{
  "best_metric": 0.4566049873828888,
  "best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-500",
  "epoch": 0.837696335078534,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08376963350785341,
      "grad_norm": 2.9717624187469482,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 1.0424,
      "step": 50
    },
    {
      "epoch": 0.16753926701570682,
      "grad_norm": 2.9720630645751953,
      "learning_rate": 4.950000000000001e-06,
      "loss": 0.8474,
      "step": 100
    },
    {
      "epoch": 0.2513089005235602,
      "grad_norm": 2.445929765701294,
      "learning_rate": 7.45e-06,
      "loss": 0.7336,
      "step": 150
    },
    {
      "epoch": 0.33507853403141363,
      "grad_norm": 5.502955913543701,
      "learning_rate": 9.950000000000001e-06,
      "loss": 0.6492,
      "step": 200
    },
    {
      "epoch": 0.418848167539267,
      "grad_norm": 2.3356130123138428,
      "learning_rate": 1.2450000000000001e-05,
      "loss": 0.6133,
      "step": 250
    },
    {
      "epoch": 0.5026178010471204,
      "grad_norm": 1.937270164489746,
      "learning_rate": 1.4950000000000001e-05,
      "loss": 0.5889,
      "step": 300
    },
    {
      "epoch": 0.5863874345549738,
      "grad_norm": 2.392244338989258,
      "learning_rate": 1.745e-05,
      "loss": 0.5694,
      "step": 350
    },
    {
      "epoch": 0.6701570680628273,
      "grad_norm": 7.3209919929504395,
      "learning_rate": 1.995e-05,
      "loss": 0.5477,
      "step": 400
    },
    {
      "epoch": 0.7539267015706806,
      "grad_norm": 3.415917158126831,
      "learning_rate": 2.245e-05,
      "loss": 0.5329,
      "step": 450
    },
    {
      "epoch": 0.837696335078534,
      "grad_norm": 3.0256705284118652,
      "learning_rate": 2.495e-05,
      "loss": 0.5173,
      "step": 500
    },
    {
      "epoch": 0.837696335078534,
      "eval_loss": 0.4566049873828888,
      "eval_runtime": 281.3712,
      "eval_samples_per_second": 30.17,
      "eval_steps_per_second": 3.774,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 8000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 14,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8963407491426432.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}