last-checkpoint/trainer_state.json

{
  "best_metric": 1.9168668985366821,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.08955223880597014,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0029850746268656717,
      "eval_loss": 1.991752028465271,
      "eval_runtime": 9.8496,
      "eval_samples_per_second": 14.315,
      "eval_steps_per_second": 7.208,
      "step": 1
    },
    {
      "epoch": 0.008955223880597015,
      "grad_norm": 0.3167933523654938,
      "learning_rate": 0.00012,
      "loss": 2.0488,
      "step": 3
    },
    {
      "epoch": 0.014925373134328358,
      "eval_loss": 1.967607855796814,
      "eval_runtime": 9.858,
      "eval_samples_per_second": 14.303,
      "eval_steps_per_second": 7.202,
      "step": 5
    },
    {
      "epoch": 0.01791044776119403,
      "grad_norm": 0.304219514131546,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.965,
      "step": 6
    },
    {
      "epoch": 0.026865671641791045,
      "grad_norm": 0.31642717123031616,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.9491,
      "step": 9
    },
    {
      "epoch": 0.029850746268656716,
      "eval_loss": 1.9405193328857422,
      "eval_runtime": 10.1439,
      "eval_samples_per_second": 13.9,
      "eval_steps_per_second": 6.999,
      "step": 10
    },
    {
      "epoch": 0.03582089552238806,
      "grad_norm": 0.30999255180358887,
      "learning_rate": 0.000163742398974869,
      "loss": 1.9542,
      "step": 12
    },
    {
      "epoch": 0.04477611940298507,
      "grad_norm": 0.3122391998767853,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.9043,
      "step": 15
    },
    {
      "epoch": 0.04477611940298507,
      "eval_loss": 1.9285753965377808,
      "eval_runtime": 10.3158,
      "eval_samples_per_second": 13.668,
      "eval_steps_per_second": 6.883,
      "step": 15
    },
    {
      "epoch": 0.05373134328358209,
      "grad_norm": 0.31301966309547424,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.0048,
      "step": 18
    },
    {
      "epoch": 0.05970149253731343,
      "eval_loss": 1.92122220993042,
      "eval_runtime": 10.4497,
      "eval_samples_per_second": 13.493,
      "eval_steps_per_second": 6.794,
      "step": 20
    },
    {
      "epoch": 0.0626865671641791,
      "grad_norm": 0.3020223379135132,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.9412,
      "step": 21
    },
    {
      "epoch": 0.07164179104477612,
      "grad_norm": 0.3058167099952698,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.9293,
      "step": 24
    },
    {
      "epoch": 0.07462686567164178,
      "eval_loss": 1.9176359176635742,
      "eval_runtime": 10.5315,
      "eval_samples_per_second": 13.388,
      "eval_steps_per_second": 6.742,
      "step": 25
    },
    {
      "epoch": 0.08059701492537313,
      "grad_norm": 0.3004499077796936,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.8636,
      "step": 27
    },
    {
      "epoch": 0.08955223880597014,
      "grad_norm": 0.2995579242706299,
      "learning_rate": 0.0,
      "loss": 1.9513,
      "step": 30
    },
    {
      "epoch": 0.08955223880597014,
      "eval_loss": 1.9168668985366821,
      "eval_runtime": 10.5857,
      "eval_samples_per_second": 13.32,
      "eval_steps_per_second": 6.707,
      "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": 3088106316103680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}