last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 1.7857142857142856,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07142857142857142,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.07142857142857142,
      "eval_loss": NaN,
      "eval_runtime": 1.732,
      "eval_samples_per_second": 28.868,
      "eval_steps_per_second": 7.506,
      "step": 1
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": NaN,
      "learning_rate": 9.986128001799077e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": NaN,
      "learning_rate": 9.94459753267812e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": NaN,
      "learning_rate": 9.875664641789545e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": NaN,
      "learning_rate": 9.779754323328192e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.5,
      "grad_norm": NaN,
      "learning_rate": 9.657457896300791e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": NaN,
      "learning_rate": 9.509529358847655e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": NaN,
      "learning_rate": 9.336880739593416e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": NaN,
      "learning_rate": 9.140576474687264e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": NaN,
      "learning_rate": 8.921826845200139e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": NaN,
      "learning_rate": 8.681980515339464e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": NaN,
      "learning_rate": 8.422516217485826e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 1.0,
      "grad_norm": NaN,
      "learning_rate": 8.14503363531613e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.0714285714285714,
      "grad_norm": NaN,
      "learning_rate": 7.85124354122177e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": NaN,
      "learning_rate": 7.542957248827961e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.2142857142857142,
      "grad_norm": NaN,
      "learning_rate": 7.222075445642904e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": NaN,
      "learning_rate": 6.890576474687263e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 1.3571428571428572,
      "grad_norm": NaN,
      "learning_rate": 6.550504137351576e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": NaN,
      "learning_rate": 6.203955092681039e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 1.5,
      "grad_norm": NaN,
      "learning_rate": 5.8530659307753036e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 1.6428571428571428,
      "grad_norm": NaN,
      "learning_rate": 5.1469340692246995e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": NaN,
      "learning_rate": 4.7960449073189606e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 1.7857142857142856,
      "grad_norm": NaN,
      "learning_rate": 4.4494958626484276e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 1.7857142857142856,
      "eval_loss": NaN,
      "eval_runtime": 1.0462,
      "eval_samples_per_second": 47.79,
      "eval_steps_per_second": 12.425,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 42,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.127497768894464e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}