last-checkpoint/trainer_state.json

{
  "best_metric": 0.6306657195091248,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.01942690626517727,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001942690626517727,
      "grad_norm": 0.6803475618362427,
      "learning_rate": 1e-05,
      "loss": 2.2766,
      "step": 1
    },
    {
      "epoch": 0.001942690626517727,
      "eval_loss": 0.6704726219177246,
      "eval_runtime": 42.8729,
      "eval_samples_per_second": 5.061,
      "eval_steps_per_second": 2.542,
      "step": 1
    },
    {
      "epoch": 0.003885381253035454,
      "grad_norm": 0.60342937707901,
      "learning_rate": 2e-05,
      "loss": 2.507,
      "step": 2
    },
    {
      "epoch": 0.005828071879553181,
      "grad_norm": 0.5822948217391968,
      "learning_rate": 3e-05,
      "loss": 1.8993,
      "step": 3
    },
    {
      "epoch": 0.007770762506070908,
      "grad_norm": 0.707507848739624,
      "learning_rate": 4e-05,
      "loss": 2.534,
      "step": 4
    },
    {
      "epoch": 0.009713453132588635,
      "grad_norm": 0.4827619791030884,
      "learning_rate": 5e-05,
      "loss": 2.3013,
      "step": 5
    },
    {
      "epoch": 0.009713453132588635,
      "eval_loss": 0.6683055758476257,
      "eval_runtime": 43.1261,
      "eval_samples_per_second": 5.032,
      "eval_steps_per_second": 2.527,
      "step": 5
    },
    {
      "epoch": 0.011656143759106362,
      "grad_norm": 0.7720835208892822,
      "learning_rate": 6e-05,
      "loss": 2.1516,
      "step": 6
    },
    {
      "epoch": 0.013598834385624089,
      "grad_norm": 0.6448253393173218,
      "learning_rate": 7e-05,
      "loss": 1.9544,
      "step": 7
    },
    {
      "epoch": 0.015541525012141816,
      "grad_norm": 0.7023385763168335,
      "learning_rate": 8e-05,
      "loss": 2.2042,
      "step": 8
    },
    {
      "epoch": 0.017484215638659543,
      "grad_norm": 1.196603775024414,
      "learning_rate": 9e-05,
      "loss": 2.7489,
      "step": 9
    },
    {
      "epoch": 0.01942690626517727,
      "grad_norm": 0.9811630845069885,
      "learning_rate": 0.0001,
      "loss": 2.2584,
      "step": 10
    },
    {
      "epoch": 0.01942690626517727,
      "eval_loss": 0.6306657195091248,
      "eval_runtime": 43.2127,
      "eval_samples_per_second": 5.022,
      "eval_steps_per_second": 2.522,
      "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": 3166224305356800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}