last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 249,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.20080321285140562,
      "grad_norm": 0.10567375272512436,
      "learning_rate": 0.0002,
      "loss": 0.9058,
      "step": 50
    },
    {
      "epoch": 0.40160642570281124,
      "grad_norm": 0.15347909927368164,
      "learning_rate": 0.0002,
      "loss": 0.7477,
      "step": 100
    },
    {
      "epoch": 0.6024096385542169,
      "grad_norm": 0.15224330127239227,
      "learning_rate": 0.0002,
      "loss": 0.7067,
      "step": 150
    },
    {
      "epoch": 0.8032128514056225,
      "grad_norm": 0.17291581630706787,
      "learning_rate": 0.0002,
      "loss": 0.7172,
      "step": 200
    }
  ],
  "logging_steps": 50,
  "max_steps": 249,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.750937083720499e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}