last-checkpoint/trainer_state.json

{
  "best_metric": 1.296627163887024,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.024524831391784182,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008174943797261394,
      "eval_loss": 1.6600309610366821,
      "eval_runtime": 20.0591,
      "eval_samples_per_second": 25.674,
      "eval_steps_per_second": 12.862,
      "step": 1
    },
    {
      "epoch": 0.002452483139178418,
      "grad_norm": 0.657343327999115,
      "learning_rate": 6e-05,
      "loss": 1.6849,
      "step": 3
    },
    {
      "epoch": 0.004087471898630697,
      "eval_loss": 1.6067190170288086,
      "eval_runtime": 19.7624,
      "eval_samples_per_second": 26.06,
      "eval_steps_per_second": 13.055,
      "step": 5
    },
    {
      "epoch": 0.004904966278356836,
      "grad_norm": 0.6308304667472839,
      "learning_rate": 9.96057350657239e-05,
      "loss": 1.6658,
      "step": 6
    },
    {
      "epoch": 0.007357449417535254,
      "grad_norm": 0.6857329607009888,
      "learning_rate": 9.381533400219318e-05,
      "loss": 1.534,
      "step": 9
    },
    {
      "epoch": 0.008174943797261395,
      "eval_loss": 1.456212043762207,
      "eval_runtime": 20.3175,
      "eval_samples_per_second": 25.348,
      "eval_steps_per_second": 12.698,
      "step": 10
    },
    {
      "epoch": 0.009809932556713672,
      "grad_norm": 0.7650735974311829,
      "learning_rate": 8.18711994874345e-05,
      "loss": 1.4606,
      "step": 12
    },
    {
      "epoch": 0.012262415695892091,
      "grad_norm": 0.7929948568344116,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.3442,
      "step": 15
    },
    {
      "epoch": 0.012262415695892091,
      "eval_loss": 1.3643509149551392,
      "eval_runtime": 20.8425,
      "eval_samples_per_second": 24.709,
      "eval_steps_per_second": 12.379,
      "step": 15
    },
    {
      "epoch": 0.014714898835070508,
      "grad_norm": 0.6958890557289124,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 1.3561,
      "step": 18
    },
    {
      "epoch": 0.01634988759452279,
      "eval_loss": 1.3194067478179932,
      "eval_runtime": 21.3468,
      "eval_samples_per_second": 24.125,
      "eval_steps_per_second": 12.086,
      "step": 20
    },
    {
      "epoch": 0.017167381974248927,
      "grad_norm": 0.6224148869514465,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 1.3279,
      "step": 21
    },
    {
      "epoch": 0.019619865113427344,
      "grad_norm": 0.605733335018158,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 1.2968,
      "step": 24
    },
    {
      "epoch": 0.020437359493153485,
      "eval_loss": 1.3003891706466675,
      "eval_runtime": 21.694,
      "eval_samples_per_second": 23.739,
      "eval_steps_per_second": 11.893,
      "step": 25
    },
    {
      "epoch": 0.022072348252605765,
      "grad_norm": 0.5556307435035706,
      "learning_rate": 3.511175705587433e-06,
      "loss": 1.3199,
      "step": 27
    },
    {
      "epoch": 0.024524831391784182,
      "grad_norm": 0.6132944822311401,
      "learning_rate": 0.0,
      "loss": 1.3598,
      "step": 30
    },
    {
      "epoch": 0.024524831391784182,
      "eval_loss": 1.296627163887024,
      "eval_runtime": 21.933,
      "eval_samples_per_second": 23.481,
      "eval_steps_per_second": 11.763,
      "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": 1560452643422208.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}