last-checkpoint/trainer_state.json

{
  "best_metric": 0.5702555179595947,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.06359300476947535,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0021197668256491787,
      "eval_loss": 1.1466405391693115,
      "eval_runtime": 57.3747,
      "eval_samples_per_second": 6.937,
      "eval_steps_per_second": 1.743,
      "step": 1
    },
    {
      "epoch": 0.006359300476947536,
      "grad_norm": 0.8094033002853394,
      "learning_rate": 0.00012,
      "loss": 4.3741,
      "step": 3
    },
    {
      "epoch": 0.010598834128245893,
      "eval_loss": 1.0699783563613892,
      "eval_runtime": 57.8117,
      "eval_samples_per_second": 6.884,
      "eval_steps_per_second": 1.73,
      "step": 5
    },
    {
      "epoch": 0.012718600953895072,
      "grad_norm": 0.9818021059036255,
      "learning_rate": 0.0001992114701314478,
      "loss": 4.1815,
      "step": 6
    },
    {
      "epoch": 0.019077901430842606,
      "grad_norm": 1.0205563306808472,
      "learning_rate": 0.00018763066800438636,
      "loss": 3.6212,
      "step": 9
    },
    {
      "epoch": 0.021197668256491786,
      "eval_loss": 0.7989693880081177,
      "eval_runtime": 57.6089,
      "eval_samples_per_second": 6.909,
      "eval_steps_per_second": 1.736,
      "step": 10
    },
    {
      "epoch": 0.025437201907790145,
      "grad_norm": 1.0461260080337524,
      "learning_rate": 0.000163742398974869,
      "loss": 2.9535,
      "step": 12
    },
    {
      "epoch": 0.03179650238473768,
      "grad_norm": 0.7129300832748413,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.645,
      "step": 15
    },
    {
      "epoch": 0.03179650238473768,
      "eval_loss": 0.6562170386314392,
      "eval_runtime": 57.0299,
      "eval_samples_per_second": 6.979,
      "eval_steps_per_second": 1.753,
      "step": 15
    },
    {
      "epoch": 0.03815580286168521,
      "grad_norm": 0.5910429954528809,
      "learning_rate": 9.372094804706867e-05,
      "loss": 2.3756,
      "step": 18
    },
    {
      "epoch": 0.04239533651298357,
      "eval_loss": 0.5977821946144104,
      "eval_runtime": 57.8021,
      "eval_samples_per_second": 6.886,
      "eval_steps_per_second": 1.73,
      "step": 20
    },
    {
      "epoch": 0.04451510333863275,
      "grad_norm": 0.5103761553764343,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 2.2397,
      "step": 21
    },
    {
      "epoch": 0.05087440381558029,
      "grad_norm": 0.573857307434082,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 2.169,
      "step": 24
    },
    {
      "epoch": 0.052994170641229466,
      "eval_loss": 0.5750617384910583,
      "eval_runtime": 57.4007,
      "eval_samples_per_second": 6.934,
      "eval_steps_per_second": 1.742,
      "step": 25
    },
    {
      "epoch": 0.057233704292527825,
      "grad_norm": 0.5762279629707336,
      "learning_rate": 7.022351411174866e-06,
      "loss": 2.1634,
      "step": 27
    },
    {
      "epoch": 0.06359300476947535,
      "grad_norm": 0.566165566444397,
      "learning_rate": 0.0,
      "loss": 2.1161,
      "step": 30
    },
    {
      "epoch": 0.06359300476947535,
      "eval_loss": 0.5702555179595947,
      "eval_runtime": 57.4317,
      "eval_samples_per_second": 6.93,
      "eval_steps_per_second": 1.741,
      "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": 3.920787866124288e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}