last-checkpoint/trainer_state.json

{
  "best_metric": 5.40103006362915,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 1.069767441860465,
  "eval_steps": 5,
  "global_step": 11,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 13325.74609375,
      "learning_rate": 2e-05,
      "loss": 21.6324,
      "step": 1
    },
    {
      "epoch": 0.09302325581395349,
      "eval_loss": 5.627406120300293,
      "eval_runtime": 1.2851,
      "eval_samples_per_second": 3.891,
      "eval_steps_per_second": 2.335,
      "step": 1
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 18721.21484375,
      "learning_rate": 4e-05,
      "loss": 21.6678,
      "step": 2
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 17467.193359375,
      "learning_rate": 6e-05,
      "loss": 22.3477,
      "step": 3
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 10115.0625,
      "learning_rate": 8e-05,
      "loss": 18.5666,
      "step": 4
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 10420.9462890625,
      "learning_rate": 0.0001,
      "loss": 20.1187,
      "step": 5
    },
    {
      "epoch": 0.46511627906976744,
      "eval_loss": 5.418543815612793,
      "eval_runtime": 0.1439,
      "eval_samples_per_second": 34.74,
      "eval_steps_per_second": 20.844,
      "step": 5
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 14169.80078125,
      "learning_rate": 0.00012,
      "loss": 20.5495,
      "step": 6
    },
    {
      "epoch": 0.6511627906976745,
      "grad_norm": 15486.2841796875,
      "learning_rate": 0.00014,
      "loss": 19.657,
      "step": 7
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 18293.513671875,
      "learning_rate": 0.00016,
      "loss": 21.1569,
      "step": 8
    },
    {
      "epoch": 0.8372093023255814,
      "grad_norm": 14902.0244140625,
      "learning_rate": 0.00018,
      "loss": 17.7378,
      "step": 9
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 21317.369140625,
      "learning_rate": 0.0002,
      "loss": 21.4221,
      "step": 10
    },
    {
      "epoch": 0.9302325581395349,
      "eval_loss": 5.40103006362915,
      "eval_runtime": 0.1405,
      "eval_samples_per_second": 35.577,
      "eval_steps_per_second": 21.346,
      "step": 10
    },
    {
      "epoch": 1.069767441860465,
      "grad_norm": 15934.6513671875,
      "learning_rate": 0.0,
      "loss": 19.8753,
      "step": 11
    }
  ],
  "logging_steps": 1,
  "max_steps": 11,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2088914386944.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}