last-checkpoint/trainer_state.json

{
  "best_metric": 2.0538229942321777,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.002442648645347772,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.14216215115924e-05,
      "eval_loss": 2.145434856414795,
      "eval_runtime": 887.6574,
      "eval_samples_per_second": 5.827,
      "eval_steps_per_second": 2.913,
      "step": 1
    },
    {
      "epoch": 0.0002442648645347772,
      "grad_norm": 1.412853479385376,
      "learning_rate": 3e-05,
      "loss": 8.4364,
      "step": 3
    },
    {
      "epoch": 0.00040710810755796204,
      "eval_loss": 2.140377998352051,
      "eval_runtime": 890.5261,
      "eval_samples_per_second": 5.808,
      "eval_steps_per_second": 2.904,
      "step": 5
    },
    {
      "epoch": 0.0004885297290695544,
      "grad_norm": 1.4299758672714233,
      "learning_rate": 6e-05,
      "loss": 8.7309,
      "step": 6
    },
    {
      "epoch": 0.0007327945936043316,
      "grad_norm": 1.3283333778381348,
      "learning_rate": 9e-05,
      "loss": 8.7558,
      "step": 9
    },
    {
      "epoch": 0.0008142162151159241,
      "eval_loss": 2.112894058227539,
      "eval_runtime": 889.8076,
      "eval_samples_per_second": 5.812,
      "eval_steps_per_second": 2.906,
      "step": 10
    },
    {
      "epoch": 0.0009770594581391089,
      "grad_norm": 1.175682544708252,
      "learning_rate": 9.755282581475769e-05,
      "loss": 8.3941,
      "step": 12
    },
    {
      "epoch": 0.001221324322673886,
      "grad_norm": 1.2302436828613281,
      "learning_rate": 8.535533905932738e-05,
      "loss": 8.6082,
      "step": 15
    },
    {
      "epoch": 0.001221324322673886,
      "eval_loss": 2.081014394760132,
      "eval_runtime": 891.2828,
      "eval_samples_per_second": 5.803,
      "eval_steps_per_second": 2.901,
      "step": 15
    },
    {
      "epoch": 0.0014655891872086633,
      "grad_norm": 1.4797160625457764,
      "learning_rate": 6.545084971874738e-05,
      "loss": 8.1861,
      "step": 18
    },
    {
      "epoch": 0.0016284324302318482,
      "eval_loss": 2.0656561851501465,
      "eval_runtime": 890.9267,
      "eval_samples_per_second": 5.805,
      "eval_steps_per_second": 2.903,
      "step": 20
    },
    {
      "epoch": 0.0017098540517434405,
      "grad_norm": 1.0811505317687988,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 8.3596,
      "step": 21
    },
    {
      "epoch": 0.0019541189162782177,
      "grad_norm": 1.0642000436782837,
      "learning_rate": 2.061073738537635e-05,
      "loss": 8.0844,
      "step": 24
    },
    {
      "epoch": 0.0020355405377898103,
      "eval_loss": 2.055866003036499,
      "eval_runtime": 890.5227,
      "eval_samples_per_second": 5.808,
      "eval_steps_per_second": 2.904,
      "step": 25
    },
    {
      "epoch": 0.002198383780812995,
      "grad_norm": 1.077531099319458,
      "learning_rate": 5.449673790581611e-06,
      "loss": 8.3103,
      "step": 27
    },
    {
      "epoch": 0.002442648645347772,
      "grad_norm": 1.0193705558776855,
      "learning_rate": 0.0,
      "loss": 8.3276,
      "step": 30
    },
    {
      "epoch": 0.002442648645347772,
      "eval_loss": 2.0538229942321777,
      "eval_runtime": 890.5686,
      "eval_samples_per_second": 5.808,
      "eval_steps_per_second": 2.904,
      "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": 7460470608887808.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}