last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.013770943309616708,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004590314436538903,
      "eval_loss": 11.07474422454834,
      "eval_runtime": 2.5632,
      "eval_samples_per_second": 358.146,
      "eval_steps_per_second": 179.073,
      "step": 1
    },
    {
      "epoch": 0.001377094330961671,
      "grad_norm": 1.4334861040115356,
      "learning_rate": 6e-05,
      "loss": 44.2871,
      "step": 3
    },
    {
      "epoch": 0.0022951572182694515,
      "eval_loss": 11.072781562805176,
      "eval_runtime": 2.6631,
      "eval_samples_per_second": 344.709,
      "eval_steps_per_second": 172.355,
      "step": 5
    },
    {
      "epoch": 0.002754188661923342,
      "grad_norm": 1.4296221733093262,
      "learning_rate": 0.00012,
      "loss": 44.2959,
      "step": 6
    },
    {
      "epoch": 0.004131282992885013,
      "grad_norm": 1.5644625425338745,
      "learning_rate": 0.00018,
      "loss": 44.3045,
      "step": 9
    },
    {
      "epoch": 0.004590314436538903,
      "eval_loss": 11.06622314453125,
      "eval_runtime": 2.6927,
      "eval_samples_per_second": 340.923,
      "eval_steps_per_second": 170.461,
      "step": 10
    },
    {
      "epoch": 0.005508377323846684,
      "grad_norm": 1.4708709716796875,
      "learning_rate": 0.00019510565162951537,
      "loss": 44.2587,
      "step": 12
    },
    {
      "epoch": 0.006885471654808354,
      "grad_norm": 1.4738435745239258,
      "learning_rate": 0.00017071067811865476,
      "loss": 44.2408,
      "step": 15
    },
    {
      "epoch": 0.006885471654808354,
      "eval_loss": 11.058080673217773,
      "eval_runtime": 2.7188,
      "eval_samples_per_second": 337.648,
      "eval_steps_per_second": 168.824,
      "step": 15
    },
    {
      "epoch": 0.008262565985770026,
      "grad_norm": 1.3765307664871216,
      "learning_rate": 0.00013090169943749476,
      "loss": 44.2229,
      "step": 18
    },
    {
      "epoch": 0.009180628873077806,
      "eval_loss": 11.050945281982422,
      "eval_runtime": 2.5585,
      "eval_samples_per_second": 358.808,
      "eval_steps_per_second": 179.404,
      "step": 20
    },
    {
      "epoch": 0.009639660316731696,
      "grad_norm": 1.4532055854797363,
      "learning_rate": 8.435655349597689e-05,
      "loss": 44.1706,
      "step": 21
    },
    {
      "epoch": 0.011016754647693368,
      "grad_norm": 1.2766399383544922,
      "learning_rate": 4.12214747707527e-05,
      "loss": 44.215,
      "step": 24
    },
    {
      "epoch": 0.011475786091347258,
      "eval_loss": 11.048693656921387,
      "eval_runtime": 2.7201,
      "eval_samples_per_second": 337.49,
      "eval_steps_per_second": 168.745,
      "step": 25
    },
    {
      "epoch": 0.012393848978655038,
      "grad_norm": 1.5444846153259277,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 44.1775,
      "step": 27
    },
    {
      "epoch": 0.013770943309616708,
      "grad_norm": 1.5085878372192383,
      "learning_rate": 0.0,
      "loss": 44.2091,
      "step": 30
    },
    {
      "epoch": 0.013770943309616708,
      "eval_loss": 11.04821491241455,
      "eval_runtime": 2.6777,
      "eval_samples_per_second": 342.83,
      "eval_steps_per_second": 171.415,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 56151244800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}