BERT-mdgender-convai-ternary / trainer_state.json
Cameron Clarke
add updated model files
b8ad197
{
"best_metric": 0.8275862068965517,
"best_model_checkpoint": "/scratch/ccc779/md_gender_convai_ternary_model/checkpoint-131438",
"epoch": 2.0,
"global_step": 131438,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 1.2135202030247535e-05,
"loss": 0.97,
"step": 500
},
{
"epoch": 0.02,
"learning_rate": 1.208886253357641e-05,
"loss": 0.8436,
"step": 1000
},
{
"epoch": 0.02,
"learning_rate": 1.2042523036905285e-05,
"loss": 1.0016,
"step": 1500
},
{
"epoch": 0.03,
"learning_rate": 1.199618354023416e-05,
"loss": 0.9233,
"step": 2000
},
{
"epoch": 0.04,
"learning_rate": 1.1949844043563036e-05,
"loss": 0.9718,
"step": 2500
},
{
"epoch": 0.05,
"learning_rate": 1.190350454689191e-05,
"loss": 0.9926,
"step": 3000
},
{
"epoch": 0.05,
"learning_rate": 1.1857165050220785e-05,
"loss": 0.9396,
"step": 3500
},
{
"epoch": 0.06,
"learning_rate": 1.181082555354966e-05,
"loss": 0.9144,
"step": 4000
},
{
"epoch": 0.07,
"learning_rate": 1.1764486056878534e-05,
"loss": 0.8765,
"step": 4500
},
{
"epoch": 0.08,
"learning_rate": 1.171814656020741e-05,
"loss": 0.8983,
"step": 5000
},
{
"epoch": 0.08,
"learning_rate": 1.1671807063536285e-05,
"loss": 0.9176,
"step": 5500
},
{
"epoch": 0.09,
"learning_rate": 1.162546756686516e-05,
"loss": 0.9547,
"step": 6000
},
{
"epoch": 0.1,
"learning_rate": 1.1579128070194034e-05,
"loss": 0.8182,
"step": 6500
},
{
"epoch": 0.11,
"learning_rate": 1.153278857352291e-05,
"loss": 0.8777,
"step": 7000
},
{
"epoch": 0.11,
"learning_rate": 1.1486449076851784e-05,
"loss": 0.8809,
"step": 7500
},
{
"epoch": 0.12,
"learning_rate": 1.144010958018066e-05,
"loss": 0.9266,
"step": 8000
},
{
"epoch": 0.13,
"learning_rate": 1.1393770083509534e-05,
"loss": 0.9281,
"step": 8500
},
{
"epoch": 0.14,
"learning_rate": 1.134743058683841e-05,
"loss": 0.8483,
"step": 9000
},
{
"epoch": 0.14,
"learning_rate": 1.1301091090167285e-05,
"loss": 0.8762,
"step": 9500
},
{
"epoch": 0.15,
"learning_rate": 1.1254751593496159e-05,
"loss": 0.9793,
"step": 10000
},
{
"epoch": 0.16,
"learning_rate": 1.1208412096825035e-05,
"loss": 0.9105,
"step": 10500
},
{
"epoch": 0.17,
"learning_rate": 1.116207260015391e-05,
"loss": 0.7965,
"step": 11000
},
{
"epoch": 0.17,
"learning_rate": 1.1115733103482786e-05,
"loss": 0.86,
"step": 11500
},
{
"epoch": 0.18,
"learning_rate": 1.106939360681166e-05,
"loss": 0.9278,
"step": 12000
},
{
"epoch": 0.19,
"learning_rate": 1.1023054110140535e-05,
"loss": 0.8292,
"step": 12500
},
{
"epoch": 0.2,
"learning_rate": 1.0976714613469409e-05,
"loss": 0.8638,
"step": 13000
},
{
"epoch": 0.21,
"learning_rate": 1.0930375116798284e-05,
"loss": 0.8204,
"step": 13500
},
{
"epoch": 0.21,
"learning_rate": 1.088403562012716e-05,
"loss": 0.8842,
"step": 14000
},
{
"epoch": 0.22,
"learning_rate": 1.0837696123456035e-05,
"loss": 0.8406,
"step": 14500
},
{
"epoch": 0.23,
"learning_rate": 1.079135662678491e-05,
"loss": 0.8279,
"step": 15000
},
{
"epoch": 0.24,
"learning_rate": 1.0745017130113784e-05,
"loss": 0.8094,
"step": 15500
},
{
"epoch": 0.24,
"learning_rate": 1.069867763344266e-05,
"loss": 0.8117,
"step": 16000
},
{
"epoch": 0.25,
"learning_rate": 1.0652338136771533e-05,
"loss": 0.7755,
"step": 16500
},
{
"epoch": 0.26,
"learning_rate": 1.0605998640100409e-05,
"loss": 0.8578,
"step": 17000
},
{
"epoch": 0.27,
"learning_rate": 1.0559659143429284e-05,
"loss": 0.8197,
"step": 17500
},
{
"epoch": 0.27,
"learning_rate": 1.051331964675816e-05,
"loss": 0.7661,
"step": 18000
},
{
"epoch": 0.28,
"learning_rate": 1.0466980150087035e-05,
"loss": 0.8264,
"step": 18500
},
{
"epoch": 0.29,
"learning_rate": 1.0420640653415909e-05,
"loss": 0.7782,
"step": 19000
},
{
"epoch": 0.3,
"learning_rate": 1.0374301156744785e-05,
"loss": 0.8347,
"step": 19500
},
{
"epoch": 0.3,
"learning_rate": 1.0327961660073658e-05,
"loss": 0.817,
"step": 20000
},
{
"epoch": 0.31,
"learning_rate": 1.0281622163402535e-05,
"loss": 0.806,
"step": 20500
},
{
"epoch": 0.32,
"learning_rate": 1.023528266673141e-05,
"loss": 0.8229,
"step": 21000
},
{
"epoch": 0.33,
"learning_rate": 1.0188943170060285e-05,
"loss": 0.8891,
"step": 21500
},
{
"epoch": 0.33,
"learning_rate": 1.0142603673389158e-05,
"loss": 0.9,
"step": 22000
},
{
"epoch": 0.34,
"learning_rate": 1.0096264176718034e-05,
"loss": 0.7981,
"step": 22500
},
{
"epoch": 0.35,
"learning_rate": 1.004992468004691e-05,
"loss": 0.8458,
"step": 23000
},
{
"epoch": 0.36,
"learning_rate": 1.0003585183375783e-05,
"loss": 0.834,
"step": 23500
},
{
"epoch": 0.37,
"learning_rate": 9.95724568670466e-06,
"loss": 0.8188,
"step": 24000
},
{
"epoch": 0.37,
"learning_rate": 9.910906190033534e-06,
"loss": 0.8165,
"step": 24500
},
{
"epoch": 0.38,
"learning_rate": 9.86456669336241e-06,
"loss": 0.8537,
"step": 25000
},
{
"epoch": 0.39,
"learning_rate": 9.818227196691283e-06,
"loss": 0.7667,
"step": 25500
},
{
"epoch": 0.4,
"learning_rate": 9.771887700020159e-06,
"loss": 0.7433,
"step": 26000
},
{
"epoch": 0.4,
"learning_rate": 9.725548203349034e-06,
"loss": 0.8836,
"step": 26500
},
{
"epoch": 0.41,
"learning_rate": 9.67920870667791e-06,
"loss": 0.7998,
"step": 27000
},
{
"epoch": 0.42,
"learning_rate": 9.632869210006785e-06,
"loss": 0.784,
"step": 27500
},
{
"epoch": 0.43,
"learning_rate": 9.586529713335659e-06,
"loss": 0.8494,
"step": 28000
},
{
"epoch": 0.43,
"learning_rate": 9.540190216664534e-06,
"loss": 0.862,
"step": 28500
},
{
"epoch": 0.44,
"learning_rate": 9.493850719993408e-06,
"loss": 0.7669,
"step": 29000
},
{
"epoch": 0.45,
"learning_rate": 9.447511223322284e-06,
"loss": 0.793,
"step": 29500
},
{
"epoch": 0.46,
"learning_rate": 9.401171726651159e-06,
"loss": 0.7934,
"step": 30000
},
{
"epoch": 0.46,
"learning_rate": 9.354832229980035e-06,
"loss": 0.8459,
"step": 30500
},
{
"epoch": 0.47,
"learning_rate": 9.308492733308908e-06,
"loss": 0.7797,
"step": 31000
},
{
"epoch": 0.48,
"learning_rate": 9.262153236637784e-06,
"loss": 0.8046,
"step": 31500
},
{
"epoch": 0.49,
"learning_rate": 9.21581373996666e-06,
"loss": 0.7799,
"step": 32000
},
{
"epoch": 0.49,
"learning_rate": 9.169474243295533e-06,
"loss": 0.8351,
"step": 32500
},
{
"epoch": 0.5,
"learning_rate": 9.12313474662441e-06,
"loss": 0.7595,
"step": 33000
},
{
"epoch": 0.51,
"learning_rate": 9.076795249953284e-06,
"loss": 0.7491,
"step": 33500
},
{
"epoch": 0.52,
"learning_rate": 9.03045575328216e-06,
"loss": 0.8001,
"step": 34000
},
{
"epoch": 0.52,
"learning_rate": 8.984116256611033e-06,
"loss": 0.7088,
"step": 34500
},
{
"epoch": 0.53,
"learning_rate": 8.937776759939909e-06,
"loss": 0.8585,
"step": 35000
},
{
"epoch": 0.54,
"learning_rate": 8.891437263268784e-06,
"loss": 0.788,
"step": 35500
},
{
"epoch": 0.55,
"learning_rate": 8.845097766597658e-06,
"loss": 0.7944,
"step": 36000
},
{
"epoch": 0.56,
"learning_rate": 8.798758269926535e-06,
"loss": 0.7515,
"step": 36500
},
{
"epoch": 0.56,
"learning_rate": 8.752418773255409e-06,
"loss": 0.726,
"step": 37000
},
{
"epoch": 0.57,
"learning_rate": 8.706079276584284e-06,
"loss": 0.7129,
"step": 37500
},
{
"epoch": 0.58,
"learning_rate": 8.659739779913158e-06,
"loss": 0.8299,
"step": 38000
},
{
"epoch": 0.59,
"learning_rate": 8.613400283242034e-06,
"loss": 0.7474,
"step": 38500
},
{
"epoch": 0.59,
"learning_rate": 8.567060786570907e-06,
"loss": 0.8529,
"step": 39000
},
{
"epoch": 0.6,
"learning_rate": 8.520721289899785e-06,
"loss": 0.744,
"step": 39500
},
{
"epoch": 0.61,
"learning_rate": 8.474381793228658e-06,
"loss": 0.7902,
"step": 40000
},
{
"epoch": 0.62,
"learning_rate": 8.428042296557534e-06,
"loss": 0.7782,
"step": 40500
},
{
"epoch": 0.62,
"learning_rate": 8.38170279988641e-06,
"loss": 0.8096,
"step": 41000
},
{
"epoch": 0.63,
"learning_rate": 8.335363303215283e-06,
"loss": 0.8217,
"step": 41500
},
{
"epoch": 0.64,
"learning_rate": 8.289023806544158e-06,
"loss": 0.7936,
"step": 42000
},
{
"epoch": 0.65,
"learning_rate": 8.242684309873034e-06,
"loss": 0.7779,
"step": 42500
},
{
"epoch": 0.65,
"learning_rate": 8.19634481320191e-06,
"loss": 0.8445,
"step": 43000
},
{
"epoch": 0.66,
"learning_rate": 8.150005316530783e-06,
"loss": 0.7202,
"step": 43500
},
{
"epoch": 0.67,
"learning_rate": 8.103665819859659e-06,
"loss": 0.7763,
"step": 44000
},
{
"epoch": 0.68,
"learning_rate": 8.057326323188534e-06,
"loss": 0.7784,
"step": 44500
},
{
"epoch": 0.68,
"learning_rate": 8.010986826517408e-06,
"loss": 0.7495,
"step": 45000
},
{
"epoch": 0.69,
"learning_rate": 7.964647329846283e-06,
"loss": 0.7319,
"step": 45500
},
{
"epoch": 0.7,
"learning_rate": 7.918307833175159e-06,
"loss": 0.8379,
"step": 46000
},
{
"epoch": 0.71,
"learning_rate": 7.871968336504034e-06,
"loss": 0.7961,
"step": 46500
},
{
"epoch": 0.72,
"learning_rate": 7.825628839832908e-06,
"loss": 0.7989,
"step": 47000
},
{
"epoch": 0.72,
"learning_rate": 7.779289343161783e-06,
"loss": 0.8076,
"step": 47500
},
{
"epoch": 0.73,
"learning_rate": 7.732949846490657e-06,
"loss": 0.7502,
"step": 48000
},
{
"epoch": 0.74,
"learning_rate": 7.686610349819533e-06,
"loss": 0.7824,
"step": 48500
},
{
"epoch": 0.75,
"learning_rate": 7.640270853148408e-06,
"loss": 0.8043,
"step": 49000
},
{
"epoch": 0.75,
"learning_rate": 7.593931356477284e-06,
"loss": 0.757,
"step": 49500
},
{
"epoch": 0.76,
"learning_rate": 7.547591859806158e-06,
"loss": 0.7516,
"step": 50000
},
{
"epoch": 0.77,
"learning_rate": 7.501252363135033e-06,
"loss": 0.8096,
"step": 50500
},
{
"epoch": 0.78,
"learning_rate": 7.4549128664639075e-06,
"loss": 0.8333,
"step": 51000
},
{
"epoch": 0.78,
"learning_rate": 7.408573369792783e-06,
"loss": 0.7646,
"step": 51500
},
{
"epoch": 0.79,
"learning_rate": 7.3622338731216584e-06,
"loss": 0.7475,
"step": 52000
},
{
"epoch": 0.8,
"learning_rate": 7.315894376450534e-06,
"loss": 0.796,
"step": 52500
},
{
"epoch": 0.81,
"learning_rate": 7.2695548797794085e-06,
"loss": 0.7512,
"step": 53000
},
{
"epoch": 0.81,
"learning_rate": 7.223215383108283e-06,
"loss": 0.785,
"step": 53500
},
{
"epoch": 0.82,
"learning_rate": 7.176875886437158e-06,
"loss": 0.8754,
"step": 54000
},
{
"epoch": 0.83,
"learning_rate": 7.130536389766032e-06,
"loss": 0.8607,
"step": 54500
},
{
"epoch": 0.84,
"learning_rate": 7.084196893094909e-06,
"loss": 0.6862,
"step": 55000
},
{
"epoch": 0.84,
"learning_rate": 7.037857396423783e-06,
"loss": 0.74,
"step": 55500
},
{
"epoch": 0.85,
"learning_rate": 6.991517899752658e-06,
"loss": 0.7719,
"step": 56000
},
{
"epoch": 0.86,
"learning_rate": 6.945178403081533e-06,
"loss": 0.8145,
"step": 56500
},
{
"epoch": 0.87,
"learning_rate": 6.898838906410408e-06,
"loss": 0.7445,
"step": 57000
},
{
"epoch": 0.87,
"learning_rate": 6.852499409739283e-06,
"loss": 0.7442,
"step": 57500
},
{
"epoch": 0.88,
"learning_rate": 6.806159913068157e-06,
"loss": 0.7485,
"step": 58000
},
{
"epoch": 0.89,
"learning_rate": 6.7598204163970336e-06,
"loss": 0.7928,
"step": 58500
},
{
"epoch": 0.9,
"learning_rate": 6.713480919725908e-06,
"loss": 0.755,
"step": 59000
},
{
"epoch": 0.91,
"learning_rate": 6.667141423054783e-06,
"loss": 0.7776,
"step": 59500
},
{
"epoch": 0.91,
"learning_rate": 6.6208019263836574e-06,
"loss": 0.7751,
"step": 60000
},
{
"epoch": 0.92,
"learning_rate": 6.574462429712533e-06,
"loss": 0.7002,
"step": 60500
},
{
"epoch": 0.93,
"learning_rate": 6.5281229330414075e-06,
"loss": 0.6988,
"step": 61000
},
{
"epoch": 0.94,
"learning_rate": 6.481783436370284e-06,
"loss": 0.7816,
"step": 61500
},
{
"epoch": 0.94,
"learning_rate": 6.4354439396991584e-06,
"loss": 0.749,
"step": 62000
},
{
"epoch": 0.95,
"learning_rate": 6.389104443028033e-06,
"loss": 0.6716,
"step": 62500
},
{
"epoch": 0.96,
"learning_rate": 6.342764946356908e-06,
"loss": 0.8237,
"step": 63000
},
{
"epoch": 0.97,
"learning_rate": 6.296425449685782e-06,
"loss": 0.6827,
"step": 63500
},
{
"epoch": 0.97,
"learning_rate": 6.250085953014657e-06,
"loss": 0.7911,
"step": 64000
},
{
"epoch": 0.98,
"learning_rate": 6.203746456343533e-06,
"loss": 0.7225,
"step": 64500
},
{
"epoch": 0.99,
"learning_rate": 6.157406959672408e-06,
"loss": 0.7058,
"step": 65000
},
{
"epoch": 1.0,
"learning_rate": 6.111067463001283e-06,
"loss": 0.7854,
"step": 65500
},
{
"epoch": 1.0,
"eval_accuracy": 0.8102807332393283,
"eval_f1": 0.8102807332393283,
"eval_loss": 0.8477435111999512,
"eval_precision": 0.8102807332393283,
"eval_recall": 0.8102807332393283,
"eval_runtime": 31.5242,
"eval_samples_per_second": 247.461,
"step": 65719
},
{
"epoch": 1.0,
"learning_rate": 6.064727966330158e-06,
"loss": 0.6451,
"step": 66000
},
{
"epoch": 1.01,
"learning_rate": 6.0183884696590325e-06,
"loss": 0.5225,
"step": 66500
},
{
"epoch": 1.02,
"learning_rate": 5.972048972987908e-06,
"loss": 0.5895,
"step": 67000
},
{
"epoch": 1.03,
"learning_rate": 5.925709476316783e-06,
"loss": 0.6018,
"step": 67500
},
{
"epoch": 1.03,
"learning_rate": 5.879369979645657e-06,
"loss": 0.4894,
"step": 68000
},
{
"epoch": 1.04,
"learning_rate": 5.833030482974533e-06,
"loss": 0.5711,
"step": 68500
},
{
"epoch": 1.05,
"learning_rate": 5.786690986303407e-06,
"loss": 0.536,
"step": 69000
},
{
"epoch": 1.06,
"learning_rate": 5.740351489632283e-06,
"loss": 0.5781,
"step": 69500
},
{
"epoch": 1.07,
"learning_rate": 5.694011992961158e-06,
"loss": 0.5464,
"step": 70000
},
{
"epoch": 1.07,
"learning_rate": 5.647672496290033e-06,
"loss": 0.5311,
"step": 70500
},
{
"epoch": 1.08,
"learning_rate": 5.6013329996189075e-06,
"loss": 0.6152,
"step": 71000
},
{
"epoch": 1.09,
"learning_rate": 5.554993502947783e-06,
"loss": 0.5713,
"step": 71500
},
{
"epoch": 1.1,
"learning_rate": 5.508654006276658e-06,
"loss": 0.5792,
"step": 72000
},
{
"epoch": 1.1,
"learning_rate": 5.462314509605532e-06,
"loss": 0.6048,
"step": 72500
},
{
"epoch": 1.11,
"learning_rate": 5.415975012934407e-06,
"loss": 0.4939,
"step": 73000
},
{
"epoch": 1.12,
"learning_rate": 5.369635516263282e-06,
"loss": 0.5341,
"step": 73500
},
{
"epoch": 1.13,
"learning_rate": 5.323296019592158e-06,
"loss": 0.6046,
"step": 74000
},
{
"epoch": 1.13,
"learning_rate": 5.276956522921032e-06,
"loss": 0.609,
"step": 74500
},
{
"epoch": 1.14,
"learning_rate": 5.230617026249908e-06,
"loss": 0.6428,
"step": 75000
},
{
"epoch": 1.15,
"learning_rate": 5.1842775295787825e-06,
"loss": 0.5532,
"step": 75500
},
{
"epoch": 1.16,
"learning_rate": 5.137938032907657e-06,
"loss": 0.5404,
"step": 76000
},
{
"epoch": 1.16,
"learning_rate": 5.0915985362365325e-06,
"loss": 0.5694,
"step": 76500
},
{
"epoch": 1.17,
"learning_rate": 5.045259039565407e-06,
"loss": 0.6135,
"step": 77000
},
{
"epoch": 1.18,
"learning_rate": 4.998919542894282e-06,
"loss": 0.476,
"step": 77500
},
{
"epoch": 1.19,
"learning_rate": 4.952580046223157e-06,
"loss": 0.6044,
"step": 78000
},
{
"epoch": 1.19,
"learning_rate": 4.906240549552033e-06,
"loss": 0.4917,
"step": 78500
},
{
"epoch": 1.2,
"learning_rate": 4.859901052880907e-06,
"loss": 0.5818,
"step": 79000
},
{
"epoch": 1.21,
"learning_rate": 4.813561556209783e-06,
"loss": 0.5566,
"step": 79500
},
{
"epoch": 1.22,
"learning_rate": 4.767222059538657e-06,
"loss": 0.5429,
"step": 80000
},
{
"epoch": 1.22,
"learning_rate": 4.720882562867532e-06,
"loss": 0.5324,
"step": 80500
},
{
"epoch": 1.23,
"learning_rate": 4.6745430661964075e-06,
"loss": 0.6156,
"step": 81000
},
{
"epoch": 1.24,
"learning_rate": 4.628203569525282e-06,
"loss": 0.5669,
"step": 81500
},
{
"epoch": 1.25,
"learning_rate": 4.581864072854157e-06,
"loss": 0.5366,
"step": 82000
},
{
"epoch": 1.26,
"learning_rate": 4.535524576183032e-06,
"loss": 0.585,
"step": 82500
},
{
"epoch": 1.26,
"learning_rate": 4.489185079511908e-06,
"loss": 0.6453,
"step": 83000
},
{
"epoch": 1.27,
"learning_rate": 4.442845582840782e-06,
"loss": 0.5645,
"step": 83500
},
{
"epoch": 1.28,
"learning_rate": 4.396506086169657e-06,
"loss": 0.4818,
"step": 84000
},
{
"epoch": 1.29,
"learning_rate": 4.350166589498532e-06,
"loss": 0.5146,
"step": 84500
},
{
"epoch": 1.29,
"learning_rate": 4.303827092827407e-06,
"loss": 0.4498,
"step": 85000
},
{
"epoch": 1.3,
"learning_rate": 4.257487596156282e-06,
"loss": 0.5887,
"step": 85500
},
{
"epoch": 1.31,
"learning_rate": 4.211148099485157e-06,
"loss": 0.561,
"step": 86000
},
{
"epoch": 1.32,
"learning_rate": 4.164808602814032e-06,
"loss": 0.5548,
"step": 86500
},
{
"epoch": 1.32,
"learning_rate": 4.118469106142907e-06,
"loss": 0.6372,
"step": 87000
},
{
"epoch": 1.33,
"learning_rate": 4.072129609471782e-06,
"loss": 0.5906,
"step": 87500
},
{
"epoch": 1.34,
"learning_rate": 4.025790112800657e-06,
"loss": 0.5392,
"step": 88000
},
{
"epoch": 1.35,
"learning_rate": 3.979450616129532e-06,
"loss": 0.6352,
"step": 88500
},
{
"epoch": 1.35,
"learning_rate": 3.933111119458407e-06,
"loss": 0.5866,
"step": 89000
},
{
"epoch": 1.36,
"learning_rate": 3.886771622787282e-06,
"loss": 0.5514,
"step": 89500
},
{
"epoch": 1.37,
"learning_rate": 3.8404321261161566e-06,
"loss": 0.6203,
"step": 90000
},
{
"epoch": 1.38,
"learning_rate": 3.794092629445032e-06,
"loss": 0.5595,
"step": 90500
},
{
"epoch": 1.38,
"learning_rate": 3.747753132773907e-06,
"loss": 0.5385,
"step": 91000
},
{
"epoch": 1.39,
"learning_rate": 3.7014136361027817e-06,
"loss": 0.5292,
"step": 91500
},
{
"epoch": 1.4,
"learning_rate": 3.655074139431657e-06,
"loss": 0.5479,
"step": 92000
},
{
"epoch": 1.41,
"learning_rate": 3.6087346427605318e-06,
"loss": 0.5703,
"step": 92500
},
{
"epoch": 1.42,
"learning_rate": 3.562395146089407e-06,
"loss": 0.6236,
"step": 93000
},
{
"epoch": 1.42,
"learning_rate": 3.5160556494182823e-06,
"loss": 0.5756,
"step": 93500
},
{
"epoch": 1.43,
"learning_rate": 3.469716152747157e-06,
"loss": 0.5292,
"step": 94000
},
{
"epoch": 1.44,
"learning_rate": 3.4233766560760315e-06,
"loss": 0.6054,
"step": 94500
},
{
"epoch": 1.45,
"learning_rate": 3.3770371594049066e-06,
"loss": 0.5793,
"step": 95000
},
{
"epoch": 1.45,
"learning_rate": 3.330697662733782e-06,
"loss": 0.5395,
"step": 95500
},
{
"epoch": 1.46,
"learning_rate": 3.2843581660626566e-06,
"loss": 0.6115,
"step": 96000
},
{
"epoch": 1.47,
"learning_rate": 3.2380186693915313e-06,
"loss": 0.4849,
"step": 96500
},
{
"epoch": 1.48,
"learning_rate": 3.1916791727204067e-06,
"loss": 0.464,
"step": 97000
},
{
"epoch": 1.48,
"learning_rate": 3.1453396760492818e-06,
"loss": 0.6028,
"step": 97500
},
{
"epoch": 1.49,
"learning_rate": 3.0990001793781564e-06,
"loss": 0.5619,
"step": 98000
},
{
"epoch": 1.5,
"learning_rate": 3.052660682707032e-06,
"loss": 0.5166,
"step": 98500
},
{
"epoch": 1.51,
"learning_rate": 3.0063211860359065e-06,
"loss": 0.6031,
"step": 99000
},
{
"epoch": 1.51,
"learning_rate": 2.9599816893647815e-06,
"loss": 0.5564,
"step": 99500
},
{
"epoch": 1.52,
"learning_rate": 2.9136421926936566e-06,
"loss": 0.4914,
"step": 100000
},
{
"epoch": 1.53,
"learning_rate": 2.8673026960225316e-06,
"loss": 0.604,
"step": 100500
},
{
"epoch": 1.54,
"learning_rate": 2.8209631993514066e-06,
"loss": 0.5508,
"step": 101000
},
{
"epoch": 1.54,
"learning_rate": 2.7746237026802813e-06,
"loss": 0.6134,
"step": 101500
},
{
"epoch": 1.55,
"learning_rate": 2.7282842060091567e-06,
"loss": 0.5617,
"step": 102000
},
{
"epoch": 1.56,
"learning_rate": 2.6819447093380318e-06,
"loss": 0.4908,
"step": 102500
},
{
"epoch": 1.57,
"learning_rate": 2.6356052126669064e-06,
"loss": 0.5266,
"step": 103000
},
{
"epoch": 1.57,
"learning_rate": 2.5892657159957814e-06,
"loss": 0.5332,
"step": 103500
},
{
"epoch": 1.58,
"learning_rate": 2.5429262193246565e-06,
"loss": 0.5346,
"step": 104000
},
{
"epoch": 1.59,
"learning_rate": 2.4965867226535315e-06,
"loss": 0.5322,
"step": 104500
},
{
"epoch": 1.6,
"learning_rate": 2.4502472259824066e-06,
"loss": 0.5149,
"step": 105000
},
{
"epoch": 1.61,
"learning_rate": 2.403907729311281e-06,
"loss": 0.4975,
"step": 105500
},
{
"epoch": 1.61,
"learning_rate": 2.3575682326401562e-06,
"loss": 0.5733,
"step": 106000
},
{
"epoch": 1.62,
"learning_rate": 2.3112287359690317e-06,
"loss": 0.56,
"step": 106500
},
{
"epoch": 1.63,
"learning_rate": 2.2648892392979063e-06,
"loss": 0.5057,
"step": 107000
},
{
"epoch": 1.64,
"learning_rate": 2.2185497426267813e-06,
"loss": 0.552,
"step": 107500
},
{
"epoch": 1.64,
"learning_rate": 2.1722102459556564e-06,
"loss": 0.5314,
"step": 108000
},
{
"epoch": 1.65,
"learning_rate": 2.1258707492845314e-06,
"loss": 0.5059,
"step": 108500
},
{
"epoch": 1.66,
"learning_rate": 2.0795312526134065e-06,
"loss": 0.6283,
"step": 109000
},
{
"epoch": 1.67,
"learning_rate": 2.033191755942281e-06,
"loss": 0.4504,
"step": 109500
},
{
"epoch": 1.67,
"learning_rate": 1.986852259271156e-06,
"loss": 0.49,
"step": 110000
},
{
"epoch": 1.68,
"learning_rate": 1.940512762600031e-06,
"loss": 0.5386,
"step": 110500
},
{
"epoch": 1.69,
"learning_rate": 1.894173265928906e-06,
"loss": 0.415,
"step": 111000
},
{
"epoch": 1.7,
"learning_rate": 1.8478337692577813e-06,
"loss": 0.4801,
"step": 111500
},
{
"epoch": 1.7,
"learning_rate": 1.8014942725866563e-06,
"loss": 0.5269,
"step": 112000
},
{
"epoch": 1.71,
"learning_rate": 1.7551547759155311e-06,
"loss": 0.541,
"step": 112500
},
{
"epoch": 1.72,
"learning_rate": 1.7088152792444062e-06,
"loss": 0.545,
"step": 113000
},
{
"epoch": 1.73,
"learning_rate": 1.6624757825732812e-06,
"loss": 0.4706,
"step": 113500
},
{
"epoch": 1.73,
"learning_rate": 1.616136285902156e-06,
"loss": 0.5384,
"step": 114000
},
{
"epoch": 1.74,
"learning_rate": 1.569796789231031e-06,
"loss": 0.5383,
"step": 114500
},
{
"epoch": 1.75,
"learning_rate": 1.523457292559906e-06,
"loss": 0.5646,
"step": 115000
},
{
"epoch": 1.76,
"learning_rate": 1.477117795888781e-06,
"loss": 0.5501,
"step": 115500
},
{
"epoch": 1.77,
"learning_rate": 1.430778299217656e-06,
"loss": 0.4665,
"step": 116000
},
{
"epoch": 1.77,
"learning_rate": 1.384438802546531e-06,
"loss": 0.5477,
"step": 116500
},
{
"epoch": 1.78,
"learning_rate": 1.338099305875406e-06,
"loss": 0.4837,
"step": 117000
},
{
"epoch": 1.79,
"learning_rate": 1.291759809204281e-06,
"loss": 0.4897,
"step": 117500
},
{
"epoch": 1.8,
"learning_rate": 1.245420312533156e-06,
"loss": 0.5589,
"step": 118000
},
{
"epoch": 1.8,
"learning_rate": 1.199080815862031e-06,
"loss": 0.4314,
"step": 118500
},
{
"epoch": 1.81,
"learning_rate": 1.1527413191909058e-06,
"loss": 0.557,
"step": 119000
},
{
"epoch": 1.82,
"learning_rate": 1.1064018225197809e-06,
"loss": 0.6037,
"step": 119500
},
{
"epoch": 1.83,
"learning_rate": 1.060062325848656e-06,
"loss": 0.5269,
"step": 120000
},
{
"epoch": 1.83,
"learning_rate": 1.013722829177531e-06,
"loss": 0.4751,
"step": 120500
},
{
"epoch": 1.84,
"learning_rate": 9.673833325064058e-07,
"loss": 0.4963,
"step": 121000
},
{
"epoch": 1.85,
"learning_rate": 9.210438358352809e-07,
"loss": 0.5109,
"step": 121500
},
{
"epoch": 1.86,
"learning_rate": 8.747043391641559e-07,
"loss": 0.4847,
"step": 122000
},
{
"epoch": 1.86,
"learning_rate": 8.283648424930308e-07,
"loss": 0.5456,
"step": 122500
},
{
"epoch": 1.87,
"learning_rate": 7.820253458219057e-07,
"loss": 0.5245,
"step": 123000
},
{
"epoch": 1.88,
"learning_rate": 7.356858491507808e-07,
"loss": 0.5304,
"step": 123500
},
{
"epoch": 1.89,
"learning_rate": 6.893463524796558e-07,
"loss": 0.5908,
"step": 124000
},
{
"epoch": 1.89,
"learning_rate": 6.430068558085308e-07,
"loss": 0.5694,
"step": 124500
},
{
"epoch": 1.9,
"learning_rate": 5.966673591374057e-07,
"loss": 0.4949,
"step": 125000
},
{
"epoch": 1.91,
"learning_rate": 5.503278624662806e-07,
"loss": 0.4919,
"step": 125500
},
{
"epoch": 1.92,
"learning_rate": 5.039883657951557e-07,
"loss": 0.5348,
"step": 126000
},
{
"epoch": 1.92,
"learning_rate": 4.576488691240306e-07,
"loss": 0.49,
"step": 126500
},
{
"epoch": 1.93,
"learning_rate": 4.1130937245290565e-07,
"loss": 0.4791,
"step": 127000
},
{
"epoch": 1.94,
"learning_rate": 3.6496987578178064e-07,
"loss": 0.5993,
"step": 127500
},
{
"epoch": 1.95,
"learning_rate": 3.1863037911065563e-07,
"loss": 0.4965,
"step": 128000
},
{
"epoch": 1.96,
"learning_rate": 2.7229088243953057e-07,
"loss": 0.468,
"step": 128500
},
{
"epoch": 1.96,
"learning_rate": 2.2595138576840556e-07,
"loss": 0.5393,
"step": 129000
},
{
"epoch": 1.97,
"learning_rate": 1.7961188909728057e-07,
"loss": 0.5332,
"step": 129500
},
{
"epoch": 1.98,
"learning_rate": 1.3327239242615553e-07,
"loss": 0.4801,
"step": 130000
},
{
"epoch": 1.99,
"learning_rate": 8.693289575503054e-08,
"loss": 0.4601,
"step": 130500
},
{
"epoch": 1.99,
"learning_rate": 4.059339908390551e-08,
"loss": 0.5695,
"step": 131000
},
{
"epoch": 2.0,
"eval_accuracy": 0.8275862068965517,
"eval_f1": 0.8275862068965517,
"eval_loss": 0.9246299862861633,
"eval_precision": 0.8275862068965517,
"eval_recall": 0.8275862068965517,
"eval_runtime": 31.7083,
"eval_samples_per_second": 246.024,
"step": 131438
}
],
"max_steps": 131438,
"num_train_epochs": 2,
"total_flos": 2885604374424708.0,
"trial_name": null,
"trial_params": null
}