last-checkpoint/trainer_state.json

{
  "best_metric": 3.3020966053009033,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.17543859649122806,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005847953216374269,
      "eval_loss": 4.815151214599609,
      "eval_runtime": 3.7796,
      "eval_samples_per_second": 19.049,
      "eval_steps_per_second": 9.525,
      "step": 1
    },
    {
      "epoch": 0.017543859649122806,
      "grad_norm": 4.078864097595215,
      "learning_rate": 6e-05,
      "loss": 4.7019,
      "step": 3
    },
    {
      "epoch": 0.029239766081871343,
      "eval_loss": 4.256248474121094,
      "eval_runtime": 3.7876,
      "eval_samples_per_second": 19.009,
      "eval_steps_per_second": 9.505,
      "step": 5
    },
    {
      "epoch": 0.03508771929824561,
      "grad_norm": 3.195171356201172,
      "learning_rate": 0.00012,
      "loss": 4.3382,
      "step": 6
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 3.5134713649749756,
      "learning_rate": 0.00018,
      "loss": 3.9086,
      "step": 9
    },
    {
      "epoch": 0.05847953216374269,
      "eval_loss": 3.64383864402771,
      "eval_runtime": 3.7859,
      "eval_samples_per_second": 19.018,
      "eval_steps_per_second": 9.509,
      "step": 10
    },
    {
      "epoch": 0.07017543859649122,
      "grad_norm": 3.6851561069488525,
      "learning_rate": 0.00019510565162951537,
      "loss": 3.5827,
      "step": 12
    },
    {
      "epoch": 0.08771929824561403,
      "grad_norm": 2.6502652168273926,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.328,
      "step": 15
    },
    {
      "epoch": 0.08771929824561403,
      "eval_loss": 3.435582160949707,
      "eval_runtime": 3.7881,
      "eval_samples_per_second": 19.007,
      "eval_steps_per_second": 9.503,
      "step": 15
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 2.3518097400665283,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.348,
      "step": 18
    },
    {
      "epoch": 0.11695906432748537,
      "eval_loss": 3.360213041305542,
      "eval_runtime": 3.7903,
      "eval_samples_per_second": 18.996,
      "eval_steps_per_second": 9.498,
      "step": 20
    },
    {
      "epoch": 0.12280701754385964,
      "grad_norm": 2.3523964881896973,
      "learning_rate": 8.435655349597689e-05,
      "loss": 3.2867,
      "step": 21
    },
    {
      "epoch": 0.14035087719298245,
      "grad_norm": 2.754035472869873,
      "learning_rate": 4.12214747707527e-05,
      "loss": 3.2694,
      "step": 24
    },
    {
      "epoch": 0.14619883040935672,
      "eval_loss": 3.3148889541625977,
      "eval_runtime": 3.7993,
      "eval_samples_per_second": 18.951,
      "eval_steps_per_second": 9.475,
      "step": 25
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 2.3271331787109375,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 3.1204,
      "step": 27
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 2.160839557647705,
      "learning_rate": 0.0,
      "loss": 3.0623,
      "step": 30
    },
    {
      "epoch": 0.17543859649122806,
      "eval_loss": 3.3020966053009033,
      "eval_runtime": 3.7873,
      "eval_samples_per_second": 19.011,
      "eval_steps_per_second": 9.506,
      "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": 3015894871572480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}