{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 586,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034129692832764506,
      "grad_norm": 2.1603376841170863,
      "learning_rate": 7.627118644067798e-06,
      "loss": 0.4996,
      "step": 10
    },
    {
      "epoch": 0.06825938566552901,
      "grad_norm": 0.5838590067986015,
      "learning_rate": 1.6101694915254237e-05,
      "loss": 0.3996,
      "step": 20
    },
    {
      "epoch": 0.10238907849829351,
      "grad_norm": 0.38210973694074024,
      "learning_rate": 2.457627118644068e-05,
      "loss": 0.3445,
      "step": 30
    },
    {
      "epoch": 0.13651877133105803,
      "grad_norm": 0.4387683119356415,
      "learning_rate": 3.305084745762712e-05,
      "loss": 0.3147,
      "step": 40
    },
    {
      "epoch": 0.17064846416382254,
      "grad_norm": 0.6536457936799677,
      "learning_rate": 4.152542372881356e-05,
      "loss": 0.3043,
      "step": 50
    },
    {
      "epoch": 0.20477815699658702,
      "grad_norm": 1.2322790540487472,
      "learning_rate": 5e-05,
      "loss": 0.2924,
      "step": 60
    },
    {
      "epoch": 0.23890784982935154,
      "grad_norm": 0.5178539355330064,
      "learning_rate": 4.995559213315266e-05,
      "loss": 0.2879,
      "step": 70
    },
    {
      "epoch": 0.27303754266211605,
      "grad_norm": 0.5415626303289514,
      "learning_rate": 4.9822526297301663e-05,
      "loss": 0.2796,
      "step": 80
    },
    {
      "epoch": 0.30716723549488056,
      "grad_norm": 0.48335874151292063,
      "learning_rate": 4.960127522604064e-05,
      "loss": 0.2762,
      "step": 90
    },
    {
      "epoch": 0.3412969283276451,
      "grad_norm": 0.409794839229201,
      "learning_rate": 4.929262494241859e-05,
      "loss": 0.2708,
      "step": 100
    },
    {
      "epoch": 0.37542662116040953,
      "grad_norm": 0.4374713665627254,
      "learning_rate": 4.889767196649131e-05,
      "loss": 0.2686,
      "step": 110
    },
    {
      "epoch": 0.40955631399317405,
      "grad_norm": 0.3532833758922861,
      "learning_rate": 4.841781941979207e-05,
      "loss": 0.2664,
      "step": 120
    },
    {
      "epoch": 0.44368600682593856,
      "grad_norm": 0.4623516562954162,
      "learning_rate": 4.785477204056089e-05,
      "loss": 0.2643,
      "step": 130
    },
    {
      "epoch": 0.4778156996587031,
      "grad_norm": 0.37098917281032373,
      "learning_rate": 4.721053012744142e-05,
      "loss": 0.2617,
      "step": 140
    },
    {
      "epoch": 0.5119453924914675,
      "grad_norm": 0.2929092888247453,
      "learning_rate": 4.6487382433161274e-05,
      "loss": 0.2607,
      "step": 150
    },
    {
      "epoch": 0.5460750853242321,
      "grad_norm": 0.2570706614318041,
      "learning_rate": 4.568789803344195e-05,
      "loss": 0.2599,
      "step": 160
    },
    {
      "epoch": 0.5802047781569966,
      "grad_norm": 0.41025716969789583,
      "learning_rate": 4.481491720002499e-05,
      "loss": 0.2592,
      "step": 170
    },
    {
      "epoch": 0.6143344709897611,
      "grad_norm": 0.4399291010999774,
      "learning_rate": 4.387154131023924e-05,
      "loss": 0.2575,
      "step": 180
    },
    {
      "epoch": 0.6484641638225256,
      "grad_norm": 0.30596219135401376,
      "learning_rate": 4.286112182895675e-05,
      "loss": 0.2569,
      "step": 190
    },
    {
      "epoch": 0.6825938566552902,
      "grad_norm": 0.25267877953552986,
      "learning_rate": 4.1787248402080296e-05,
      "loss": 0.2574,
      "step": 200
    },
    {
      "epoch": 0.7167235494880546,
      "grad_norm": 0.23432325310358476,
      "learning_rate": 4.065373610386201e-05,
      "loss": 0.2524,
      "step": 210
    },
    {
      "epoch": 0.7508532423208191,
      "grad_norm": 0.2924730814934213,
      "learning_rate": 3.9464611883358624e-05,
      "loss": 0.2507,
      "step": 220
    },
    {
      "epoch": 0.7849829351535836,
      "grad_norm": 0.3021088059986536,
      "learning_rate": 3.822410025817406e-05,
      "loss": 0.2516,
      "step": 230
    },
    {
      "epoch": 0.8191126279863481,
      "grad_norm": 0.2667059393685656,
      "learning_rate": 3.693660830631422e-05,
      "loss": 0.2505,
      "step": 240
    },
    {
      "epoch": 0.8532423208191127,
      "grad_norm": 0.244542027349249,
      "learning_rate": 3.5606710009472335e-05,
      "loss": 0.2491,
      "step": 250
    },
    {
      "epoch": 0.8873720136518771,
      "grad_norm": 0.26159530562399463,
      "learning_rate": 3.423913000336732e-05,
      "loss": 0.2477,
      "step": 260
    },
    {
      "epoch": 0.9215017064846417,
      "grad_norm": 0.2858955474994395,
      "learning_rate": 3.2838726792864315e-05,
      "loss": 0.2485,
      "step": 270
    },
    {
      "epoch": 0.9556313993174061,
      "grad_norm": 0.2770393923788652,
      "learning_rate": 3.14104754915077e-05,
      "loss": 0.2478,
      "step": 280
    },
    {
      "epoch": 0.9897610921501706,
      "grad_norm": 0.22785950804509028,
      "learning_rate": 2.9959450146786673e-05,
      "loss": 0.2457,
      "step": 290
    },
    {
      "epoch": 1.023890784982935,
      "grad_norm": 0.23421155213289707,
      "learning_rate": 2.8490805713925296e-05,
      "loss": 0.2298,
      "step": 300
    },
    {
      "epoch": 1.0580204778156996,
      "grad_norm": 0.21985798404580123,
      "learning_rate": 2.700975974223719e-05,
      "loss": 0.2237,
      "step": 310
    },
    {
      "epoch": 1.0921501706484642,
      "grad_norm": 0.20124153757024305,
      "learning_rate": 2.5521573839106815e-05,
      "loss": 0.2241,
      "step": 320
    },
    {
      "epoch": 1.1262798634812285,
      "grad_norm": 0.2397135880483819,
      "learning_rate": 2.403153497744859e-05,
      "loss": 0.226,
      "step": 330
    },
    {
      "epoch": 1.1604095563139931,
      "grad_norm": 0.2101589906088161,
      "learning_rate": 2.254493671305179e-05,
      "loss": 0.2232,
      "step": 340
    },
    {
      "epoch": 1.1945392491467577,
      "grad_norm": 0.24282668966573942,
      "learning_rate": 2.106706037853887e-05,
      "loss": 0.2222,
      "step": 350
    },
    {
      "epoch": 1.2286689419795223,
      "grad_norm": 0.21219900401990696,
      "learning_rate": 1.9603156320748238e-05,
      "loss": 0.2224,
      "step": 360
    },
    {
      "epoch": 1.2627986348122868,
      "grad_norm": 0.2168006279638592,
      "learning_rate": 1.815842524819793e-05,
      "loss": 0.2239,
      "step": 370
    },
    {
      "epoch": 1.2969283276450512,
      "grad_norm": 0.20793463466337964,
      "learning_rate": 1.6737999754895965e-05,
      "loss": 0.2197,
      "step": 380
    },
    {
      "epoch": 1.3310580204778157,
      "grad_norm": 0.20836524233515424,
      "learning_rate": 1.534692608613617e-05,
      "loss": 0.2221,
      "step": 390
    },
    {
      "epoch": 1.36518771331058,
      "grad_norm": 0.16935850421121607,
      "learning_rate": 1.399014621105914e-05,
      "loss": 0.2216,
      "step": 400
    },
    {
      "epoch": 1.3993174061433447,
      "grad_norm": 0.16940108303751525,
      "learning_rate": 1.2672480265667552e-05,
      "loss": 0.2208,
      "step": 410
    },
    {
      "epoch": 1.4334470989761092,
      "grad_norm": 0.1747851858452811,
      "learning_rate": 1.1398609428669582e-05,
      "loss": 0.2207,
      "step": 420
    },
    {
      "epoch": 1.4675767918088738,
      "grad_norm": 0.17678231973968545,
      "learning_rate": 1.0173059290986048e-05,
      "loss": 0.2201,
      "step": 430
    },
    {
      "epoch": 1.5017064846416384,
      "grad_norm": 0.21178232315358259,
      "learning_rate": 9.000183778003246e-06,
      "loss": 0.2188,
      "step": 440
    },
    {
      "epoch": 1.5358361774744027,
      "grad_norm": 0.15098284776881885,
      "learning_rate": 7.884149681689936e-06,
      "loss": 0.2197,
      "step": 450
    },
    {
      "epoch": 1.5699658703071673,
      "grad_norm": 0.14496437963744124,
      "learning_rate": 6.828921857529774e-06,
      "loss": 0.2187,
      "step": 460
    },
    {
      "epoch": 1.6040955631399316,
      "grad_norm": 0.14026043380017464,
      "learning_rate": 5.8382491388595085e-06,
      "loss": 0.2166,
      "step": 470
    },
    {
      "epoch": 1.6382252559726962,
      "grad_norm": 0.14596364242532536,
      "learning_rate": 4.915651018653511e-06,
      "loss": 0.2178,
      "step": 480
    },
    {
      "epoch": 1.6723549488054608,
      "grad_norm": 0.13351276939717058,
      "learning_rate": 4.0644051460698635e-06,
      "loss": 0.2188,
      "step": 490
    },
    {
      "epoch": 1.7064846416382253,
      "grad_norm": 0.13347280961177027,
      "learning_rate": 3.287535682177667e-06,
      "loss": 0.2178,
      "step": 500
    },
    {
      "epoch": 1.74061433447099,
      "grad_norm": 0.13124763132663678,
      "learning_rate": 2.587802556233765e-06,
      "loss": 0.2189,
      "step": 510
    },
    {
      "epoch": 1.7747440273037542,
      "grad_norm": 0.1386006902961326,
      "learning_rate": 1.9676916606769873e-06,
      "loss": 0.2174,
      "step": 520
    },
    {
      "epoch": 1.8088737201365188,
      "grad_norm": 0.13339605718946854,
      "learning_rate": 1.4294060196737873e-06,
      "loss": 0.2189,
      "step": 530
    },
    {
      "epoch": 1.8430034129692832,
      "grad_norm": 0.12911952131837473,
      "learning_rate": 9.748579625898758e-07,
      "loss": 0.2166,
      "step": 540
    },
    {
      "epoch": 1.8771331058020477,
      "grad_norm": 0.11984718491943239,
      "learning_rate": 6.056623301928327e-07,
      "loss": 0.2156,
      "step": 550
    },
    {
      "epoch": 1.9112627986348123,
      "grad_norm": 0.12684531395290052,
      "learning_rate": 3.2313073772138327e-07,
      "loss": 0.2179,
      "step": 560
    },
    {
      "epoch": 1.9453924914675769,
      "grad_norm": 0.1221834502930387,
      "learning_rate": 1.2826691520262114e-07,
      "loss": 0.2189,
      "step": 570
    },
    {
      "epoch": 1.9795221843003414,
      "grad_norm": 0.1315855215642499,
      "learning_rate": 2.1763141571248813e-08,
      "loss": 0.2177,
      "step": 580
    },
    {
      "epoch": 2.0,
      "step": 586,
      "total_flos": 1486449496031232.0,
      "train_loss": 0.24971539962006917,
      "train_runtime": 42813.5195,
      "train_samples_per_second": 7.007,
      "train_steps_per_second": 0.014
    }
  ],
  "logging_steps": 10,
  "max_steps": 586,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1486449496031232.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}