{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.869565217391304,
  "eval_steps": 500,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 2.2188591957092285,
      "learning_rate": 8e-05,
      "loss": 2.602,
      "mean_token_accuracy": 0.48853018043069,
      "step": 2,
      "timestamp_in_seconds": 1739743157.9311142
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 2.5741384029388428,
      "learning_rate": 0.00016,
      "loss": 2.1612,
      "mean_token_accuracy": 0.5326818635271061,
      "step": 4,
      "timestamp_in_seconds": 1739743162.1825073
    },
    {
      "contract_score": 0.34910623408499225,
      "epoch": 0.8695652173913043,
      "eval_loss": 2.4004902839660645,
      "eval_mean_token_accuracy": 0.503935521779025,
      "eval_runtime": 0.2454,
      "eval_samples_per_second": 20.376,
      "eval_steps_per_second": 4.075,
      "step": 5,
      "timestamp_in_seconds": 1739743177.970281
    },
    {
      "epoch": 1.1739130434782608,
      "grad_norm": 1.9574916362762451,
      "learning_rate": 0.00019555555555555556,
      "loss": 2.9931,
      "mean_token_accuracy": 0.5272848937741852,
      "step": 6,
      "timestamp_in_seconds": 1739743180.0917573
    },
    {
      "epoch": 1.5217391304347827,
      "grad_norm": 0.9764134287834167,
      "learning_rate": 0.0001866666666666667,
      "loss": 1.6627,
      "mean_token_accuracy": 0.5663752612519408,
      "step": 8,
      "timestamp_in_seconds": 1739743184.3513172
    },
    {
      "epoch": 1.8695652173913042,
      "grad_norm": 0.9813716411590576,
      "learning_rate": 0.00017777777777777779,
      "loss": 1.6998,
      "mean_token_accuracy": 0.5967085254561969,
      "step": 10,
      "timestamp_in_seconds": 1739743188.5616908
    },
    {
      "contract_score": 0.46610584077380945,
      "epoch": 1.8695652173913042,
      "eval_loss": 2.3716249465942383,
      "eval_mean_token_accuracy": 0.5109471680152309,
      "eval_runtime": 0.245,
      "eval_samples_per_second": 20.411,
      "eval_steps_per_second": 4.082,
      "step": 10,
      "timestamp_in_seconds": 1739743202.5728328
    },
    {
      "epoch": 2.3478260869565215,
      "grad_norm": 0.9766614437103271,
      "learning_rate": 0.00016888888888888889,
      "loss": 2.1352,
      "mean_token_accuracy": 0.6407472585826552,
      "step": 12,
      "timestamp_in_seconds": 1739743206.7989218
    },
    {
      "epoch": 2.6956521739130435,
      "grad_norm": 1.0900976657867432,
      "learning_rate": 0.00016,
      "loss": 1.428,
      "mean_token_accuracy": 0.6146520151561914,
      "step": 14,
      "timestamp_in_seconds": 1739743210.9801657
    },
    {
      "epoch": 2.869565217391304,
      "eval_loss": 2.482854127883911,
      "eval_mean_token_accuracy": 0.5848563778138411,
      "eval_runtime": 0.2444,
      "eval_samples_per_second": 20.457,
      "eval_steps_per_second": 4.091,
      "step": 15
    }
  ],
  "logging_steps": 2,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 2390259035480064.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}