{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9913258983890955,
  "eval_steps": 50,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.061957868649318466,
      "grad_norm": 1.2862273454666138,
      "learning_rate": 2.37987987987988e-05,
      "loss": 0.9967,
      "step": 50
    },
    {
      "epoch": 0.061957868649318466,
      "eval_loss": 0.6054196357727051,
      "eval_runtime": 113.1174,
      "eval_samples_per_second": 1.786,
      "eval_steps_per_second": 0.23,
      "step": 50
    },
    {
      "epoch": 0.12391573729863693,
      "grad_norm": 1.1672418117523193,
      "learning_rate": 2.2547547547547548e-05,
      "loss": 0.5784,
      "step": 100
    },
    {
      "epoch": 0.12391573729863693,
      "eval_loss": 0.5818283557891846,
      "eval_runtime": 113.0178,
      "eval_samples_per_second": 1.787,
      "eval_steps_per_second": 0.23,
      "step": 100
    },
    {
      "epoch": 0.18587360594795538,
      "grad_norm": 1.5880266427993774,
      "learning_rate": 2.1296296296296296e-05,
      "loss": 0.541,
      "step": 150
    },
    {
      "epoch": 0.18587360594795538,
      "eval_loss": 0.5644930005073547,
      "eval_runtime": 113.2567,
      "eval_samples_per_second": 1.784,
      "eval_steps_per_second": 0.23,
      "step": 150
    },
    {
      "epoch": 0.24783147459727387,
      "grad_norm": 1.7589224576950073,
      "learning_rate": 2.0045045045045048e-05,
      "loss": 0.5533,
      "step": 200
    },
    {
      "epoch": 0.24783147459727387,
      "eval_loss": 0.5503261089324951,
      "eval_runtime": 113.0371,
      "eval_samples_per_second": 1.787,
      "eval_steps_per_second": 0.23,
      "step": 200
    },
    {
      "epoch": 0.3097893432465923,
      "grad_norm": 1.5382256507873535,
      "learning_rate": 1.8793793793793796e-05,
      "loss": 0.5148,
      "step": 250
    },
    {
      "epoch": 0.3097893432465923,
      "eval_loss": 0.536943793296814,
      "eval_runtime": 113.1985,
      "eval_samples_per_second": 1.784,
      "eval_steps_per_second": 0.23,
      "step": 250
    },
    {
      "epoch": 0.37174721189591076,
      "grad_norm": 1.673969030380249,
      "learning_rate": 1.754254254254254e-05,
      "loss": 0.5416,
      "step": 300
    },
    {
      "epoch": 0.37174721189591076,
      "eval_loss": 0.5312764644622803,
      "eval_runtime": 113.1787,
      "eval_samples_per_second": 1.785,
      "eval_steps_per_second": 0.23,
      "step": 300
    },
    {
      "epoch": 0.43370508054522927,
      "grad_norm": 1.2669477462768555,
      "learning_rate": 1.629129129129129e-05,
      "loss": 0.5168,
      "step": 350
    },
    {
      "epoch": 0.43370508054522927,
      "eval_loss": 0.5231972932815552,
      "eval_runtime": 112.8353,
      "eval_samples_per_second": 1.79,
      "eval_steps_per_second": 0.23,
      "step": 350
    },
    {
      "epoch": 0.49566294919454773,
      "grad_norm": 1.5182968378067017,
      "learning_rate": 1.504004004004004e-05,
      "loss": 0.508,
      "step": 400
    },
    {
      "epoch": 0.49566294919454773,
      "eval_loss": 0.5176748633384705,
      "eval_runtime": 112.9134,
      "eval_samples_per_second": 1.789,
      "eval_steps_per_second": 0.23,
      "step": 400
    },
    {
      "epoch": 0.5576208178438662,
      "grad_norm": 2.9578964710235596,
      "learning_rate": 1.378878878878879e-05,
      "loss": 0.5021,
      "step": 450
    },
    {
      "epoch": 0.5576208178438662,
      "eval_loss": 0.5131492614746094,
      "eval_runtime": 112.9644,
      "eval_samples_per_second": 1.788,
      "eval_steps_per_second": 0.23,
      "step": 450
    },
    {
      "epoch": 0.6195786864931846,
      "grad_norm": 2.4446771144866943,
      "learning_rate": 1.2537537537537538e-05,
      "loss": 0.4929,
      "step": 500
    },
    {
      "epoch": 0.6195786864931846,
      "eval_loss": 0.5092382431030273,
      "eval_runtime": 113.0528,
      "eval_samples_per_second": 1.787,
      "eval_steps_per_second": 0.23,
      "step": 500
    },
    {
      "epoch": 0.6815365551425031,
      "grad_norm": 1.5840567350387573,
      "learning_rate": 1.1286286286286286e-05,
      "loss": 0.5108,
      "step": 550
    },
    {
      "epoch": 0.6815365551425031,
      "eval_loss": 0.5048378705978394,
      "eval_runtime": 112.995,
      "eval_samples_per_second": 1.788,
      "eval_steps_per_second": 0.23,
      "step": 550
    },
    {
      "epoch": 0.7434944237918215,
      "grad_norm": 1.5897728204727173,
      "learning_rate": 1.0035035035035035e-05,
      "loss": 0.4952,
      "step": 600
    },
    {
      "epoch": 0.7434944237918215,
      "eval_loss": 0.5033619999885559,
      "eval_runtime": 112.9428,
      "eval_samples_per_second": 1.789,
      "eval_steps_per_second": 0.23,
      "step": 600
    },
    {
      "epoch": 0.80545229244114,
      "grad_norm": 2.2665419578552246,
      "learning_rate": 8.783783783783785e-06,
      "loss": 0.5028,
      "step": 650
    },
    {
      "epoch": 0.80545229244114,
      "eval_loss": 0.4959164559841156,
      "eval_runtime": 113.0478,
      "eval_samples_per_second": 1.787,
      "eval_steps_per_second": 0.23,
      "step": 650
    },
    {
      "epoch": 0.8674101610904585,
      "grad_norm": 2.0126755237579346,
      "learning_rate": 7.532532532532532e-06,
      "loss": 0.5094,
      "step": 700
    },
    {
      "epoch": 0.8674101610904585,
      "eval_loss": 0.4948059320449829,
      "eval_runtime": 113.1788,
      "eval_samples_per_second": 1.785,
      "eval_steps_per_second": 0.23,
      "step": 700
    },
    {
      "epoch": 0.929368029739777,
      "grad_norm": 2.2332139015197754,
      "learning_rate": 6.2812812812812815e-06,
      "loss": 0.491,
      "step": 750
    },
    {
      "epoch": 0.929368029739777,
      "eval_loss": 0.49081042408943176,
      "eval_runtime": 112.7157,
      "eval_samples_per_second": 1.792,
      "eval_steps_per_second": 0.231,
      "step": 750
    },
    {
      "epoch": 0.9913258983890955,
      "grad_norm": 1.5069801807403564,
      "learning_rate": 5.03003003003003e-06,
      "loss": 0.4795,
      "step": 800
    },
    {
      "epoch": 0.9913258983890955,
      "eval_loss": 0.48919081687927246,
      "eval_runtime": 113.1009,
      "eval_samples_per_second": 1.786,
      "eval_steps_per_second": 0.23,
      "step": 800
    }
  ],
  "logging_steps": 50,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4494640152576000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}