last-checkpoint/trainer_state.json

{
  "best_metric": 1.4784965515136719,
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
  "epoch": 0.05517748758506529,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003678499172337686,
      "eval_loss": 2.6280200481414795,
      "eval_runtime": 65.3457,
      "eval_samples_per_second": 17.522,
      "eval_steps_per_second": 4.392,
      "step": 1
    },
    {
      "epoch": 0.0036784991723376862,
      "grad_norm": 1.1987358331680298,
      "learning_rate": 4.02e-05,
      "loss": 2.5141,
      "step": 10
    },
    {
      "epoch": 0.0073569983446753725,
      "grad_norm": 1.3015245199203491,
      "learning_rate": 8.04e-05,
      "loss": 1.9684,
      "step": 20
    },
    {
      "epoch": 0.011035497517013059,
      "grad_norm": 1.007439136505127,
      "learning_rate": 0.0001206,
      "loss": 1.6286,
      "step": 30
    },
    {
      "epoch": 0.014713996689350745,
      "grad_norm": 1.1959398984909058,
      "learning_rate": 0.0001608,
      "loss": 1.5259,
      "step": 40
    },
    {
      "epoch": 0.01839249586168843,
      "grad_norm": 1.1850124597549438,
      "learning_rate": 0.000201,
      "loss": 1.373,
      "step": 50
    },
    {
      "epoch": 0.01839249586168843,
      "eval_loss": 1.5826470851898193,
      "eval_runtime": 65.3579,
      "eval_samples_per_second": 17.519,
      "eval_steps_per_second": 4.391,
      "step": 50
    },
    {
      "epoch": 0.022070995034026118,
      "grad_norm": 0.9022707939147949,
      "learning_rate": 0.00020075518705111234,
      "loss": 1.6254,
      "step": 60
    },
    {
      "epoch": 0.025749494206363802,
      "grad_norm": 0.8804805874824524,
      "learning_rate": 0.00020002194090852784,
      "loss": 1.5379,
      "step": 70
    },
    {
      "epoch": 0.02942799337870149,
      "grad_norm": 0.9261283874511719,
      "learning_rate": 0.00019880383387374748,
      "loss": 1.4729,
      "step": 80
    },
    {
      "epoch": 0.033106492551039174,
      "grad_norm": 0.9060719013214111,
      "learning_rate": 0.00019710680044180106,
      "loss": 1.4268,
      "step": 90
    },
    {
      "epoch": 0.03678499172337686,
      "grad_norm": 1.1774567365646362,
      "learning_rate": 0.0001949391083889838,
      "loss": 1.383,
      "step": 100
    },
    {
      "epoch": 0.03678499172337686,
      "eval_loss": 1.49298894405365,
      "eval_runtime": 65.3303,
      "eval_samples_per_second": 17.526,
      "eval_steps_per_second": 4.393,
      "step": 100
    },
    {
      "epoch": 0.04046349089571455,
      "grad_norm": 0.8449574708938599,
      "learning_rate": 0.00019231131849308138,
      "loss": 1.5649,
      "step": 110
    },
    {
      "epoch": 0.044141990068052236,
      "grad_norm": 0.9605708718299866,
      "learning_rate": 0.00018923623308232218,
      "loss": 1.4462,
      "step": 120
    },
    {
      "epoch": 0.047820489240389924,
      "grad_norm": 0.93846595287323,
      "learning_rate": 0.00018572883366372081,
      "loss": 1.4542,
      "step": 130
    },
    {
      "epoch": 0.051498988412727605,
      "grad_norm": 0.9066504240036011,
      "learning_rate": 0.00018180620793468224,
      "loss": 1.3955,
      "step": 140
    },
    {
      "epoch": 0.05517748758506529,
      "grad_norm": 1.112593412399292,
      "learning_rate": 0.00017748746653345728,
      "loss": 1.3078,
      "step": 150
    },
    {
      "epoch": 0.05517748758506529,
      "eval_loss": 1.4784965515136719,
      "eval_runtime": 65.2041,
      "eval_samples_per_second": 17.56,
      "eval_steps_per_second": 4.402,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "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": 2.6660412850176e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}