last-checkpoint/trainer_state.json

{
  "best_metric": 1.7032551765441895,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.04095339503644852,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.190679007289704e-05,
      "eval_loss": 4.057403087615967,
      "eval_runtime": 2241.2696,
      "eval_samples_per_second": 9.175,
      "eval_steps_per_second": 2.294,
      "step": 1
    },
    {
      "epoch": 0.004095339503644852,
      "grad_norm": 3.7699906826019287,
      "learning_rate": 0.000107,
      "loss": 2.3342,
      "step": 50
    },
    {
      "epoch": 0.008190679007289705,
      "grad_norm": 3.0266530513763428,
      "learning_rate": 0.000214,
      "loss": 1.7833,
      "step": 100
    },
    {
      "epoch": 0.012286018510934556,
      "grad_norm": 3.03035831451416,
      "learning_rate": 0.0002058551099787077,
      "loss": 1.8136,
      "step": 150
    },
    {
      "epoch": 0.01638135801457941,
      "grad_norm": 3.3899314403533936,
      "learning_rate": 0.00018266042558696057,
      "loss": 1.8081,
      "step": 200
    },
    {
      "epoch": 0.02047669751822426,
      "grad_norm": 2.7412288188934326,
      "learning_rate": 0.00014794712726306461,
      "loss": 1.7714,
      "step": 250
    },
    {
      "epoch": 0.024572037021869112,
      "grad_norm": 2.9588828086853027,
      "learning_rate": 0.000107,
      "loss": 1.7647,
      "step": 300
    },
    {
      "epoch": 0.028667376525513964,
      "grad_norm": 3.1882612705230713,
      "learning_rate": 6.60528727369354e-05,
      "loss": 1.7318,
      "step": 350
    },
    {
      "epoch": 0.03276271602915882,
      "grad_norm": 2.568800687789917,
      "learning_rate": 3.1339574413039424e-05,
      "loss": 1.6906,
      "step": 400
    },
    {
      "epoch": 0.03685805553280367,
      "grad_norm": 2.665541887283325,
      "learning_rate": 8.14489002129232e-06,
      "loss": 1.728,
      "step": 450
    },
    {
      "epoch": 0.04095339503644852,
      "grad_norm": 2.430924654006958,
      "learning_rate": 0.0,
      "loss": 1.6905,
      "step": 500
    },
    {
      "epoch": 0.04095339503644852,
      "eval_loss": 1.7032551765441895,
      "eval_runtime": 2238.9494,
      "eval_samples_per_second": 9.184,
      "eval_steps_per_second": 2.296,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "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": 7.54256789372928e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}