last-checkpoint/trainer_state.json

{
  "best_metric": 2.3391101360321045,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.01485148514851485,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004950495049504951,
      "eval_loss": 3.2170538902282715,
      "eval_runtime": 21.1086,
      "eval_samples_per_second": 40.315,
      "eval_steps_per_second": 20.181,
      "step": 1
    },
    {
      "epoch": 0.0014851485148514852,
      "grad_norm": 6.267305374145508,
      "learning_rate": 6e-05,
      "loss": 2.9922,
      "step": 3
    },
    {
      "epoch": 0.0024752475247524753,
      "eval_loss": 3.0375988483428955,
      "eval_runtime": 20.3267,
      "eval_samples_per_second": 41.866,
      "eval_steps_per_second": 20.958,
      "step": 5
    },
    {
      "epoch": 0.0029702970297029703,
      "grad_norm": 2.7017316818237305,
      "learning_rate": 0.00012,
      "loss": 2.9299,
      "step": 6
    },
    {
      "epoch": 0.004455445544554455,
      "grad_norm": 1.412431240081787,
      "learning_rate": 0.00018,
      "loss": 2.8589,
      "step": 9
    },
    {
      "epoch": 0.0049504950495049506,
      "eval_loss": 2.746622085571289,
      "eval_runtime": 20.4369,
      "eval_samples_per_second": 41.64,
      "eval_steps_per_second": 20.845,
      "step": 10
    },
    {
      "epoch": 0.005940594059405941,
      "grad_norm": 1.5799742937088013,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.7037,
      "step": 12
    },
    {
      "epoch": 0.007425742574257425,
      "grad_norm": 1.2611353397369385,
      "learning_rate": 0.00017071067811865476,
      "loss": 2.6437,
      "step": 15
    },
    {
      "epoch": 0.007425742574257425,
      "eval_loss": 2.5305943489074707,
      "eval_runtime": 20.4987,
      "eval_samples_per_second": 41.515,
      "eval_steps_per_second": 20.782,
      "step": 15
    },
    {
      "epoch": 0.00891089108910891,
      "grad_norm": 1.7273961305618286,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.5966,
      "step": 18
    },
    {
      "epoch": 0.009900990099009901,
      "eval_loss": 2.3949928283691406,
      "eval_runtime": 20.425,
      "eval_samples_per_second": 41.665,
      "eval_steps_per_second": 20.857,
      "step": 20
    },
    {
      "epoch": 0.010396039603960397,
      "grad_norm": 0.8455501794815063,
      "learning_rate": 8.435655349597689e-05,
      "loss": 2.4478,
      "step": 21
    },
    {
      "epoch": 0.011881188118811881,
      "grad_norm": 0.7899941205978394,
      "learning_rate": 4.12214747707527e-05,
      "loss": 2.4047,
      "step": 24
    },
    {
      "epoch": 0.012376237623762377,
      "eval_loss": 2.348778486251831,
      "eval_runtime": 20.4392,
      "eval_samples_per_second": 41.636,
      "eval_steps_per_second": 20.842,
      "step": 25
    },
    {
      "epoch": 0.013366336633663366,
      "grad_norm": 0.7957627773284912,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 2.3724,
      "step": 27
    },
    {
      "epoch": 0.01485148514851485,
      "grad_norm": 0.6960504651069641,
      "learning_rate": 0.0,
      "loss": 2.3079,
      "step": 30
    },
    {
      "epoch": 0.01485148514851485,
      "eval_loss": 2.3391101360321045,
      "eval_runtime": 20.4205,
      "eval_samples_per_second": 41.674,
      "eval_steps_per_second": 20.861,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1608388706304000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}