checkpoint-694/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 694,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1440922190201729,
      "grad_norm": 0.8574005961418152,
      "learning_rate": 9.98886824135084e-05,
      "loss": 1.7489,
      "step": 50
    },
    {
      "epoch": 0.2881844380403458,
      "grad_norm": 0.41624724864959717,
      "learning_rate": 9.769082245289474e-05,
      "loss": 0.2055,
      "step": 100
    },
    {
      "epoch": 0.4322766570605187,
      "grad_norm": 0.34527522325515747,
      "learning_rate": 9.279617620528497e-05,
      "loss": 0.1596,
      "step": 150
    },
    {
      "epoch": 0.5763688760806917,
      "grad_norm": 0.48223987221717834,
      "learning_rate": 8.548152260216614e-05,
      "loss": 0.1554,
      "step": 200
    },
    {
      "epoch": 0.7204610951008645,
      "grad_norm": 0.2791622281074524,
      "learning_rate": 7.61604854083727e-05,
      "loss": 0.1334,
      "step": 250
    },
    {
      "epoch": 0.8645533141210374,
      "grad_norm": 0.36355826258659363,
      "learning_rate": 6.536014392327366e-05,
      "loss": 0.1359,
      "step": 300
    },
    {
      "epoch": 1.0086455331412103,
      "grad_norm": 0.6473142504692078,
      "learning_rate": 5.369122808008955e-05,
      "loss": 0.1261,
      "step": 350
    },
    {
      "epoch": 1.1527377521613833,
      "grad_norm": 0.2150665819644928,
      "learning_rate": 4.181358332940144e-05,
      "loss": 0.1066,
      "step": 400
    },
    {
      "epoch": 1.2968299711815563,
      "grad_norm": 0.4351930022239685,
      "learning_rate": 3.0398858173751e-05,
      "loss": 0.1123,
      "step": 450
    },
    {
      "epoch": 1.440922190201729,
      "grad_norm": 0.4223170578479767,
      "learning_rate": 2.0092524271757474e-05,
      "loss": 0.1103,
      "step": 500
    },
    {
      "epoch": 1.585014409221902,
      "grad_norm": 0.38104602694511414,
      "learning_rate": 1.1477376771555548e-05,
      "loss": 0.1088,
      "step": 550
    },
    {
      "epoch": 1.729106628242075,
      "grad_norm": 0.44926750659942627,
      "learning_rate": 5.040578830416043e-06,
      "loss": 0.1058,
      "step": 600
    },
    {
      "epoch": 1.8731988472622478,
      "grad_norm": 0.39785438776016235,
      "learning_rate": 1.1461138633235612e-06,
      "loss": 0.1006,
      "step": 650
    }
  ],
  "logging_steps": 50,
  "max_steps": 694,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.141442919656243e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}