trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 50,
  "global_step": 8676,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11526048870447211,
      "grad_norm": 20.16172218322754,
      "learning_rate": 9.960000000000001e-06,
      "loss": 2.3764,
      "step": 500
    },
    {
      "epoch": 0.23052097740894423,
      "grad_norm": 16.483428955078125,
      "learning_rate": 9.393346379647749e-06,
      "loss": 0.5479,
      "step": 1000
    },
    {
      "epoch": 0.3457814661134163,
      "grad_norm": 13.152728080749512,
      "learning_rate": 8.781800391389433e-06,
      "loss": 0.4338,
      "step": 1500
    },
    {
      "epoch": 0.46104195481788846,
      "grad_norm": 8.478280067443848,
      "learning_rate": 8.170254403131116e-06,
      "loss": 0.3804,
      "step": 2000
    },
    {
      "epoch": 0.5763024435223605,
      "grad_norm": 7.399623870849609,
      "learning_rate": 7.558708414872799e-06,
      "loss": 0.3876,
      "step": 2500
    },
    {
      "epoch": 0.6915629322268326,
      "grad_norm": 15.365309715270996,
      "learning_rate": 6.947162426614482e-06,
      "loss": 0.3612,
      "step": 3000
    },
    {
      "epoch": 0.8068234209313048,
      "grad_norm": 5.001895427703857,
      "learning_rate": 6.335616438356164e-06,
      "loss": 0.3709,
      "step": 3500
    },
    {
      "epoch": 0.9220839096357769,
      "grad_norm": 20.685277938842773,
      "learning_rate": 5.7240704500978485e-06,
      "loss": 0.3376,
      "step": 4000
    },
    {
      "epoch": 1.037344398340249,
      "grad_norm": 12.555818557739258,
      "learning_rate": 5.112524461839531e-06,
      "loss": 0.2983,
      "step": 4500
    },
    {
      "epoch": 1.152604887044721,
      "grad_norm": 7.005858898162842,
      "learning_rate": 4.502201565557731e-06,
      "loss": 0.221,
      "step": 5000
    },
    {
      "epoch": 1.2678653757491931,
      "grad_norm": 4.69966459274292,
      "learning_rate": 3.890655577299413e-06,
      "loss": 0.2095,
      "step": 5500
    },
    {
      "epoch": 1.3831258644536653,
      "grad_norm": 24.06895637512207,
      "learning_rate": 3.2791095890410964e-06,
      "loss": 0.2292,
      "step": 6000
    },
    {
      "epoch": 1.4983863531581374,
      "grad_norm": 9.91574764251709,
      "learning_rate": 2.6675636007827793e-06,
      "loss": 0.2304,
      "step": 6500
    },
    {
      "epoch": 1.6136468418626095,
      "grad_norm": 3.978304862976074,
      "learning_rate": 2.0560176125244623e-06,
      "loss": 0.2102,
      "step": 7000
    },
    {
      "epoch": 1.7289073305670817,
      "grad_norm": 8.447595596313477,
      "learning_rate": 1.4469178082191781e-06,
      "loss": 0.2171,
      "step": 7500
    },
    {
      "epoch": 1.8441678192715538,
      "grad_norm": 3.0918211936950684,
      "learning_rate": 8.353718199608611e-07,
      "loss": 0.2166,
      "step": 8000
    },
    {
      "epoch": 1.959428307976026,
      "grad_norm": 1.6782150268554688,
      "learning_rate": 2.2382583170254403e-07,
      "loss": 0.2146,
      "step": 8500
    },
    {
      "epoch": 2.0,
      "step": 8676,
      "total_flos": 9.602043799869562e+16,
      "train_loss": 0.42129573760465744,
      "train_runtime": 3759.5481,
      "train_samples_per_second": 36.919,
      "train_steps_per_second": 2.308
    }
  ],
  "logging_steps": 500,
  "max_steps": 8676,
  "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": 9.602043799869562e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}