last-checkpoint/trainer_state.json

{
  "best_metric": 0.9053700566291809,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.3157894736842105,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010526315789473684,
      "eval_loss": 1.1585334539413452,
      "eval_runtime": 1.698,
      "eval_samples_per_second": 23.558,
      "eval_steps_per_second": 11.779,
      "step": 1
    },
    {
      "epoch": 0.031578947368421054,
      "grad_norm": 0.8730560541152954,
      "learning_rate": 6e-05,
      "loss": 4.8303,
      "step": 3
    },
    {
      "epoch": 0.05263157894736842,
      "eval_loss": 1.1531161069869995,
      "eval_runtime": 1.685,
      "eval_samples_per_second": 23.739,
      "eval_steps_per_second": 11.87,
      "step": 5
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 1.0616966485977173,
      "learning_rate": 0.00012,
      "loss": 4.5507,
      "step": 6
    },
    {
      "epoch": 0.09473684210526316,
      "grad_norm": 1.1517345905303955,
      "learning_rate": 0.00018,
      "loss": 4.4919,
      "step": 9
    },
    {
      "epoch": 0.10526315789473684,
      "eval_loss": 1.0547163486480713,
      "eval_runtime": 1.6859,
      "eval_samples_per_second": 23.726,
      "eval_steps_per_second": 11.863,
      "step": 10
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 1.323952555656433,
      "learning_rate": 0.00019510565162951537,
      "loss": 4.3055,
      "step": 12
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 1.4276947975158691,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.7414,
      "step": 15
    },
    {
      "epoch": 0.15789473684210525,
      "eval_loss": 0.9728013277053833,
      "eval_runtime": 1.7105,
      "eval_samples_per_second": 23.386,
      "eval_steps_per_second": 11.693,
      "step": 15
    },
    {
      "epoch": 0.18947368421052632,
      "grad_norm": 1.4990589618682861,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.9735,
      "step": 18
    },
    {
      "epoch": 0.21052631578947367,
      "eval_loss": 0.9311612844467163,
      "eval_runtime": 1.6769,
      "eval_samples_per_second": 23.853,
      "eval_steps_per_second": 11.926,
      "step": 20
    },
    {
      "epoch": 0.22105263157894736,
      "grad_norm": 1.3441416025161743,
      "learning_rate": 8.435655349597689e-05,
      "loss": 3.6624,
      "step": 21
    },
    {
      "epoch": 0.25263157894736843,
      "grad_norm": 1.47910737991333,
      "learning_rate": 4.12214747707527e-05,
      "loss": 3.7006,
      "step": 24
    },
    {
      "epoch": 0.2631578947368421,
      "eval_loss": 0.9099543690681458,
      "eval_runtime": 1.6772,
      "eval_samples_per_second": 23.849,
      "eval_steps_per_second": 11.924,
      "step": 25
    },
    {
      "epoch": 0.28421052631578947,
      "grad_norm": 1.3131358623504639,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 3.6337,
      "step": 27
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 1.1569862365722656,
      "learning_rate": 0.0,
      "loss": 3.5561,
      "step": 30
    },
    {
      "epoch": 0.3157894736842105,
      "eval_loss": 0.9053700566291809,
      "eval_runtime": 1.6825,
      "eval_samples_per_second": 23.774,
      "eval_steps_per_second": 11.887,
      "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": 1802813193584640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}