{
  "best_global_step": 134,
  "best_metric": 1.0328843593597412,
  "best_model_checkpoint": "./mistral-mts-summary_1\\checkpoint-134",
  "epoch": 1.988929889298893,
  "eval_steps": 500,
  "global_step": 134,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7380073800738007,
      "grad_norm": 0.9010652899742126,
      "learning_rate": 0.0002253731343283582,
      "loss": 1.398,
      "step": 50
    },
    {
      "epoch": 0.988929889298893,
      "eval_loss": 1.150829553604126,
      "eval_runtime": 31.503,
      "eval_samples_per_second": 3.809,
      "eval_steps_per_second": 3.809,
      "step": 67
    },
    {
      "epoch": 1.4870848708487086,
      "grad_norm": 1.3859751224517822,
      "learning_rate": 0.00015074626865671642,
      "loss": 1.2572,
      "step": 100
    },
    {
      "epoch": 1.988929889298893,
      "eval_loss": 1.0328843593597412,
      "eval_runtime": 31.5091,
      "eval_samples_per_second": 3.808,
      "eval_steps_per_second": 3.808,
      "step": 134
    }
  ],
  "logging_steps": 50,
  "max_steps": 201,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.703073202706842e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}