last-checkpoint/trainer_state.json

{
  "best_metric": 1.8901664018630981,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.12944983818770225,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004314994606256742,
      "eval_loss": 3.223127603530884,
      "eval_runtime": 18.5616,
      "eval_samples_per_second": 10.506,
      "eval_steps_per_second": 2.64,
      "step": 1
    },
    {
      "epoch": 0.012944983818770227,
      "grad_norm": 4.634566783905029,
      "learning_rate": 0.00012,
      "loss": 10.607,
      "step": 3
    },
    {
      "epoch": 0.021574973031283712,
      "eval_loss": 3.0253074169158936,
      "eval_runtime": 18.8904,
      "eval_samples_per_second": 10.323,
      "eval_steps_per_second": 2.594,
      "step": 5
    },
    {
      "epoch": 0.025889967637540454,
      "grad_norm": 3.368901014328003,
      "learning_rate": 0.0001992114701314478,
      "loss": 10.2728,
      "step": 6
    },
    {
      "epoch": 0.038834951456310676,
      "grad_norm": 3.3519389629364014,
      "learning_rate": 0.00018763066800438636,
      "loss": 9.7708,
      "step": 9
    },
    {
      "epoch": 0.043149946062567425,
      "eval_loss": 2.438471555709839,
      "eval_runtime": 18.9815,
      "eval_samples_per_second": 10.273,
      "eval_steps_per_second": 2.581,
      "step": 10
    },
    {
      "epoch": 0.05177993527508091,
      "grad_norm": 3.322448492050171,
      "learning_rate": 0.000163742398974869,
      "loss": 9.0185,
      "step": 12
    },
    {
      "epoch": 0.06472491909385113,
      "grad_norm": 3.0929150581359863,
      "learning_rate": 0.00013090169943749476,
      "loss": 8.532,
      "step": 15
    },
    {
      "epoch": 0.06472491909385113,
      "eval_loss": 2.1120529174804688,
      "eval_runtime": 18.9051,
      "eval_samples_per_second": 10.315,
      "eval_steps_per_second": 2.592,
      "step": 15
    },
    {
      "epoch": 0.07766990291262135,
      "grad_norm": 3.2946879863739014,
      "learning_rate": 9.372094804706867e-05,
      "loss": 8.1404,
      "step": 18
    },
    {
      "epoch": 0.08629989212513485,
      "eval_loss": 1.959831714630127,
      "eval_runtime": 18.9926,
      "eval_samples_per_second": 10.267,
      "eval_steps_per_second": 2.58,
      "step": 20
    },
    {
      "epoch": 0.09061488673139159,
      "grad_norm": 3.3498525619506836,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 7.7349,
      "step": 21
    },
    {
      "epoch": 0.10355987055016182,
      "grad_norm": 3.1760308742523193,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 7.4737,
      "step": 24
    },
    {
      "epoch": 0.10787486515641856,
      "eval_loss": 1.8999488353729248,
      "eval_runtime": 18.9426,
      "eval_samples_per_second": 10.294,
      "eval_steps_per_second": 2.587,
      "step": 25
    },
    {
      "epoch": 0.11650485436893204,
      "grad_norm": 4.965217590332031,
      "learning_rate": 7.022351411174866e-06,
      "loss": 7.5005,
      "step": 27
    },
    {
      "epoch": 0.12944983818770225,
      "grad_norm": 3.8475265502929688,
      "learning_rate": 0.0,
      "loss": 7.7703,
      "step": 30
    },
    {
      "epoch": 0.12944983818770225,
      "eval_loss": 1.8901664018630981,
      "eval_runtime": 18.9937,
      "eval_samples_per_second": 10.267,
      "eval_steps_per_second": 2.58,
      "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": 1.105254905020416e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}