last-checkpoint/trainer_state.json

{
  "best_metric": 1.4174914360046387,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.05762028233938346,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005762028233938346,
      "eval_loss": 2.759286642074585,
      "eval_runtime": 44.2859,
      "eval_samples_per_second": 16.506,
      "eval_steps_per_second": 4.132,
      "step": 1
    },
    {
      "epoch": 0.005762028233938346,
      "grad_norm": 0.6934571266174316,
      "learning_rate": 4.3e-05,
      "loss": 2.2019,
      "step": 10
    },
    {
      "epoch": 0.011524056467876692,
      "grad_norm": 1.1018927097320557,
      "learning_rate": 8.6e-05,
      "loss": 2.072,
      "step": 20
    },
    {
      "epoch": 0.01728608470181504,
      "grad_norm": 1.6100819110870361,
      "learning_rate": 0.000129,
      "loss": 1.4799,
      "step": 30
    },
    {
      "epoch": 0.023048112935753384,
      "grad_norm": 1.5464179515838623,
      "learning_rate": 0.000172,
      "loss": 1.2626,
      "step": 40
    },
    {
      "epoch": 0.02881014116969173,
      "grad_norm": 1.7817376852035522,
      "learning_rate": 0.000215,
      "loss": 1.0018,
      "step": 50
    },
    {
      "epoch": 0.02881014116969173,
      "eval_loss": 1.4174914360046387,
      "eval_runtime": 44.7179,
      "eval_samples_per_second": 16.347,
      "eval_steps_per_second": 4.092,
      "step": 50
    },
    {
      "epoch": 0.03457216940363008,
      "grad_norm": 0.6755384802818298,
      "learning_rate": 0.0002147381354029311,
      "loss": 1.8599,
      "step": 60
    },
    {
      "epoch": 0.040334197637568424,
      "grad_norm": 0.9027474522590637,
      "learning_rate": 0.0002139538173897188,
      "loss": 1.5252,
      "step": 70
    },
    {
      "epoch": 0.04609622587150677,
      "grad_norm": 1.0059105157852173,
      "learning_rate": 0.0002126508670788841,
      "loss": 1.2772,
      "step": 80
    },
    {
      "epoch": 0.05185825410544512,
      "grad_norm": 0.9736582636833191,
      "learning_rate": 0.00021083563231336926,
      "loss": 1.0586,
      "step": 90
    },
    {
      "epoch": 0.05762028233938346,
      "grad_norm": 1.0923612117767334,
      "learning_rate": 0.00020851695673448515,
      "loss": 0.7892,
      "step": 100
    },
    {
      "epoch": 0.05762028233938346,
      "eval_loss": 1.486754298210144,
      "eval_runtime": 44.9804,
      "eval_samples_per_second": 16.252,
      "eval_steps_per_second": 4.068,
      "step": 100
    }
  ],
  "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": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.808762618983219e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}