last-checkpoint/trainer_state.json

{
  "best_metric": 1.3994572162628174,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.005567928730512249,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001855976243504083,
      "eval_loss": 1.4602749347686768,
      "eval_runtime": 717.4461,
      "eval_samples_per_second": 3.163,
      "eval_steps_per_second": 1.582,
      "step": 1
    },
    {
      "epoch": 0.0005567928730512249,
      "grad_norm": 0.14608144760131836,
      "learning_rate": 6e-05,
      "loss": 1.0202,
      "step": 3
    },
    {
      "epoch": 0.0009279881217520415,
      "eval_loss": 1.45856511592865,
      "eval_runtime": 719.7655,
      "eval_samples_per_second": 3.152,
      "eval_steps_per_second": 1.577,
      "step": 5
    },
    {
      "epoch": 0.0011135857461024498,
      "grad_norm": 0.1549440622329712,
      "learning_rate": 9.96057350657239e-05,
      "loss": 1.2388,
      "step": 6
    },
    {
      "epoch": 0.0016703786191536749,
      "grad_norm": 0.20745107531547546,
      "learning_rate": 9.381533400219318e-05,
      "loss": 1.4404,
      "step": 9
    },
    {
      "epoch": 0.001855976243504083,
      "eval_loss": 1.4470257759094238,
      "eval_runtime": 720.0798,
      "eval_samples_per_second": 3.151,
      "eval_steps_per_second": 1.576,
      "step": 10
    },
    {
      "epoch": 0.0022271714922048997,
      "grad_norm": 0.26866665482521057,
      "learning_rate": 8.18711994874345e-05,
      "loss": 1.1653,
      "step": 12
    },
    {
      "epoch": 0.0027839643652561247,
      "grad_norm": 0.33343741297721863,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.2522,
      "step": 15
    },
    {
      "epoch": 0.0027839643652561247,
      "eval_loss": 1.4270999431610107,
      "eval_runtime": 719.6493,
      "eval_samples_per_second": 3.153,
      "eval_steps_per_second": 1.577,
      "step": 15
    },
    {
      "epoch": 0.0033407572383073497,
      "grad_norm": 0.2684028148651123,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 1.3132,
      "step": 18
    },
    {
      "epoch": 0.003711952487008166,
      "eval_loss": 1.4096044301986694,
      "eval_runtime": 719.784,
      "eval_samples_per_second": 3.152,
      "eval_steps_per_second": 1.577,
      "step": 20
    },
    {
      "epoch": 0.0038975501113585748,
      "grad_norm": 0.39812251925468445,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 1.0605,
      "step": 21
    },
    {
      "epoch": 0.004454342984409799,
      "grad_norm": 0.2763131260871887,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 1.1889,
      "step": 24
    },
    {
      "epoch": 0.0046399406087602076,
      "eval_loss": 1.400766134262085,
      "eval_runtime": 719.9183,
      "eval_samples_per_second": 3.152,
      "eval_steps_per_second": 1.577,
      "step": 25
    },
    {
      "epoch": 0.005011135857461025,
      "grad_norm": 0.21701176464557648,
      "learning_rate": 3.511175705587433e-06,
      "loss": 1.2503,
      "step": 27
    },
    {
      "epoch": 0.005567928730512249,
      "grad_norm": 0.22581584751605988,
      "learning_rate": 0.0,
      "loss": 0.9867,
      "step": 30
    },
    {
      "epoch": 0.005567928730512249,
      "eval_loss": 1.3994572162628174,
      "eval_runtime": 719.7204,
      "eval_samples_per_second": 3.153,
      "eval_steps_per_second": 1.577,
      "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": 1.4941952069861376e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}