last-checkpoint/trainer_state.json

{
  "best_metric": 1.1581802368164062,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.006438113632705618,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00021460378775685392,
      "eval_loss": 3.633948802947998,
      "eval_runtime": 729.6428,
      "eval_samples_per_second": 5.378,
      "eval_steps_per_second": 1.344,
      "step": 1
    },
    {
      "epoch": 0.0006438113632705617,
      "grad_norm": 3.337303400039673,
      "learning_rate": 0.00012,
      "loss": 2.5927,
      "step": 3
    },
    {
      "epoch": 0.0010730189387842695,
      "eval_loss": 2.1056129932403564,
      "eval_runtime": 734.0903,
      "eval_samples_per_second": 5.345,
      "eval_steps_per_second": 1.336,
      "step": 5
    },
    {
      "epoch": 0.0012876227265411235,
      "grad_norm": 1.438804030418396,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.0973,
      "step": 6
    },
    {
      "epoch": 0.001931434089811685,
      "grad_norm": 0.9999722838401794,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.5578,
      "step": 9
    },
    {
      "epoch": 0.002146037877568539,
      "eval_loss": 1.3293501138687134,
      "eval_runtime": 734.0141,
      "eval_samples_per_second": 5.346,
      "eval_steps_per_second": 1.336,
      "step": 10
    },
    {
      "epoch": 0.002575245453082247,
      "grad_norm": 1.227637529373169,
      "learning_rate": 0.000163742398974869,
      "loss": 1.2881,
      "step": 12
    },
    {
      "epoch": 0.003219056816352809,
      "grad_norm": 1.231693148612976,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.2856,
      "step": 15
    },
    {
      "epoch": 0.003219056816352809,
      "eval_loss": 1.2313477993011475,
      "eval_runtime": 733.9654,
      "eval_samples_per_second": 5.346,
      "eval_steps_per_second": 1.337,
      "step": 15
    },
    {
      "epoch": 0.00386286817962337,
      "grad_norm": 1.0194306373596191,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.2727,
      "step": 18
    },
    {
      "epoch": 0.004292075755137078,
      "eval_loss": 1.1837564706802368,
      "eval_runtime": 734.1115,
      "eval_samples_per_second": 5.345,
      "eval_steps_per_second": 1.336,
      "step": 20
    },
    {
      "epoch": 0.0045066795428939325,
      "grad_norm": 0.9390937685966492,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.1718,
      "step": 21
    },
    {
      "epoch": 0.005150490906164494,
      "grad_norm": 0.9786153435707092,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.1053,
      "step": 24
    },
    {
      "epoch": 0.005365094693921347,
      "eval_loss": 1.162328839302063,
      "eval_runtime": 734.1206,
      "eval_samples_per_second": 5.345,
      "eval_steps_per_second": 1.336,
      "step": 25
    },
    {
      "epoch": 0.005794302269435055,
      "grad_norm": 0.9463156461715698,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.2137,
      "step": 27
    },
    {
      "epoch": 0.006438113632705618,
      "grad_norm": 0.9180121421813965,
      "learning_rate": 0.0,
      "loss": 1.19,
      "step": 30
    },
    {
      "epoch": 0.006438113632705618,
      "eval_loss": 1.1581802368164062,
      "eval_runtime": 733.7793,
      "eval_samples_per_second": 5.348,
      "eval_steps_per_second": 1.337,
      "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": 2.470837626077184e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}