last-checkpoint/trainer_state.json

{
  "best_metric": 1.3567347526550293,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.004545454545454545,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00045454545454545455,
      "grad_norm": 0.31628403067588806,
      "learning_rate": 1e-05,
      "loss": 1.362,
      "step": 1
    },
    {
      "epoch": 0.00045454545454545455,
      "eval_loss": 1.3756574392318726,
      "eval_runtime": 83.7745,
      "eval_samples_per_second": 11.065,
      "eval_steps_per_second": 5.539,
      "step": 1
    },
    {
      "epoch": 0.0009090909090909091,
      "grad_norm": 0.2886245548725128,
      "learning_rate": 2e-05,
      "loss": 1.4369,
      "step": 2
    },
    {
      "epoch": 0.0013636363636363637,
      "grad_norm": 0.21225334703922272,
      "learning_rate": 3e-05,
      "loss": 0.8945,
      "step": 3
    },
    {
      "epoch": 0.0018181818181818182,
      "grad_norm": 0.30762138962745667,
      "learning_rate": 4e-05,
      "loss": 1.5411,
      "step": 4
    },
    {
      "epoch": 0.0022727272727272726,
      "grad_norm": 0.2719841003417969,
      "learning_rate": 5e-05,
      "loss": 1.2252,
      "step": 5
    },
    {
      "epoch": 0.0022727272727272726,
      "eval_loss": 1.3746238946914673,
      "eval_runtime": 82.7616,
      "eval_samples_per_second": 11.201,
      "eval_steps_per_second": 5.606,
      "step": 5
    },
    {
      "epoch": 0.0027272727272727275,
      "grad_norm": 0.30843380093574524,
      "learning_rate": 6e-05,
      "loss": 1.4724,
      "step": 6
    },
    {
      "epoch": 0.003181818181818182,
      "grad_norm": 0.2783626914024353,
      "learning_rate": 7e-05,
      "loss": 1.1183,
      "step": 7
    },
    {
      "epoch": 0.0036363636363636364,
      "grad_norm": 0.28724151849746704,
      "learning_rate": 8e-05,
      "loss": 1.5419,
      "step": 8
    },
    {
      "epoch": 0.004090909090909091,
      "grad_norm": 0.2586436867713928,
      "learning_rate": 9e-05,
      "loss": 1.3643,
      "step": 9
    },
    {
      "epoch": 0.004545454545454545,
      "grad_norm": 0.2510312497615814,
      "learning_rate": 0.0001,
      "loss": 1.2918,
      "step": 10
    },
    {
      "epoch": 0.004545454545454545,
      "eval_loss": 1.3567347526550293,
      "eval_runtime": 79.2338,
      "eval_samples_per_second": 11.7,
      "eval_steps_per_second": 5.856,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 543199583010816.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}