last-checkpoint/trainer_state.json

{
  "best_metric": 2.205273389816284,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.005196154845414394,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001732051615138131,
      "eval_loss": 6.304304599761963,
      "eval_runtime": 591.6269,
      "eval_samples_per_second": 4.109,
      "eval_steps_per_second": 2.055,
      "step": 1
    },
    {
      "epoch": 0.0005196154845414394,
      "grad_norm": 10.378375053405762,
      "learning_rate": 3e-05,
      "loss": 4.644,
      "step": 3
    },
    {
      "epoch": 0.0008660258075690655,
      "eval_loss": 5.5202250480651855,
      "eval_runtime": 620.0845,
      "eval_samples_per_second": 3.92,
      "eval_steps_per_second": 1.961,
      "step": 5
    },
    {
      "epoch": 0.0010392309690828788,
      "grad_norm": 7.568704605102539,
      "learning_rate": 6e-05,
      "loss": 4.6156,
      "step": 6
    },
    {
      "epoch": 0.001558846453624318,
      "grad_norm": 13.759147644042969,
      "learning_rate": 9e-05,
      "loss": 4.5151,
      "step": 9
    },
    {
      "epoch": 0.001732051615138131,
      "eval_loss": 3.928494930267334,
      "eval_runtime": 618.5461,
      "eval_samples_per_second": 3.93,
      "eval_steps_per_second": 1.966,
      "step": 10
    },
    {
      "epoch": 0.0020784619381657575,
      "grad_norm": 10.802489280700684,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.1631,
      "step": 12
    },
    {
      "epoch": 0.002598077422707197,
      "grad_norm": 2.1900992393493652,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.2454,
      "step": 15
    },
    {
      "epoch": 0.002598077422707197,
      "eval_loss": 2.272615671157837,
      "eval_runtime": 619.4784,
      "eval_samples_per_second": 3.924,
      "eval_steps_per_second": 1.963,
      "step": 15
    },
    {
      "epoch": 0.003117692907248636,
      "grad_norm": 2.057917594909668,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.3091,
      "step": 18
    },
    {
      "epoch": 0.003464103230276262,
      "eval_loss": 2.2350587844848633,
      "eval_runtime": 618.5987,
      "eval_samples_per_second": 3.93,
      "eval_steps_per_second": 1.966,
      "step": 20
    },
    {
      "epoch": 0.0036373083917900753,
      "grad_norm": 1.9875291585922241,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 2.0286,
      "step": 21
    },
    {
      "epoch": 0.004156923876331515,
      "grad_norm": 1.7483538389205933,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.3018,
      "step": 24
    },
    {
      "epoch": 0.004330129037845328,
      "eval_loss": 2.2109057903289795,
      "eval_runtime": 617.9201,
      "eval_samples_per_second": 3.934,
      "eval_steps_per_second": 1.968,
      "step": 25
    },
    {
      "epoch": 0.004676539360872954,
      "grad_norm": 3.080596446990967,
      "learning_rate": 5.449673790581611e-06,
      "loss": 2.1834,
      "step": 27
    },
    {
      "epoch": 0.005196154845414394,
      "grad_norm": 1.67843496799469,
      "learning_rate": 0.0,
      "loss": 1.9795,
      "step": 30
    },
    {
      "epoch": 0.005196154845414394,
      "eval_loss": 2.205273389816284,
      "eval_runtime": 617.5665,
      "eval_samples_per_second": 3.936,
      "eval_steps_per_second": 1.969,
      "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": 1,
        "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": 1.150341542313984e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}