last-checkpoint/trainer_state.json

{
  "best_metric": 2.3780980110168457,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.003699593044765076,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003699593044765076,
      "grad_norm": 1.4009169340133667,
      "learning_rate": 2e-05,
      "loss": 10.4429,
      "step": 1
    },
    {
      "epoch": 0.0003699593044765076,
      "eval_loss": 2.509531021118164,
      "eval_runtime": 104.6884,
      "eval_samples_per_second": 10.88,
      "eval_steps_per_second": 5.445,
      "step": 1
    },
    {
      "epoch": 0.0007399186089530152,
      "grad_norm": 1.3309544324874878,
      "learning_rate": 4e-05,
      "loss": 9.6322,
      "step": 2
    },
    {
      "epoch": 0.0011098779134295228,
      "grad_norm": 1.5765141248703003,
      "learning_rate": 6e-05,
      "loss": 10.378,
      "step": 3
    },
    {
      "epoch": 0.0014798372179060304,
      "grad_norm": 1.1468253135681152,
      "learning_rate": 8e-05,
      "loss": 9.2956,
      "step": 4
    },
    {
      "epoch": 0.001849796522382538,
      "grad_norm": 1.2961140871047974,
      "learning_rate": 0.0001,
      "loss": 9.8093,
      "step": 5
    },
    {
      "epoch": 0.001849796522382538,
      "eval_loss": 2.5007569789886475,
      "eval_runtime": 104.7232,
      "eval_samples_per_second": 10.876,
      "eval_steps_per_second": 5.443,
      "step": 5
    },
    {
      "epoch": 0.0022197558268590455,
      "grad_norm": 1.6239173412322998,
      "learning_rate": 0.00012,
      "loss": 9.2224,
      "step": 6
    },
    {
      "epoch": 0.002589715131335553,
      "grad_norm": 1.4490967988967896,
      "learning_rate": 0.00014,
      "loss": 9.5077,
      "step": 7
    },
    {
      "epoch": 0.0029596744358120607,
      "grad_norm": 1.7314764261245728,
      "learning_rate": 0.00016,
      "loss": 9.5829,
      "step": 8
    },
    {
      "epoch": 0.003329633740288568,
      "grad_norm": 1.7692434787750244,
      "learning_rate": 0.00018,
      "loss": 9.8363,
      "step": 9
    },
    {
      "epoch": 0.003699593044765076,
      "grad_norm": 2.1426827907562256,
      "learning_rate": 0.0002,
      "loss": 10.0488,
      "step": 10
    },
    {
      "epoch": 0.003699593044765076,
      "eval_loss": 2.3780980110168457,
      "eval_runtime": 104.8377,
      "eval_samples_per_second": 10.864,
      "eval_steps_per_second": 5.437,
      "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": 917953377730560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}