{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7914012738853504,
  "eval_steps": 7000,
  "global_step": 63000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19904458598726116,
      "grad_norm": 0.15043310821056366,
      "learning_rate": 9.94455501848166e-06,
      "loss": 0.0057,
      "step": 7000
    },
    {
      "epoch": 0.19904458598726116,
      "eval_loss": 0.002587760565802455,
      "eval_runtime": 385.9016,
      "eval_samples_per_second": 182.264,
      "eval_steps_per_second": 22.783,
      "step": 7000
    },
    {
      "epoch": 0.3980891719745223,
      "grad_norm": 0.0009809082839637995,
      "learning_rate": 8.900666645603615e-06,
      "loss": 0.0019,
      "step": 14000
    },
    {
      "epoch": 0.3980891719745223,
      "eval_loss": 0.0018288933206349611,
      "eval_runtime": 386.974,
      "eval_samples_per_second": 181.759,
      "eval_steps_per_second": 22.72,
      "step": 14000
    },
    {
      "epoch": 0.5971337579617835,
      "grad_norm": 0.004145281855016947,
      "learning_rate": 7.79517234842501e-06,
      "loss": 0.0016,
      "step": 21000
    },
    {
      "epoch": 0.5971337579617835,
      "eval_loss": 0.0012058253632858396,
      "eval_runtime": 385.6472,
      "eval_samples_per_second": 182.384,
      "eval_steps_per_second": 22.798,
      "step": 21000
    },
    {
      "epoch": 0.7961783439490446,
      "grad_norm": 0.0015833042562007904,
      "learning_rate": 6.689678051246407e-06,
      "loss": 0.001,
      "step": 28000
    },
    {
      "epoch": 0.7961783439490446,
      "eval_loss": 0.0009336507064290345,
      "eval_runtime": 386.8698,
      "eval_samples_per_second": 181.808,
      "eval_steps_per_second": 22.726,
      "step": 28000
    },
    {
      "epoch": 0.9952229299363057,
      "grad_norm": 0.0003439185384195298,
      "learning_rate": 5.5843417269596545e-06,
      "loss": 0.001,
      "step": 35000
    },
    {
      "epoch": 0.9952229299363057,
      "eval_loss": 0.0008668347145430744,
      "eval_runtime": 386.7927,
      "eval_samples_per_second": 181.844,
      "eval_steps_per_second": 22.731,
      "step": 35000
    },
    {
      "epoch": 1.194267515923567,
      "grad_norm": 0.0005341056967154145,
      "learning_rate": 4.478847429781049e-06,
      "loss": 0.0007,
      "step": 42000
    },
    {
      "epoch": 1.194267515923567,
      "eval_loss": 0.0008429304580204189,
      "eval_runtime": 387.0524,
      "eval_samples_per_second": 181.722,
      "eval_steps_per_second": 22.715,
      "step": 42000
    },
    {
      "epoch": 1.393312101910828,
      "grad_norm": 0.00042841769754886627,
      "learning_rate": 3.3735111054942974e-06,
      "loss": 0.0004,
      "step": 49000
    },
    {
      "epoch": 1.393312101910828,
      "eval_loss": 0.0009025875478982925,
      "eval_runtime": 390.6459,
      "eval_samples_per_second": 180.051,
      "eval_steps_per_second": 22.506,
      "step": 49000
    },
    {
      "epoch": 1.5923566878980893,
      "grad_norm": 0.0007971890736371279,
      "learning_rate": 2.2678588354238415e-06,
      "loss": 0.0003,
      "step": 56000
    },
    {
      "epoch": 1.5923566878980893,
      "eval_loss": 0.0009143418865278363,
      "eval_runtime": 388.6682,
      "eval_samples_per_second": 180.967,
      "eval_steps_per_second": 22.621,
      "step": 56000
    },
    {
      "epoch": 1.7914012738853504,
      "grad_norm": 0.02023099735379219,
      "learning_rate": 1.162522511137089e-06,
      "loss": 0.0002,
      "step": 63000
    },
    {
      "epoch": 1.7914012738853504,
      "eval_loss": 0.0008290820405818522,
      "eval_runtime": 389.2129,
      "eval_samples_per_second": 180.713,
      "eval_steps_per_second": 22.589,
      "step": 63000
    }
  ],
  "logging_steps": 7000,
  "max_steps": 70336,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 7000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}