{
  "best_global_step": 2049,
  "best_metric": 0.6017569546120058,
  "best_model_checkpoint": "./saved_models/cotext_2cc/checkpoint-2049",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 3415,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07320644216691069,
      "grad_norm": 2.1882169246673584,
      "learning_rate": 1.971303074670571e-05,
      "loss": 0.7735,
      "step": 50
    },
    {
      "epoch": 0.14641288433382138,
      "grad_norm": 1.3151637315750122,
      "learning_rate": 1.942020497803807e-05,
      "loss": 0.6965,
      "step": 100
    },
    {
      "epoch": 0.21961932650073207,
      "grad_norm": 1.8874374628067017,
      "learning_rate": 1.9127379209370426e-05,
      "loss": 0.6919,
      "step": 150
    },
    {
      "epoch": 0.29282576866764276,
      "grad_norm": 3.595515012741089,
      "learning_rate": 1.8834553440702785e-05,
      "loss": 0.6911,
      "step": 200
    },
    {
      "epoch": 0.36603221083455345,
      "grad_norm": 2.7481727600097656,
      "learning_rate": 1.854172767203514e-05,
      "loss": 0.6904,
      "step": 250
    },
    {
      "epoch": 0.43923865300146414,
      "grad_norm": 2.4479894638061523,
      "learning_rate": 1.8248901903367496e-05,
      "loss": 0.6773,
      "step": 300
    },
    {
      "epoch": 0.5124450951683748,
      "grad_norm": 2.0022459030151367,
      "learning_rate": 1.7956076134699855e-05,
      "loss": 0.6846,
      "step": 350
    },
    {
      "epoch": 0.5856515373352855,
      "grad_norm": 0.9217310547828674,
      "learning_rate": 1.766325036603221e-05,
      "loss": 0.6873,
      "step": 400
    },
    {
      "epoch": 0.6588579795021962,
      "grad_norm": 1.0517982244491577,
      "learning_rate": 1.737042459736457e-05,
      "loss": 0.6854,
      "step": 450
    },
    {
      "epoch": 0.7320644216691069,
      "grad_norm": 2.381688117980957,
      "learning_rate": 1.7077598828696925e-05,
      "loss": 0.6829,
      "step": 500
    },
    {
      "epoch": 0.8052708638360175,
      "grad_norm": 1.3180112838745117,
      "learning_rate": 1.6784773060029284e-05,
      "loss": 0.6902,
      "step": 550
    },
    {
      "epoch": 0.8784773060029283,
      "grad_norm": 1.1734063625335693,
      "learning_rate": 1.649194729136164e-05,
      "loss": 0.6849,
      "step": 600
    },
    {
      "epoch": 0.9516837481698389,
      "grad_norm": 1.2252230644226074,
      "learning_rate": 1.6199121522694e-05,
      "loss": 0.685,
      "step": 650
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5666178623718887,
      "eval_loss": 0.6766132116317749,
      "eval_runtime": 22.7682,
      "eval_samples_per_second": 119.992,
      "eval_steps_per_second": 1.889,
      "step": 683
    },
    {
      "epoch": 1.0248901903367496,
      "grad_norm": 1.903355360031128,
      "learning_rate": 1.5906295754026355e-05,
      "loss": 0.6792,
      "step": 700
    },
    {
      "epoch": 1.0980966325036603,
      "grad_norm": 1.0279943943023682,
      "learning_rate": 1.5613469985358714e-05,
      "loss": 0.6825,
      "step": 750
    },
    {
      "epoch": 1.171303074670571,
      "grad_norm": 4.962799072265625,
      "learning_rate": 1.532064421669107e-05,
      "loss": 0.6774,
      "step": 800
    },
    {
      "epoch": 1.2445095168374818,
      "grad_norm": 1.9989827871322632,
      "learning_rate": 1.5027818448023428e-05,
      "loss": 0.6819,
      "step": 850
    },
    {
      "epoch": 1.3177159590043923,
      "grad_norm": 1.2916970252990723,
      "learning_rate": 1.4734992679355784e-05,
      "loss": 0.6742,
      "step": 900
    },
    {
      "epoch": 1.390922401171303,
      "grad_norm": 2.063950777053833,
      "learning_rate": 1.4442166910688143e-05,
      "loss": 0.6742,
      "step": 950
    },
    {
      "epoch": 1.4641288433382138,
      "grad_norm": 1.099249005317688,
      "learning_rate": 1.4149341142020499e-05,
      "loss": 0.6783,
      "step": 1000
    },
    {
      "epoch": 1.5373352855051245,
      "grad_norm": 1.780521273612976,
      "learning_rate": 1.3856515373352856e-05,
      "loss": 0.6798,
      "step": 1050
    },
    {
      "epoch": 1.610541727672035,
      "grad_norm": 1.3341678380966187,
      "learning_rate": 1.3563689604685213e-05,
      "loss": 0.6685,
      "step": 1100
    },
    {
      "epoch": 1.6837481698389458,
      "grad_norm": 1.1097255945205688,
      "learning_rate": 1.327086383601757e-05,
      "loss": 0.6735,
      "step": 1150
    },
    {
      "epoch": 1.7569546120058566,
      "grad_norm": 1.7918726205825806,
      "learning_rate": 1.2978038067349928e-05,
      "loss": 0.6661,
      "step": 1200
    },
    {
      "epoch": 1.830161054172767,
      "grad_norm": 1.6219556331634521,
      "learning_rate": 1.2685212298682286e-05,
      "loss": 0.6677,
      "step": 1250
    },
    {
      "epoch": 1.903367496339678,
      "grad_norm": 2.006284236907959,
      "learning_rate": 1.2392386530014641e-05,
      "loss": 0.6689,
      "step": 1300
    },
    {
      "epoch": 1.9765739385065886,
      "grad_norm": 1.2488888502120972,
      "learning_rate": 1.2099560761347e-05,
      "loss": 0.6624,
      "step": 1350
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5647877013177159,
      "eval_loss": 0.6730920076370239,
      "eval_runtime": 22.7575,
      "eval_samples_per_second": 120.048,
      "eval_steps_per_second": 1.889,
      "step": 1366
    },
    {
      "epoch": 2.049780380673499,
      "grad_norm": 1.610883355140686,
      "learning_rate": 1.1806734992679356e-05,
      "loss": 0.6636,
      "step": 1400
    },
    {
      "epoch": 2.12298682284041,
      "grad_norm": 1.841633915901184,
      "learning_rate": 1.1513909224011715e-05,
      "loss": 0.6557,
      "step": 1450
    },
    {
      "epoch": 2.1961932650073206,
      "grad_norm": 2.1673364639282227,
      "learning_rate": 1.122108345534407e-05,
      "loss": 0.6569,
      "step": 1500
    },
    {
      "epoch": 2.269399707174231,
      "grad_norm": 1.2526633739471436,
      "learning_rate": 1.092825768667643e-05,
      "loss": 0.6608,
      "step": 1550
    },
    {
      "epoch": 2.342606149341142,
      "grad_norm": 1.2852518558502197,
      "learning_rate": 1.0635431918008785e-05,
      "loss": 0.6575,
      "step": 1600
    },
    {
      "epoch": 2.4158125915080526,
      "grad_norm": 2.687999725341797,
      "learning_rate": 1.0342606149341143e-05,
      "loss": 0.6595,
      "step": 1650
    },
    {
      "epoch": 2.4890190336749636,
      "grad_norm": 2.0115835666656494,
      "learning_rate": 1.00497803806735e-05,
      "loss": 0.6656,
      "step": 1700
    },
    {
      "epoch": 2.562225475841874,
      "grad_norm": 1.2562048435211182,
      "learning_rate": 9.756954612005857e-06,
      "loss": 0.6602,
      "step": 1750
    },
    {
      "epoch": 2.6354319180087846,
      "grad_norm": 3.354336738586426,
      "learning_rate": 9.464128843338215e-06,
      "loss": 0.6578,
      "step": 1800
    },
    {
      "epoch": 2.7086383601756956,
      "grad_norm": 5.723195552825928,
      "learning_rate": 9.171303074670572e-06,
      "loss": 0.6507,
      "step": 1850
    },
    {
      "epoch": 2.781844802342606,
      "grad_norm": 1.9592162370681763,
      "learning_rate": 8.87847730600293e-06,
      "loss": 0.6547,
      "step": 1900
    },
    {
      "epoch": 2.855051244509517,
      "grad_norm": 3.2084081172943115,
      "learning_rate": 8.585651537335287e-06,
      "loss": 0.6519,
      "step": 1950
    },
    {
      "epoch": 2.9282576866764276,
      "grad_norm": 2.990320920944214,
      "learning_rate": 8.292825768667644e-06,
      "loss": 0.651,
      "step": 2000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6017569546120058,
      "eval_loss": 0.6528917551040649,
      "eval_runtime": 22.7498,
      "eval_samples_per_second": 120.089,
      "eval_steps_per_second": 1.89,
      "step": 2049
    },
    {
      "epoch": 3.001464128843338,
      "grad_norm": 1.819231390953064,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.6551,
      "step": 2050
    },
    {
      "epoch": 3.074670571010249,
      "grad_norm": 1.5196412801742554,
      "learning_rate": 7.707174231332359e-06,
      "loss": 0.6417,
      "step": 2100
    },
    {
      "epoch": 3.1478770131771596,
      "grad_norm": 1.6357721090316772,
      "learning_rate": 7.414348462664715e-06,
      "loss": 0.6496,
      "step": 2150
    },
    {
      "epoch": 3.22108345534407,
      "grad_norm": 1.4427732229232788,
      "learning_rate": 7.1215226939970725e-06,
      "loss": 0.645,
      "step": 2200
    },
    {
      "epoch": 3.294289897510981,
      "grad_norm": 9.609319686889648,
      "learning_rate": 6.82869692532943e-06,
      "loss": 0.6469,
      "step": 2250
    },
    {
      "epoch": 3.3674963396778916,
      "grad_norm": 2.0619852542877197,
      "learning_rate": 6.535871156661787e-06,
      "loss": 0.6533,
      "step": 2300
    },
    {
      "epoch": 3.440702781844802,
      "grad_norm": 2.3825881481170654,
      "learning_rate": 6.2430453879941446e-06,
      "loss": 0.6411,
      "step": 2350
    },
    {
      "epoch": 3.513909224011713,
      "grad_norm": 2.9434738159179688,
      "learning_rate": 5.950219619326502e-06,
      "loss": 0.6449,
      "step": 2400
    },
    {
      "epoch": 3.5871156661786237,
      "grad_norm": 2.3528411388397217,
      "learning_rate": 5.657393850658858e-06,
      "loss": 0.6527,
      "step": 2450
    },
    {
      "epoch": 3.660322108345534,
      "grad_norm": 3.008011817932129,
      "learning_rate": 5.364568081991216e-06,
      "loss": 0.6566,
      "step": 2500
    },
    {
      "epoch": 3.733528550512445,
      "grad_norm": 2.1544880867004395,
      "learning_rate": 5.071742313323573e-06,
      "loss": 0.6464,
      "step": 2550
    },
    {
      "epoch": 3.8067349926793557,
      "grad_norm": 2.4027340412139893,
      "learning_rate": 4.77891654465593e-06,
      "loss": 0.6311,
      "step": 2600
    },
    {
      "epoch": 3.8799414348462666,
      "grad_norm": 3.0393288135528564,
      "learning_rate": 4.486090775988287e-06,
      "loss": 0.6388,
      "step": 2650
    },
    {
      "epoch": 3.953147877013177,
      "grad_norm": 2.6928722858428955,
      "learning_rate": 4.193265007320644e-06,
      "loss": 0.6414,
      "step": 2700
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.5937042459736457,
      "eval_loss": 0.6503124237060547,
      "eval_runtime": 22.7539,
      "eval_samples_per_second": 120.067,
      "eval_steps_per_second": 1.89,
      "step": 2732
    },
    {
      "epoch": 4.026354319180088,
      "grad_norm": 3.9657881259918213,
      "learning_rate": 3.900439238653002e-06,
      "loss": 0.6399,
      "step": 2750
    },
    {
      "epoch": 4.099560761346998,
      "grad_norm": 1.924501895904541,
      "learning_rate": 3.607613469985359e-06,
      "loss": 0.6337,
      "step": 2800
    },
    {
      "epoch": 4.172767203513909,
      "grad_norm": 3.779348134994507,
      "learning_rate": 3.314787701317716e-06,
      "loss": 0.6471,
      "step": 2850
    },
    {
      "epoch": 4.24597364568082,
      "grad_norm": 3.295867443084717,
      "learning_rate": 3.0219619326500732e-06,
      "loss": 0.6527,
      "step": 2900
    },
    {
      "epoch": 4.31918008784773,
      "grad_norm": 2.370459794998169,
      "learning_rate": 2.7291361639824306e-06,
      "loss": 0.6427,
      "step": 2950
    },
    {
      "epoch": 4.392386530014641,
      "grad_norm": 2.1006791591644287,
      "learning_rate": 2.436310395314788e-06,
      "loss": 0.6207,
      "step": 3000
    },
    {
      "epoch": 4.465592972181552,
      "grad_norm": 17.736797332763672,
      "learning_rate": 2.1434846266471453e-06,
      "loss": 0.6413,
      "step": 3050
    },
    {
      "epoch": 4.538799414348462,
      "grad_norm": 2.149487018585205,
      "learning_rate": 1.8506588579795024e-06,
      "loss": 0.6354,
      "step": 3100
    },
    {
      "epoch": 4.612005856515373,
      "grad_norm": 2.3940281867980957,
      "learning_rate": 1.5578330893118595e-06,
      "loss": 0.6342,
      "step": 3150
    },
    {
      "epoch": 4.685212298682284,
      "grad_norm": 2.103952646255493,
      "learning_rate": 1.2650073206442169e-06,
      "loss": 0.6341,
      "step": 3200
    },
    {
      "epoch": 4.758418740849194,
      "grad_norm": 3.5245349407196045,
      "learning_rate": 9.72181551976574e-07,
      "loss": 0.6348,
      "step": 3250
    },
    {
      "epoch": 4.831625183016105,
      "grad_norm": 2.1685941219329834,
      "learning_rate": 6.793557833089313e-07,
      "loss": 0.6469,
      "step": 3300
    },
    {
      "epoch": 4.904831625183016,
      "grad_norm": 2.7275354862213135,
      "learning_rate": 3.865300146412885e-07,
      "loss": 0.6309,
      "step": 3350
    },
    {
      "epoch": 4.978038067349927,
      "grad_norm": 2.66701602935791,
      "learning_rate": 9.370424597364569e-08,
      "loss": 0.6405,
      "step": 3400
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.5995607613469985,
      "eval_loss": 0.6519700288772583,
      "eval_runtime": 22.7428,
      "eval_samples_per_second": 120.126,
      "eval_steps_per_second": 1.891,
      "step": 3415
    }
  ],
  "logging_steps": 50,
  "max_steps": 3415,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 3.33697966920192e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}