last-checkpoint/trainer_state.json

{
  "best_metric": 0.6661520004272461,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.06972690296339337,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002324230098779779,
      "eval_loss": 0.8673978447914124,
      "eval_runtime": 18.2804,
      "eval_samples_per_second": 19.857,
      "eval_steps_per_second": 4.978,
      "step": 1
    },
    {
      "epoch": 0.006972690296339338,
      "grad_norm": 0.6794880628585815,
      "learning_rate": 0.00012,
      "loss": 2.502,
      "step": 3
    },
    {
      "epoch": 0.011621150493898896,
      "eval_loss": 0.815407395362854,
      "eval_runtime": 18.1654,
      "eval_samples_per_second": 19.983,
      "eval_steps_per_second": 5.01,
      "step": 5
    },
    {
      "epoch": 0.013945380592678676,
      "grad_norm": 0.8472484946250916,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.841,
      "step": 6
    },
    {
      "epoch": 0.020918070889018012,
      "grad_norm": 0.9918720126152039,
      "learning_rate": 0.00018763066800438636,
      "loss": 2.6403,
      "step": 9
    },
    {
      "epoch": 0.023242300987797792,
      "eval_loss": 0.7263683676719666,
      "eval_runtime": 18.1721,
      "eval_samples_per_second": 19.976,
      "eval_steps_per_second": 5.008,
      "step": 10
    },
    {
      "epoch": 0.02789076118535735,
      "grad_norm": 0.8753803372383118,
      "learning_rate": 0.000163742398974869,
      "loss": 2.7183,
      "step": 12
    },
    {
      "epoch": 0.034863451481696686,
      "grad_norm": 0.8354143500328064,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.5805,
      "step": 15
    },
    {
      "epoch": 0.034863451481696686,
      "eval_loss": 0.6912750005722046,
      "eval_runtime": 18.092,
      "eval_samples_per_second": 20.064,
      "eval_steps_per_second": 5.03,
      "step": 15
    },
    {
      "epoch": 0.041836141778036025,
      "grad_norm": 0.8130712509155273,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.7872,
      "step": 18
    },
    {
      "epoch": 0.046484601975595584,
      "eval_loss": 0.6753512024879456,
      "eval_runtime": 18.1904,
      "eval_samples_per_second": 19.956,
      "eval_steps_per_second": 5.003,
      "step": 20
    },
    {
      "epoch": 0.04880883207437536,
      "grad_norm": 0.8119775056838989,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.6321,
      "step": 21
    },
    {
      "epoch": 0.0557815223707147,
      "grad_norm": 0.8773228526115417,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.5255,
      "step": 24
    },
    {
      "epoch": 0.05810575246949448,
      "eval_loss": 0.667984127998352,
      "eval_runtime": 18.2411,
      "eval_samples_per_second": 19.9,
      "eval_steps_per_second": 4.989,
      "step": 25
    },
    {
      "epoch": 0.06275421266705404,
      "grad_norm": 0.9739271402359009,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.7575,
      "step": 27
    },
    {
      "epoch": 0.06972690296339337,
      "grad_norm": 0.9907110929489136,
      "learning_rate": 0.0,
      "loss": 2.8631,
      "step": 30
    },
    {
      "epoch": 0.06972690296339337,
      "eval_loss": 0.6661520004272461,
      "eval_runtime": 18.1893,
      "eval_samples_per_second": 19.957,
      "eval_steps_per_second": 5.003,
      "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": 2.009383970852045e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}