{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 1000,
  "global_step": 6166,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.032435939020434644,
      "grad_norm": 0.35351359844207764,
      "learning_rate": 4.918910152448913e-05,
      "loss": 0.1337,
      "step": 100
    },
    {
      "epoch": 0.06487187804086929,
      "grad_norm": 0.2617332935333252,
      "learning_rate": 4.837820304897827e-05,
      "loss": 0.1762,
      "step": 200
    },
    {
      "epoch": 0.09730781706130393,
      "grad_norm": 0.26761409640312195,
      "learning_rate": 4.7567304573467406e-05,
      "loss": 0.1729,
      "step": 300
    },
    {
      "epoch": 0.12974375608173858,
      "grad_norm": 0.2583613991737366,
      "learning_rate": 4.675640609795654e-05,
      "loss": 0.1728,
      "step": 400
    },
    {
      "epoch": 0.1621796951021732,
      "grad_norm": 0.24968299269676208,
      "learning_rate": 4.594550762244567e-05,
      "loss": 0.1721,
      "step": 500
    },
    {
      "epoch": 0.19461563412260785,
      "grad_norm": 0.252204567193985,
      "learning_rate": 4.513460914693481e-05,
      "loss": 0.1729,
      "step": 600
    },
    {
      "epoch": 0.2270515731430425,
      "grad_norm": 0.25790390372276306,
      "learning_rate": 4.432371067142394e-05,
      "loss": 0.1716,
      "step": 700
    },
    {
      "epoch": 0.25948751216347715,
      "grad_norm": 0.2649690508842468,
      "learning_rate": 4.351281219591307e-05,
      "loss": 0.1726,
      "step": 800
    },
    {
      "epoch": 0.2919234511839118,
      "grad_norm": 0.2653878927230835,
      "learning_rate": 4.270191372040221e-05,
      "loss": 0.172,
      "step": 900
    },
    {
      "epoch": 0.3243593902043464,
      "grad_norm": 0.2365722954273224,
      "learning_rate": 4.1891015244891344e-05,
      "loss": 0.1734,
      "step": 1000
    },
    {
      "epoch": 0.3243593902043464,
      "eval_gen_len": 19.97732987265796,
      "eval_loss": 0.17071112990379333,
      "eval_rouge1": 0.146,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.146,
      "eval_rougeLsum": 0.1477,
      "eval_runtime": 2204.8687,
      "eval_samples_per_second": 11.183,
      "eval_steps_per_second": 0.35,
      "step": 1000
    },
    {
      "epoch": 0.3567953292247811,
      "grad_norm": 0.2285241037607193,
      "learning_rate": 4.108011676938048e-05,
      "loss": 0.1721,
      "step": 1100
    },
    {
      "epoch": 0.3892312682452157,
      "grad_norm": 0.2493802011013031,
      "learning_rate": 4.026921829386961e-05,
      "loss": 0.1694,
      "step": 1200
    },
    {
      "epoch": 0.4216672072656503,
      "grad_norm": 0.25236544013023376,
      "learning_rate": 3.945831981835874e-05,
      "loss": 0.1698,
      "step": 1300
    },
    {
      "epoch": 0.454103146286085,
      "grad_norm": 0.243851900100708,
      "learning_rate": 3.864742134284788e-05,
      "loss": 0.1683,
      "step": 1400
    },
    {
      "epoch": 0.4865390853065196,
      "grad_norm": 0.24125412106513977,
      "learning_rate": 3.783652286733701e-05,
      "loss": 0.1694,
      "step": 1500
    },
    {
      "epoch": 0.5189750243269543,
      "grad_norm": 0.25099146366119385,
      "learning_rate": 3.7025624391826144e-05,
      "loss": 0.1669,
      "step": 1600
    },
    {
      "epoch": 0.5514109633473889,
      "grad_norm": 0.23592032492160797,
      "learning_rate": 3.621472591631528e-05,
      "loss": 0.1668,
      "step": 1700
    },
    {
      "epoch": 0.5838469023678236,
      "grad_norm": 0.25207582116127014,
      "learning_rate": 3.540382744080442e-05,
      "loss": 0.1678,
      "step": 1800
    },
    {
      "epoch": 0.6162828413882582,
      "grad_norm": 0.2521522045135498,
      "learning_rate": 3.459292896529355e-05,
      "loss": 0.166,
      "step": 1900
    },
    {
      "epoch": 0.6487187804086928,
      "grad_norm": 0.2497226446866989,
      "learning_rate": 3.378203048978268e-05,
      "loss": 0.169,
      "step": 2000
    },
    {
      "epoch": 0.6487187804086928,
      "eval_gen_len": 19.993389569308135,
      "eval_loss": 0.1660359501838684,
      "eval_rouge1": 0.1899,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.1899,
      "eval_rougeLsum": 0.1913,
      "eval_runtime": 2195.0671,
      "eval_samples_per_second": 11.233,
      "eval_steps_per_second": 0.351,
      "step": 2000
    },
    {
      "epoch": 0.6811547194291274,
      "grad_norm": 0.25921228528022766,
      "learning_rate": 3.2971132014271815e-05,
      "loss": 0.1663,
      "step": 2100
    },
    {
      "epoch": 0.7135906584495622,
      "grad_norm": 0.22675295174121857,
      "learning_rate": 3.2160233538760945e-05,
      "loss": 0.1661,
      "step": 2200
    },
    {
      "epoch": 0.7460265974699968,
      "grad_norm": 0.253683477640152,
      "learning_rate": 3.134933506325008e-05,
      "loss": 0.1661,
      "step": 2300
    },
    {
      "epoch": 0.7784625364904314,
      "grad_norm": 0.23699304461479187,
      "learning_rate": 3.053843658773922e-05,
      "loss": 0.1664,
      "step": 2400
    },
    {
      "epoch": 0.810898475510866,
      "grad_norm": 0.21723595261573792,
      "learning_rate": 2.972753811222835e-05,
      "loss": 0.1628,
      "step": 2500
    },
    {
      "epoch": 0.8433344145313006,
      "grad_norm": 0.2416258603334427,
      "learning_rate": 2.8916639636717486e-05,
      "loss": 0.1684,
      "step": 2600
    },
    {
      "epoch": 0.8757703535517353,
      "grad_norm": 0.24152766168117523,
      "learning_rate": 2.8105741161206616e-05,
      "loss": 0.1655,
      "step": 2700
    },
    {
      "epoch": 0.90820629257217,
      "grad_norm": 0.23950466513633728,
      "learning_rate": 2.7294842685695753e-05,
      "loss": 0.1662,
      "step": 2800
    },
    {
      "epoch": 0.9406422315926046,
      "grad_norm": 0.2509647011756897,
      "learning_rate": 2.6483944210184886e-05,
      "loss": 0.1642,
      "step": 2900
    },
    {
      "epoch": 0.9730781706130393,
      "grad_norm": 0.24778147041797638,
      "learning_rate": 2.5673045734674023e-05,
      "loss": 0.1628,
      "step": 3000
    },
    {
      "epoch": 0.9730781706130393,
      "eval_gen_len": 19.997323383891636,
      "eval_loss": 0.16280025243759155,
      "eval_rouge1": 0.0561,
      "eval_rouge2": 0.0,
      "eval_rougeL": 0.0561,
      "eval_rougeLsum": 0.0547,
      "eval_runtime": 2183.6993,
      "eval_samples_per_second": 11.292,
      "eval_steps_per_second": 0.353,
      "step": 3000
    },
    {
      "epoch": 1.0055141096334739,
      "grad_norm": 0.22274711728096008,
      "learning_rate": 2.4862147259163153e-05,
      "loss": 0.1629,
      "step": 3100
    },
    {
      "epoch": 1.0379500486539086,
      "grad_norm": 0.23203332722187042,
      "learning_rate": 2.405124878365229e-05,
      "loss": 0.1556,
      "step": 3200
    },
    {
      "epoch": 1.0703859876743431,
      "grad_norm": 0.24074462056159973,
      "learning_rate": 2.3240350308141423e-05,
      "loss": 0.1548,
      "step": 3300
    },
    {
      "epoch": 1.1028219266947779,
      "grad_norm": 0.23876875638961792,
      "learning_rate": 2.2429451832630553e-05,
      "loss": 0.1535,
      "step": 3400
    },
    {
      "epoch": 1.1352578657152124,
      "grad_norm": 0.23867164552211761,
      "learning_rate": 2.161855335711969e-05,
      "loss": 0.1528,
      "step": 3500
    },
    {
      "epoch": 1.167693804735647,
      "grad_norm": 0.2626864016056061,
      "learning_rate": 2.0807654881608824e-05,
      "loss": 0.1526,
      "step": 3600
    },
    {
      "epoch": 1.2001297437560818,
      "grad_norm": 0.26715072989463806,
      "learning_rate": 1.9996756406097957e-05,
      "loss": 0.1526,
      "step": 3700
    },
    {
      "epoch": 1.2325656827765163,
      "grad_norm": 0.2496395856142044,
      "learning_rate": 1.9185857930587094e-05,
      "loss": 0.1518,
      "step": 3800
    },
    {
      "epoch": 1.265001621796951,
      "grad_norm": 0.24588952958583832,
      "learning_rate": 1.8374959455076227e-05,
      "loss": 0.1519,
      "step": 3900
    },
    {
      "epoch": 1.2974375608173856,
      "grad_norm": 0.23679636418819427,
      "learning_rate": 1.7564060979565357e-05,
      "loss": 0.1504,
      "step": 4000
    },
    {
      "epoch": 1.2974375608173856,
      "eval_gen_len": 19.98292643361181,
      "eval_loss": 0.16194650530815125,
      "eval_rouge1": 0.1229,
      "eval_rouge2": 0.0041,
      "eval_rougeL": 0.123,
      "eval_rougeLsum": 0.1233,
      "eval_runtime": 2185.3639,
      "eval_samples_per_second": 11.283,
      "eval_steps_per_second": 0.353,
      "step": 4000
    },
    {
      "epoch": 1.3298734998378203,
      "grad_norm": 0.24863706529140472,
      "learning_rate": 1.6753162504054494e-05,
      "loss": 0.1511,
      "step": 4100
    },
    {
      "epoch": 1.3623094388582548,
      "grad_norm": 0.2532482445240021,
      "learning_rate": 1.5942264028543628e-05,
      "loss": 0.1503,
      "step": 4200
    },
    {
      "epoch": 1.3947453778786896,
      "grad_norm": 0.2682236135005951,
      "learning_rate": 1.5131365553032761e-05,
      "loss": 0.1529,
      "step": 4300
    },
    {
      "epoch": 1.4271813168991243,
      "grad_norm": 0.23846983909606934,
      "learning_rate": 1.4320467077521896e-05,
      "loss": 0.1514,
      "step": 4400
    },
    {
      "epoch": 1.4596172559195588,
      "grad_norm": 0.2428126037120819,
      "learning_rate": 1.350956860201103e-05,
      "loss": 0.1486,
      "step": 4500
    },
    {
      "epoch": 1.4920531949399936,
      "grad_norm": 0.25097399950027466,
      "learning_rate": 1.2698670126500161e-05,
      "loss": 0.15,
      "step": 4600
    },
    {
      "epoch": 1.524489133960428,
      "grad_norm": 0.2583732008934021,
      "learning_rate": 1.1887771650989297e-05,
      "loss": 0.1528,
      "step": 4700
    },
    {
      "epoch": 1.5569250729808628,
      "grad_norm": 0.23872007429599762,
      "learning_rate": 1.107687317547843e-05,
      "loss": 0.1486,
      "step": 4800
    },
    {
      "epoch": 1.5893610120012975,
      "grad_norm": 0.2473708838224411,
      "learning_rate": 1.0265974699967565e-05,
      "loss": 0.1493,
      "step": 4900
    },
    {
      "epoch": 1.621796951021732,
      "grad_norm": 0.24233025312423706,
      "learning_rate": 9.455076224456699e-06,
      "loss": 0.1505,
      "step": 5000
    },
    {
      "epoch": 1.621796951021732,
      "eval_gen_len": 19.982034228242355,
      "eval_loss": 0.16026677191257477,
      "eval_rouge1": 0.0744,
      "eval_rouge2": 0.0041,
      "eval_rougeL": 0.0744,
      "eval_rougeLsum": 0.0744,
      "eval_runtime": 2176.6648,
      "eval_samples_per_second": 11.328,
      "eval_steps_per_second": 0.354,
      "step": 5000
    },
    {
      "epoch": 1.6542328900421666,
      "grad_norm": 0.25053468346595764,
      "learning_rate": 8.644177748945832e-06,
      "loss": 0.1508,
      "step": 5100
    },
    {
      "epoch": 1.6866688290626013,
      "grad_norm": 0.24528223276138306,
      "learning_rate": 7.833279273434967e-06,
      "loss": 0.1499,
      "step": 5200
    },
    {
      "epoch": 1.719104768083036,
      "grad_norm": 0.2794703543186188,
      "learning_rate": 7.0223807979241e-06,
      "loss": 0.1476,
      "step": 5300
    },
    {
      "epoch": 1.7515407071034708,
      "grad_norm": 0.257614403963089,
      "learning_rate": 6.211482322413234e-06,
      "loss": 0.1498,
      "step": 5400
    },
    {
      "epoch": 1.7839766461239053,
      "grad_norm": 0.24895663559436798,
      "learning_rate": 5.400583846902368e-06,
      "loss": 0.1485,
      "step": 5500
    },
    {
      "epoch": 1.8164125851443398,
      "grad_norm": 0.26096346974372864,
      "learning_rate": 4.589685371391502e-06,
      "loss": 0.1486,
      "step": 5600
    },
    {
      "epoch": 1.8488485241647745,
      "grad_norm": 0.23756231367588043,
      "learning_rate": 3.7787868958806357e-06,
      "loss": 0.1506,
      "step": 5700
    },
    {
      "epoch": 1.8812844631852093,
      "grad_norm": 0.2549228072166443,
      "learning_rate": 2.9678884203697696e-06,
      "loss": 0.1483,
      "step": 5800
    },
    {
      "epoch": 1.913720402205644,
      "grad_norm": 0.24819372594356537,
      "learning_rate": 2.156989944858904e-06,
      "loss": 0.149,
      "step": 5900
    },
    {
      "epoch": 1.9461563412260785,
      "grad_norm": 0.23372448980808258,
      "learning_rate": 1.3460914693480378e-06,
      "loss": 0.1506,
      "step": 6000
    },
    {
      "epoch": 1.9461563412260785,
      "eval_gen_len": 19.98361586503366,
      "eval_loss": 0.15918129682540894,
      "eval_rouge1": 0.073,
      "eval_rouge2": 0.002,
      "eval_rougeL": 0.073,
      "eval_rougeLsum": 0.073,
      "eval_runtime": 2174.8737,
      "eval_samples_per_second": 11.338,
      "eval_steps_per_second": 0.355,
      "step": 6000
    },
    {
      "epoch": 1.978592280246513,
      "grad_norm": 0.25701549649238586,
      "learning_rate": 5.351929938371715e-07,
      "loss": 0.15,
      "step": 6100
    }
  ],
  "logging_steps": 100,
  "max_steps": 6166,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3.5709139077411373e+19,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}