last-checkpoint/trainer_state.json

{
  "best_metric": 1.577901840209961,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0421792618629174,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00140597539543058,
      "eval_loss": 1.7019844055175781,
      "eval_runtime": 136.6649,
      "eval_samples_per_second": 4.383,
      "eval_steps_per_second": 1.098,
      "step": 1
    },
    {
      "epoch": 0.00421792618629174,
      "grad_norm": 0.08096624910831451,
      "learning_rate": 0.00012,
      "loss": 1.8001,
      "step": 3
    },
    {
      "epoch": 0.007029876977152899,
      "eval_loss": 1.6819177865982056,
      "eval_runtime": 137.5528,
      "eval_samples_per_second": 4.355,
      "eval_steps_per_second": 1.09,
      "step": 5
    },
    {
      "epoch": 0.00843585237258348,
      "grad_norm": 0.09669382125139236,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.7866,
      "step": 6
    },
    {
      "epoch": 0.01265377855887522,
      "grad_norm": 0.14735546708106995,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.7486,
      "step": 9
    },
    {
      "epoch": 0.014059753954305799,
      "eval_loss": 1.623664379119873,
      "eval_runtime": 137.7255,
      "eval_samples_per_second": 4.349,
      "eval_steps_per_second": 1.089,
      "step": 10
    },
    {
      "epoch": 0.01687170474516696,
      "grad_norm": 0.10727108269929886,
      "learning_rate": 0.000163742398974869,
      "loss": 1.7306,
      "step": 12
    },
    {
      "epoch": 0.0210896309314587,
      "grad_norm": 0.11267288029193878,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.6182,
      "step": 15
    },
    {
      "epoch": 0.0210896309314587,
      "eval_loss": 1.5961275100708008,
      "eval_runtime": 137.7361,
      "eval_samples_per_second": 4.349,
      "eval_steps_per_second": 1.089,
      "step": 15
    },
    {
      "epoch": 0.02530755711775044,
      "grad_norm": 0.09677157551050186,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.6834,
      "step": 18
    },
    {
      "epoch": 0.028119507908611598,
      "eval_loss": 1.5855631828308105,
      "eval_runtime": 137.7,
      "eval_samples_per_second": 4.35,
      "eval_steps_per_second": 1.089,
      "step": 20
    },
    {
      "epoch": 0.02952548330404218,
      "grad_norm": 0.10177566856145859,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.5537,
      "step": 21
    },
    {
      "epoch": 0.03374340949033392,
      "grad_norm": 0.10590466111898422,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.376,
      "step": 24
    },
    {
      "epoch": 0.0351493848857645,
      "eval_loss": 1.579613208770752,
      "eval_runtime": 137.7471,
      "eval_samples_per_second": 4.349,
      "eval_steps_per_second": 1.089,
      "step": 25
    },
    {
      "epoch": 0.03796133567662566,
      "grad_norm": 0.10410355031490326,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.4243,
      "step": 27
    },
    {
      "epoch": 0.0421792618629174,
      "grad_norm": 0.10854054987430573,
      "learning_rate": 0.0,
      "loss": 1.472,
      "step": 30
    },
    {
      "epoch": 0.0421792618629174,
      "eval_loss": 1.577901840209961,
      "eval_runtime": 137.6591,
      "eval_samples_per_second": 4.351,
      "eval_steps_per_second": 1.09,
      "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": 4.194232159961088e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}