{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 10,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 1.7679167985916138,
      "learning_rate": 0.0002,
      "loss": 2.3858,
      "mean_token_accuracy": 0.5069678752841977,
      "step": 5,
      "timestamp_in_seconds": 1739801896.2577183
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.8494528532028198,
      "learning_rate": 0.00019047619047619048,
      "loss": 1.8622,
      "mean_token_accuracy": 0.5660446086812065,
      "step": 10,
      "timestamp_in_seconds": 1739801910.776645
    },
    {
      "contract_score": 0.5378601332314197,
      "epoch": 0.8888888888888888,
      "eval_loss": 1.835336446762085,
      "eval_mean_token_accuracy": 0.5587292609351433,
      "eval_runtime": 1.0359,
      "eval_samples_per_second": 9.653,
      "eval_steps_per_second": 1.931,
      "step": 10,
      "timestamp_in_seconds": 1739801926.8582673
    },
    {
      "epoch": 1.2666666666666666,
      "grad_norm": 0.8751085996627808,
      "learning_rate": 0.00018095238095238095,
      "loss": 1.5911,
      "mean_token_accuracy": 0.5871365485092056,
      "step": 15,
      "timestamp_in_seconds": 1739801938.9171028
    },
    {
      "epoch": 1.7111111111111112,
      "grad_norm": 0.9368126392364502,
      "learning_rate": 0.00017142857142857143,
      "loss": 1.6128,
      "mean_token_accuracy": 0.5925216216537559,
      "step": 20,
      "timestamp_in_seconds": 1739801953.6685803
    },
    {
      "contract_score": 0.5344367718449038,
      "epoch": 1.7111111111111112,
      "eval_loss": 1.8780924081802368,
      "eval_mean_token_accuracy": 0.5514234539969833,
      "eval_runtime": 1.04,
      "eval_samples_per_second": 9.616,
      "eval_steps_per_second": 1.923,
      "step": 20,
      "timestamp_in_seconds": 1739801968.0753272
    },
    {
      "epoch": 2.088888888888889,
      "grad_norm": 1.0232841968536377,
      "learning_rate": 0.00016190476190476192,
      "loss": 1.4347,
      "mean_token_accuracy": 0.628910414833075,
      "step": 25,
      "timestamp_in_seconds": 1739801980.2135594
    },
    {
      "epoch": 2.533333333333333,
      "grad_norm": 1.1748850345611572,
      "learning_rate": 0.00015238095238095237,
      "loss": 1.2063,
      "mean_token_accuracy": 0.6789763947731228,
      "step": 30,
      "timestamp_in_seconds": 1739801994.0725858
    },
    {
      "contract_score": 0.5540201261867204,
      "epoch": 2.533333333333333,
      "eval_loss": 2.122205972671509,
      "eval_mean_token_accuracy": 0.5495380844645551,
      "eval_runtime": 1.0386,
      "eval_samples_per_second": 9.629,
      "eval_steps_per_second": 1.926,
      "step": 30,
      "timestamp_in_seconds": 1739802010.3303163
    },
    {
      "epoch": 2.977777777777778,
      "grad_norm": 2.4268102645874023,
      "learning_rate": 0.00014285714285714287,
      "loss": 0.946,
      "mean_token_accuracy": 0.7298750072916594,
      "step": 35,
      "timestamp_in_seconds": 1739802024.8007138
    },
    {
      "epoch": 3.3555555555555556,
      "grad_norm": 1.7162376642227173,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.6421,
      "mean_token_accuracy": 0.8255746848231004,
      "step": 40,
      "timestamp_in_seconds": 1739802037.2875772
    },
    {
      "contract_score": 0.5557923053647376,
      "epoch": 3.3555555555555556,
      "eval_loss": 2.638225555419922,
      "eval_mean_token_accuracy": 0.5211161387631975,
      "eval_runtime": 1.0404,
      "eval_samples_per_second": 9.612,
      "eval_steps_per_second": 1.922,
      "step": 40,
      "timestamp_in_seconds": 1739802054.9630625
    },
    {
      "epoch": 3.8,
      "grad_norm": 1.785975456237793,
      "learning_rate": 0.0001238095238095238,
      "loss": 0.4697,
      "mean_token_accuracy": 0.8655947583935519,
      "step": 45,
      "timestamp_in_seconds": 1739802069.1940033
    },
    {
      "epoch": 4.177777777777778,
      "grad_norm": 1.2647113800048828,
      "learning_rate": 0.00011428571428571428,
      "loss": 0.3219,
      "mean_token_accuracy": 0.904521393501244,
      "step": 50,
      "timestamp_in_seconds": 1739802080.7175117
    },
    {
      "contract_score": 0.5660714248941624,
      "epoch": 4.177777777777778,
      "eval_loss": 3.285521984100342,
      "eval_mean_token_accuracy": 0.5330411010558069,
      "eval_runtime": 1.0389,
      "eval_samples_per_second": 9.625,
      "eval_steps_per_second": 1.925,
      "step": 50,
      "timestamp_in_seconds": 1739802101.2406597
    },
    {
      "epoch": 4.622222222222222,
      "grad_norm": 5.707488536834717,
      "learning_rate": 0.00010476190476190477,
      "loss": 0.1122,
      "mean_token_accuracy": 0.9662833272789735,
      "step": 55,
      "timestamp_in_seconds": 1739802115.3834107
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.8283370733261108,
      "learning_rate": 9.523809523809524e-05,
      "loss": 0.1454,
      "mean_token_accuracy": 0.9480247191005747,
      "step": 60,
      "timestamp_in_seconds": 1739802127.8953981
    },
    {
      "epoch": 5.0,
      "eval_loss": 3.9155266284942627,
      "eval_mean_token_accuracy": 0.5329939668174962,
      "eval_runtime": 1.0401,
      "eval_samples_per_second": 9.615,
      "eval_steps_per_second": 1.923,
      "step": 60
    }
  ],
  "logging_steps": 5,
  "max_steps": 110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8303894012190720.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}