last-checkpoint/trainer_state.json

{
  "best_metric": 1.9420759677886963,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.00048107568523217913,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.4053784261608958e-05,
      "eval_loss": 3.604696750640869,
      "eval_runtime": 2236.3371,
      "eval_samples_per_second": 15.655,
      "eval_steps_per_second": 3.914,
      "step": 1
    },
    {
      "epoch": 7.216135278482687e-05,
      "grad_norm": 20.582523345947266,
      "learning_rate": 0.00012,
      "loss": 10.3258,
      "step": 3
    },
    {
      "epoch": 0.00012026892130804478,
      "eval_loss": 3.3812472820281982,
      "eval_runtime": 2233.335,
      "eval_samples_per_second": 15.676,
      "eval_steps_per_second": 3.919,
      "step": 5
    },
    {
      "epoch": 0.00014432270556965373,
      "grad_norm": 11.679255485534668,
      "learning_rate": 0.0001992114701314478,
      "loss": 10.0176,
      "step": 6
    },
    {
      "epoch": 0.0002164840583544806,
      "grad_norm": 5.760318279266357,
      "learning_rate": 0.00018763066800438636,
      "loss": 9.4744,
      "step": 9
    },
    {
      "epoch": 0.00024053784261608956,
      "eval_loss": 2.6607580184936523,
      "eval_runtime": 2233.0521,
      "eval_samples_per_second": 15.678,
      "eval_steps_per_second": 3.92,
      "step": 10
    },
    {
      "epoch": 0.00028864541113930747,
      "grad_norm": 6.304234504699707,
      "learning_rate": 0.000163742398974869,
      "loss": 8.3158,
      "step": 12
    },
    {
      "epoch": 0.0003608067639241344,
      "grad_norm": 10.350303649902344,
      "learning_rate": 0.00013090169943749476,
      "loss": 7.6677,
      "step": 15
    },
    {
      "epoch": 0.0003608067639241344,
      "eval_loss": 2.1993517875671387,
      "eval_runtime": 2232.9143,
      "eval_samples_per_second": 15.679,
      "eval_steps_per_second": 3.92,
      "step": 15
    },
    {
      "epoch": 0.0004329681167089612,
      "grad_norm": 6.310632228851318,
      "learning_rate": 9.372094804706867e-05,
      "loss": 7.355,
      "step": 18
    },
    {
      "epoch": 0.00048107568523217913,
      "eval_loss": 1.9420759677886963,
      "eval_runtime": 2232.9801,
      "eval_samples_per_second": 15.679,
      "eval_steps_per_second": 3.92,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.306929288708096e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}