{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 250,
  "global_step": 1351,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.050333086602516654,
      "grad_norm": 4.236826419830322,
      "learning_rate": 5e-07,
      "loss": 0.4956,
      "step": 68
    },
    {
      "epoch": 0.10066617320503331,
      "grad_norm": 3.3058083057403564,
      "learning_rate": 1e-06,
      "loss": 0.5465,
      "step": 136
    },
    {
      "epoch": 0.15099925980754997,
      "grad_norm": 3.0439271926879883,
      "learning_rate": 9.440329218106997e-07,
      "loss": 0.4505,
      "step": 204
    },
    {
      "epoch": 0.1850481125092524,
      "eval_sft_sg_values_eval_loss": 0.3208533227443695,
      "eval_sft_sg_values_eval_runtime": 28.8285,
      "eval_sft_sg_values_eval_samples_per_second": 17.344,
      "eval_sft_sg_values_eval_steps_per_second": 8.672,
      "step": 250
    },
    {
      "epoch": 0.20133234641006661,
      "grad_norm": 3.065812110900879,
      "learning_rate": 8.880658436213991e-07,
      "loss": 0.4528,
      "step": 272
    },
    {
      "epoch": 0.25166543301258326,
      "grad_norm": 3.464308977127075,
      "learning_rate": 8.320987654320987e-07,
      "loss": 0.3473,
      "step": 340
    },
    {
      "epoch": 0.30199851961509994,
      "grad_norm": 1.8523364067077637,
      "learning_rate": 7.761316872427983e-07,
      "loss": 0.395,
      "step": 408
    },
    {
      "epoch": 0.35233160621761656,
      "grad_norm": 1.4938207864761353,
      "learning_rate": 7.201646090534979e-07,
      "loss": 0.3465,
      "step": 476
    },
    {
      "epoch": 0.3700962250185048,
      "eval_sft_sg_values_eval_loss": 0.20385459065437317,
      "eval_sft_sg_values_eval_runtime": 28.85,
      "eval_sft_sg_values_eval_samples_per_second": 17.331,
      "eval_sft_sg_values_eval_steps_per_second": 8.666,
      "step": 500
    },
    {
      "epoch": 0.40266469282013323,
      "grad_norm": 2.14213490486145,
      "learning_rate": 6.641975308641975e-07,
      "loss": 0.2638,
      "step": 544
    },
    {
      "epoch": 0.4529977794226499,
      "grad_norm": 1.6940499544143677,
      "learning_rate": 6.082304526748971e-07,
      "loss": 0.3279,
      "step": 612
    },
    {
      "epoch": 0.5033308660251665,
      "grad_norm": 1.800094485282898,
      "learning_rate": 5.522633744855967e-07,
      "loss": 0.2363,
      "step": 680
    },
    {
      "epoch": 0.5536639526276832,
      "grad_norm": 1.591727614402771,
      "learning_rate": 4.962962962962963e-07,
      "loss": 0.2179,
      "step": 748
    },
    {
      "epoch": 0.5551443375277573,
      "eval_sft_sg_values_eval_loss": 0.17694725096225739,
      "eval_sft_sg_values_eval_runtime": 28.885,
      "eval_sft_sg_values_eval_samples_per_second": 17.31,
      "eval_sft_sg_values_eval_steps_per_second": 8.655,
      "step": 750
    },
    {
      "epoch": 0.6039970392301999,
      "grad_norm": 4.029638290405273,
      "learning_rate": 4.403292181069959e-07,
      "loss": 0.2013,
      "step": 816
    },
    {
      "epoch": 0.6543301258327165,
      "grad_norm": 1.7355984449386597,
      "learning_rate": 3.8436213991769547e-07,
      "loss": 0.2014,
      "step": 884
    },
    {
      "epoch": 0.7046632124352331,
      "grad_norm": 2.6946229934692383,
      "learning_rate": 3.2839506172839506e-07,
      "loss": 0.2954,
      "step": 952
    },
    {
      "epoch": 0.7401924500370096,
      "eval_sft_sg_values_eval_loss": 0.16258862614631653,
      "eval_sft_sg_values_eval_runtime": 28.8506,
      "eval_sft_sg_values_eval_samples_per_second": 17.331,
      "eval_sft_sg_values_eval_steps_per_second": 8.665,
      "step": 1000
    },
    {
      "epoch": 0.7549962990377498,
      "grad_norm": 2.2922027111053467,
      "learning_rate": 2.7242798353909465e-07,
      "loss": 0.2395,
      "step": 1020
    },
    {
      "epoch": 0.8053293856402665,
      "grad_norm": 1.3803716897964478,
      "learning_rate": 2.1646090534979421e-07,
      "loss": 0.249,
      "step": 1088
    },
    {
      "epoch": 0.8556624722427831,
      "grad_norm": 1.8623427152633667,
      "learning_rate": 1.604938271604938e-07,
      "loss": 0.2043,
      "step": 1156
    },
    {
      "epoch": 0.9059955588452998,
      "grad_norm": 2.6236300468444824,
      "learning_rate": 1.0452674897119341e-07,
      "loss": 0.2347,
      "step": 1224
    },
    {
      "epoch": 0.9252405625462621,
      "eval_sft_sg_values_eval_loss": 0.15717695653438568,
      "eval_sft_sg_values_eval_runtime": 28.8569,
      "eval_sft_sg_values_eval_samples_per_second": 17.327,
      "eval_sft_sg_values_eval_steps_per_second": 8.663,
      "step": 1250
    },
    {
      "epoch": 0.9563286454478165,
      "grad_norm": 1.8058063983917236,
      "learning_rate": 4.8559670781893e-08,
      "loss": 0.27,
      "step": 1292
    },
    {
      "epoch": 1.0,
      "step": 1351,
      "total_flos": 9.434186513311334e+16,
      "train_loss": 0.3092916518295367,
      "train_runtime": 2173.1432,
      "train_samples_per_second": 4.973,
      "train_steps_per_second": 0.622
    }
  ],
  "logging_steps": 68,
  "max_steps": 1351,
  "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": 9.434186513311334e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}