expC/mmlu_stem/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.6,
  "eval_steps": 500,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 1.4153553247451782,
      "learning_rate": 1e-05,
      "loss": 18.4468,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.4177454710006714,
      "learning_rate": 1e-05,
      "loss": 18.2763,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.4095497131347656,
      "learning_rate": 1e-05,
      "loss": 18.4526,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.4071496725082397,
      "learning_rate": 1e-05,
      "loss": 18.3346,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.405538558959961,
      "learning_rate": 1e-05,
      "loss": 18.4757,
      "step": 250
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.4037182331085205,
      "learning_rate": 1e-05,
      "loss": 18.4638,
      "step": 300
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.4086352586746216,
      "learning_rate": 1e-05,
      "loss": 18.426,
      "step": 350
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.390128493309021,
      "learning_rate": 1e-05,
      "loss": 18.4442,
      "step": 400
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.4001573324203491,
      "learning_rate": 1e-05,
      "loss": 18.7401,
      "step": 450
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.3665372133255005,
      "learning_rate": 1e-05,
      "loss": 18.6871,
      "step": 500
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.37483549118042,
      "learning_rate": 1e-05,
      "loss": 18.6444,
      "step": 550
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.356723666191101,
      "learning_rate": 1e-05,
      "loss": 18.6972,
      "step": 600
    },
    {
      "epoch": 5.2,
      "grad_norm": 1.3741450309753418,
      "learning_rate": 1e-05,
      "loss": 18.6829,
      "step": 650
    },
    {
      "epoch": 5.6,
      "grad_norm": 1.3221684694290161,
      "learning_rate": 1e-05,
      "loss": 18.8957,
      "step": 700
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.3087866306304932,
      "learning_rate": 1e-05,
      "loss": 19.0889,
      "step": 750
    },
    {
      "epoch": 6.4,
      "grad_norm": 1.3595120906829834,
      "learning_rate": 1e-05,
      "loss": 19.106,
      "step": 800
    },
    {
      "epoch": 6.8,
      "grad_norm": 1.2227513790130615,
      "learning_rate": 1e-05,
      "loss": 19.3717,
      "step": 850
    },
    {
      "epoch": 7.2,
      "grad_norm": 1.2404745817184448,
      "learning_rate": 1e-05,
      "loss": 19.1219,
      "step": 900
    },
    {
      "epoch": 7.6,
      "grad_norm": 1.0410410165786743,
      "learning_rate": 1e-05,
      "loss": 19.8345,
      "step": 950
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.2170908451080322,
      "learning_rate": 1e-05,
      "loss": 19.5539,
      "step": 1000
    },
    {
      "epoch": 8.4,
      "grad_norm": 1.3088499307632446,
      "learning_rate": 1e-05,
      "loss": 19.6415,
      "step": 1050
    },
    {
      "epoch": 8.8,
      "grad_norm": 1.0727498531341553,
      "learning_rate": 1e-05,
      "loss": 20.2071,
      "step": 1100
    },
    {
      "epoch": 9.2,
      "grad_norm": 1.1626911163330078,
      "learning_rate": 1e-05,
      "loss": 20.5491,
      "step": 1150
    },
    {
      "epoch": 9.6,
      "grad_norm": 1.0018223524093628,
      "learning_rate": 1e-05,
      "loss": 21.2063,
      "step": 1200
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}