last-checkpoint/trainer_state.json

{
  "best_metric": 1.4337732791900635,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0015241869415283786,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.620934707641892e-05,
      "eval_loss": 1.807066559791565,
      "eval_runtime": 576.1883,
      "eval_samples_per_second": 9.589,
      "eval_steps_per_second": 4.795,
      "step": 1
    },
    {
      "epoch": 0.00022862804122925678,
      "grad_norm": 5.381506443023682,
      "learning_rate": 3e-05,
      "loss": 7.1048,
      "step": 3
    },
    {
      "epoch": 0.00038104673538209464,
      "eval_loss": 1.7532647848129272,
      "eval_runtime": 577.68,
      "eval_samples_per_second": 9.564,
      "eval_steps_per_second": 4.783,
      "step": 5
    },
    {
      "epoch": 0.00045725608245851356,
      "grad_norm": 5.005251884460449,
      "learning_rate": 4.980286753286195e-05,
      "loss": 7.1625,
      "step": 6
    },
    {
      "epoch": 0.0006858841236877703,
      "grad_norm": 3.4449706077575684,
      "learning_rate": 4.690766700109659e-05,
      "loss": 6.5864,
      "step": 9
    },
    {
      "epoch": 0.0007620934707641893,
      "eval_loss": 1.5595622062683105,
      "eval_runtime": 579.6011,
      "eval_samples_per_second": 9.532,
      "eval_steps_per_second": 4.767,
      "step": 10
    },
    {
      "epoch": 0.0009145121649170271,
      "grad_norm": 2.1917099952697754,
      "learning_rate": 4.093559974371725e-05,
      "loss": 6.4835,
      "step": 12
    },
    {
      "epoch": 0.0011431402061462838,
      "grad_norm": 1.7847143411636353,
      "learning_rate": 3.272542485937369e-05,
      "loss": 5.2452,
      "step": 15
    },
    {
      "epoch": 0.0011431402061462838,
      "eval_loss": 1.472966194152832,
      "eval_runtime": 576.322,
      "eval_samples_per_second": 9.587,
      "eval_steps_per_second": 4.794,
      "step": 15
    },
    {
      "epoch": 0.0013717682473755406,
      "grad_norm": 1.906245470046997,
      "learning_rate": 2.3430237011767167e-05,
      "loss": 5.4955,
      "step": 18
    },
    {
      "epoch": 0.0015241869415283786,
      "eval_loss": 1.4337732791900635,
      "eval_runtime": 576.6791,
      "eval_samples_per_second": 9.581,
      "eval_steps_per_second": 4.791,
      "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": 3684183016734720.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}