{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.39800995024875624,
  "eval_steps": 35,
  "global_step": 70,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.028429282160625444,
      "grad_norm": 14.865596771240234,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 1.887,
      "step": 5
    },
    {
      "epoch": 0.05685856432125089,
      "grad_norm": 8.584558486938477,
      "learning_rate": 2.857142857142857e-05,
      "loss": 1.5936,
      "step": 10
    },
    {
      "epoch": 0.08528784648187633,
      "grad_norm": 4.329889297485352,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.5385,
      "step": 15
    },
    {
      "epoch": 0.11371712864250177,
      "grad_norm": 1.5808465480804443,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.4072,
      "step": 20
    },
    {
      "epoch": 0.14214641080312723,
      "grad_norm": 1.9611109495162964,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.3629,
      "step": 25
    },
    {
      "epoch": 0.17057569296375266,
      "grad_norm": 0.6985721588134766,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.3385,
      "step": 30
    },
    {
      "epoch": 0.19900497512437812,
      "grad_norm": 0.5211701989173889,
      "learning_rate": 0.0001,
      "loss": 0.3051,
      "step": 35
    },
    {
      "epoch": 0.19900497512437812,
      "eval_loss": 0.25876832008361816,
      "eval_runtime": 1601.7861,
      "eval_samples_per_second": 1.561,
      "eval_steps_per_second": 1.561,
      "step": 35
    },
    {
      "epoch": 0.22743425728500355,
      "grad_norm": 0.7382380962371826,
      "learning_rate": 9.993784606094612e-05,
      "loss": 0.2997,
      "step": 40
    },
    {
      "epoch": 0.255863539445629,
      "grad_norm": 0.7649598121643066,
      "learning_rate": 9.975153876827008e-05,
      "loss": 0.2794,
      "step": 45
    },
    {
      "epoch": 0.28429282160625446,
      "grad_norm": 0.8737666606903076,
      "learning_rate": 9.944154131125642e-05,
      "loss": 0.2777,
      "step": 50
    },
    {
      "epoch": 0.31272210376687987,
      "grad_norm": 18.472232818603516,
      "learning_rate": 9.900862439242719e-05,
      "loss": 0.2866,
      "step": 55
    },
    {
      "epoch": 0.3411513859275053,
      "grad_norm": 0.9156910181045532,
      "learning_rate": 9.84538643114539e-05,
      "loss": 0.2993,
      "step": 60
    },
    {
      "epoch": 0.3695806680881308,
      "grad_norm": 0.5505309700965881,
      "learning_rate": 9.777864028930705e-05,
      "loss": 0.2459,
      "step": 65
    },
    {
      "epoch": 0.39800995024875624,
      "grad_norm": 0.6314955949783325,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2726,
      "step": 70
    },
    {
      "epoch": 0.39800995024875624,
      "eval_loss": 0.24190224707126617,
      "eval_runtime": 1601.1971,
      "eval_samples_per_second": 1.561,
      "eval_steps_per_second": 1.561,
      "step": 70
    }
  ],
  "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": 2.316756459838243e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}