{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9996261682242991,
  "eval_steps": 250,
  "global_step": 1337,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05009345794392523,
      "grad_norm": 28.664648056030273,
      "learning_rate": 4.925373134328357e-07,
      "loss": 2.0415,
      "step": 67
    },
    {
      "epoch": 0.10018691588785046,
      "grad_norm": 15.266758918762207,
      "learning_rate": 9.925373134328357e-07,
      "loss": 1.5231,
      "step": 134
    },
    {
      "epoch": 0.1502803738317757,
      "grad_norm": 3.644252061843872,
      "learning_rate": 9.451371571072319e-07,
      "loss": 0.4422,
      "step": 201
    },
    {
      "epoch": 0.18691588785046728,
      "eval_loss": 0.26753509044647217,
      "eval_runtime": 29.4536,
      "eval_samples_per_second": 16.976,
      "eval_steps_per_second": 8.488,
      "step": 250
    },
    {
      "epoch": 0.20037383177570092,
      "grad_norm": 2.716437339782715,
      "learning_rate": 8.894430590191188e-07,
      "loss": 0.2826,
      "step": 268
    },
    {
      "epoch": 0.2504672897196262,
      "grad_norm": 2.4839746952056885,
      "learning_rate": 8.337489609310058e-07,
      "loss": 0.2107,
      "step": 335
    },
    {
      "epoch": 0.3005607476635514,
      "grad_norm": 1.4838812351226807,
      "learning_rate": 7.780548628428927e-07,
      "loss": 0.1864,
      "step": 402
    },
    {
      "epoch": 0.3506542056074766,
      "grad_norm": 1.873056411743164,
      "learning_rate": 7.223607647547797e-07,
      "loss": 0.1727,
      "step": 469
    },
    {
      "epoch": 0.37383177570093457,
      "eval_loss": 0.16795502603054047,
      "eval_runtime": 29.4488,
      "eval_samples_per_second": 16.979,
      "eval_steps_per_second": 8.489,
      "step": 500
    },
    {
      "epoch": 0.40074766355140184,
      "grad_norm": 1.8321393728256226,
      "learning_rate": 6.666666666666666e-07,
      "loss": 0.1551,
      "step": 536
    },
    {
      "epoch": 0.4508411214953271,
      "grad_norm": 2.681673049926758,
      "learning_rate": 6.109725685785536e-07,
      "loss": 0.148,
      "step": 603
    },
    {
      "epoch": 0.5009345794392523,
      "grad_norm": 2.600128650665283,
      "learning_rate": 5.552784704904405e-07,
      "loss": 0.1521,
      "step": 670
    },
    {
      "epoch": 0.5510280373831775,
      "grad_norm": 3.1303086280822754,
      "learning_rate": 4.995843724023275e-07,
      "loss": 0.1475,
      "step": 737
    },
    {
      "epoch": 0.5607476635514018,
      "eval_loss": 0.14567767083644867,
      "eval_runtime": 29.4447,
      "eval_samples_per_second": 16.981,
      "eval_steps_per_second": 8.49,
      "step": 750
    },
    {
      "epoch": 0.6011214953271028,
      "grad_norm": 2.5121614933013916,
      "learning_rate": 4.438902743142144e-07,
      "loss": 0.1327,
      "step": 804
    },
    {
      "epoch": 0.6512149532710281,
      "grad_norm": 2.2810795307159424,
      "learning_rate": 3.881961762261014e-07,
      "loss": 0.1394,
      "step": 871
    },
    {
      "epoch": 0.7013084112149532,
      "grad_norm": 2.4329702854156494,
      "learning_rate": 3.3250207813798835e-07,
      "loss": 0.1284,
      "step": 938
    },
    {
      "epoch": 0.7476635514018691,
      "eval_loss": 0.13731907308101654,
      "eval_runtime": 29.4402,
      "eval_samples_per_second": 16.984,
      "eval_steps_per_second": 8.492,
      "step": 1000
    },
    {
      "epoch": 0.7514018691588785,
      "grad_norm": 2.148538112640381,
      "learning_rate": 2.7680798004987534e-07,
      "loss": 0.1065,
      "step": 1005
    },
    {
      "epoch": 0.8014953271028037,
      "grad_norm": 2.3607959747314453,
      "learning_rate": 2.2111388196176226e-07,
      "loss": 0.1167,
      "step": 1072
    },
    {
      "epoch": 0.851588785046729,
      "grad_norm": 4.869778633117676,
      "learning_rate": 1.6541978387364923e-07,
      "loss": 0.1278,
      "step": 1139
    },
    {
      "epoch": 0.9016822429906542,
      "grad_norm": 1.291765570640564,
      "learning_rate": 1.0972568578553615e-07,
      "loss": 0.1066,
      "step": 1206
    },
    {
      "epoch": 0.9345794392523364,
      "eval_loss": 0.13475529849529266,
      "eval_runtime": 29.4487,
      "eval_samples_per_second": 16.979,
      "eval_steps_per_second": 8.489,
      "step": 1250
    },
    {
      "epoch": 0.9517757009345794,
      "grad_norm": 2.3237946033477783,
      "learning_rate": 5.403158769742311e-08,
      "loss": 0.108,
      "step": 1273
    },
    {
      "epoch": 0.9996261682242991,
      "step": 1337,
      "total_flos": 9.834180665971507e+16,
      "train_loss": 0.32745340464270284,
      "train_runtime": 2094.2749,
      "train_samples_per_second": 5.109,
      "train_steps_per_second": 0.638
    }
  ],
  "logging_steps": 67,
  "max_steps": 1337,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.834180665971507e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}