last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00042689434364994664,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.268943436499467e-05,
      "grad_norm": 0.1177913025021553,
      "learning_rate": 2e-05,
      "loss": 0.3328,
      "step": 1
    },
    {
      "epoch": 4.268943436499467e-05,
      "eval_loss": 0.42210280895233154,
      "eval_runtime": 179.241,
      "eval_samples_per_second": 55.032,
      "eval_steps_per_second": 27.516,
      "step": 1
    },
    {
      "epoch": 8.537886872998933e-05,
      "grad_norm": 0.1340344250202179,
      "learning_rate": 4e-05,
      "loss": 0.4383,
      "step": 2
    },
    {
      "epoch": 0.000128068303094984,
      "grad_norm": 0.14472071826457977,
      "learning_rate": 6e-05,
      "loss": 0.4729,
      "step": 3
    },
    {
      "epoch": 0.000128068303094984,
      "eval_loss": 0.42182931303977966,
      "eval_runtime": 178.3396,
      "eval_samples_per_second": 55.31,
      "eval_steps_per_second": 27.655,
      "step": 3
    },
    {
      "epoch": 0.00017075773745997867,
      "grad_norm": 0.1268327683210373,
      "learning_rate": 8e-05,
      "loss": 0.3947,
      "step": 4
    },
    {
      "epoch": 0.00021344717182497332,
      "grad_norm": 0.11968627572059631,
      "learning_rate": 0.0001,
      "loss": 0.2831,
      "step": 5
    },
    {
      "epoch": 0.000256136606189968,
      "grad_norm": 0.11458567529916763,
      "learning_rate": 0.00012,
      "loss": 0.2773,
      "step": 6
    },
    {
      "epoch": 0.000256136606189968,
      "eval_loss": 0.41927647590637207,
      "eval_runtime": 178.1556,
      "eval_samples_per_second": 55.367,
      "eval_steps_per_second": 27.684,
      "step": 6
    },
    {
      "epoch": 0.00029882604055496263,
      "grad_norm": 0.17352427542209625,
      "learning_rate": 0.00014,
      "loss": 0.3429,
      "step": 7
    },
    {
      "epoch": 0.00034151547491995734,
      "grad_norm": 0.21564540266990662,
      "learning_rate": 0.00016,
      "loss": 0.6892,
      "step": 8
    },
    {
      "epoch": 0.000384204909284952,
      "grad_norm": 0.15529322624206543,
      "learning_rate": 0.00018,
      "loss": 0.3492,
      "step": 9
    },
    {
      "epoch": 0.000384204909284952,
      "eval_loss": 0.4086187779903412,
      "eval_runtime": 178.276,
      "eval_samples_per_second": 55.33,
      "eval_steps_per_second": 27.665,
      "step": 9
    },
    {
      "epoch": 0.00042689434364994664,
      "grad_norm": 0.202046200633049,
      "learning_rate": 0.0002,
      "loss": 0.4599,
      "step": 10
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 390082766831616.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}