last-checkpoint/trainer_state.json

{
  "best_metric": 0.5853016376495361,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.05154639175257732,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001718213058419244,
      "eval_loss": 0.7922400832176208,
      "eval_runtime": 61.5597,
      "eval_samples_per_second": 7.96,
      "eval_steps_per_second": 1.998,
      "step": 1
    },
    {
      "epoch": 0.005154639175257732,
      "grad_norm": 0.23845116794109344,
      "learning_rate": 0.00012,
      "loss": 0.6075,
      "step": 3
    },
    {
      "epoch": 0.00859106529209622,
      "eval_loss": 0.7301011085510254,
      "eval_runtime": 62.7509,
      "eval_samples_per_second": 7.809,
      "eval_steps_per_second": 1.96,
      "step": 5
    },
    {
      "epoch": 0.010309278350515464,
      "grad_norm": 0.23803502321243286,
      "learning_rate": 0.0001992114701314478,
      "loss": 0.6034,
      "step": 6
    },
    {
      "epoch": 0.015463917525773196,
      "grad_norm": 0.3054950535297394,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.5065,
      "step": 9
    },
    {
      "epoch": 0.01718213058419244,
      "eval_loss": 0.6248545050621033,
      "eval_runtime": 62.8126,
      "eval_samples_per_second": 7.801,
      "eval_steps_per_second": 1.958,
      "step": 10
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": 0.2894194722175598,
      "learning_rate": 0.000163742398974869,
      "loss": 0.4676,
      "step": 12
    },
    {
      "epoch": 0.02577319587628866,
      "grad_norm": 0.28897491097450256,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.5345,
      "step": 15
    },
    {
      "epoch": 0.02577319587628866,
      "eval_loss": 0.6064522862434387,
      "eval_runtime": 62.3155,
      "eval_samples_per_second": 7.863,
      "eval_steps_per_second": 1.974,
      "step": 15
    },
    {
      "epoch": 0.030927835051546393,
      "grad_norm": 0.28419238328933716,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.5069,
      "step": 18
    },
    {
      "epoch": 0.03436426116838488,
      "eval_loss": 0.5925209522247314,
      "eval_runtime": 61.8126,
      "eval_samples_per_second": 7.927,
      "eval_steps_per_second": 1.99,
      "step": 20
    },
    {
      "epoch": 0.03608247422680412,
      "grad_norm": 0.2848334014415741,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.5134,
      "step": 21
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 0.2977289855480194,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.4784,
      "step": 24
    },
    {
      "epoch": 0.0429553264604811,
      "eval_loss": 0.5870580673217773,
      "eval_runtime": 62.2808,
      "eval_samples_per_second": 7.868,
      "eval_steps_per_second": 1.975,
      "step": 25
    },
    {
      "epoch": 0.04639175257731959,
      "grad_norm": 0.36105167865753174,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.5298,
      "step": 27
    },
    {
      "epoch": 0.05154639175257732,
      "grad_norm": 0.3599168658256531,
      "learning_rate": 0.0,
      "loss": 0.6005,
      "step": 30
    },
    {
      "epoch": 0.05154639175257732,
      "eval_loss": 0.5853016376495361,
      "eval_runtime": 61.6901,
      "eval_samples_per_second": 7.943,
      "eval_steps_per_second": 1.994,
      "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": 2.2813033969483776e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}