last-checkpoint/trainer_state.json

{
  "best_metric": 2.614351987838745,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0009678824345469504,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.226274781823168e-05,
      "eval_loss": 6.432010650634766,
      "eval_runtime": 2572.0509,
      "eval_samples_per_second": 5.074,
      "eval_steps_per_second": 2.537,
      "step": 1
    },
    {
      "epoch": 9.678824345469504e-05,
      "grad_norm": 23.091167449951172,
      "learning_rate": 6e-05,
      "loss": 6.4572,
      "step": 3
    },
    {
      "epoch": 0.0001613137390911584,
      "eval_loss": 3.5393335819244385,
      "eval_runtime": 2582.2736,
      "eval_samples_per_second": 5.054,
      "eval_steps_per_second": 2.527,
      "step": 5
    },
    {
      "epoch": 0.00019357648690939008,
      "grad_norm": 40.88241958618164,
      "learning_rate": 9.96057350657239e-05,
      "loss": 4.7654,
      "step": 6
    },
    {
      "epoch": 0.0002903647303640851,
      "grad_norm": 2.1575276851654053,
      "learning_rate": 9.381533400219318e-05,
      "loss": 2.9621,
      "step": 9
    },
    {
      "epoch": 0.0003226274781823168,
      "eval_loss": 2.791510820388794,
      "eval_runtime": 2580.6635,
      "eval_samples_per_second": 5.057,
      "eval_steps_per_second": 2.529,
      "step": 10
    },
    {
      "epoch": 0.00038715297381878015,
      "grad_norm": 1.2754595279693604,
      "learning_rate": 8.18711994874345e-05,
      "loss": 2.8637,
      "step": 12
    },
    {
      "epoch": 0.0004839412172734752,
      "grad_norm": 1.3381720781326294,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.6175,
      "step": 15
    },
    {
      "epoch": 0.0004839412172734752,
      "eval_loss": 2.6785662174224854,
      "eval_runtime": 2581.1799,
      "eval_samples_per_second": 5.056,
      "eval_steps_per_second": 2.528,
      "step": 15
    },
    {
      "epoch": 0.0005807294607281702,
      "grad_norm": 1.039152979850769,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 2.4836,
      "step": 18
    },
    {
      "epoch": 0.0006452549563646336,
      "eval_loss": 2.6314613819122314,
      "eval_runtime": 2581.419,
      "eval_samples_per_second": 5.056,
      "eval_steps_per_second": 2.528,
      "step": 20
    },
    {
      "epoch": 0.0006775177041828652,
      "grad_norm": 1.0345968008041382,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 2.4778,
      "step": 21
    },
    {
      "epoch": 0.0007743059476375603,
      "grad_norm": 34.092132568359375,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 2.4162,
      "step": 24
    },
    {
      "epoch": 0.0008065686954557919,
      "eval_loss": 2.617173433303833,
      "eval_runtime": 2582.2997,
      "eval_samples_per_second": 5.054,
      "eval_steps_per_second": 2.527,
      "step": 25
    },
    {
      "epoch": 0.0008710941910922553,
      "grad_norm": 0.993025541305542,
      "learning_rate": 3.511175705587433e-06,
      "loss": 2.7704,
      "step": 27
    },
    {
      "epoch": 0.0009678824345469504,
      "grad_norm": 1.1003926992416382,
      "learning_rate": 0.0,
      "loss": 2.5651,
      "step": 30
    },
    {
      "epoch": 0.0009678824345469504,
      "eval_loss": 2.614351987838745,
      "eval_runtime": 2582.0015,
      "eval_samples_per_second": 5.055,
      "eval_steps_per_second": 2.527,
      "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": 1.2457139698139136e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}