Text2Text Generation
Transformers
PyTorch
English
Kinyarwanda
m2m_100
Inference Endpoints
Nllb_finetuned_general_en_kin / trainer_state.json
Kleber's picture
Upload folder using huggingface_hub
e6cb1d0
raw
history blame
14 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"global_step": 53168,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 4.9529792356304544e-05,
"loss": 0.5805,
"step": 500
},
{
"epoch": 0.04,
"learning_rate": 4.905958471260909e-05,
"loss": 0.566,
"step": 1000
},
{
"epoch": 0.06,
"learning_rate": 4.8589377068913635e-05,
"loss": 0.5748,
"step": 1500
},
{
"epoch": 0.08,
"learning_rate": 4.811916942521818e-05,
"loss": 0.577,
"step": 2000
},
{
"epoch": 0.09,
"learning_rate": 4.7648961781522725e-05,
"loss": 0.5681,
"step": 2500
},
{
"epoch": 0.11,
"learning_rate": 4.717875413782727e-05,
"loss": 0.5619,
"step": 3000
},
{
"epoch": 0.13,
"learning_rate": 4.670854649413181e-05,
"loss": 0.5643,
"step": 3500
},
{
"epoch": 0.15,
"learning_rate": 4.623833885043635e-05,
"loss": 0.5567,
"step": 4000
},
{
"epoch": 0.17,
"learning_rate": 4.57681312067409e-05,
"loss": 0.5544,
"step": 4500
},
{
"epoch": 0.19,
"learning_rate": 4.529792356304544e-05,
"loss": 0.5453,
"step": 5000
},
{
"epoch": 0.21,
"learning_rate": 4.482771591934999e-05,
"loss": 0.5963,
"step": 5500
},
{
"epoch": 0.23,
"learning_rate": 4.435750827565453e-05,
"loss": 0.561,
"step": 6000
},
{
"epoch": 0.24,
"learning_rate": 4.388730063195908e-05,
"loss": 0.584,
"step": 6500
},
{
"epoch": 0.26,
"learning_rate": 4.341709298826362e-05,
"loss": 0.5583,
"step": 7000
},
{
"epoch": 0.28,
"learning_rate": 4.2946885344568164e-05,
"loss": 0.578,
"step": 7500
},
{
"epoch": 0.3,
"learning_rate": 4.2476677700872706e-05,
"loss": 0.5764,
"step": 8000
},
{
"epoch": 0.32,
"learning_rate": 4.200647005717725e-05,
"loss": 0.5873,
"step": 8500
},
{
"epoch": 0.34,
"learning_rate": 4.1536262413481796e-05,
"loss": 0.6006,
"step": 9000
},
{
"epoch": 0.36,
"learning_rate": 4.106605476978634e-05,
"loss": 0.6151,
"step": 9500
},
{
"epoch": 0.38,
"learning_rate": 4.059584712609089e-05,
"loss": 0.6026,
"step": 10000
},
{
"epoch": 0.39,
"learning_rate": 4.012563948239543e-05,
"loss": 0.6029,
"step": 10500
},
{
"epoch": 0.41,
"learning_rate": 3.965543183869998e-05,
"loss": 0.6321,
"step": 11000
},
{
"epoch": 0.43,
"learning_rate": 3.918522419500452e-05,
"loss": 0.609,
"step": 11500
},
{
"epoch": 0.45,
"learning_rate": 3.871501655130906e-05,
"loss": 0.6285,
"step": 12000
},
{
"epoch": 0.47,
"learning_rate": 3.82448089076136e-05,
"loss": 0.6045,
"step": 12500
},
{
"epoch": 0.49,
"learning_rate": 3.7774601263918145e-05,
"loss": 0.6652,
"step": 13000
},
{
"epoch": 0.51,
"learning_rate": 3.7304393620222693e-05,
"loss": 0.645,
"step": 13500
},
{
"epoch": 0.53,
"learning_rate": 3.6834185976527235e-05,
"loss": 0.7,
"step": 14000
},
{
"epoch": 0.55,
"learning_rate": 3.6363978332831784e-05,
"loss": 0.6917,
"step": 14500
},
{
"epoch": 0.56,
"learning_rate": 3.5893770689136326e-05,
"loss": 0.6928,
"step": 15000
},
{
"epoch": 0.58,
"learning_rate": 3.542356304544087e-05,
"loss": 0.6743,
"step": 15500
},
{
"epoch": 0.6,
"learning_rate": 3.4953355401745416e-05,
"loss": 0.6652,
"step": 16000
},
{
"epoch": 0.62,
"learning_rate": 3.448314775804996e-05,
"loss": 0.706,
"step": 16500
},
{
"epoch": 0.64,
"learning_rate": 3.40129401143545e-05,
"loss": 0.688,
"step": 17000
},
{
"epoch": 0.66,
"learning_rate": 3.354273247065904e-05,
"loss": 0.7293,
"step": 17500
},
{
"epoch": 0.68,
"learning_rate": 3.307252482696359e-05,
"loss": 0.7225,
"step": 18000
},
{
"epoch": 0.7,
"learning_rate": 3.260231718326813e-05,
"loss": 0.756,
"step": 18500
},
{
"epoch": 0.71,
"learning_rate": 3.2132109539572674e-05,
"loss": 0.7508,
"step": 19000
},
{
"epoch": 0.73,
"learning_rate": 3.166190189587722e-05,
"loss": 0.7115,
"step": 19500
},
{
"epoch": 0.75,
"learning_rate": 3.1191694252181765e-05,
"loss": 0.7543,
"step": 20000
},
{
"epoch": 0.77,
"learning_rate": 3.072148660848631e-05,
"loss": 0.7587,
"step": 20500
},
{
"epoch": 0.79,
"learning_rate": 3.025127896479085e-05,
"loss": 0.7785,
"step": 21000
},
{
"epoch": 0.81,
"learning_rate": 2.97810713210954e-05,
"loss": 0.7991,
"step": 21500
},
{
"epoch": 0.83,
"learning_rate": 2.9310863677399942e-05,
"loss": 0.8171,
"step": 22000
},
{
"epoch": 0.85,
"learning_rate": 2.8840656033704484e-05,
"loss": 0.843,
"step": 22500
},
{
"epoch": 0.87,
"learning_rate": 2.837044839000903e-05,
"loss": 0.8072,
"step": 23000
},
{
"epoch": 0.88,
"learning_rate": 2.790024074631357e-05,
"loss": 0.8326,
"step": 23500
},
{
"epoch": 0.9,
"learning_rate": 2.743003310261812e-05,
"loss": 0.8578,
"step": 24000
},
{
"epoch": 0.92,
"learning_rate": 2.695982545892266e-05,
"loss": 0.8621,
"step": 24500
},
{
"epoch": 0.94,
"learning_rate": 2.6489617815227207e-05,
"loss": 0.9032,
"step": 25000
},
{
"epoch": 0.96,
"learning_rate": 2.601941017153175e-05,
"loss": 0.9124,
"step": 25500
},
{
"epoch": 0.98,
"learning_rate": 2.554920252783629e-05,
"loss": 0.9126,
"step": 26000
},
{
"epoch": 1.0,
"learning_rate": 2.507899488414084e-05,
"loss": 0.9252,
"step": 26500
},
{
"epoch": 1.0,
"eval_bleu": 34.6634,
"eval_chrf++": 61.3155,
"eval_gen_len": 20.4231,
"eval_loss": 0.9675707817077637,
"eval_runtime": 2539.8863,
"eval_samples_per_second": 4.979,
"eval_spbleu": 48.2634,
"eval_steps_per_second": 0.996,
"eval_ter": 53.1762,
"step": 26584
},
{
"epoch": 1.02,
"learning_rate": 2.4608787240445384e-05,
"loss": 0.6562,
"step": 27000
},
{
"epoch": 1.03,
"learning_rate": 2.4138579596749926e-05,
"loss": 0.5603,
"step": 27500
},
{
"epoch": 1.05,
"learning_rate": 2.3668371953054468e-05,
"loss": 0.549,
"step": 28000
},
{
"epoch": 1.07,
"learning_rate": 2.3198164309359013e-05,
"loss": 0.5384,
"step": 28500
},
{
"epoch": 1.09,
"learning_rate": 2.272795666566356e-05,
"loss": 0.5653,
"step": 29000
},
{
"epoch": 1.11,
"learning_rate": 2.2257749021968104e-05,
"loss": 0.556,
"step": 29500
},
{
"epoch": 1.13,
"learning_rate": 2.1787541378272646e-05,
"loss": 0.5604,
"step": 30000
},
{
"epoch": 1.15,
"learning_rate": 2.131733373457719e-05,
"loss": 0.5572,
"step": 30500
},
{
"epoch": 1.17,
"learning_rate": 2.0847126090881736e-05,
"loss": 0.5569,
"step": 31000
},
{
"epoch": 1.18,
"learning_rate": 2.0376918447186278e-05,
"loss": 0.5539,
"step": 31500
},
{
"epoch": 1.2,
"learning_rate": 1.9906710803490823e-05,
"loss": 0.5361,
"step": 32000
},
{
"epoch": 1.22,
"learning_rate": 1.9436503159795365e-05,
"loss": 0.5396,
"step": 32500
},
{
"epoch": 1.24,
"learning_rate": 1.896629551609991e-05,
"loss": 0.5457,
"step": 33000
},
{
"epoch": 1.26,
"learning_rate": 1.8496087872404456e-05,
"loss": 0.5638,
"step": 33500
},
{
"epoch": 1.28,
"learning_rate": 1.8025880228709e-05,
"loss": 0.5548,
"step": 34000
},
{
"epoch": 1.3,
"learning_rate": 1.7555672585013543e-05,
"loss": 0.533,
"step": 34500
},
{
"epoch": 1.32,
"learning_rate": 1.7085464941318085e-05,
"loss": 0.5455,
"step": 35000
},
{
"epoch": 1.34,
"learning_rate": 1.661525729762263e-05,
"loss": 0.5675,
"step": 35500
},
{
"epoch": 1.35,
"learning_rate": 1.6145049653927175e-05,
"loss": 0.5444,
"step": 36000
},
{
"epoch": 1.37,
"learning_rate": 1.567484201023172e-05,
"loss": 0.5677,
"step": 36500
},
{
"epoch": 1.39,
"learning_rate": 1.5204634366536264e-05,
"loss": 0.551,
"step": 37000
},
{
"epoch": 1.41,
"learning_rate": 1.4734426722840807e-05,
"loss": 0.5588,
"step": 37500
},
{
"epoch": 1.43,
"learning_rate": 1.4264219079145353e-05,
"loss": 0.5602,
"step": 38000
},
{
"epoch": 1.45,
"learning_rate": 1.3794011435449896e-05,
"loss": 0.5434,
"step": 38500
},
{
"epoch": 1.47,
"learning_rate": 1.3323803791754438e-05,
"loss": 0.5642,
"step": 39000
},
{
"epoch": 1.49,
"learning_rate": 1.2853596148058983e-05,
"loss": 0.5516,
"step": 39500
},
{
"epoch": 1.5,
"learning_rate": 1.2383388504363527e-05,
"loss": 0.5639,
"step": 40000
},
{
"epoch": 1.52,
"learning_rate": 1.1913180860668072e-05,
"loss": 0.531,
"step": 40500
},
{
"epoch": 1.54,
"learning_rate": 1.1442973216972616e-05,
"loss": 0.5301,
"step": 41000
},
{
"epoch": 1.56,
"learning_rate": 1.0972765573277159e-05,
"loss": 0.5677,
"step": 41500
},
{
"epoch": 1.58,
"learning_rate": 1.0502557929581704e-05,
"loss": 0.5308,
"step": 42000
},
{
"epoch": 1.6,
"learning_rate": 1.0032350285886248e-05,
"loss": 0.5224,
"step": 42500
},
{
"epoch": 1.62,
"learning_rate": 9.562142642190793e-06,
"loss": 0.5864,
"step": 43000
},
{
"epoch": 1.64,
"learning_rate": 9.091934998495335e-06,
"loss": 0.5345,
"step": 43500
},
{
"epoch": 1.66,
"learning_rate": 8.62172735479988e-06,
"loss": 0.5531,
"step": 44000
},
{
"epoch": 1.67,
"learning_rate": 8.151519711104424e-06,
"loss": 0.5274,
"step": 44500
},
{
"epoch": 1.69,
"learning_rate": 7.681312067408967e-06,
"loss": 0.543,
"step": 45000
},
{
"epoch": 1.71,
"learning_rate": 7.211104423713512e-06,
"loss": 0.5486,
"step": 45500
},
{
"epoch": 1.73,
"learning_rate": 6.740896780018056e-06,
"loss": 0.5469,
"step": 46000
},
{
"epoch": 1.75,
"learning_rate": 6.2706891363226005e-06,
"loss": 0.5427,
"step": 46500
},
{
"epoch": 1.77,
"learning_rate": 5.800481492627145e-06,
"loss": 0.5424,
"step": 47000
},
{
"epoch": 1.79,
"learning_rate": 5.330273848931688e-06,
"loss": 0.556,
"step": 47500
},
{
"epoch": 1.81,
"learning_rate": 4.860066205236233e-06,
"loss": 0.5411,
"step": 48000
},
{
"epoch": 1.82,
"learning_rate": 4.389858561540776e-06,
"loss": 0.5639,
"step": 48500
},
{
"epoch": 1.84,
"learning_rate": 3.919650917845321e-06,
"loss": 0.5344,
"step": 49000
},
{
"epoch": 1.86,
"learning_rate": 3.4494432741498647e-06,
"loss": 0.5245,
"step": 49500
},
{
"epoch": 1.88,
"learning_rate": 2.9792356304544087e-06,
"loss": 0.5638,
"step": 50000
},
{
"epoch": 1.9,
"learning_rate": 2.509027986758953e-06,
"loss": 0.5466,
"step": 50500
},
{
"epoch": 1.92,
"learning_rate": 2.038820343063497e-06,
"loss": 0.5473,
"step": 51000
},
{
"epoch": 1.94,
"learning_rate": 1.568612699368041e-06,
"loss": 0.5281,
"step": 51500
},
{
"epoch": 1.96,
"learning_rate": 1.098405055672585e-06,
"loss": 0.5205,
"step": 52000
},
{
"epoch": 1.97,
"learning_rate": 6.281974119771292e-07,
"loss": 0.543,
"step": 52500
},
{
"epoch": 1.99,
"learning_rate": 1.579897682816732e-07,
"loss": 0.5409,
"step": 53000
},
{
"epoch": 2.0,
"eval_bleu": 36.0011,
"eval_chrf++": 62.004,
"eval_gen_len": 20.4066,
"eval_loss": 1.0103600025177002,
"eval_runtime": 2543.0781,
"eval_samples_per_second": 4.973,
"eval_spbleu": 49.2767,
"eval_steps_per_second": 0.995,
"eval_ter": 51.8536,
"step": 53168
}
],
"max_steps": 53168,
"num_train_epochs": 2,
"total_flos": 2.262694057958441e+17,
"trial_name": null,
"trial_params": null
}