last-checkpoint/trainer_state.json

{
  "best_metric": 2.578435182571411,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.100418410041841,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0033472803347280333,
      "eval_loss": 2.776822090148926,
      "eval_runtime": 8.4599,
      "eval_samples_per_second": 14.894,
      "eval_steps_per_second": 7.447,
      "step": 1
    },
    {
      "epoch": 0.0100418410041841,
      "grad_norm": 0.8456981182098389,
      "learning_rate": 6e-05,
      "loss": 11.0996,
      "step": 3
    },
    {
      "epoch": 0.016736401673640166,
      "eval_loss": 2.7615139484405518,
      "eval_runtime": 8.5339,
      "eval_samples_per_second": 14.765,
      "eval_steps_per_second": 7.382,
      "step": 5
    },
    {
      "epoch": 0.0200836820083682,
      "grad_norm": 1.2621592283248901,
      "learning_rate": 0.00012,
      "loss": 11.1193,
      "step": 6
    },
    {
      "epoch": 0.0301255230125523,
      "grad_norm": 2.677032709121704,
      "learning_rate": 0.00018,
      "loss": 10.9084,
      "step": 9
    },
    {
      "epoch": 0.03347280334728033,
      "eval_loss": 2.678286552429199,
      "eval_runtime": 8.5822,
      "eval_samples_per_second": 14.681,
      "eval_steps_per_second": 7.341,
      "step": 10
    },
    {
      "epoch": 0.0401673640167364,
      "grad_norm": 3.4736223220825195,
      "learning_rate": 0.00019510565162951537,
      "loss": 10.7916,
      "step": 12
    },
    {
      "epoch": 0.0502092050209205,
      "grad_norm": 2.7995059490203857,
      "learning_rate": 0.00017071067811865476,
      "loss": 10.586,
      "step": 15
    },
    {
      "epoch": 0.0502092050209205,
      "eval_loss": 2.61759877204895,
      "eval_runtime": 8.5959,
      "eval_samples_per_second": 14.658,
      "eval_steps_per_second": 7.329,
      "step": 15
    },
    {
      "epoch": 0.0602510460251046,
      "grad_norm": 2.393590211868286,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.6794,
      "step": 18
    },
    {
      "epoch": 0.06694560669456066,
      "eval_loss": 2.590780019760132,
      "eval_runtime": 8.5879,
      "eval_samples_per_second": 14.672,
      "eval_steps_per_second": 7.336,
      "step": 20
    },
    {
      "epoch": 0.07029288702928871,
      "grad_norm": 2.298074722290039,
      "learning_rate": 8.435655349597689e-05,
      "loss": 10.5228,
      "step": 21
    },
    {
      "epoch": 0.0803347280334728,
      "grad_norm": 2.0576088428497314,
      "learning_rate": 4.12214747707527e-05,
      "loss": 10.24,
      "step": 24
    },
    {
      "epoch": 0.08368200836820083,
      "eval_loss": 2.5811612606048584,
      "eval_runtime": 8.6291,
      "eval_samples_per_second": 14.602,
      "eval_steps_per_second": 7.301,
      "step": 25
    },
    {
      "epoch": 0.09037656903765691,
      "grad_norm": 2.148491144180298,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 10.0213,
      "step": 27
    },
    {
      "epoch": 0.100418410041841,
      "grad_norm": 2.1588032245635986,
      "learning_rate": 0.0,
      "loss": 10.3203,
      "step": 30
    },
    {
      "epoch": 0.100418410041841,
      "eval_loss": 2.578435182571411,
      "eval_runtime": 8.6245,
      "eval_samples_per_second": 14.609,
      "eval_steps_per_second": 7.305,
      "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": 9818930738626560.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}