,
      "eval_runtime": 648.4012,
      "eval_samples_per_second": 9.116,
      "eval_steps_per_second": 4.559,
      "step": 20
    },
    {
      "epoch": 0.00037401820221917467,
      "grad_norm": 7.219645023345947,
      "learning_rate": 3.308693936411421e-05,
      "loss": 2.2832,
      "step": 21
    },
    {
      "epoch": 0.00042744937396477104,
      "grad_norm": 5.5584635734558105,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 2.1534,
      "step": 24
    },
    {
      "epoch": 0.0004452597645466365,
      "eval_loss": 2.349764585494995,
      "eval_runtime": 653.0315,
      "eval_samples_per_second": 9.052,
      "eval_steps_per_second": 4.527,
      "step": 25
    }
  ],
  "logging_steps": 3,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 112649109504000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}