last-checkpoint/trainer_state.json

{
  "best_metric": 11.761639595031738,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.02852388875683385,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009507962918944616,
      "eval_loss": 11.763189315795898,
      "eval_runtime": 9.3719,
      "eval_samples_per_second": 47.269,
      "eval_steps_per_second": 23.688,
      "step": 1
    },
    {
      "epoch": 0.0028523888756833847,
      "grad_norm": 0.0472789965569973,
      "learning_rate": 6e-05,
      "loss": 11.7618,
      "step": 3
    },
    {
      "epoch": 0.004753981459472308,
      "eval_loss": 11.762984275817871,
      "eval_runtime": 10.0648,
      "eval_samples_per_second": 44.015,
      "eval_steps_per_second": 22.057,
      "step": 5
    },
    {
      "epoch": 0.0057047777513667694,
      "grad_norm": 0.05081987753510475,
      "learning_rate": 9.96057350657239e-05,
      "loss": 11.7597,
      "step": 6
    },
    {
      "epoch": 0.008557166627050155,
      "grad_norm": 0.04358455166220665,
      "learning_rate": 9.381533400219318e-05,
      "loss": 11.7614,
      "step": 9
    },
    {
      "epoch": 0.009507962918944617,
      "eval_loss": 11.76247787475586,
      "eval_runtime": 9.8069,
      "eval_samples_per_second": 45.172,
      "eval_steps_per_second": 22.637,
      "step": 10
    },
    {
      "epoch": 0.011409555502733539,
      "grad_norm": 0.04291345179080963,
      "learning_rate": 8.18711994874345e-05,
      "loss": 11.761,
      "step": 12
    },
    {
      "epoch": 0.014261944378416925,
      "grad_norm": 0.0457707941532135,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.762,
      "step": 15
    },
    {
      "epoch": 0.014261944378416925,
      "eval_loss": 11.762060165405273,
      "eval_runtime": 9.392,
      "eval_samples_per_second": 47.168,
      "eval_steps_per_second": 23.637,
      "step": 15
    },
    {
      "epoch": 0.01711433325410031,
      "grad_norm": 0.04285963624715805,
      "learning_rate": 4.6860474023534335e-05,
      "loss": 11.7608,
      "step": 18
    },
    {
      "epoch": 0.019015925837889233,
      "eval_loss": 11.761784553527832,
      "eval_runtime": 9.8536,
      "eval_samples_per_second": 44.958,
      "eval_steps_per_second": 22.53,
      "step": 20
    },
    {
      "epoch": 0.019966722129783693,
      "grad_norm": 0.046757008880376816,
      "learning_rate": 2.8711035421746367e-05,
      "loss": 11.761,
      "step": 21
    },
    {
      "epoch": 0.022819111005467078,
      "grad_norm": 0.053075361996889114,
      "learning_rate": 1.3551568628929434e-05,
      "loss": 11.7616,
      "step": 24
    },
    {
      "epoch": 0.02376990729736154,
      "eval_loss": 11.761663436889648,
      "eval_runtime": 9.3829,
      "eval_samples_per_second": 47.214,
      "eval_steps_per_second": 23.66,
      "step": 25
    },
    {
      "epoch": 0.025671499881150462,
      "grad_norm": 0.04611106216907501,
      "learning_rate": 3.511175705587433e-06,
      "loss": 11.7612,
      "step": 27
    },
    {
      "epoch": 0.02852388875683385,
      "grad_norm": 0.0431927815079689,
      "learning_rate": 0.0,
      "loss": 11.7593,
      "step": 30
    },
    {
      "epoch": 0.02852388875683385,
      "eval_loss": 11.761639595031738,
      "eval_runtime": 9.8419,
      "eval_samples_per_second": 45.012,
      "eval_steps_per_second": 22.557,
      "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": 6111001313280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}