trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.963855421686747,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0963855421686747,
      "grad_norm": 0.5874277949333191,
      "learning_rate": 0.0001,
      "loss": 3.0129,
      "step": 10
    },
    {
      "epoch": 0.1927710843373494,
      "grad_norm": 0.5504733920097351,
      "learning_rate": 0.0001,
      "loss": 1.3638,
      "step": 20
    },
    {
      "epoch": 0.2891566265060241,
      "grad_norm": 0.28183117508888245,
      "learning_rate": 0.0001,
      "loss": 0.5456,
      "step": 30
    },
    {
      "epoch": 0.3855421686746988,
      "grad_norm": 0.22062893211841583,
      "learning_rate": 0.0001,
      "loss": 0.4025,
      "step": 40
    },
    {
      "epoch": 0.4819277108433735,
      "grad_norm": 0.19783374667167664,
      "learning_rate": 0.0001,
      "loss": 0.3357,
      "step": 50
    },
    {
      "epoch": 0.5783132530120482,
      "grad_norm": 0.2082074135541916,
      "learning_rate": 0.0001,
      "loss": 0.3078,
      "step": 60
    },
    {
      "epoch": 0.6746987951807228,
      "grad_norm": 0.21820276975631714,
      "learning_rate": 0.0001,
      "loss": 0.287,
      "step": 70
    },
    {
      "epoch": 0.7710843373493976,
      "grad_norm": 0.18571995198726654,
      "learning_rate": 0.0001,
      "loss": 0.2769,
      "step": 80
    },
    {
      "epoch": 0.8674698795180723,
      "grad_norm": 0.1946105808019638,
      "learning_rate": 0.0001,
      "loss": 0.2721,
      "step": 90
    },
    {
      "epoch": 0.963855421686747,
      "grad_norm": 0.16163858771324158,
      "learning_rate": 0.0001,
      "loss": 0.2676,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 309,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5158452580270080.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}