last-checkpoint/trainer_state.json

{
  "best_metric": 2.5439529418945312,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.03623844899438304,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003623844899438304,
      "eval_loss": 3.253896474838257,
      "eval_runtime": 74.5486,
      "eval_samples_per_second": 15.587,
      "eval_steps_per_second": 3.903,
      "step": 1
    },
    {
      "epoch": 0.003623844899438304,
      "grad_norm": 2.0134332180023193,
      "learning_rate": 4.12e-05,
      "loss": 2.878,
      "step": 10
    },
    {
      "epoch": 0.007247689798876608,
      "grad_norm": 1.886479377746582,
      "learning_rate": 8.24e-05,
      "loss": 2.5585,
      "step": 20
    },
    {
      "epoch": 0.010871534698314912,
      "grad_norm": 1.836480975151062,
      "learning_rate": 0.0001236,
      "loss": 2.4347,
      "step": 30
    },
    {
      "epoch": 0.014495379597753216,
      "grad_norm": 2.0984137058258057,
      "learning_rate": 0.0001648,
      "loss": 2.3679,
      "step": 40
    },
    {
      "epoch": 0.01811922449719152,
      "grad_norm": 4.840346813201904,
      "learning_rate": 0.000206,
      "loss": 2.3008,
      "step": 50
    },
    {
      "epoch": 0.01811922449719152,
      "eval_loss": 2.5439529418945312,
      "eval_runtime": 74.1639,
      "eval_samples_per_second": 15.668,
      "eval_steps_per_second": 3.924,
      "step": 50
    },
    {
      "epoch": 0.021743069396629823,
      "grad_norm": 1.3696887493133545,
      "learning_rate": 0.0002057490971767619,
      "loss": 2.384,
      "step": 60
    },
    {
      "epoch": 0.02536691429606813,
      "grad_norm": 1.702624797821045,
      "learning_rate": 0.00020499761108038175,
      "loss": 2.4112,
      "step": 70
    },
    {
      "epoch": 0.028990759195506432,
      "grad_norm": 1.841941237449646,
      "learning_rate": 0.00020374920287558198,
      "loss": 2.3759,
      "step": 80
    },
    {
      "epoch": 0.03261460409494474,
      "grad_norm": 2.737161874771118,
      "learning_rate": 0.00020200995468164684,
      "loss": 2.2692,
      "step": 90
    },
    {
      "epoch": 0.03623844899438304,
      "grad_norm": 4.560957431793213,
      "learning_rate": 0.00019978833994094855,
      "loss": 2.1869,
      "step": 100
    },
    {
      "epoch": 0.03623844899438304,
      "eval_loss": 2.719433307647705,
      "eval_runtime": 74.2575,
      "eval_samples_per_second": 15.648,
      "eval_steps_per_second": 3.919,
      "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": 1.932783022768128e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}