last-checkpoint/trainer_state.json

{
  "best_metric": 1.38326895236969,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.42406573018817917,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010601643254704478,
      "eval_loss": 2.004267930984497,
      "eval_runtime": 54.6705,
      "eval_samples_per_second": 14.542,
      "eval_steps_per_second": 7.28,
      "step": 1
    },
    {
      "epoch": 0.042406573018817915,
      "grad_norm": 26.655275344848633,
      "learning_rate": 5e-05,
      "loss": 12.9919,
      "step": 40
    },
    {
      "epoch": 0.053008216273522396,
      "eval_loss": 1.7225255966186523,
      "eval_runtime": 54.8128,
      "eval_samples_per_second": 14.504,
      "eval_steps_per_second": 7.261,
      "step": 50
    },
    {
      "epoch": 0.08481314603763583,
      "grad_norm": 23.30101203918457,
      "learning_rate": 0.0001,
      "loss": 11.8,
      "step": 80
    },
    {
      "epoch": 0.10601643254704479,
      "eval_loss": 1.7713738679885864,
      "eval_runtime": 54.7281,
      "eval_samples_per_second": 14.526,
      "eval_steps_per_second": 7.272,
      "step": 100
    },
    {
      "epoch": 0.12721971905645374,
      "grad_norm": 15.772492408752441,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.7626,
      "step": 120
    },
    {
      "epoch": 0.1590246488205672,
      "eval_loss": 1.620514154434204,
      "eval_runtime": 54.6402,
      "eval_samples_per_second": 14.55,
      "eval_steps_per_second": 7.284,
      "step": 150
    },
    {
      "epoch": 0.16962629207527166,
      "grad_norm": 13.623527526855469,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.3132,
      "step": 160
    },
    {
      "epoch": 0.21203286509408958,
      "grad_norm": 36.52813720703125,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.344,
      "step": 200
    },
    {
      "epoch": 0.21203286509408958,
      "eval_loss": 1.6030395030975342,
      "eval_runtime": 54.8289,
      "eval_samples_per_second": 14.5,
      "eval_steps_per_second": 7.259,
      "step": 200
    },
    {
      "epoch": 0.2544394381129075,
      "grad_norm": 21.09881019592285,
      "learning_rate": 5e-05,
      "loss": 11.9366,
      "step": 240
    },
    {
      "epoch": 0.26504108136761195,
      "eval_loss": 1.5612239837646484,
      "eval_runtime": 54.8542,
      "eval_samples_per_second": 14.493,
      "eval_steps_per_second": 7.256,
      "step": 250
    },
    {
      "epoch": 0.29684601113172543,
      "grad_norm": 17.57182502746582,
      "learning_rate": 3.086582838174551e-05,
      "loss": 11.5103,
      "step": 280
    },
    {
      "epoch": 0.3180492976411344,
      "eval_loss": 1.4548931121826172,
      "eval_runtime": 54.8131,
      "eval_samples_per_second": 14.504,
      "eval_steps_per_second": 7.261,
      "step": 300
    },
    {
      "epoch": 0.3392525841505433,
      "grad_norm": 14.403338432312012,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 11.2139,
      "step": 320
    },
    {
      "epoch": 0.37105751391465674,
      "eval_loss": 1.3930524587631226,
      "eval_runtime": 56.2238,
      "eval_samples_per_second": 14.14,
      "eval_steps_per_second": 7.079,
      "step": 350
    },
    {
      "epoch": 0.3816591571693613,
      "grad_norm": 13.651220321655273,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 11.0192,
      "step": 360
    },
    {
      "epoch": 0.42406573018817917,
      "grad_norm": 41.51972961425781,
      "learning_rate": 0.0,
      "loss": 11.2909,
      "step": 400
    },
    {
      "epoch": 0.42406573018817917,
      "eval_loss": 1.38326895236969,
      "eval_runtime": 54.7598,
      "eval_samples_per_second": 14.518,
      "eval_steps_per_second": 7.268,
      "step": 400
    }
  ],
  "logging_steps": 40,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "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": 1.4290924208337715e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}