last-checkpoint/trainer_state.json

{
  "best_metric": 2.349881649017334,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.004232132465746178,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002116066232873089,
      "eval_loss": 3.5384063720703125,
      "eval_runtime": 263.0713,
      "eval_samples_per_second": 7.564,
      "eval_steps_per_second": 3.782,
      "step": 1
    },
    {
      "epoch": 0.0006348198698619266,
      "grad_norm": 6.477469444274902,
      "learning_rate": 0.00012,
      "loss": 16.16,
      "step": 3
    },
    {
      "epoch": 0.0010580331164365445,
      "eval_loss": 3.07458758354187,
      "eval_runtime": 265.7045,
      "eval_samples_per_second": 7.49,
      "eval_steps_per_second": 3.745,
      "step": 5
    },
    {
      "epoch": 0.0012696397397238533,
      "grad_norm": 7.566404819488525,
      "learning_rate": 0.0001992114701314478,
      "loss": 14.3284,
      "step": 6
    },
    {
      "epoch": 0.0019044596095857801,
      "grad_norm": 13.658580780029297,
      "learning_rate": 0.00018763066800438636,
      "loss": 11.0626,
      "step": 9
    },
    {
      "epoch": 0.002116066232873089,
      "eval_loss": 2.6848888397216797,
      "eval_runtime": 265.7329,
      "eval_samples_per_second": 7.489,
      "eval_steps_per_second": 3.744,
      "step": 10
    },
    {
      "epoch": 0.0025392794794477066,
      "grad_norm": 7.996623992919922,
      "learning_rate": 0.000163742398974869,
      "loss": 10.4054,
      "step": 12
    },
    {
      "epoch": 0.0031740993493096334,
      "grad_norm": 6.5161848068237305,
      "learning_rate": 0.00013090169943749476,
      "loss": 10.1166,
      "step": 15
    },
    {
      "epoch": 0.0031740993493096334,
      "eval_loss": 2.428469657897949,
      "eval_runtime": 265.7298,
      "eval_samples_per_second": 7.489,
      "eval_steps_per_second": 3.744,
      "step": 15
    },
    {
      "epoch": 0.0038089192191715603,
      "grad_norm": 6.505863189697266,
      "learning_rate": 9.372094804706867e-05,
      "loss": 11.0634,
      "step": 18
    },
    {
      "epoch": 0.004232132465746178,
      "eval_loss": 2.349881649017334,
      "eval_runtime": 265.7323,
      "eval_samples_per_second": 7.489,
      "eval_steps_per_second": 3.744,
      "step": 20
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5777796587520000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}