last-checkpoint/trainer_state.json

{
  "best_metric": 1.2234210968017578,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0005095909258842464,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6986364196141547e-05,
      "eval_loss": 1.3468016386032104,
      "eval_runtime": 3825.0823,
      "eval_samples_per_second": 6.48,
      "eval_steps_per_second": 3.24,
      "step": 1
    },
    {
      "epoch": 5.095909258842464e-05,
      "grad_norm": 15.381132125854492,
      "learning_rate": 3e-05,
      "loss": 5.8377,
      "step": 3
    },
    {
      "epoch": 8.493182098070774e-05,
      "eval_loss": 1.34633207321167,
      "eval_runtime": 3844.7283,
      "eval_samples_per_second": 6.447,
      "eval_steps_per_second": 3.224,
      "step": 5
    },
    {
      "epoch": 0.00010191818517684929,
      "grad_norm": 13.268209457397461,
      "learning_rate": 6e-05,
      "loss": 5.5592,
      "step": 6
    },
    {
      "epoch": 0.00015287727776527394,
      "grad_norm": 38.36406707763672,
      "learning_rate": 9e-05,
      "loss": 5.5275,
      "step": 9
    },
    {
      "epoch": 0.00016986364196141547,
      "eval_loss": 1.335775375366211,
      "eval_runtime": 3844.3305,
      "eval_samples_per_second": 6.448,
      "eval_steps_per_second": 3.224,
      "step": 10
    },
    {
      "epoch": 0.00020383637035369857,
      "grad_norm": 48.66492462158203,
      "learning_rate": 9.755282581475769e-05,
      "loss": 5.9054,
      "step": 12
    },
    {
      "epoch": 0.0002547954629421232,
      "grad_norm": 5.9232587814331055,
      "learning_rate": 8.535533905932738e-05,
      "loss": 5.7512,
      "step": 15
    },
    {
      "epoch": 0.0002547954629421232,
      "eval_loss": 1.3063114881515503,
      "eval_runtime": 3840.6394,
      "eval_samples_per_second": 6.454,
      "eval_steps_per_second": 3.227,
      "step": 15
    },
    {
      "epoch": 0.0003057545555305479,
      "grad_norm": 2.6109163761138916,
      "learning_rate": 6.545084971874738e-05,
      "loss": 5.721,
      "step": 18
    },
    {
      "epoch": 0.00033972728392283095,
      "eval_loss": 1.2575994729995728,
      "eval_runtime": 3839.1217,
      "eval_samples_per_second": 6.457,
      "eval_steps_per_second": 3.228,
      "step": 20
    },
    {
      "epoch": 0.0003567136481189725,
      "grad_norm": 2.105696439743042,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 4.4662,
      "step": 21
    },
    {
      "epoch": 0.00040767274070739715,
      "grad_norm": 5.003188610076904,
      "learning_rate": 2.061073738537635e-05,
      "loss": 5.2284,
      "step": 24
    },
    {
      "epoch": 0.0004246591049035387,
      "eval_loss": 1.2291550636291504,
      "eval_runtime": 3835.1312,
      "eval_samples_per_second": 6.463,
      "eval_steps_per_second": 3.232,
      "step": 25
    },
    {
      "epoch": 0.00045863183329582176,
      "grad_norm": 2.9324259757995605,
      "learning_rate": 5.449673790581611e-06,
      "loss": 5.1058,
      "step": 27
    },
    {
      "epoch": 0.0005095909258842464,
      "grad_norm": 2.1682016849517822,
      "learning_rate": 0.0,
      "loss": 4.3811,
      "step": 30
    },
    {
      "epoch": 0.0005095909258842464,
      "eval_loss": 1.2234210968017578,
      "eval_runtime": 3832.4715,
      "eval_samples_per_second": 6.468,
      "eval_steps_per_second": 3.234,
      "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": 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": 1.0128701987487744e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}