last-checkpoint/trainer_state.json

{
  "best_metric": 0.7517985105514526,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0005684078895015062,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.894692965005021e-05,
      "eval_loss": 1.1155023574829102,
      "eval_runtime": 611.6129,
      "eval_samples_per_second": 36.335,
      "eval_steps_per_second": 18.168,
      "step": 1
    },
    {
      "epoch": 5.684078895015063e-05,
      "grad_norm": 3.5881972312927246,
      "learning_rate": 6e-05,
      "loss": 4.7128,
      "step": 3
    },
    {
      "epoch": 9.473464825025105e-05,
      "eval_loss": 1.0708171129226685,
      "eval_runtime": 610.5335,
      "eval_samples_per_second": 36.399,
      "eval_steps_per_second": 18.2,
      "step": 5
    },
    {
      "epoch": 0.00011368157790030126,
      "grad_norm": 2.9608662128448486,
      "learning_rate": 0.00012,
      "loss": 4.4798,
      "step": 6
    },
    {
      "epoch": 0.0001705223668504519,
      "grad_norm": 1.8586539030075073,
      "learning_rate": 0.00018,
      "loss": 4.169,
      "step": 9
    },
    {
      "epoch": 0.0001894692965005021,
      "eval_loss": 0.9538518190383911,
      "eval_runtime": 610.6021,
      "eval_samples_per_second": 36.395,
      "eval_steps_per_second": 18.198,
      "step": 10
    },
    {
      "epoch": 0.00022736315580060252,
      "grad_norm": 2.8327860832214355,
      "learning_rate": 0.00019510565162951537,
      "loss": 4.0678,
      "step": 12
    },
    {
      "epoch": 0.0002842039447507531,
      "grad_norm": 2.088928699493408,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.6133,
      "step": 15
    },
    {
      "epoch": 0.0002842039447507531,
      "eval_loss": 0.8411197662353516,
      "eval_runtime": 611.4098,
      "eval_samples_per_second": 36.347,
      "eval_steps_per_second": 18.174,
      "step": 15
    },
    {
      "epoch": 0.0003410447337009038,
      "grad_norm": 2.09635329246521,
      "learning_rate": 0.00013090169943749476,
      "loss": 3.3791,
      "step": 18
    },
    {
      "epoch": 0.0003789385930010042,
      "eval_loss": 0.785580575466156,
      "eval_runtime": 611.1393,
      "eval_samples_per_second": 36.363,
      "eval_steps_per_second": 18.182,
      "step": 20
    },
    {
      "epoch": 0.0003978855226510544,
      "grad_norm": 2.369555950164795,
      "learning_rate": 8.435655349597689e-05,
      "loss": 3.2738,
      "step": 21
    },
    {
      "epoch": 0.00045472631160120504,
      "grad_norm": 2.318856716156006,
      "learning_rate": 4.12214747707527e-05,
      "loss": 3.1185,
      "step": 24
    },
    {
      "epoch": 0.0004736732412512552,
      "eval_loss": 0.7574231624603271,
      "eval_runtime": 610.8614,
      "eval_samples_per_second": 36.38,
      "eval_steps_per_second": 18.191,
      "step": 25
    },
    {
      "epoch": 0.0005115671005513556,
      "grad_norm": 1.9150217771530151,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 3.0714,
      "step": 27
    },
    {
      "epoch": 0.0005684078895015062,
      "grad_norm": 2.5222971439361572,
      "learning_rate": 0.0,
      "loss": 3.2386,
      "step": 30
    },
    {
      "epoch": 0.0005684078895015062,
      "eval_loss": 0.7517985105514526,
      "eval_runtime": 610.903,
      "eval_samples_per_second": 36.377,
      "eval_steps_per_second": 18.189,
      "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": 2118560985907200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}