Text2Text Generation
English
pseudonymization-seq2seq / spacy /trainer_state.json
olexandryermilov's picture
Initiaal commit
89956b5
raw
history blame
11.7 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"global_step": 45807,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 4.9454231885956296e-05,
"loss": 1.6382,
"step": 500
},
{
"epoch": 0.07,
"learning_rate": 4.89084637719126e-05,
"loss": 1.4459,
"step": 1000
},
{
"epoch": 0.1,
"learning_rate": 4.836269565786889e-05,
"loss": 1.3761,
"step": 1500
},
{
"epoch": 0.13,
"learning_rate": 4.781692754382518e-05,
"loss": 1.3464,
"step": 2000
},
{
"epoch": 0.16,
"learning_rate": 4.727115942978148e-05,
"loss": 1.312,
"step": 2500
},
{
"epoch": 0.2,
"learning_rate": 4.672539131573777e-05,
"loss": 1.2837,
"step": 3000
},
{
"epoch": 0.23,
"learning_rate": 4.6179623201694066e-05,
"loss": 1.2755,
"step": 3500
},
{
"epoch": 0.26,
"learning_rate": 4.563385508765036e-05,
"loss": 1.2409,
"step": 4000
},
{
"epoch": 0.29,
"learning_rate": 4.508808697360666e-05,
"loss": 1.2413,
"step": 4500
},
{
"epoch": 0.33,
"learning_rate": 4.4542318859562955e-05,
"loss": 1.2013,
"step": 5000
},
{
"epoch": 0.36,
"learning_rate": 4.399655074551924e-05,
"loss": 1.2081,
"step": 5500
},
{
"epoch": 0.39,
"learning_rate": 4.345078263147554e-05,
"loss": 1.1968,
"step": 6000
},
{
"epoch": 0.43,
"learning_rate": 4.2905014517431836e-05,
"loss": 1.1905,
"step": 6500
},
{
"epoch": 0.46,
"learning_rate": 4.235924640338813e-05,
"loss": 1.1819,
"step": 7000
},
{
"epoch": 0.49,
"learning_rate": 4.1813478289344424e-05,
"loss": 1.1742,
"step": 7500
},
{
"epoch": 0.52,
"learning_rate": 4.1267710175300724e-05,
"loss": 1.1643,
"step": 8000
},
{
"epoch": 0.56,
"learning_rate": 4.072194206125701e-05,
"loss": 1.1635,
"step": 8500
},
{
"epoch": 0.59,
"learning_rate": 4.0176173947213305e-05,
"loss": 1.1576,
"step": 9000
},
{
"epoch": 0.62,
"learning_rate": 3.9630405833169606e-05,
"loss": 1.1285,
"step": 9500
},
{
"epoch": 0.65,
"learning_rate": 3.90846377191259e-05,
"loss": 1.1492,
"step": 10000
},
{
"epoch": 0.69,
"learning_rate": 3.8538869605082194e-05,
"loss": 1.1324,
"step": 10500
},
{
"epoch": 0.72,
"learning_rate": 3.799310149103849e-05,
"loss": 1.1287,
"step": 11000
},
{
"epoch": 0.75,
"learning_rate": 3.744733337699479e-05,
"loss": 1.1413,
"step": 11500
},
{
"epoch": 0.79,
"learning_rate": 3.6901565262951075e-05,
"loss": 1.118,
"step": 12000
},
{
"epoch": 0.82,
"learning_rate": 3.635579714890737e-05,
"loss": 1.1147,
"step": 12500
},
{
"epoch": 0.85,
"learning_rate": 3.581002903486367e-05,
"loss": 1.1188,
"step": 13000
},
{
"epoch": 0.88,
"learning_rate": 3.5264260920819964e-05,
"loss": 1.1077,
"step": 13500
},
{
"epoch": 0.92,
"learning_rate": 3.471849280677626e-05,
"loss": 1.1016,
"step": 14000
},
{
"epoch": 0.95,
"learning_rate": 3.417272469273256e-05,
"loss": 1.1124,
"step": 14500
},
{
"epoch": 0.98,
"learning_rate": 3.362695657868885e-05,
"loss": 1.0993,
"step": 15000
},
{
"epoch": 1.02,
"learning_rate": 3.308118846464514e-05,
"loss": 1.0778,
"step": 15500
},
{
"epoch": 1.05,
"learning_rate": 3.253542035060144e-05,
"loss": 1.0797,
"step": 16000
},
{
"epoch": 1.08,
"learning_rate": 3.1989652236557734e-05,
"loss": 1.0757,
"step": 16500
},
{
"epoch": 1.11,
"learning_rate": 3.144388412251403e-05,
"loss": 1.0684,
"step": 17000
},
{
"epoch": 1.15,
"learning_rate": 3.089811600847032e-05,
"loss": 1.0735,
"step": 17500
},
{
"epoch": 1.18,
"learning_rate": 3.035234789442662e-05,
"loss": 1.0597,
"step": 18000
},
{
"epoch": 1.21,
"learning_rate": 2.9806579780382916e-05,
"loss": 1.0563,
"step": 18500
},
{
"epoch": 1.24,
"learning_rate": 2.9260811666339206e-05,
"loss": 1.0599,
"step": 19000
},
{
"epoch": 1.28,
"learning_rate": 2.87150435522955e-05,
"loss": 1.0488,
"step": 19500
},
{
"epoch": 1.31,
"learning_rate": 2.8169275438251797e-05,
"loss": 1.0554,
"step": 20000
},
{
"epoch": 1.34,
"learning_rate": 2.762350732420809e-05,
"loss": 1.0584,
"step": 20500
},
{
"epoch": 1.38,
"learning_rate": 2.707773921016439e-05,
"loss": 1.0517,
"step": 21000
},
{
"epoch": 1.41,
"learning_rate": 2.6531971096120682e-05,
"loss": 1.0518,
"step": 21500
},
{
"epoch": 1.44,
"learning_rate": 2.5986202982076973e-05,
"loss": 1.0526,
"step": 22000
},
{
"epoch": 1.47,
"learning_rate": 2.544043486803327e-05,
"loss": 1.0544,
"step": 22500
},
{
"epoch": 1.51,
"learning_rate": 2.4894666753989564e-05,
"loss": 1.049,
"step": 23000
},
{
"epoch": 1.54,
"learning_rate": 2.434889863994586e-05,
"loss": 1.0368,
"step": 23500
},
{
"epoch": 1.57,
"learning_rate": 2.3803130525902155e-05,
"loss": 1.0358,
"step": 24000
},
{
"epoch": 1.6,
"learning_rate": 2.325736241185845e-05,
"loss": 1.0322,
"step": 24500
},
{
"epoch": 1.64,
"learning_rate": 2.2711594297814746e-05,
"loss": 1.0346,
"step": 25000
},
{
"epoch": 1.67,
"learning_rate": 2.216582618377104e-05,
"loss": 1.0306,
"step": 25500
},
{
"epoch": 1.7,
"learning_rate": 2.1620058069727337e-05,
"loss": 1.0452,
"step": 26000
},
{
"epoch": 1.74,
"learning_rate": 2.1074289955683628e-05,
"loss": 1.029,
"step": 26500
},
{
"epoch": 1.77,
"learning_rate": 2.0528521841639925e-05,
"loss": 1.0272,
"step": 27000
},
{
"epoch": 1.8,
"learning_rate": 1.9982753727596222e-05,
"loss": 1.0333,
"step": 27500
},
{
"epoch": 1.83,
"learning_rate": 1.9436985613552513e-05,
"loss": 1.0249,
"step": 28000
},
{
"epoch": 1.87,
"learning_rate": 1.889121749950881e-05,
"loss": 1.026,
"step": 28500
},
{
"epoch": 1.9,
"learning_rate": 1.8345449385465104e-05,
"loss": 1.0333,
"step": 29000
},
{
"epoch": 1.93,
"learning_rate": 1.77996812714214e-05,
"loss": 1.0298,
"step": 29500
},
{
"epoch": 1.96,
"learning_rate": 1.7253913157377695e-05,
"loss": 1.0357,
"step": 30000
},
{
"epoch": 2.0,
"learning_rate": 1.670814504333399e-05,
"loss": 1.0204,
"step": 30500
},
{
"epoch": 2.03,
"learning_rate": 1.6162376929290286e-05,
"loss": 1.0019,
"step": 31000
},
{
"epoch": 2.06,
"learning_rate": 1.5616608815246576e-05,
"loss": 1.0006,
"step": 31500
},
{
"epoch": 2.1,
"learning_rate": 1.5070840701202874e-05,
"loss": 1.007,
"step": 32000
},
{
"epoch": 2.13,
"learning_rate": 1.452507258715917e-05,
"loss": 1.0071,
"step": 32500
},
{
"epoch": 2.16,
"learning_rate": 1.3979304473115461e-05,
"loss": 1.0002,
"step": 33000
},
{
"epoch": 2.19,
"learning_rate": 1.3433536359071759e-05,
"loss": 1.0088,
"step": 33500
},
{
"epoch": 2.23,
"learning_rate": 1.2887768245028054e-05,
"loss": 1.0037,
"step": 34000
},
{
"epoch": 2.26,
"learning_rate": 1.2342000130984348e-05,
"loss": 1.0029,
"step": 34500
},
{
"epoch": 2.29,
"learning_rate": 1.1796232016940644e-05,
"loss": 1.0053,
"step": 35000
},
{
"epoch": 2.32,
"learning_rate": 1.1250463902896937e-05,
"loss": 0.9949,
"step": 35500
},
{
"epoch": 2.36,
"learning_rate": 1.0704695788853231e-05,
"loss": 0.9993,
"step": 36000
},
{
"epoch": 2.39,
"learning_rate": 1.0158927674809529e-05,
"loss": 0.9943,
"step": 36500
},
{
"epoch": 2.42,
"learning_rate": 9.613159560765822e-06,
"loss": 1.0047,
"step": 37000
},
{
"epoch": 2.46,
"learning_rate": 9.067391446722118e-06,
"loss": 0.9933,
"step": 37500
},
{
"epoch": 2.49,
"learning_rate": 8.521623332678412e-06,
"loss": 0.9915,
"step": 38000
},
{
"epoch": 2.52,
"learning_rate": 7.975855218634706e-06,
"loss": 0.9846,
"step": 38500
},
{
"epoch": 2.55,
"learning_rate": 7.430087104591002e-06,
"loss": 0.9901,
"step": 39000
},
{
"epoch": 2.59,
"learning_rate": 6.884318990547296e-06,
"loss": 0.9887,
"step": 39500
},
{
"epoch": 2.62,
"learning_rate": 6.338550876503592e-06,
"loss": 0.9959,
"step": 40000
},
{
"epoch": 2.65,
"learning_rate": 5.792782762459886e-06,
"loss": 0.9942,
"step": 40500
},
{
"epoch": 2.69,
"learning_rate": 5.247014648416181e-06,
"loss": 1.0078,
"step": 41000
},
{
"epoch": 2.72,
"learning_rate": 4.701246534372476e-06,
"loss": 0.9922,
"step": 41500
},
{
"epoch": 2.75,
"learning_rate": 4.155478420328771e-06,
"loss": 0.9876,
"step": 42000
},
{
"epoch": 2.78,
"learning_rate": 3.6097103062850654e-06,
"loss": 0.9978,
"step": 42500
},
{
"epoch": 2.82,
"learning_rate": 3.0639421922413605e-06,
"loss": 0.9917,
"step": 43000
},
{
"epoch": 2.85,
"learning_rate": 2.5181740781976556e-06,
"loss": 0.9875,
"step": 43500
},
{
"epoch": 2.88,
"learning_rate": 1.9724059641539503e-06,
"loss": 0.9979,
"step": 44000
},
{
"epoch": 2.91,
"learning_rate": 1.4266378501102453e-06,
"loss": 0.9892,
"step": 44500
},
{
"epoch": 2.95,
"learning_rate": 8.808697360665402e-07,
"loss": 0.9923,
"step": 45000
},
{
"epoch": 2.98,
"learning_rate": 3.35101622022835e-07,
"loss": 0.9898,
"step": 45500
},
{
"epoch": 3.0,
"step": 45807,
"total_flos": 6.509187922187059e+17,
"train_loss": 1.0828881245932322,
"train_runtime": 19368.7282,
"train_samples_per_second": 75.677,
"train_steps_per_second": 2.365
}
],
"max_steps": 45807,
"num_train_epochs": 3,
"total_flos": 6.509187922187059e+17,
"trial_name": null,
"trial_params": null
}