{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7960199004975125,
  "eval_steps": 35,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028429282160625444,
      "grad_norm": 11.854507446289062,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.9685,
      "step": 5
    },
    {
      "epoch": 0.05685856432125089,
      "grad_norm": 2.9244329929351807,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.5325,
      "step": 10
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 2.8243346214294434,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.2362,
      "step": 15
    },
    {
      "epoch": 0.11371712864250177,
      "grad_norm": 1.644755244255066,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.2163,
      "step": 20
    },
    {
      "epoch": 0.14214641080312723,
      "grad_norm": 5.001497268676758,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.2204,
      "step": 25
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 1.6563094854354858,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.2098,
      "step": 30
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 1.911417841911316,
      "learning_rate": 0.0001,
      "loss": 0.1803,
      "step": 35
    },
    {
      "epoch": 0.19900497512437812,
      "eval_loss": 0.16817478835582733,
      "eval_runtime": 318.5306,
      "eval_samples_per_second": 7.849,
      "eval_steps_per_second": 7.849,
      "step": 35
    },
    {
      "epoch": 0.22743425728500355,
      "grad_norm": 1.6745359897613525,
      "learning_rate": 9.993784606094612e-05,
      "loss": 0.1843,
      "step": 40
    },
    {
      "epoch": 0.255863539445629,
      "grad_norm": 0.9290557503700256,
      "learning_rate": 9.975153876827008e-05,
      "loss": 0.1751,
      "step": 45
    },
    {
      "epoch": 0.28429282160625446,
      "grad_norm": 1.3401949405670166,
      "learning_rate": 9.944154131125642e-05,
      "loss": 0.1722,
      "step": 50
    },
    {
      "epoch": 0.31272210376687987,
      "grad_norm": 0.9433913826942444,
      "learning_rate": 9.900862439242719e-05,
      "loss": 0.165,
      "step": 55
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 1.2080743312835693,
      "learning_rate": 9.84538643114539e-05,
      "loss": 0.1734,
      "step": 60
    },
    {
      "epoch": 0.3695806680881308,
      "grad_norm": 0.9101002812385559,
      "learning_rate": 9.777864028930705e-05,
      "loss": 0.1476,
      "step": 65
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 0.9633578658103943,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1583,
      "step": 70
    },
    {
      "epoch": 0.39800995024875624,
      "eval_loss": 0.15481097996234894,
      "eval_runtime": 318.1907,
      "eval_samples_per_second": 7.857,
      "eval_steps_per_second": 7.857,
      "step": 70
    },
    {
      "epoch": 0.42643923240938164,
      "grad_norm": 0.9153623580932617,
      "learning_rate": 9.607381059352038e-05,
      "loss": 0.1632,
      "step": 75
    },
    {
      "epoch": 0.4548685145700071,
      "grad_norm": 0.9270277619361877,
      "learning_rate": 9.504844339512095e-05,
      "loss": 0.1503,
      "step": 80
    },
    {
      "epoch": 0.48329779673063256,
      "grad_norm": 0.863593578338623,
      "learning_rate": 9.391107866851143e-05,
      "loss": 0.1527,
      "step": 85
    },
    {
      "epoch": 0.511727078891258,
      "grad_norm": 0.9579532146453857,
      "learning_rate": 9.266454408160779e-05,
      "loss": 0.1523,
      "step": 90
    },
    {
      "epoch": 0.5401563610518835,
      "grad_norm": 1.0070995092391968,
      "learning_rate": 9.131193871579975e-05,
      "loss": 0.1512,
      "step": 95
    },
    {
      "epoch": 0.5685856432125089,
      "grad_norm": 1.0314483642578125,
      "learning_rate": 8.985662536114613e-05,
      "loss": 0.1485,
      "step": 100
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.5653307437896729,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.1439,
      "step": 105
    },
    {
      "epoch": 0.5970149253731343,
      "eval_loss": 0.14900080859661102,
      "eval_runtime": 317.9816,
      "eval_samples_per_second": 7.862,
      "eval_steps_per_second": 7.862,
      "step": 105
    },
    {
      "epoch": 0.6254442075337597,
      "grad_norm": 0.6183350682258606,
      "learning_rate": 8.665259359149132e-05,
      "loss": 0.1459,
      "step": 110
    },
    {
      "epoch": 0.6538734896943852,
      "grad_norm": 0.667679488658905,
      "learning_rate": 8.491184090430364e-05,
      "loss": 0.1367,
      "step": 115
    },
    {
      "epoch": 0.6823027718550106,
      "grad_norm": 0.8107192516326904,
      "learning_rate": 8.308429187984297e-05,
      "loss": 0.1468,
      "step": 120
    },
    {
      "epoch": 0.7107320540156361,
      "grad_norm": 0.7757948637008667,
      "learning_rate": 8.117449009293668e-05,
      "loss": 0.1349,
      "step": 125
    },
    {
      "epoch": 0.7391613361762616,
      "grad_norm": 0.8467870354652405,
      "learning_rate": 7.91871836117395e-05,
      "loss": 0.1411,
      "step": 130
    },
    {
      "epoch": 0.767590618336887,
      "grad_norm": 1.0613672733306885,
      "learning_rate": 7.712731319328798e-05,
      "loss": 0.1663,
      "step": 135
    },
    {
      "epoch": 0.7960199004975125,
      "grad_norm": 0.7184066772460938,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.1488,
      "step": 140
    },
    {
      "epoch": 0.7960199004975125,
      "eval_loss": 0.13560061156749725,
      "eval_runtime": 316.1201,
      "eval_samples_per_second": 7.908,
      "eval_steps_per_second": 7.908,
      "step": 140
    }
  ],
  "logging_steps": 5,
  "max_steps": 350,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 35,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.677220077453967e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}