last-checkpoint/trainer_state.json

{
  "best_metric": 3.150834560394287,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.18045112781954886,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006015037593984963,
      "eval_loss": 4.414499759674072,
      "eval_runtime": 4.6248,
      "eval_samples_per_second": 30.271,
      "eval_steps_per_second": 7.568,
      "step": 1
    },
    {
      "epoch": 0.01804511278195489,
      "grad_norm": 1.3610951900482178,
      "learning_rate": 0.00012,
      "loss": 3.6943,
      "step": 3
    },
    {
      "epoch": 0.03007518796992481,
      "eval_loss": 4.200321197509766,
      "eval_runtime": 4.6218,
      "eval_samples_per_second": 30.291,
      "eval_steps_per_second": 7.573,
      "step": 5
    },
    {
      "epoch": 0.03609022556390978,
      "grad_norm": 1.5284638404846191,
      "learning_rate": 0.0001992114701314478,
      "loss": 3.6051,
      "step": 6
    },
    {
      "epoch": 0.05413533834586466,
      "grad_norm": 1.4452353715896606,
      "learning_rate": 0.00018763066800438636,
      "loss": 3.4892,
      "step": 9
    },
    {
      "epoch": 0.06015037593984962,
      "eval_loss": 3.781726837158203,
      "eval_runtime": 4.6196,
      "eval_samples_per_second": 30.305,
      "eval_steps_per_second": 7.576,
      "step": 10
    },
    {
      "epoch": 0.07218045112781955,
      "grad_norm": 1.206869125366211,
      "learning_rate": 0.000163742398974869,
      "loss": 3.3797,
      "step": 12
    },
    {
      "epoch": 0.09022556390977443,
      "grad_norm": 1.5519403219223022,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.2448,
      "step": 15
    },
    {
      "epoch": 0.09022556390977443,
      "eval_loss": 3.3792545795440674,
      "eval_runtime": 4.608,
      "eval_samples_per_second": 30.382,
      "eval_steps_per_second": 7.595,
      "step": 15
    },
    {
      "epoch": 0.10827067669172932,
      "grad_norm": 1.5599372386932373,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.9298,
      "step": 18
    },
    {
      "epoch": 0.12030075187969924,
      "eval_loss": 3.2186026573181152,
      "eval_runtime": 4.6123,
      "eval_samples_per_second": 30.353,
      "eval_steps_per_second": 7.588,
      "step": 20
    },
    {
      "epoch": 0.12631578947368421,
      "grad_norm": 1.5489070415496826,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.8736,
      "step": 21
    },
    {
      "epoch": 0.1443609022556391,
      "grad_norm": 1.7707982063293457,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 3.008,
      "step": 24
    },
    {
      "epoch": 0.15037593984962405,
      "eval_loss": 3.1601390838623047,
      "eval_runtime": 4.6131,
      "eval_samples_per_second": 30.348,
      "eval_steps_per_second": 7.587,
      "step": 25
    },
    {
      "epoch": 0.162406015037594,
      "grad_norm": 2.0040459632873535,
      "learning_rate": 7.022351411174866e-06,
      "loss": 3.1299,
      "step": 27
    },
    {
      "epoch": 0.18045112781954886,
      "grad_norm": 2.284895896911621,
      "learning_rate": 0.0,
      "loss": 3.1871,
      "step": 30
    },
    {
      "epoch": 0.18045112781954886,
      "eval_loss": 3.150834560394287,
      "eval_runtime": 4.6277,
      "eval_samples_per_second": 30.253,
      "eval_steps_per_second": 7.563,
      "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": 8271418475151360.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}