last-checkpoint/trainer_state.json

{
  "best_metric": 2.685049295425415,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.005792903692976104,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005792903692976104,
      "grad_norm": 2.838529109954834,
      "learning_rate": 2e-05,
      "loss": 12.5795,
      "step": 1
    },
    {
      "epoch": 0.0005792903692976104,
      "eval_loss": 3.121882677078247,
      "eval_runtime": 104.4145,
      "eval_samples_per_second": 6.963,
      "eval_steps_per_second": 3.486,
      "step": 1
    },
    {
      "epoch": 0.0011585807385952208,
      "grad_norm": 3.1008856296539307,
      "learning_rate": 4e-05,
      "loss": 12.8641,
      "step": 2
    },
    {
      "epoch": 0.0017378711078928314,
      "grad_norm": 3.484205484390259,
      "learning_rate": 6e-05,
      "loss": 11.9847,
      "step": 3
    },
    {
      "epoch": 0.0023171614771904415,
      "grad_norm": 3.1738972663879395,
      "learning_rate": 8e-05,
      "loss": 13.3681,
      "step": 4
    },
    {
      "epoch": 0.002896451846488052,
      "grad_norm": 2.6525840759277344,
      "learning_rate": 0.0001,
      "loss": 10.3859,
      "step": 5
    },
    {
      "epoch": 0.002896451846488052,
      "eval_loss": 3.0464909076690674,
      "eval_runtime": 102.3038,
      "eval_samples_per_second": 7.106,
      "eval_steps_per_second": 3.558,
      "step": 5
    },
    {
      "epoch": 0.0034757422157856628,
      "grad_norm": 4.349057197570801,
      "learning_rate": 0.00012,
      "loss": 13.4115,
      "step": 6
    },
    {
      "epoch": 0.004055032585083273,
      "grad_norm": 4.680722236633301,
      "learning_rate": 0.00014,
      "loss": 12.9696,
      "step": 7
    },
    {
      "epoch": 0.004634322954380883,
      "grad_norm": 3.7882301807403564,
      "learning_rate": 0.00016,
      "loss": 10.0891,
      "step": 8
    },
    {
      "epoch": 0.0052136133236784935,
      "grad_norm": 4.43908166885376,
      "learning_rate": 0.00018,
      "loss": 12.1125,
      "step": 9
    },
    {
      "epoch": 0.005792903692976104,
      "grad_norm": 3.733471393585205,
      "learning_rate": 0.0002,
      "loss": 9.6618,
      "step": 10
    },
    {
      "epoch": 0.005792903692976104,
      "eval_loss": 2.685049295425415,
      "eval_runtime": 101.5745,
      "eval_samples_per_second": 7.157,
      "eval_steps_per_second": 3.584,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2852805358387200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}