last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0002820299891888504,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.1336665465427825e-05,
      "grad_norm": 2.747194290161133,
      "learning_rate": 2e-05,
      "loss": 5.6666,
      "step": 1
    },
    {
      "epoch": 3.1336665465427825e-05,
      "eval_loss": 1.4083447456359863,
      "eval_runtime": 508.9513,
      "eval_samples_per_second": 26.401,
      "eval_steps_per_second": 13.202,
      "step": 1
    },
    {
      "epoch": 6.267333093085565e-05,
      "grad_norm": 2.738959789276123,
      "learning_rate": 4e-05,
      "loss": 5.5558,
      "step": 2
    },
    {
      "epoch": 9.400999639628348e-05,
      "grad_norm": 2.8455700874328613,
      "learning_rate": 6e-05,
      "loss": 6.0107,
      "step": 3
    },
    {
      "epoch": 9.400999639628348e-05,
      "eval_loss": 1.3986142873764038,
      "eval_runtime": 2417.1682,
      "eval_samples_per_second": 5.559,
      "eval_steps_per_second": 2.78,
      "step": 3
    },
    {
      "epoch": 0.0001253466618617113,
      "grad_norm": 2.9821786880493164,
      "learning_rate": 8e-05,
      "loss": 5.7619,
      "step": 4
    },
    {
      "epoch": 0.00015668332732713913,
      "grad_norm": 2.56919527053833,
      "learning_rate": 0.0001,
      "loss": 5.373,
      "step": 5
    },
    {
      "epoch": 0.00018801999279256695,
      "grad_norm": 3.3672869205474854,
      "learning_rate": 0.00012,
      "loss": 6.0174,
      "step": 6
    },
    {
      "epoch": 0.00018801999279256695,
      "eval_loss": 1.259867548942566,
      "eval_runtime": 2164.2279,
      "eval_samples_per_second": 6.209,
      "eval_steps_per_second": 3.105,
      "step": 6
    },
    {
      "epoch": 0.00021935665825799478,
      "grad_norm": 3.372671127319336,
      "learning_rate": 0.00014,
      "loss": 5.3123,
      "step": 7
    },
    {
      "epoch": 0.0002506933237234226,
      "grad_norm": 4.1703200340271,
      "learning_rate": 0.00016,
      "loss": 4.5542,
      "step": 8
    },
    {
      "epoch": 0.0002820299891888504,
      "grad_norm": 5.527759075164795,
      "learning_rate": 0.00018,
      "loss": 4.0244,
      "step": 9
    },
    {
      "epoch": 0.0002820299891888504,
      "eval_loss": 0.775801420211792,
      "eval_runtime": 597.8751,
      "eval_samples_per_second": 22.475,
      "eval_steps_per_second": 11.238,
      "step": 9
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1465874317836288.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}