last-checkpoint/trainer_state.json

{
  "best_metric": 2.4360692501068115,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.029977516862353237,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009992505620784412,
      "eval_loss": 3.334719657897949,
      "eval_runtime": 150.4317,
      "eval_samples_per_second": 2.805,
      "eval_steps_per_second": 1.403,
      "step": 1
    },
    {
      "epoch": 0.0029977516862353237,
      "grad_norm": 3.9588115215301514,
      "learning_rate": 0.00012,
      "loss": 9.0256,
      "step": 3
    },
    {
      "epoch": 0.004996252810392206,
      "eval_loss": 3.162672281265259,
      "eval_runtime": 163.1181,
      "eval_samples_per_second": 2.587,
      "eval_steps_per_second": 1.294,
      "step": 5
    },
    {
      "epoch": 0.005995503372470647,
      "grad_norm": 3.516874313354492,
      "learning_rate": 0.0001992114701314478,
      "loss": 10.0092,
      "step": 6
    },
    {
      "epoch": 0.008993255058705971,
      "grad_norm": 3.2138047218322754,
      "learning_rate": 0.00018763066800438636,
      "loss": 9.5826,
      "step": 9
    },
    {
      "epoch": 0.009992505620784412,
      "eval_loss": 2.834376811981201,
      "eval_runtime": 162.8008,
      "eval_samples_per_second": 2.592,
      "eval_steps_per_second": 1.296,
      "step": 10
    },
    {
      "epoch": 0.011991006744941295,
      "grad_norm": 4.357197284698486,
      "learning_rate": 0.000163742398974869,
      "loss": 9.6877,
      "step": 12
    },
    {
      "epoch": 0.014988758431176618,
      "grad_norm": 5.791210174560547,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.6052,
      "step": 15
    },
    {
      "epoch": 0.014988758431176618,
      "eval_loss": 2.6564278602600098,
      "eval_runtime": 162.1433,
      "eval_samples_per_second": 2.603,
      "eval_steps_per_second": 1.301,
      "step": 15
    },
    {
      "epoch": 0.017986510117411942,
      "grad_norm": 7.677189350128174,
      "learning_rate": 9.372094804706867e-05,
      "loss": 10.0151,
      "step": 18
    },
    {
      "epoch": 0.019985011241568824,
      "eval_loss": 2.5079739093780518,
      "eval_runtime": 162.1387,
      "eval_samples_per_second": 2.603,
      "eval_steps_per_second": 1.301,
      "step": 20
    },
    {
      "epoch": 0.020984261803647264,
      "grad_norm": 8.353514671325684,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 10.3783,
      "step": 21
    },
    {
      "epoch": 0.02398201348988259,
      "grad_norm": 11.086196899414062,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 9.4603,
      "step": 24
    },
    {
      "epoch": 0.02498126405196103,
      "eval_loss": 2.4464001655578613,
      "eval_runtime": 162.0333,
      "eval_samples_per_second": 2.604,
      "eval_steps_per_second": 1.302,
      "step": 25
    },
    {
      "epoch": 0.02697976517611791,
      "grad_norm": 6.061897277832031,
      "learning_rate": 7.022351411174866e-06,
      "loss": 9.5595,
      "step": 27
    },
    {
      "epoch": 0.029977516862353237,
      "grad_norm": 5.1886305809021,
      "learning_rate": 0.0,
      "loss": 9.5828,
      "step": 30
    },
    {
      "epoch": 0.029977516862353237,
      "eval_loss": 2.4360692501068115,
      "eval_runtime": 162.3182,
      "eval_samples_per_second": 2.6,
      "eval_steps_per_second": 1.3,
      "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": 1.90434898870272e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}