last-checkpoint/trainer_state.json

{
  "best_metric": 1.598532795906067,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.024524831391784182,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002452483139178418,
      "grad_norm": 1.1990253925323486,
      "learning_rate": 2e-05,
      "loss": 2.0032,
      "step": 1
    },
    {
      "epoch": 0.002452483139178418,
      "eval_loss": 1.8322724103927612,
      "eval_runtime": 37.6173,
      "eval_samples_per_second": 4.572,
      "eval_steps_per_second": 2.286,
      "step": 1
    },
    {
      "epoch": 0.004904966278356836,
      "grad_norm": 1.1349740028381348,
      "learning_rate": 4e-05,
      "loss": 2.0293,
      "step": 2
    },
    {
      "epoch": 0.007357449417535254,
      "grad_norm": 1.104918360710144,
      "learning_rate": 6e-05,
      "loss": 1.9023,
      "step": 3
    },
    {
      "epoch": 0.009809932556713672,
      "grad_norm": 0.9111782312393188,
      "learning_rate": 8e-05,
      "loss": 1.9264,
      "step": 4
    },
    {
      "epoch": 0.012262415695892091,
      "grad_norm": 1.0062782764434814,
      "learning_rate": 0.0001,
      "loss": 1.6187,
      "step": 5
    },
    {
      "epoch": 0.012262415695892091,
      "eval_loss": 1.8154027462005615,
      "eval_runtime": 36.0268,
      "eval_samples_per_second": 4.774,
      "eval_steps_per_second": 2.387,
      "step": 5
    },
    {
      "epoch": 0.014714898835070508,
      "grad_norm": 1.078047275543213,
      "learning_rate": 0.00012,
      "loss": 1.5573,
      "step": 6
    },
    {
      "epoch": 0.017167381974248927,
      "grad_norm": 1.1716063022613525,
      "learning_rate": 0.00014,
      "loss": 1.8802,
      "step": 7
    },
    {
      "epoch": 0.019619865113427344,
      "grad_norm": 1.2709145545959473,
      "learning_rate": 0.00016,
      "loss": 1.9394,
      "step": 8
    },
    {
      "epoch": 0.022072348252605765,
      "grad_norm": 1.5057402849197388,
      "learning_rate": 0.00018,
      "loss": 1.8044,
      "step": 9
    },
    {
      "epoch": 0.024524831391784182,
      "grad_norm": 1.3489257097244263,
      "learning_rate": 0.0002,
      "loss": 1.5431,
      "step": 10
    },
    {
      "epoch": 0.024524831391784182,
      "eval_loss": 1.598532795906067,
      "eval_runtime": 36.0453,
      "eval_samples_per_second": 4.772,
      "eval_steps_per_second": 2.386,
      "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": 3135311286632448.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}