last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004276245456489203,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014254151521630675,
      "eval_loss": 2.955134868621826,
      "eval_runtime": 93.1906,
      "eval_samples_per_second": 31.698,
      "eval_steps_per_second": 15.849,
      "step": 1
    },
    {
      "epoch": 0.00042762454564892024,
      "grad_norm": 7.354737281799316,
      "learning_rate": 6e-05,
      "loss": 12.2222,
      "step": 3
    },
    {
      "epoch": 0.0007127075760815337,
      "eval_loss": 2.8305256366729736,
      "eval_runtime": 113.5607,
      "eval_samples_per_second": 26.013,
      "eval_steps_per_second": 13.006,
      "step": 5
    },
    {
      "epoch": 0.0008552490912978405,
      "grad_norm": 9.722517013549805,
      "learning_rate": 0.00012,
      "loss": 11.2221,
      "step": 6
    },
    {
      "epoch": 0.0012828736369467607,
      "grad_norm": 3.4644076824188232,
      "learning_rate": 0.00018,
      "loss": 9.67,
      "step": 9
    },
    {
      "epoch": 0.0014254151521630675,
      "eval_loss": 2.532275676727295,
      "eval_runtime": 204.5424,
      "eval_samples_per_second": 14.442,
      "eval_steps_per_second": 7.221,
      "step": 10
    },
    {
      "epoch": 0.001710498182595681,
      "grad_norm": 4.4212164878845215,
      "learning_rate": 0.00019510565162951537,
      "loss": 9.4872,
      "step": 12
    },
    {
      "epoch": 0.0021381227282446015,
      "grad_norm": 5.554760932922363,
      "learning_rate": 0.00017071067811865476,
      "loss": 8.319,
      "step": 15
    },
    {
      "epoch": 0.0021381227282446015,
      "eval_loss": 2.215949535369873,
      "eval_runtime": 205.1547,
      "eval_samples_per_second": 14.399,
      "eval_steps_per_second": 7.199,
      "step": 15
    },
    {
      "epoch": 0.0025657472738935213,
      "grad_norm": 6.3015546798706055,
      "learning_rate": 0.00013090169943749476,
      "loss": 8.5909,
      "step": 18
    },
    {
      "epoch": 0.002850830304326135,
      "eval_loss": 2.092536211013794,
      "eval_runtime": 204.734,
      "eval_samples_per_second": 14.428,
      "eval_steps_per_second": 7.214,
      "step": 20
    },
    {
      "epoch": 0.0029933718195424416,
      "grad_norm": 3.86482572555542,
      "learning_rate": 8.435655349597689e-05,
      "loss": 8.2771,
      "step": 21
    },
    {
      "epoch": 0.003420996365191362,
      "grad_norm": 3.8096251487731934,
      "learning_rate": 4.12214747707527e-05,
      "loss": 8.6305,
      "step": 24
    },
    {
      "epoch": 0.003563537880407669,
      "eval_loss": 2.031748056411743,
      "eval_runtime": 205.1472,
      "eval_samples_per_second": 14.399,
      "eval_steps_per_second": 7.2,
      "step": 25
    },
    {
      "epoch": 0.003848620910840282,
      "grad_norm": 4.132391452789307,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 7.9521,
      "step": 27
    },
    {
      "epoch": 0.004276245456489203,
      "grad_norm": 3.2936885356903076,
      "learning_rate": 0.0,
      "loss": 8.5835,
      "step": 30
    },
    {
      "epoch": 0.004276245456489203,
      "eval_loss": 2.0245609283447266,
      "eval_runtime": 203.5227,
      "eval_samples_per_second": 14.514,
      "eval_steps_per_second": 7.257,
      "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": 515730680315904.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}