last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.4333694474539545,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01733477789815818,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.01733477789815818,
      "eval_loss": NaN,
      "eval_runtime": 0.7507,
      "eval_samples_per_second": 66.605,
      "eval_steps_per_second": 17.317,
      "step": 1
    },
    {
      "epoch": 0.03466955579631636,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.05200433369447454,
      "grad_norm": NaN,
      "learning_rate": 9.958086757163489e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.06933911159263272,
      "grad_norm": NaN,
      "learning_rate": 9.833127793065098e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0866738894907909,
      "grad_norm": NaN,
      "learning_rate": 9.627450856774539e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.10400866738894908,
      "grad_norm": NaN,
      "learning_rate": 9.3448873204592e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.12134344528710726,
      "grad_norm": NaN,
      "learning_rate": 8.990700808169889e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.13867822318526543,
      "grad_norm": NaN,
      "learning_rate": 8.571489144483944e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.1560130010834236,
      "grad_norm": NaN,
      "learning_rate": 8.095061449516903e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.1733477789815818,
      "grad_norm": NaN,
      "learning_rate": 7.570292669790186e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.19068255687973998,
      "grad_norm": NaN,
      "learning_rate": 7.006958254769438e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.20801733477789816,
      "grad_norm": NaN,
      "learning_rate": 6.415552058736854e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.22535211267605634,
      "grad_norm": NaN,
      "learning_rate": 5.80709086014102e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.24268689057421453,
      "grad_norm": NaN,
      "learning_rate": 5.192909139858981e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.2600216684723727,
      "grad_norm": NaN,
      "learning_rate": 4.584447941263149e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.27735644637053086,
      "grad_norm": NaN,
      "learning_rate": 3.9930417452305626e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.29469122426868904,
      "grad_norm": NaN,
      "learning_rate": 3.4297073302098156e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.3120260021668472,
      "grad_norm": NaN,
      "learning_rate": 2.9049385504830985e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.3293607800650054,
      "grad_norm": NaN,
      "learning_rate": 2.4285108555160577e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.3466955579631636,
      "grad_norm": NaN,
      "learning_rate": 2.0092991918301108e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.3640303358613218,
      "grad_norm": NaN,
      "learning_rate": 1.6551126795408016e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.38136511375947996,
      "grad_norm": NaN,
      "learning_rate": 1.3725491432254624e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.39869989165763814,
      "grad_norm": NaN,
      "learning_rate": 1.1668722069349041e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.4160346695557963,
      "grad_norm": NaN,
      "learning_rate": 1.0419132428365116e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.4333694474539545,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.4333694474539545,
      "eval_loss": NaN,
      "eval_runtime": 0.764,
      "eval_samples_per_second": 65.445,
      "eval_steps_per_second": 17.016,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "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": 1.47650456322048e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}