last-checkpoint/trainer_state.json

{
  "best_metric": 1.17819082736969,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0008595065000179064,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.8650216667263546e-05,
      "eval_loss": 1.5329145193099976,
      "eval_runtime": 2839.9472,
      "eval_samples_per_second": 5.175,
      "eval_steps_per_second": 2.588,
      "step": 1
    },
    {
      "epoch": 8.595065000179063e-05,
      "grad_norm": 0.5544006824493408,
      "learning_rate": 6e-05,
      "loss": 1.5192,
      "step": 3
    },
    {
      "epoch": 0.00014325108333631772,
      "eval_loss": 1.5068271160125732,
      "eval_runtime": 2856.8577,
      "eval_samples_per_second": 5.144,
      "eval_steps_per_second": 2.572,
      "step": 5
    },
    {
      "epoch": 0.00017190130000358127,
      "grad_norm": 0.5922831892967224,
      "learning_rate": 9.96057350657239e-05,
      "loss": 1.4088,
      "step": 6
    },
    {
      "epoch": 0.0002578519500053719,
      "grad_norm": 0.7716346979141235,
      "learning_rate": 9.381533400219318e-05,
      "loss": 1.3972,
      "step": 9
    },
    {
      "epoch": 0.00028650216667263544,
      "eval_loss": 1.3494272232055664,
      "eval_runtime": 2856.9727,
      "eval_samples_per_second": 5.144,
      "eval_steps_per_second": 2.572,
      "step": 10
    },
    {
      "epoch": 0.00034380260000716254,
      "grad_norm": 0.996634840965271,
      "learning_rate": 8.18711994874345e-05,
      "loss": 1.4681,
      "step": 12
    },
    {
      "epoch": 0.0004297532500089532,
      "grad_norm": 0.5805554389953613,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.2658,
      "step": 15
    },
    {
      "epoch": 0.0004297532500089532,
      "eval_loss": 1.246420979499817,
      "eval_runtime": 2855.937,
      "eval_samples_per_second": 5.146,
      "eval_steps_per_second": 2.573,
      "step": 15
    },
    {
      "epoch": 0.0005157039000107438,
      "grad_norm": 0.669230580329895,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 1.2075,
      "step": 18
    },
    {
      "epoch": 0.0005730043333452709,
      "eval_loss": 1.201594352722168,
      "eval_runtime": 2854.0241,
      "eval_samples_per_second": 5.15,
      "eval_steps_per_second": 2.575,
      "step": 20
    },
    {
      "epoch": 0.0006016545500125345,
      "grad_norm": 0.6407626867294312,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 1.1543,
      "step": 21
    },
    {
      "epoch": 0.0006876052000143251,
      "grad_norm": 0.579468846321106,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 1.1352,
      "step": 24
    },
    {
      "epoch": 0.0007162554166815887,
      "eval_loss": 1.1811610460281372,
      "eval_runtime": 2854.1127,
      "eval_samples_per_second": 5.149,
      "eval_steps_per_second": 2.575,
      "step": 25
    },
    {
      "epoch": 0.0007735558500161158,
      "grad_norm": 0.5746999382972717,
      "learning_rate": 3.511175705587433e-06,
      "loss": 1.1843,
      "step": 27
    },
    {
      "epoch": 0.0008595065000179064,
      "grad_norm": 0.655366837978363,
      "learning_rate": 0.0,
      "loss": 1.1799,
      "step": 30
    },
    {
      "epoch": 0.0008595065000179064,
      "eval_loss": 1.17819082736969,
      "eval_runtime": 2854.4994,
      "eval_samples_per_second": 5.149,
      "eval_steps_per_second": 2.575,
      "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": 1.9043369091072e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}