last-checkpoint/trainer_state.json

{
  "best_metric": 1.1476502418518066,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.00404122044857547,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000134707348285849,
      "eval_loss": 1.244446039199829,
      "eval_runtime": 2233.2353,
      "eval_samples_per_second": 1.4,
      "eval_steps_per_second": 0.7,
      "step": 1
    },
    {
      "epoch": 0.00040412204485754696,
      "grad_norm": 0.585106611251831,
      "learning_rate": 3e-05,
      "loss": 4.7745,
      "step": 3
    },
    {
      "epoch": 0.000673536741429245,
      "eval_loss": 1.2407771348953247,
      "eval_runtime": 1121.6196,
      "eval_samples_per_second": 2.787,
      "eval_steps_per_second": 1.394,
      "step": 5
    },
    {
      "epoch": 0.0008082440897150939,
      "grad_norm": 0.6482850313186646,
      "learning_rate": 6e-05,
      "loss": 4.896,
      "step": 6
    },
    {
      "epoch": 0.0012123661345726409,
      "grad_norm": 0.716135561466217,
      "learning_rate": 9e-05,
      "loss": 4.8981,
      "step": 9
    },
    {
      "epoch": 0.00134707348285849,
      "eval_loss": 1.2191153764724731,
      "eval_runtime": 1120.8615,
      "eval_samples_per_second": 2.789,
      "eval_steps_per_second": 1.394,
      "step": 10
    },
    {
      "epoch": 0.0016164881794301878,
      "grad_norm": 0.7936702966690063,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.7597,
      "step": 12
    },
    {
      "epoch": 0.002020610224287735,
      "grad_norm": 1.5666340589523315,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.6971,
      "step": 15
    },
    {
      "epoch": 0.002020610224287735,
      "eval_loss": 1.1779574155807495,
      "eval_runtime": 1121.3367,
      "eval_samples_per_second": 2.788,
      "eval_steps_per_second": 1.394,
      "step": 15
    },
    {
      "epoch": 0.0024247322691452818,
      "grad_norm": 0.8135265111923218,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.4632,
      "step": 18
    },
    {
      "epoch": 0.00269414696571698,
      "eval_loss": 1.157989501953125,
      "eval_runtime": 1121.0708,
      "eval_samples_per_second": 2.788,
      "eval_steps_per_second": 1.394,
      "step": 20
    },
    {
      "epoch": 0.002828854314002829,
      "grad_norm": 1.841718077659607,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 4.2348,
      "step": 21
    },
    {
      "epoch": 0.0032329763588603757,
      "grad_norm": 0.9845360517501831,
      "learning_rate": 2.061073738537635e-05,
      "loss": 4.7971,
      "step": 24
    },
    {
      "epoch": 0.0033676837071462246,
      "eval_loss": 1.1491330862045288,
      "eval_runtime": 1121.0419,
      "eval_samples_per_second": 2.788,
      "eval_steps_per_second": 1.394,
      "step": 25
    },
    {
      "epoch": 0.003637098403717923,
      "grad_norm": 1.054880142211914,
      "learning_rate": 5.449673790581611e-06,
      "loss": 4.7465,
      "step": 27
    },
    {
      "epoch": 0.00404122044857547,
      "grad_norm": 0.9601097702980042,
      "learning_rate": 0.0,
      "loss": 4.8153,
      "step": 30
    },
    {
      "epoch": 0.00404122044857547,
      "eval_loss": 1.1476502418518066,
      "eval_runtime": 1121.3989,
      "eval_samples_per_second": 2.788,
      "eval_steps_per_second": 1.394,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.76106539548672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}