expA/software_development/mmlu_social_science/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.4,
  "eval_steps": 500,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4,
      "grad_norm": 1.4250736236572266,
      "learning_rate": 1e-05,
      "loss": 18.599,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.4153586626052856,
      "learning_rate": 1e-05,
      "loss": 18.5873,
      "step": 100
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.3992971181869507,
      "learning_rate": 1e-05,
      "loss": 18.5797,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.4152840375900269,
      "learning_rate": 1e-05,
      "loss": 18.3774,
      "step": 200
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.4251123666763306,
      "learning_rate": 1e-05,
      "loss": 18.7414,
      "step": 250
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.3725128173828125,
      "learning_rate": 1e-05,
      "loss": 18.5638,
      "step": 300
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.3802931308746338,
      "learning_rate": 1e-05,
      "loss": 18.6044,
      "step": 350
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.401808261871338,
      "learning_rate": 1e-05,
      "loss": 18.3672,
      "step": 400
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.4075677394866943,
      "learning_rate": 1e-05,
      "loss": 18.5341,
      "step": 450
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.3577747344970703,
      "learning_rate": 1e-05,
      "loss": 18.7034,
      "step": 500
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.2046217918395996,
      "learning_rate": 1e-05,
      "loss": 18.5874,
      "step": 550
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.3263092041015625,
      "learning_rate": 1e-05,
      "loss": 18.5656,
      "step": 600
    },
    {
      "epoch": 5.2,
      "grad_norm": 1.168810248374939,
      "learning_rate": 1e-05,
      "loss": 18.5508,
      "step": 650
    },
    {
      "epoch": 5.6,
      "grad_norm": 1.0646147727966309,
      "learning_rate": 1e-05,
      "loss": 18.7087,
      "step": 700
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.1354812383651733,
      "learning_rate": 1e-05,
      "loss": 19.0304,
      "step": 750
    },
    {
      "epoch": 6.4,
      "grad_norm": 1.2251195907592773,
      "learning_rate": 1e-05,
      "loss": 19.4701,
      "step": 800
    }
  ],
  "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
}