last-checkpoint/trainer_state.json

{
  "best_metric": 1.1903597116470337,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0010412147505422993,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.470715835140998e-05,
      "eval_loss": 1.3499997854232788,
      "eval_runtime": 1831.1632,
      "eval_samples_per_second": 6.625,
      "eval_steps_per_second": 3.313,
      "step": 1
    },
    {
      "epoch": 0.00010412147505422994,
      "grad_norm": 3.2817139625549316,
      "learning_rate": 3e-05,
      "loss": 5.6987,
      "step": 3
    },
    {
      "epoch": 0.0001735357917570499,
      "eval_loss": 1.3320451974868774,
      "eval_runtime": 1837.8637,
      "eval_samples_per_second": 6.601,
      "eval_steps_per_second": 3.301,
      "step": 5
    },
    {
      "epoch": 0.00020824295010845987,
      "grad_norm": 2.2102863788604736,
      "learning_rate": 6e-05,
      "loss": 5.5276,
      "step": 6
    },
    {
      "epoch": 0.0003123644251626898,
      "grad_norm": 4.29848575592041,
      "learning_rate": 9e-05,
      "loss": 5.1643,
      "step": 9
    },
    {
      "epoch": 0.0003470715835140998,
      "eval_loss": 1.2517874240875244,
      "eval_runtime": 2333.7955,
      "eval_samples_per_second": 5.198,
      "eval_steps_per_second": 2.599,
      "step": 10
    },
    {
      "epoch": 0.00041648590021691975,
      "grad_norm": 3.965546131134033,
      "learning_rate": 9.755282581475769e-05,
      "loss": 5.3549,
      "step": 12
    },
    {
      "epoch": 0.0005206073752711496,
      "grad_norm": 2.184412956237793,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.4727,
      "step": 15
    },
    {
      "epoch": 0.0005206073752711496,
      "eval_loss": 1.2216558456420898,
      "eval_runtime": 1479.7059,
      "eval_samples_per_second": 8.199,
      "eval_steps_per_second": 4.099,
      "step": 15
    },
    {
      "epoch": 0.0006247288503253796,
      "grad_norm": 2.2891042232513428,
      "learning_rate": 6.545084971874738e-05,
      "loss": 5.0955,
      "step": 18
    },
    {
      "epoch": 0.0006941431670281996,
      "eval_loss": 1.1996384859085083,
      "eval_runtime": 1103.7842,
      "eval_samples_per_second": 10.991,
      "eval_steps_per_second": 5.496,
      "step": 20
    },
    {
      "epoch": 0.0007288503253796095,
      "grad_norm": 2.0232975482940674,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 4.4981,
      "step": 21
    },
    {
      "epoch": 0.0008329718004338395,
      "grad_norm": 2.182401418685913,
      "learning_rate": 2.061073738537635e-05,
      "loss": 4.6256,
      "step": 24
    },
    {
      "epoch": 0.0008676789587852494,
      "eval_loss": 1.1918320655822754,
      "eval_runtime": 1104.7539,
      "eval_samples_per_second": 10.982,
      "eval_steps_per_second": 5.491,
      "step": 25
    },
    {
      "epoch": 0.0009370932754880694,
      "grad_norm": 2.29049015045166,
      "learning_rate": 5.449673790581611e-06,
      "loss": 4.8211,
      "step": 27
    },
    {
      "epoch": 0.0010412147505422993,
      "grad_norm": 4.216933727264404,
      "learning_rate": 0.0,
      "loss": 5.218,
      "step": 30
    },
    {
      "epoch": 0.0010412147505422993,
      "eval_loss": 1.1903597116470337,
      "eval_runtime": 1104.119,
      "eval_samples_per_second": 10.988,
      "eval_steps_per_second": 5.494,
      "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": 6063618313420800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}