{
  "best_metric": 4.690371513366699,
  "best_model_checkpoint": "/home/p318482/babyLM_controlled/models_trained/de_clm/childes_30/checkpoint-20000",
  "epoch": 20.964360587002098,
  "eval_steps": 2000,
  "global_step": 20000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.0964360587002098,
      "eval_loss": 7.102903366088867,
      "eval_runtime": 0.9708,
      "eval_samples_per_second": 1416.286,
      "eval_steps_per_second": 88.582,
      "step": 2000
    },
    {
      "epoch": 4.1928721174004195,
      "grad_norm": 1.3964662551879883,
      "learning_rate": 1e-05,
      "loss": 6.9987,
      "step": 4000
    },
    {
      "epoch": 4.1928721174004195,
      "eval_loss": 5.884151935577393,
      "eval_runtime": 0.966,
      "eval_samples_per_second": 1423.408,
      "eval_steps_per_second": 89.028,
      "step": 4000
    },
    {
      "epoch": 6.289308176100629,
      "eval_loss": 5.54873514175415,
      "eval_runtime": 0.9657,
      "eval_samples_per_second": 1423.84,
      "eval_steps_per_second": 89.055,
      "step": 6000
    },
    {
      "epoch": 8.385744234800839,
      "grad_norm": 2.7172107696533203,
      "learning_rate": 2e-05,
      "loss": 5.2204,
      "step": 8000
    },
    {
      "epoch": 8.385744234800839,
      "eval_loss": 5.2793288230896,
      "eval_runtime": 0.9644,
      "eval_samples_per_second": 1425.779,
      "eval_steps_per_second": 89.176,
      "step": 8000
    },
    {
      "epoch": 10.482180293501049,
      "eval_loss": 5.10486364364624,
      "eval_runtime": 0.9641,
      "eval_samples_per_second": 1426.204,
      "eval_steps_per_second": 89.203,
      "step": 10000
    },
    {
      "epoch": 12.578616352201259,
      "grad_norm": 2.500443458557129,
      "learning_rate": 2.99925e-05,
      "loss": 4.7358,
      "step": 12000
    },
    {
      "epoch": 12.578616352201259,
      "eval_loss": 4.983631134033203,
      "eval_runtime": 0.9644,
      "eval_samples_per_second": 1425.809,
      "eval_steps_per_second": 89.178,
      "step": 12000
    },
    {
      "epoch": 14.675052410901468,
      "eval_loss": 4.882917404174805,
      "eval_runtime": 0.9686,
      "eval_samples_per_second": 1419.612,
      "eval_steps_per_second": 88.79,
      "step": 14000
    },
    {
      "epoch": 16.771488469601678,
      "grad_norm": 2.400749444961548,
      "learning_rate": 3.999e-05,
      "loss": 4.4216,
      "step": 16000
    },
    {
      "epoch": 16.771488469601678,
      "eval_loss": 4.802889823913574,
      "eval_runtime": 0.9763,
      "eval_samples_per_second": 1408.393,
      "eval_steps_per_second": 88.089,
      "step": 16000
    },
    {
      "epoch": 18.867924528301888,
      "eval_loss": 4.74226188659668,
      "eval_runtime": 0.976,
      "eval_samples_per_second": 1408.882,
      "eval_steps_per_second": 88.119,
      "step": 18000
    },
    {
      "epoch": 20.964360587002098,
      "grad_norm": 2.2613022327423096,
      "learning_rate": 4.9985e-05,
      "loss": 4.1842,
      "step": 20000
    },
    {
      "epoch": 20.964360587002098,
      "eval_loss": 4.690371513366699,
      "eval_runtime": 0.9669,
      "eval_samples_per_second": 1422.037,
      "eval_steps_per_second": 88.942,
      "step": 20000
    }
  ],
  "logging_steps": 4000,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 105,
  "save_steps": 4000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5171323153711104.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}