last-checkpoint/trainer_state.json

{
  "best_metric": 0.4689041078090668,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.022922636103151862,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002292263610315186,
      "grad_norm": 7.594876289367676,
      "learning_rate": 2e-05,
      "loss": 2.6697,
      "step": 1
    },
    {
      "epoch": 0.002292263610315186,
      "eval_loss": 0.6890747547149658,
      "eval_runtime": 56.7744,
      "eval_samples_per_second": 3.241,
      "eval_steps_per_second": 1.62,
      "step": 1
    },
    {
      "epoch": 0.004584527220630372,
      "grad_norm": 8.860320091247559,
      "learning_rate": 4e-05,
      "loss": 2.8621,
      "step": 2
    },
    {
      "epoch": 0.006876790830945559,
      "grad_norm": 6.397947311401367,
      "learning_rate": 6e-05,
      "loss": 2.836,
      "step": 3
    },
    {
      "epoch": 0.009169054441260744,
      "grad_norm": 8.215444564819336,
      "learning_rate": 8e-05,
      "loss": 2.5098,
      "step": 4
    },
    {
      "epoch": 0.011461318051575931,
      "grad_norm": 8.26395034790039,
      "learning_rate": 0.0001,
      "loss": 2.3572,
      "step": 5
    },
    {
      "epoch": 0.011461318051575931,
      "eval_loss": 0.6056112051010132,
      "eval_runtime": 55.9895,
      "eval_samples_per_second": 3.286,
      "eval_steps_per_second": 1.643,
      "step": 5
    },
    {
      "epoch": 0.013753581661891117,
      "grad_norm": 5.971251487731934,
      "learning_rate": 0.00012,
      "loss": 2.4809,
      "step": 6
    },
    {
      "epoch": 0.016045845272206302,
      "grad_norm": 6.999272346496582,
      "learning_rate": 0.00014,
      "loss": 2.1776,
      "step": 7
    },
    {
      "epoch": 0.01833810888252149,
      "grad_norm": 4.562480449676514,
      "learning_rate": 0.00016,
      "loss": 1.9463,
      "step": 8
    },
    {
      "epoch": 0.020630372492836675,
      "grad_norm": 5.3542304039001465,
      "learning_rate": 0.00018,
      "loss": 2.0711,
      "step": 9
    },
    {
      "epoch": 0.022922636103151862,
      "grad_norm": 5.165809631347656,
      "learning_rate": 0.0002,
      "loss": 2.187,
      "step": 10
    },
    {
      "epoch": 0.022922636103151862,
      "eval_loss": 0.4689041078090668,
      "eval_runtime": 55.7448,
      "eval_samples_per_second": 3.301,
      "eval_steps_per_second": 1.65,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3505343598428160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}