last-checkpoint/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.05288207297726071,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021152829190904283,
      "grad_norm": NaN,
      "learning_rate": 5e-06,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.0021152829190904283,
      "eval_loss": NaN,
      "eval_runtime": 53.5823,
      "eval_samples_per_second": 14.874,
      "eval_steps_per_second": 1.866,
      "step": 1
    },
    {
      "epoch": 0.004230565838180857,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.006345848757271285,
      "grad_norm": NaN,
      "learning_rate": 1.5e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.008461131676361713,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.010576414595452142,
      "grad_norm": NaN,
      "learning_rate": 2.5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.01269169751454257,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.014806980433632998,
      "grad_norm": NaN,
      "learning_rate": 3.5e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.016922263352723427,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.019037546271813855,
      "grad_norm": NaN,
      "learning_rate": 4.5e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.021152829190904283,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.023268112109994712,
      "grad_norm": NaN,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 0.02538339502908514,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.02749867794817557,
      "grad_norm": NaN,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 0.029613960867265997,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 0.03172924378635643,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.033844526705446853,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 0.035959809624537285,
      "grad_norm": NaN,
      "learning_rate": 8.5e-05,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 0.03807509254362771,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.04019037546271814,
      "grad_norm": NaN,
      "learning_rate": 9.5e-05,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 0.04230565838180857,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.044420941300899,
      "grad_norm": NaN,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.046536224219989424,
      "grad_norm": NaN,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0,
      "step": 22
    },
    {
      "epoch": 0.048651507139079855,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 23
    },
    {
      "epoch": 0.05076679005817028,
      "grad_norm": NaN,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.05288207297726071,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.05288207297726071,
      "eval_loss": NaN,
      "eval_runtime": 53.7342,
      "eval_samples_per_second": 14.832,
      "eval_steps_per_second": 1.861,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.5547217133568e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}