last-checkpoint/trainer_state.json

{
  "best_metric": 1.1751959323883057,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.012730744748567792,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000424358158285593,
      "eval_loss": 1.508124828338623,
      "eval_runtime": 128.6731,
      "eval_samples_per_second": 7.717,
      "eval_steps_per_second": 3.863,
      "step": 1
    },
    {
      "epoch": 0.001273074474856779,
      "grad_norm": 0.5830173492431641,
      "learning_rate": 6e-05,
      "loss": 1.5825,
      "step": 3
    },
    {
      "epoch": 0.0021217907914279654,
      "eval_loss": 1.466567039489746,
      "eval_runtime": 129.6671,
      "eval_samples_per_second": 7.658,
      "eval_steps_per_second": 3.833,
      "step": 5
    },
    {
      "epoch": 0.002546148949713558,
      "grad_norm": 0.5419243574142456,
      "learning_rate": 0.00012,
      "loss": 1.427,
      "step": 6
    },
    {
      "epoch": 0.0038192234245703373,
      "grad_norm": 0.8369843363761902,
      "learning_rate": 0.00018,
      "loss": 1.3801,
      "step": 9
    },
    {
      "epoch": 0.004243581582855931,
      "eval_loss": 1.3134835958480835,
      "eval_runtime": 129.6779,
      "eval_samples_per_second": 7.657,
      "eval_steps_per_second": 3.833,
      "step": 10
    },
    {
      "epoch": 0.005092297899427116,
      "grad_norm": 0.7152264714241028,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.3058,
      "step": 12
    },
    {
      "epoch": 0.006365372374283896,
      "grad_norm": 0.5883220434188843,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.2339,
      "step": 15
    },
    {
      "epoch": 0.006365372374283896,
      "eval_loss": 1.2224185466766357,
      "eval_runtime": 129.5429,
      "eval_samples_per_second": 7.665,
      "eval_steps_per_second": 3.837,
      "step": 15
    },
    {
      "epoch": 0.0076384468491406746,
      "grad_norm": 0.6324528455734253,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.1509,
      "step": 18
    },
    {
      "epoch": 0.008487163165711862,
      "eval_loss": 1.1928067207336426,
      "eval_runtime": 129.2663,
      "eval_samples_per_second": 7.682,
      "eval_steps_per_second": 3.845,
      "step": 20
    },
    {
      "epoch": 0.008911521323997454,
      "grad_norm": 0.5210100412368774,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.1578,
      "step": 21
    },
    {
      "epoch": 0.010184595798854232,
      "grad_norm": 0.5522451996803284,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.1488,
      "step": 24
    },
    {
      "epoch": 0.010608953957139827,
      "eval_loss": 1.1779961585998535,
      "eval_runtime": 129.2539,
      "eval_samples_per_second": 7.683,
      "eval_steps_per_second": 3.845,
      "step": 25
    },
    {
      "epoch": 0.011457670273711012,
      "grad_norm": 0.5235723853111267,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.1235,
      "step": 27
    },
    {
      "epoch": 0.012730744748567792,
      "grad_norm": 0.5206447243690491,
      "learning_rate": 0.0,
      "loss": 1.0994,
      "step": 30
    },
    {
      "epoch": 0.012730744748567792,
      "eval_loss": 1.1751959323883057,
      "eval_runtime": 129.2843,
      "eval_samples_per_second": 7.681,
      "eval_steps_per_second": 3.844,
      "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": 1.1221045163851776e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}