last-checkpoint/trainer_state.json

{
  "best_metric": 1.1986429691314697,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0005658855873656611,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.8862852912188704e-05,
      "eval_loss": 2.3256702423095703,
      "eval_runtime": 2351.6575,
      "eval_samples_per_second": 9.492,
      "eval_steps_per_second": 4.746,
      "step": 1
    },
    {
      "epoch": 5.658855873656611e-05,
      "grad_norm": 3.7873220443725586,
      "learning_rate": 6e-05,
      "loss": 9.49,
      "step": 3
    },
    {
      "epoch": 9.431426456094352e-05,
      "eval_loss": 2.1790850162506104,
      "eval_runtime": 2360.0183,
      "eval_samples_per_second": 9.458,
      "eval_steps_per_second": 4.729,
      "step": 5
    },
    {
      "epoch": 0.00011317711747313222,
      "grad_norm": 3.8151333332061768,
      "learning_rate": 0.00012,
      "loss": 10.5024,
      "step": 6
    },
    {
      "epoch": 0.00016976567620969834,
      "grad_norm": 3.9081547260284424,
      "learning_rate": 0.00018,
      "loss": 8.0328,
      "step": 9
    },
    {
      "epoch": 0.00018862852912188705,
      "eval_loss": 1.6334725618362427,
      "eval_runtime": 2359.8748,
      "eval_samples_per_second": 9.459,
      "eval_steps_per_second": 4.729,
      "step": 10
    },
    {
      "epoch": 0.00022635423494626444,
      "grad_norm": 3.5249745845794678,
      "learning_rate": 0.00019510565162951537,
      "loss": 6.4489,
      "step": 12
    },
    {
      "epoch": 0.00028294279368283056,
      "grad_norm": 325.7086486816406,
      "learning_rate": 0.00017071067811865476,
      "loss": 5.6484,
      "step": 15
    },
    {
      "epoch": 0.00028294279368283056,
      "eval_loss": 1.4027833938598633,
      "eval_runtime": 2359.2465,
      "eval_samples_per_second": 9.461,
      "eval_steps_per_second": 4.731,
      "step": 15
    },
    {
      "epoch": 0.0003395313524193967,
      "grad_norm": 8.564092636108398,
      "learning_rate": 0.00013090169943749476,
      "loss": 5.9477,
      "step": 18
    },
    {
      "epoch": 0.0003772570582437741,
      "eval_loss": 1.2646969556808472,
      "eval_runtime": 2361.1534,
      "eval_samples_per_second": 9.454,
      "eval_steps_per_second": 4.727,
      "step": 20
    },
    {
      "epoch": 0.0003961199111559628,
      "grad_norm": 3.294726610183716,
      "learning_rate": 8.435655349597689e-05,
      "loss": 4.8713,
      "step": 21
    },
    {
      "epoch": 0.0004527084698925289,
      "grad_norm": 3.5907199382781982,
      "learning_rate": 4.12214747707527e-05,
      "loss": 5.0274,
      "step": 24
    },
    {
      "epoch": 0.0004715713228047176,
      "eval_loss": 1.2100105285644531,
      "eval_runtime": 2361.223,
      "eval_samples_per_second": 9.454,
      "eval_steps_per_second": 4.727,
      "step": 25
    },
    {
      "epoch": 0.000509297028629095,
      "grad_norm": 3.3346734046936035,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 5.081,
      "step": 27
    },
    {
      "epoch": 0.0005658855873656611,
      "grad_norm": 3.953141927719116,
      "learning_rate": 0.0,
      "loss": 5.0118,
      "step": 30
    },
    {
      "epoch": 0.0005658855873656611,
      "eval_loss": 1.1986429691314697,
      "eval_runtime": 2361.282,
      "eval_samples_per_second": 9.453,
      "eval_steps_per_second": 4.727,
      "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": 9533364369408000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}