last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.014017174727771711,
  "eval_steps": 55,
  "global_step": 95,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014754920766075485,
      "eval_loss": NaN,
      "eval_runtime": 631.3294,
      "eval_samples_per_second": 5.652,
      "eval_steps_per_second": 2.826,
      "step": 1
    },
    {
      "epoch": 0.0004426476229822646,
      "grad_norm": NaN,
      "learning_rate": 6e-06,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0008852952459645292,
      "grad_norm": NaN,
      "learning_rate": 1.2e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0013279428689467938,
      "grad_norm": NaN,
      "learning_rate": 1.8e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0017705904919290583,
      "grad_norm": NaN,
      "learning_rate": 2.4e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.002213238114911323,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0026558857378935876,
      "grad_norm": NaN,
      "learning_rate": 3.6e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0030985333608758523,
      "grad_norm": NaN,
      "learning_rate": 4.2e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.0035411809838581166,
      "grad_norm": NaN,
      "learning_rate": 4.8e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.003983828606840381,
      "grad_norm": NaN,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.004426476229822646,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.00486912385280491,
      "grad_norm": NaN,
      "learning_rate": 6.6e-05,
      "loss": 0.0,
      "step": 33
    },
    {
      "epoch": 0.005311771475787175,
      "grad_norm": NaN,
      "learning_rate": 7.2e-05,
      "loss": 0.0,
      "step": 36
    },
    {
      "epoch": 0.00575441909876944,
      "grad_norm": NaN,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.0,
      "step": 39
    },
    {
      "epoch": 0.006197066721751705,
      "grad_norm": NaN,
      "learning_rate": 8.4e-05,
      "loss": 0.0,
      "step": 42
    },
    {
      "epoch": 0.0066397143447339685,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.007082361967716233,
      "grad_norm": NaN,
      "learning_rate": 9.6e-05,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.007525009590698498,
      "grad_norm": NaN,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.0,
      "step": 51
    },
    {
      "epoch": 0.007967657213680762,
      "grad_norm": NaN,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0,
      "step": 54
    },
    {
      "epoch": 0.008115206421341517,
      "eval_loss": NaN,
      "eval_runtime": 630.0862,
      "eval_samples_per_second": 5.663,
      "eval_steps_per_second": 2.831,
      "step": 55
    },
    {
      "epoch": 0.008410304836663027,
      "grad_norm": NaN,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0,
      "step": 57
    },
    {
      "epoch": 0.008852952459645291,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 60
    },
    {
      "epoch": 0.009295600082627557,
      "grad_norm": NaN,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0,
      "step": 63
    },
    {
      "epoch": 0.00973824770560982,
      "grad_norm": NaN,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0,
      "step": 66
    },
    {
      "epoch": 0.010180895328592085,
      "grad_norm": NaN,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0,
      "step": 69
    },
    {
      "epoch": 0.01062354295157435,
      "grad_norm": NaN,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.011066190574556614,
      "grad_norm": NaN,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 75
    },
    {
      "epoch": 0.01150883819753888,
      "grad_norm": NaN,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0,
      "step": 78
    },
    {
      "epoch": 0.011951485820521144,
      "grad_norm": NaN,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0,
      "step": 81
    },
    {
      "epoch": 0.01239413344350341,
      "grad_norm": NaN,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0,
      "step": 84
    },
    {
      "epoch": 0.012836781066485673,
      "grad_norm": NaN,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0,
      "step": 87
    },
    {
      "epoch": 0.013279428689467937,
      "grad_norm": NaN,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 0.013722076312450203,
      "grad_norm": NaN,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0,
      "step": 93
    }
  ],
  "logging_steps": 3,
  "max_steps": 95,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 80,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.47839968690176e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}