last-checkpoint/trainer_state.json

{
  "best_metric": 0.6260796785354614,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.14925373134328357,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004975124378109453,
      "eval_loss": 0.8322070240974426,
      "eval_runtime": 6.0506,
      "eval_samples_per_second": 28.096,
      "eval_steps_per_second": 7.107,
      "step": 1
    },
    {
      "epoch": 0.014925373134328358,
      "grad_norm": 9.024953842163086,
      "learning_rate": 0.00012,
      "loss": 0.7831,
      "step": 3
    },
    {
      "epoch": 0.024875621890547265,
      "eval_loss": 0.7414592504501343,
      "eval_runtime": 6.0376,
      "eval_samples_per_second": 28.157,
      "eval_steps_per_second": 7.122,
      "step": 5
    },
    {
      "epoch": 0.029850746268656716,
      "grad_norm": 0.4759524464607239,
      "learning_rate": 0.0001992114701314478,
      "loss": 0.7473,
      "step": 6
    },
    {
      "epoch": 0.04477611940298507,
      "grad_norm": 0.4512733221054077,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.6839,
      "step": 9
    },
    {
      "epoch": 0.04975124378109453,
      "eval_loss": 0.6773250102996826,
      "eval_runtime": 6.04,
      "eval_samples_per_second": 28.146,
      "eval_steps_per_second": 7.119,
      "step": 10
    },
    {
      "epoch": 0.05970149253731343,
      "grad_norm": 0.5345317721366882,
      "learning_rate": 0.000163742398974869,
      "loss": 0.6818,
      "step": 12
    },
    {
      "epoch": 0.07462686567164178,
      "grad_norm": 0.44765985012054443,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.6346,
      "step": 15
    },
    {
      "epoch": 0.07462686567164178,
      "eval_loss": 0.6496699452400208,
      "eval_runtime": 6.0382,
      "eval_samples_per_second": 28.154,
      "eval_steps_per_second": 7.121,
      "step": 15
    },
    {
      "epoch": 0.08955223880597014,
      "grad_norm": 0.4275529086589813,
      "learning_rate": 9.372094804706867e-05,
      "loss": 0.6198,
      "step": 18
    },
    {
      "epoch": 0.09950248756218906,
      "eval_loss": 0.6332871913909912,
      "eval_runtime": 6.0316,
      "eval_samples_per_second": 28.185,
      "eval_steps_per_second": 7.129,
      "step": 20
    },
    {
      "epoch": 0.1044776119402985,
      "grad_norm": 0.4247596859931946,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 0.6587,
      "step": 21
    },
    {
      "epoch": 0.11940298507462686,
      "grad_norm": 0.4106825590133667,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 0.6146,
      "step": 24
    },
    {
      "epoch": 0.12437810945273632,
      "eval_loss": 0.6272332668304443,
      "eval_runtime": 6.0465,
      "eval_samples_per_second": 28.116,
      "eval_steps_per_second": 7.112,
      "step": 25
    },
    {
      "epoch": 0.13432835820895522,
      "grad_norm": 0.4225139617919922,
      "learning_rate": 7.022351411174866e-06,
      "loss": 0.6011,
      "step": 27
    },
    {
      "epoch": 0.14925373134328357,
      "grad_norm": 0.43210238218307495,
      "learning_rate": 0.0,
      "loss": 0.6208,
      "step": 30
    },
    {
      "epoch": 0.14925373134328357,
      "eval_loss": 0.6260796785354614,
      "eval_runtime": 6.0498,
      "eval_samples_per_second": 28.1,
      "eval_steps_per_second": 7.108,
      "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": 6082054657671168.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}