last-checkpoint/trainer_state.json

{
  "best_metric": 0.7341243028640747,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.005285179475886369,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001761726491962123,
      "eval_loss": 1.2554974555969238,
      "eval_runtime": 773.1604,
      "eval_samples_per_second": 3.093,
      "eval_steps_per_second": 1.547,
      "step": 1
    },
    {
      "epoch": 0.0005285179475886368,
      "grad_norm": 1.7705259323120117,
      "learning_rate": 6e-05,
      "loss": 4.7927,
      "step": 3
    },
    {
      "epoch": 0.0008808632459810614,
      "eval_loss": 1.1834067106246948,
      "eval_runtime": 780.6272,
      "eval_samples_per_second": 3.063,
      "eval_steps_per_second": 1.532,
      "step": 5
    },
    {
      "epoch": 0.0010570358951772737,
      "grad_norm": 2.296821117401123,
      "learning_rate": 9.96057350657239e-05,
      "loss": 5.1837,
      "step": 6
    },
    {
      "epoch": 0.0015855538427659106,
      "grad_norm": 1.795020341873169,
      "learning_rate": 9.381533400219318e-05,
      "loss": 4.4933,
      "step": 9
    },
    {
      "epoch": 0.0017617264919621229,
      "eval_loss": 0.9860424995422363,
      "eval_runtime": 780.0353,
      "eval_samples_per_second": 3.065,
      "eval_steps_per_second": 1.533,
      "step": 10
    },
    {
      "epoch": 0.0021140717903545474,
      "grad_norm": 1.7132139205932617,
      "learning_rate": 8.18711994874345e-05,
      "loss": 3.8929,
      "step": 12
    },
    {
      "epoch": 0.0026425897379431843,
      "grad_norm": 1.8616305589675903,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.6906,
      "step": 15
    },
    {
      "epoch": 0.0026425897379431843,
      "eval_loss": 0.8647217750549316,
      "eval_runtime": 777.3119,
      "eval_samples_per_second": 3.076,
      "eval_steps_per_second": 1.539,
      "step": 15
    },
    {
      "epoch": 0.0031711076855318212,
      "grad_norm": 1.8421508073806763,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 3.2375,
      "step": 18
    },
    {
      "epoch": 0.0035234529839242457,
      "eval_loss": 0.7788602709770203,
      "eval_runtime": 781.0425,
      "eval_samples_per_second": 3.061,
      "eval_steps_per_second": 1.531,
      "step": 20
    },
    {
      "epoch": 0.003699625633120458,
      "grad_norm": 1.5902005434036255,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 2.9492,
      "step": 21
    },
    {
      "epoch": 0.004228143580709095,
      "grad_norm": 1.705464243888855,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 3.3754,
      "step": 24
    },
    {
      "epoch": 0.004404316229905308,
      "eval_loss": 0.7406635880470276,
      "eval_runtime": 780.7439,
      "eval_samples_per_second": 3.062,
      "eval_steps_per_second": 1.532,
      "step": 25
    },
    {
      "epoch": 0.004756661528297732,
      "grad_norm": 1.763797402381897,
      "learning_rate": 3.511175705587433e-06,
      "loss": 3.1869,
      "step": 27
    },
    {
      "epoch": 0.005285179475886369,
      "grad_norm": 1.737493872642517,
      "learning_rate": 0.0,
      "loss": 3.0219,
      "step": 30
    },
    {
      "epoch": 0.005285179475886369,
      "eval_loss": 0.7341243028640747,
      "eval_runtime": 779.2463,
      "eval_samples_per_second": 3.068,
      "eval_steps_per_second": 1.535,
      "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": 3.43032427708416e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}