last-checkpoint/trainer_state.json

{
  "best_metric": 2.0195255279541016,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.021409455842997322,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007136485280999108,
      "eval_loss": 2.0849006175994873,
      "eval_runtime": 166.9589,
      "eval_samples_per_second": 3.534,
      "eval_steps_per_second": 1.767,
      "step": 1
    },
    {
      "epoch": 0.0021409455842997323,
      "grad_norm": 0.6842705607414246,
      "learning_rate": 6e-05,
      "loss": 8.1855,
      "step": 3
    },
    {
      "epoch": 0.003568242640499554,
      "eval_loss": 2.080864429473877,
      "eval_runtime": 168.3342,
      "eval_samples_per_second": 3.505,
      "eval_steps_per_second": 1.752,
      "step": 5
    },
    {
      "epoch": 0.004281891168599465,
      "grad_norm": 5.52883243560791,
      "learning_rate": 0.00012,
      "loss": 8.1743,
      "step": 6
    },
    {
      "epoch": 0.006422836752899197,
      "grad_norm": 32.8885498046875,
      "learning_rate": 0.00018,
      "loss": 8.4995,
      "step": 9
    },
    {
      "epoch": 0.007136485280999108,
      "eval_loss": 2.0631089210510254,
      "eval_runtime": 168.2486,
      "eval_samples_per_second": 3.507,
      "eval_steps_per_second": 1.753,
      "step": 10
    },
    {
      "epoch": 0.00856378233719893,
      "grad_norm": 26.971921920776367,
      "learning_rate": 0.00019510565162951537,
      "loss": 8.2353,
      "step": 12
    },
    {
      "epoch": 0.010704727921498661,
      "grad_norm": 15.235742568969727,
      "learning_rate": 0.00017071067811865476,
      "loss": 8.2829,
      "step": 15
    },
    {
      "epoch": 0.010704727921498661,
      "eval_loss": 2.049189329147339,
      "eval_runtime": 168.2105,
      "eval_samples_per_second": 3.508,
      "eval_steps_per_second": 1.754,
      "step": 15
    },
    {
      "epoch": 0.012845673505798395,
      "grad_norm": 3.738413095474243,
      "learning_rate": 0.00013090169943749476,
      "loss": 8.0633,
      "step": 18
    },
    {
      "epoch": 0.014272970561998216,
      "eval_loss": 2.0383806228637695,
      "eval_runtime": 168.3892,
      "eval_samples_per_second": 3.504,
      "eval_steps_per_second": 1.752,
      "step": 20
    },
    {
      "epoch": 0.014986619090098127,
      "grad_norm": 1.3492414951324463,
      "learning_rate": 8.435655349597689e-05,
      "loss": 8.193,
      "step": 21
    },
    {
      "epoch": 0.01712756467439786,
      "grad_norm": 0.8906028270721436,
      "learning_rate": 4.12214747707527e-05,
      "loss": 8.0867,
      "step": 24
    },
    {
      "epoch": 0.01784121320249777,
      "eval_loss": 2.0230188369750977,
      "eval_runtime": 168.4697,
      "eval_samples_per_second": 3.502,
      "eval_steps_per_second": 1.751,
      "step": 25
    },
    {
      "epoch": 0.01926851025869759,
      "grad_norm": 0.8579123020172119,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 7.9533,
      "step": 27
    },
    {
      "epoch": 0.021409455842997322,
      "grad_norm": 0.9165276288986206,
      "learning_rate": 0.0,
      "loss": 8.1795,
      "step": 30
    },
    {
      "epoch": 0.021409455842997322,
      "eval_loss": 2.0195255279541016,
      "eval_runtime": 168.4856,
      "eval_samples_per_second": 3.502,
      "eval_steps_per_second": 1.751,
      "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": 1.6826714592116736e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}