{
  "best_global_step": 383,
  "best_metric": 0.37941670417785645,
  "best_model_checkpoint": "./lora_qwen7b_cpp_adiff_v1/checkpoint-383",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 383,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02611818478615736,
      "grad_norm": 0.3439924716949463,
      "learning_rate": 2.347826086956522e-06,
      "loss": 0.9253,
      "step": 10
    },
    {
      "epoch": 0.05223636957231472,
      "grad_norm": 0.37593239545822144,
      "learning_rate": 4.956521739130435e-06,
      "loss": 0.8942,
      "step": 20
    },
    {
      "epoch": 0.07835455435847209,
      "grad_norm": 0.4532669186592102,
      "learning_rate": 7.5652173913043475e-06,
      "loss": 0.9621,
      "step": 30
    },
    {
      "epoch": 0.10447273914462944,
      "grad_norm": 0.30326446890830994,
      "learning_rate": 1.017391304347826e-05,
      "loss": 0.8363,
      "step": 40
    },
    {
      "epoch": 0.1305909239307868,
      "grad_norm": 0.4317711591720581,
      "learning_rate": 1.2782608695652173e-05,
      "loss": 0.7811,
      "step": 50
    },
    {
      "epoch": 0.15670910871694418,
      "grad_norm": 0.3774474263191223,
      "learning_rate": 1.5391304347826088e-05,
      "loss": 0.5888,
      "step": 60
    },
    {
      "epoch": 0.18282729350310153,
      "grad_norm": 0.1916833221912384,
      "learning_rate": 1.8e-05,
      "loss": 0.4563,
      "step": 70
    },
    {
      "epoch": 0.20894547828925888,
      "grad_norm": 0.13702069222927094,
      "learning_rate": 2.0608695652173913e-05,
      "loss": 0.4354,
      "step": 80
    },
    {
      "epoch": 0.23506366307541626,
      "grad_norm": 0.10257239639759064,
      "learning_rate": 2.3217391304347826e-05,
      "loss": 0.408,
      "step": 90
    },
    {
      "epoch": 0.2611818478615736,
      "grad_norm": 0.15386034548282623,
      "learning_rate": 2.582608695652174e-05,
      "loss": 0.3986,
      "step": 100
    },
    {
      "epoch": 0.28730003264773096,
      "grad_norm": 0.12275378406047821,
      "learning_rate": 2.8434782608695652e-05,
      "loss": 0.3773,
      "step": 110
    },
    {
      "epoch": 0.31341821743388837,
      "grad_norm": 0.13668131828308105,
      "learning_rate": 2.988394584139265e-05,
      "loss": 0.3579,
      "step": 120
    },
    {
      "epoch": 0.3395364022200457,
      "grad_norm": 0.11877596378326416,
      "learning_rate": 2.9593810444874276e-05,
      "loss": 0.3622,
      "step": 130
    },
    {
      "epoch": 0.36565458700620307,
      "grad_norm": 0.15862952172756195,
      "learning_rate": 2.93036750483559e-05,
      "loss": 0.352,
      "step": 140
    },
    {
      "epoch": 0.3917727717923604,
      "grad_norm": 0.14640262722969055,
      "learning_rate": 2.9013539651837528e-05,
      "loss": 0.3597,
      "step": 150
    },
    {
      "epoch": 0.41789095657851777,
      "grad_norm": 0.11437654495239258,
      "learning_rate": 2.872340425531915e-05,
      "loss": 0.3456,
      "step": 160
    },
    {
      "epoch": 0.4440091413646752,
      "grad_norm": 0.1443624049425125,
      "learning_rate": 2.8433268858800773e-05,
      "loss": 0.3513,
      "step": 170
    },
    {
      "epoch": 0.4701273261508325,
      "grad_norm": 0.11668717861175537,
      "learning_rate": 2.81431334622824e-05,
      "loss": 0.3246,
      "step": 180
    },
    {
      "epoch": 0.4962455109369899,
      "grad_norm": 0.1281779706478119,
      "learning_rate": 2.785299806576402e-05,
      "loss": 0.3504,
      "step": 190
    },
    {
      "epoch": 0.5223636957231472,
      "grad_norm": 0.130177304148674,
      "learning_rate": 2.7562862669245647e-05,
      "loss": 0.3487,
      "step": 200
    },
    {
      "epoch": 0.5484818805093046,
      "grad_norm": 0.1486888825893402,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 0.3305,
      "step": 210
    },
    {
      "epoch": 0.5746000652954619,
      "grad_norm": 0.12134828418493271,
      "learning_rate": 2.69825918762089e-05,
      "loss": 0.3451,
      "step": 220
    },
    {
      "epoch": 0.6007182500816193,
      "grad_norm": 0.12231825292110443,
      "learning_rate": 2.669245647969052e-05,
      "loss": 0.3233,
      "step": 230
    },
    {
      "epoch": 0.6268364348677767,
      "grad_norm": 0.13645341992378235,
      "learning_rate": 2.6402321083172148e-05,
      "loss": 0.3365,
      "step": 240
    },
    {
      "epoch": 0.6529546196539341,
      "grad_norm": 0.14500953257083893,
      "learning_rate": 2.6112185686653773e-05,
      "loss": 0.3329,
      "step": 250
    },
    {
      "epoch": 0.6790728044400914,
      "grad_norm": 0.16711661219596863,
      "learning_rate": 2.5822050290135396e-05,
      "loss": 0.3305,
      "step": 260
    },
    {
      "epoch": 0.7051909892262488,
      "grad_norm": 0.14286471903324127,
      "learning_rate": 2.5531914893617022e-05,
      "loss": 0.3159,
      "step": 270
    },
    {
      "epoch": 0.7313091740124061,
      "grad_norm": 0.17056842148303986,
      "learning_rate": 2.5241779497098648e-05,
      "loss": 0.335,
      "step": 280
    },
    {
      "epoch": 0.7574273587985635,
      "grad_norm": 0.16313998401165009,
      "learning_rate": 2.495164410058027e-05,
      "loss": 0.318,
      "step": 290
    },
    {
      "epoch": 0.7835455435847208,
      "grad_norm": 0.16147395968437195,
      "learning_rate": 2.4661508704061896e-05,
      "loss": 0.2996,
      "step": 300
    },
    {
      "epoch": 0.8096637283708782,
      "grad_norm": 0.1918044090270996,
      "learning_rate": 2.4371373307543522e-05,
      "loss": 0.3172,
      "step": 310
    },
    {
      "epoch": 0.8357819131570355,
      "grad_norm": 0.15215300023555756,
      "learning_rate": 2.408123791102515e-05,
      "loss": 0.3258,
      "step": 320
    },
    {
      "epoch": 0.861900097943193,
      "grad_norm": 0.15154816210269928,
      "learning_rate": 2.379110251450677e-05,
      "loss": 0.3206,
      "step": 330
    },
    {
      "epoch": 0.8880182827293504,
      "grad_norm": 0.19857144355773926,
      "learning_rate": 2.3500967117988397e-05,
      "loss": 0.3038,
      "step": 340
    },
    {
      "epoch": 0.9141364675155077,
      "grad_norm": 0.1814548224210739,
      "learning_rate": 2.321083172147002e-05,
      "loss": 0.3157,
      "step": 350
    },
    {
      "epoch": 0.940254652301665,
      "grad_norm": 0.17991890013217926,
      "learning_rate": 2.2920696324951642e-05,
      "loss": 0.3044,
      "step": 360
    },
    {
      "epoch": 0.9663728370878224,
      "grad_norm": 0.17508666217327118,
      "learning_rate": 2.2630560928433268e-05,
      "loss": 0.3081,
      "step": 370
    },
    {
      "epoch": 0.9924910218739798,
      "grad_norm": 0.17764495313167572,
      "learning_rate": 2.2340425531914894e-05,
      "loss": 0.2957,
      "step": 380
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.37941670417785645,
      "eval_runtime": 41.5299,
      "eval_samples_per_second": 22.105,
      "eval_steps_per_second": 11.052,
      "step": 383
    }
  ],
  "logging_steps": 10,
  "max_steps": 1149,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.089357644575928e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}