last-checkpoint/trainer_state.json

{
  "best_metric": 1.6901915073394775,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.07286859363614283,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00048579062424095217,
      "eval_loss": 2.597476005554199,
      "eval_runtime": 51.8065,
      "eval_samples_per_second": 16.735,
      "eval_steps_per_second": 4.189,
      "step": 1
    },
    {
      "epoch": 0.004857906242409522,
      "grad_norm": 12.25637435913086,
      "learning_rate": 4.0600000000000004e-05,
      "loss": 3.1277,
      "step": 10
    },
    {
      "epoch": 0.009715812484819043,
      "grad_norm": 15.654220581054688,
      "learning_rate": 8.120000000000001e-05,
      "loss": 2.4062,
      "step": 20
    },
    {
      "epoch": 0.014573718727228565,
      "grad_norm": 15.304265022277832,
      "learning_rate": 0.00012179999999999999,
      "loss": 2.406,
      "step": 30
    },
    {
      "epoch": 0.019431624969638087,
      "grad_norm": 16.849159240722656,
      "learning_rate": 0.00016240000000000002,
      "loss": 2.9756,
      "step": 40
    },
    {
      "epoch": 0.024289531212047608,
      "grad_norm": 18.647008895874023,
      "learning_rate": 0.000203,
      "loss": 2.9989,
      "step": 50
    },
    {
      "epoch": 0.024289531212047608,
      "eval_loss": 1.6901915073394775,
      "eval_runtime": 51.7466,
      "eval_samples_per_second": 16.755,
      "eval_steps_per_second": 4.194,
      "step": 50
    },
    {
      "epoch": 0.02914743745445713,
      "grad_norm": 13.382312774658203,
      "learning_rate": 0.00020275275110137215,
      "loss": 2.9041,
      "step": 60
    },
    {
      "epoch": 0.03400534369686665,
      "grad_norm": 11.256575584411621,
      "learning_rate": 0.00020201220897726938,
      "loss": 2.3314,
      "step": 70
    },
    {
      "epoch": 0.03886324993927617,
      "grad_norm": 19.787755966186523,
      "learning_rate": 0.00020078198147448128,
      "loss": 3.2341,
      "step": 80
    },
    {
      "epoch": 0.04372115618168569,
      "grad_norm": 25.911598205566406,
      "learning_rate": 0.00019906806213773937,
      "loss": 3.3715,
      "step": 90
    },
    {
      "epoch": 0.048579062424095217,
      "grad_norm": 18.073326110839844,
      "learning_rate": 0.0001968788010097697,
      "loss": 3.3957,
      "step": 100
    },
    {
      "epoch": 0.048579062424095217,
      "eval_loss": 1.8113958835601807,
      "eval_runtime": 51.8565,
      "eval_samples_per_second": 16.719,
      "eval_steps_per_second": 4.185,
      "step": 100
    },
    {
      "epoch": 0.053436968666504735,
      "grad_norm": 13.869400978088379,
      "learning_rate": 0.00019422486395072398,
      "loss": 2.8832,
      "step": 110
    },
    {
      "epoch": 0.05829487490891426,
      "grad_norm": 14.071908950805664,
      "learning_rate": 0.0001911191806751811,
      "loss": 2.2136,
      "step": 120
    },
    {
      "epoch": 0.06315278115132378,
      "grad_norm": 18.943180084228516,
      "learning_rate": 0.00018757688175987723,
      "loss": 2.9134,
      "step": 130
    },
    {
      "epoch": 0.0680106873937333,
      "grad_norm": 22.638784408569336,
      "learning_rate": 0.00018361522492905716,
      "loss": 3.348,
      "step": 140
    },
    {
      "epoch": 0.07286859363614283,
      "grad_norm": 23.163434982299805,
      "learning_rate": 0.00017925351097657625,
      "loss": 3.1821,
      "step": 150
    },
    {
      "epoch": 0.07286859363614283,
      "eval_loss": 1.734904170036316,
      "eval_runtime": 51.755,
      "eval_samples_per_second": 16.752,
      "eval_steps_per_second": 4.193,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.68312126685184e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}