expA/games/mmlu_stem/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 11.2,
  "eval_steps": 500,
  "global_step": 1400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 1.411974549293518,
      "learning_rate": 1e-05,
      "loss": 19.1513,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.4139549732208252,
      "learning_rate": 1e-05,
      "loss": 18.8884,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.4126310348510742,
      "learning_rate": 1e-05,
      "loss": 18.9317,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.4136912822723389,
      "learning_rate": 1e-05,
      "loss": 18.9466,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4071362018585205,
      "learning_rate": 1e-05,
      "loss": 18.9537,
      "step": 250
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.3934357166290283,
      "learning_rate": 1e-05,
      "loss": 19.0735,
      "step": 300
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.4192053079605103,
      "learning_rate": 1e-05,
      "loss": 18.9429,
      "step": 350
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.3931375741958618,
      "learning_rate": 1e-05,
      "loss": 18.6424,
      "step": 400
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.4086956977844238,
      "learning_rate": 1e-05,
      "loss": 18.893,
      "step": 450
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.4049065113067627,
      "learning_rate": 1e-05,
      "loss": 19.0832,
      "step": 500
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.3881189823150635,
      "learning_rate": 1e-05,
      "loss": 19.0543,
      "step": 550
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.408837080001831,
      "learning_rate": 1e-05,
      "loss": 18.7512,
      "step": 600
    },
    {
      "epoch": 5.2,
      "grad_norm": 1.415128469467163,
      "learning_rate": 1e-05,
      "loss": 18.8432,
      "step": 650
    },
    {
      "epoch": 5.6,
      "grad_norm": 1.3774018287658691,
      "learning_rate": 1e-05,
      "loss": 18.9484,
      "step": 700
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.407077431678772,
      "learning_rate": 1e-05,
      "loss": 18.8452,
      "step": 750
    },
    {
      "epoch": 6.4,
      "grad_norm": 1.3890057802200317,
      "learning_rate": 1e-05,
      "loss": 18.8621,
      "step": 800
    },
    {
      "epoch": 6.8,
      "grad_norm": 1.4125330448150635,
      "learning_rate": 1e-05,
      "loss": 19.1534,
      "step": 850
    },
    {
      "epoch": 7.2,
      "grad_norm": 1.3675222396850586,
      "learning_rate": 1e-05,
      "loss": 18.9636,
      "step": 900
    },
    {
      "epoch": 7.6,
      "grad_norm": 1.3827025890350342,
      "learning_rate": 1e-05,
      "loss": 19.33,
      "step": 950
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.3550848960876465,
      "learning_rate": 1e-05,
      "loss": 19.0696,
      "step": 1000
    },
    {
      "epoch": 8.4,
      "grad_norm": 1.368452548980713,
      "learning_rate": 1e-05,
      "loss": 19.0625,
      "step": 1050
    },
    {
      "epoch": 8.8,
      "grad_norm": 1.3631970882415771,
      "learning_rate": 1e-05,
      "loss": 19.0052,
      "step": 1100
    },
    {
      "epoch": 9.2,
      "grad_norm": 1.3604135513305664,
      "learning_rate": 1e-05,
      "loss": 18.9448,
      "step": 1150
    },
    {
      "epoch": 9.6,
      "grad_norm": 1.2450554370880127,
      "learning_rate": 1e-05,
      "loss": 19.1216,
      "step": 1200
    },
    {
      "epoch": 10.0,
      "grad_norm": 1.2683663368225098,
      "learning_rate": 1e-05,
      "loss": 19.1535,
      "step": 1250
    },
    {
      "epoch": 10.4,
      "grad_norm": 1.2000527381896973,
      "learning_rate": 1e-05,
      "loss": 19.3041,
      "step": 1300
    },
    {
      "epoch": 10.8,
      "grad_norm": 1.1787408590316772,
      "learning_rate": 1e-05,
      "loss": 19.3801,
      "step": 1350
    },
    {
      "epoch": 11.2,
      "grad_norm": 1.0526790618896484,
      "learning_rate": 1e-05,
      "loss": 19.5929,
      "step": 1400
    }
  ],
  "logging_steps": 50,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 40,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}