last-checkpoint/trainer_state.json

{
  "best_metric": 2.6250178813934326,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.03411028993746447,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011370096645821489,
      "eval_loss": 12.575325965881348,
      "eval_runtime": 105.4367,
      "eval_samples_per_second": 7.028,
      "eval_steps_per_second": 1.764,
      "step": 1
    },
    {
      "epoch": 0.0034110289937464467,
      "grad_norm": 4.455483913421631,
      "learning_rate": 0.00012,
      "loss": 3.5782,
      "step": 3
    },
    {
      "epoch": 0.005685048322910745,
      "eval_loss": 7.4587788581848145,
      "eval_runtime": 106.0638,
      "eval_samples_per_second": 6.986,
      "eval_steps_per_second": 1.754,
      "step": 5
    },
    {
      "epoch": 0.006822057987492893,
      "grad_norm": 7.313121318817139,
      "learning_rate": 0.0001992114701314478,
      "loss": 3.9193,
      "step": 6
    },
    {
      "epoch": 0.01023308698123934,
      "grad_norm": 2.0426759719848633,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.8589,
      "step": 9
    },
    {
      "epoch": 0.01137009664582149,
      "eval_loss": 2.985470771789551,
      "eval_runtime": 106.0901,
      "eval_samples_per_second": 6.985,
      "eval_steps_per_second": 1.753,
      "step": 10
    },
    {
      "epoch": 0.013644115974985787,
      "grad_norm": 2.700772285461426,
      "learning_rate": 0.000163742398974869,
      "loss": 2.642,
      "step": 12
    },
    {
      "epoch": 0.017055144968732235,
      "grad_norm": 2.2496864795684814,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.45,
      "step": 15
    },
    {
      "epoch": 0.017055144968732235,
      "eval_loss": 2.8052423000335693,
      "eval_runtime": 106.248,
      "eval_samples_per_second": 6.974,
      "eval_steps_per_second": 1.751,
      "step": 15
    },
    {
      "epoch": 0.02046617396247868,
      "grad_norm": 2.46319580078125,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.2653,
      "step": 18
    },
    {
      "epoch": 0.02274019329164298,
      "eval_loss": 2.715874195098877,
      "eval_runtime": 106.9327,
      "eval_samples_per_second": 6.93,
      "eval_steps_per_second": 1.739,
      "step": 20
    },
    {
      "epoch": 0.023877202956225127,
      "grad_norm": 2.694730281829834,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.5534,
      "step": 21
    },
    {
      "epoch": 0.027288231949971573,
      "grad_norm": 2.9070112705230713,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.4852,
      "step": 24
    },
    {
      "epoch": 0.028425241614553724,
      "eval_loss": 2.633150815963745,
      "eval_runtime": 106.8832,
      "eval_samples_per_second": 6.933,
      "eval_steps_per_second": 1.74,
      "step": 25
    },
    {
      "epoch": 0.030699260943718023,
      "grad_norm": 2.6632487773895264,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.2376,
      "step": 27
    },
    {
      "epoch": 0.03411028993746447,
      "grad_norm": 2.7979321479797363,
      "learning_rate": 0.0,
      "loss": 2.2537,
      "step": 30
    },
    {
      "epoch": 0.03411028993746447,
      "eval_loss": 2.6250178813934326,
      "eval_runtime": 107.086,
      "eval_samples_per_second": 6.92,
      "eval_steps_per_second": 1.737,
      "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": 2.3198554436665344e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}