last-checkpoint/trainer_state.json

{
  "best_metric": 0.42227837443351746,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.1932367149758454,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00644122383252818,
      "eval_loss": 0.7935686111450195,
      "eval_runtime": 17.9516,
      "eval_samples_per_second": 7.297,
      "eval_steps_per_second": 1.838,
      "step": 1
    },
    {
      "epoch": 0.01932367149758454,
      "grad_norm": 3.8606717586517334,
      "learning_rate": 0.00012,
      "loss": 2.5727,
      "step": 3
    },
    {
      "epoch": 0.0322061191626409,
      "eval_loss": 0.6005560755729675,
      "eval_runtime": 18.3329,
      "eval_samples_per_second": 7.146,
      "eval_steps_per_second": 1.8,
      "step": 5
    },
    {
      "epoch": 0.03864734299516908,
      "grad_norm": 3.344679832458496,
      "learning_rate": 0.0001992114701314478,
      "loss": 2.2323,
      "step": 6
    },
    {
      "epoch": 0.057971014492753624,
      "grad_norm": 2.2544925212860107,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.8731,
      "step": 9
    },
    {
      "epoch": 0.0644122383252818,
      "eval_loss": 0.4851234257221222,
      "eval_runtime": 18.4273,
      "eval_samples_per_second": 7.109,
      "eval_steps_per_second": 1.791,
      "step": 10
    },
    {
      "epoch": 0.07729468599033816,
      "grad_norm": 2.36488676071167,
      "learning_rate": 0.000163742398974869,
      "loss": 1.8343,
      "step": 12
    },
    {
      "epoch": 0.0966183574879227,
      "grad_norm": 2.3981118202209473,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.6867,
      "step": 15
    },
    {
      "epoch": 0.0966183574879227,
      "eval_loss": 0.45439934730529785,
      "eval_runtime": 18.4591,
      "eval_samples_per_second": 7.097,
      "eval_steps_per_second": 1.788,
      "step": 15
    },
    {
      "epoch": 0.11594202898550725,
      "grad_norm": 2.452791690826416,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.6576,
      "step": 18
    },
    {
      "epoch": 0.1288244766505636,
      "eval_loss": 0.43519601225852966,
      "eval_runtime": 18.4367,
      "eval_samples_per_second": 7.105,
      "eval_steps_per_second": 1.79,
      "step": 20
    },
    {
      "epoch": 0.13526570048309178,
      "grad_norm": 2.4589295387268066,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 1.6213,
      "step": 21
    },
    {
      "epoch": 0.15458937198067632,
      "grad_norm": 2.756551504135132,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 1.6837,
      "step": 24
    },
    {
      "epoch": 0.1610305958132045,
      "eval_loss": 0.42500385642051697,
      "eval_runtime": 18.4295,
      "eval_samples_per_second": 7.108,
      "eval_steps_per_second": 1.791,
      "step": 25
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 2.4348251819610596,
      "learning_rate": 7.022351411174866e-06,
      "loss": 1.6359,
      "step": 27
    },
    {
      "epoch": 0.1932367149758454,
      "grad_norm": 2.640720844268799,
      "learning_rate": 0.0,
      "loss": 1.6826,
      "step": 30
    },
    {
      "epoch": 0.1932367149758454,
      "eval_loss": 0.42227837443351746,
      "eval_runtime": 18.4184,
      "eval_samples_per_second": 7.112,
      "eval_steps_per_second": 1.792,
      "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": 2.1269667335110656e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}