last-checkpoint/trainer_state.json

{
  "best_metric": 0.46889933943748474,
  "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": 7.770583629608154,
      "learning_rate": 2e-05,
      "loss": 2.6697,
      "step": 1
    },
    {
      "epoch": 0.002292263610315186,
      "eval_loss": 0.6890747547149658,
      "eval_runtime": 55.5182,
      "eval_samples_per_second": 3.314,
      "eval_steps_per_second": 1.657,
      "step": 1
    },
    {
      "epoch": 0.004584527220630372,
      "grad_norm": 9.156136512756348,
      "learning_rate": 4e-05,
      "loss": 2.8621,
      "step": 2
    },
    {
      "epoch": 0.006876790830945559,
      "grad_norm": 6.610903263092041,
      "learning_rate": 6e-05,
      "loss": 2.8403,
      "step": 3
    },
    {
      "epoch": 0.009169054441260744,
      "grad_norm": 8.174342155456543,
      "learning_rate": 8e-05,
      "loss": 2.5056,
      "step": 4
    },
    {
      "epoch": 0.011461318051575931,
      "grad_norm": 7.851437568664551,
      "learning_rate": 0.0001,
      "loss": 2.3453,
      "step": 5
    },
    {
      "epoch": 0.011461318051575931,
      "eval_loss": 0.602993905544281,
      "eval_runtime": 55.377,
      "eval_samples_per_second": 3.323,
      "eval_steps_per_second": 1.661,
      "step": 5
    },
    {
      "epoch": 0.013753581661891117,
      "grad_norm": 6.013002872467041,
      "learning_rate": 0.00012,
      "loss": 2.4657,
      "step": 6
    },
    {
      "epoch": 0.016045845272206302,
      "grad_norm": 6.81970739364624,
      "learning_rate": 0.00014,
      "loss": 2.1724,
      "step": 7
    },
    {
      "epoch": 0.01833810888252149,
      "grad_norm": 4.467923164367676,
      "learning_rate": 0.00016,
      "loss": 1.943,
      "step": 8
    },
    {
      "epoch": 0.020630372492836675,
      "grad_norm": 5.324087142944336,
      "learning_rate": 0.00018,
      "loss": 2.0512,
      "step": 9
    },
    {
      "epoch": 0.022922636103151862,
      "grad_norm": 5.302452564239502,
      "learning_rate": 0.0002,
      "loss": 2.1748,
      "step": 10
    },
    {
      "epoch": 0.022922636103151862,
      "eval_loss": 0.46889933943748474,
      "eval_runtime": 55.0819,
      "eval_samples_per_second": 3.34,
      "eval_steps_per_second": 1.67,
      "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
}