trainer_state.json

{
  "best_metric": 0.5498435497283936,
  "best_model_checkpoint": "saves/Mistral-7B/lora/train_1/checkpoint-200",
  "epoch": 0.8750341810226961,
  "eval_steps": 200,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21875854525567404,
      "grad_norm": 0.3536713123321533,
      "learning_rate": 0.00029607910744048336,
      "loss": 0.3412,
      "step": 200
    },
    {
      "epoch": 0.21875854525567404,
      "eval_loss": 0.5498435497283936,
      "eval_runtime": 2920.9291,
      "eval_samples_per_second": 16.132,
      "eval_steps_per_second": 2.016,
      "step": 200
    },
    {
      "epoch": 0.4375170905113481,
      "grad_norm": 0.8507637977600098,
      "learning_rate": 0.0002845214084081106,
      "loss": 0.2411,
      "step": 400
    },
    {
      "epoch": 0.4375170905113481,
      "eval_loss": 0.6299997568130493,
      "eval_runtime": 2923.2178,
      "eval_samples_per_second": 16.119,
      "eval_steps_per_second": 2.015,
      "step": 400
    },
    {
      "epoch": 0.6562756357670222,
      "grad_norm": 0.9282531142234802,
      "learning_rate": 0.0002659311228514304,
      "loss": 0.151,
      "step": 600
    },
    {
      "epoch": 0.6562756357670222,
      "eval_loss": 0.7690626978874207,
      "eval_runtime": 2919.5919,
      "eval_samples_per_second": 16.139,
      "eval_steps_per_second": 2.017,
      "step": 600
    },
    {
      "epoch": 0.8750341810226961,
      "grad_norm": 0.9569716453552246,
      "learning_rate": 0.00024128012426802252,
      "loss": 0.0776,
      "step": 800
    },
    {
      "epoch": 0.8750341810226961,
      "eval_loss": 0.9307376146316528,
      "eval_runtime": 2921.0195,
      "eval_samples_per_second": 16.131,
      "eval_steps_per_second": 2.016,
      "step": 800
    },
    {
      "epoch": 0.8750341810226961,
      "step": 800,
      "total_flos": 1.5356652743578092e+18,
      "train_loss": 0.20272158622741698,
      "train_runtime": 49525.417,
      "train_samples_per_second": 14.177,
      "train_steps_per_second": 0.055
    }
  ],
  "logging_steps": 200,
  "max_steps": 2742,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5356652743578092e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}