bertin-base-xnli-es / trainer_state.json
versae's picture
Gaussian 512 fine-tuned XNLI es with acc 0.7843
237ae29
raw
history blame
No virus
30.6 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.0,
"global_step": 122720,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 4.9796284224250325e-05,
"loss": 1.1171,
"step": 500
},
{
"epoch": 0.04,
"learning_rate": 4.9592568448500655e-05,
"loss": 1.0195,
"step": 1000
},
{
"epoch": 0.06,
"learning_rate": 4.938885267275098e-05,
"loss": 0.9573,
"step": 1500
},
{
"epoch": 0.08,
"learning_rate": 4.918513689700131e-05,
"loss": 0.9173,
"step": 2000
},
{
"epoch": 0.1,
"learning_rate": 4.898142112125163e-05,
"loss": 0.8778,
"step": 2500
},
{
"epoch": 0.12,
"learning_rate": 4.877770534550195e-05,
"loss": 0.8649,
"step": 3000
},
{
"epoch": 0.14,
"learning_rate": 4.857398956975228e-05,
"loss": 0.8469,
"step": 3500
},
{
"epoch": 0.16,
"learning_rate": 4.8370273794002606e-05,
"loss": 0.8093,
"step": 4000
},
{
"epoch": 0.18,
"learning_rate": 4.8166558018252936e-05,
"loss": 0.818,
"step": 4500
},
{
"epoch": 0.2,
"learning_rate": 4.7962842242503265e-05,
"loss": 0.8026,
"step": 5000
},
{
"epoch": 0.22,
"learning_rate": 4.775912646675359e-05,
"loss": 0.8043,
"step": 5500
},
{
"epoch": 0.24,
"learning_rate": 4.755541069100392e-05,
"loss": 0.7747,
"step": 6000
},
{
"epoch": 0.26,
"learning_rate": 4.735169491525424e-05,
"loss": 0.7723,
"step": 6500
},
{
"epoch": 0.29,
"learning_rate": 4.7147979139504564e-05,
"loss": 0.782,
"step": 7000
},
{
"epoch": 0.31,
"learning_rate": 4.694426336375489e-05,
"loss": 0.7642,
"step": 7500
},
{
"epoch": 0.33,
"learning_rate": 4.6740547588005216e-05,
"loss": 0.7515,
"step": 8000
},
{
"epoch": 0.35,
"learning_rate": 4.6536831812255546e-05,
"loss": 0.7417,
"step": 8500
},
{
"epoch": 0.37,
"learning_rate": 4.633311603650587e-05,
"loss": 0.7358,
"step": 9000
},
{
"epoch": 0.39,
"learning_rate": 4.612940026075619e-05,
"loss": 0.7359,
"step": 9500
},
{
"epoch": 0.41,
"learning_rate": 4.592568448500652e-05,
"loss": 0.7255,
"step": 10000
},
{
"epoch": 0.43,
"learning_rate": 4.5721968709256844e-05,
"loss": 0.727,
"step": 10500
},
{
"epoch": 0.45,
"learning_rate": 4.5518252933507174e-05,
"loss": 0.7269,
"step": 11000
},
{
"epoch": 0.47,
"learning_rate": 4.53145371577575e-05,
"loss": 0.7277,
"step": 11500
},
{
"epoch": 0.49,
"learning_rate": 4.511082138200782e-05,
"loss": 0.7054,
"step": 12000
},
{
"epoch": 0.51,
"learning_rate": 4.490710560625815e-05,
"loss": 0.7102,
"step": 12500
},
{
"epoch": 0.53,
"learning_rate": 4.470338983050847e-05,
"loss": 0.7073,
"step": 13000
},
{
"epoch": 0.55,
"learning_rate": 4.44996740547588e-05,
"loss": 0.7201,
"step": 13500
},
{
"epoch": 0.57,
"learning_rate": 4.429595827900913e-05,
"loss": 0.7081,
"step": 14000
},
{
"epoch": 0.59,
"learning_rate": 4.4092242503259455e-05,
"loss": 0.7007,
"step": 14500
},
{
"epoch": 0.61,
"learning_rate": 4.3888526727509784e-05,
"loss": 0.7043,
"step": 15000
},
{
"epoch": 0.63,
"learning_rate": 4.368481095176011e-05,
"loss": 0.6877,
"step": 15500
},
{
"epoch": 0.65,
"learning_rate": 4.348109517601043e-05,
"loss": 0.6984,
"step": 16000
},
{
"epoch": 0.67,
"learning_rate": 4.327737940026076e-05,
"loss": 0.6985,
"step": 16500
},
{
"epoch": 0.69,
"learning_rate": 4.307366362451108e-05,
"loss": 0.685,
"step": 17000
},
{
"epoch": 0.71,
"learning_rate": 4.286994784876141e-05,
"loss": 0.6981,
"step": 17500
},
{
"epoch": 0.73,
"learning_rate": 4.2666232073011735e-05,
"loss": 0.6744,
"step": 18000
},
{
"epoch": 0.75,
"learning_rate": 4.2462516297262065e-05,
"loss": 0.6863,
"step": 18500
},
{
"epoch": 0.77,
"learning_rate": 4.225880052151239e-05,
"loss": 0.7016,
"step": 19000
},
{
"epoch": 0.79,
"learning_rate": 4.205508474576271e-05,
"loss": 0.6791,
"step": 19500
},
{
"epoch": 0.81,
"learning_rate": 4.185136897001304e-05,
"loss": 0.6729,
"step": 20000
},
{
"epoch": 0.84,
"learning_rate": 4.164765319426336e-05,
"loss": 0.6784,
"step": 20500
},
{
"epoch": 0.86,
"learning_rate": 4.144393741851369e-05,
"loss": 0.6873,
"step": 21000
},
{
"epoch": 0.88,
"learning_rate": 4.1240221642764016e-05,
"loss": 0.6779,
"step": 21500
},
{
"epoch": 0.9,
"learning_rate": 4.103650586701434e-05,
"loss": 0.6866,
"step": 22000
},
{
"epoch": 0.92,
"learning_rate": 4.0832790091264675e-05,
"loss": 0.6708,
"step": 22500
},
{
"epoch": 0.94,
"learning_rate": 4.0629074315515e-05,
"loss": 0.6682,
"step": 23000
},
{
"epoch": 0.96,
"learning_rate": 4.042535853976532e-05,
"loss": 0.676,
"step": 23500
},
{
"epoch": 0.98,
"learning_rate": 4.022164276401565e-05,
"loss": 0.6684,
"step": 24000
},
{
"epoch": 1.0,
"learning_rate": 4.0017926988265974e-05,
"loss": 0.6695,
"step": 24500
},
{
"epoch": 1.02,
"learning_rate": 3.98142112125163e-05,
"loss": 0.6002,
"step": 25000
},
{
"epoch": 1.04,
"learning_rate": 3.9610495436766626e-05,
"loss": 0.605,
"step": 25500
},
{
"epoch": 1.06,
"learning_rate": 3.940677966101695e-05,
"loss": 0.6153,
"step": 26000
},
{
"epoch": 1.08,
"learning_rate": 3.920306388526728e-05,
"loss": 0.6064,
"step": 26500
},
{
"epoch": 1.1,
"learning_rate": 3.89993481095176e-05,
"loss": 0.5791,
"step": 27000
},
{
"epoch": 1.12,
"learning_rate": 3.879563233376793e-05,
"loss": 0.6018,
"step": 27500
},
{
"epoch": 1.14,
"learning_rate": 3.8591916558018254e-05,
"loss": 0.5985,
"step": 28000
},
{
"epoch": 1.16,
"learning_rate": 3.838820078226858e-05,
"loss": 0.6174,
"step": 28500
},
{
"epoch": 1.18,
"learning_rate": 3.818448500651891e-05,
"loss": 0.6066,
"step": 29000
},
{
"epoch": 1.2,
"learning_rate": 3.798076923076923e-05,
"loss": 0.6226,
"step": 29500
},
{
"epoch": 1.22,
"learning_rate": 3.777705345501956e-05,
"loss": 0.6142,
"step": 30000
},
{
"epoch": 1.24,
"learning_rate": 3.757333767926988e-05,
"loss": 0.6036,
"step": 30500
},
{
"epoch": 1.26,
"learning_rate": 3.7369621903520205e-05,
"loss": 0.5982,
"step": 31000
},
{
"epoch": 1.28,
"learning_rate": 3.716590612777054e-05,
"loss": 0.6049,
"step": 31500
},
{
"epoch": 1.3,
"learning_rate": 3.6962190352020865e-05,
"loss": 0.5926,
"step": 32000
},
{
"epoch": 1.32,
"learning_rate": 3.675847457627119e-05,
"loss": 0.597,
"step": 32500
},
{
"epoch": 1.34,
"learning_rate": 3.655475880052152e-05,
"loss": 0.5953,
"step": 33000
},
{
"epoch": 1.36,
"learning_rate": 3.635104302477184e-05,
"loss": 0.6034,
"step": 33500
},
{
"epoch": 1.39,
"learning_rate": 3.614732724902217e-05,
"loss": 0.599,
"step": 34000
},
{
"epoch": 1.41,
"learning_rate": 3.594361147327249e-05,
"loss": 0.5953,
"step": 34500
},
{
"epoch": 1.43,
"learning_rate": 3.5739895697522816e-05,
"loss": 0.6069,
"step": 35000
},
{
"epoch": 1.45,
"learning_rate": 3.5536179921773145e-05,
"loss": 0.6053,
"step": 35500
},
{
"epoch": 1.47,
"learning_rate": 3.533246414602347e-05,
"loss": 0.5862,
"step": 36000
},
{
"epoch": 1.49,
"learning_rate": 3.51287483702738e-05,
"loss": 0.5883,
"step": 36500
},
{
"epoch": 1.51,
"learning_rate": 3.492503259452412e-05,
"loss": 0.6006,
"step": 37000
},
{
"epoch": 1.53,
"learning_rate": 3.4721316818774444e-05,
"loss": 0.5842,
"step": 37500
},
{
"epoch": 1.55,
"learning_rate": 3.451760104302477e-05,
"loss": 0.6046,
"step": 38000
},
{
"epoch": 1.57,
"learning_rate": 3.4313885267275096e-05,
"loss": 0.601,
"step": 38500
},
{
"epoch": 1.59,
"learning_rate": 3.4110169491525426e-05,
"loss": 0.5899,
"step": 39000
},
{
"epoch": 1.61,
"learning_rate": 3.390645371577575e-05,
"loss": 0.5958,
"step": 39500
},
{
"epoch": 1.63,
"learning_rate": 3.370273794002607e-05,
"loss": 0.6056,
"step": 40000
},
{
"epoch": 1.65,
"learning_rate": 3.349902216427641e-05,
"loss": 0.5856,
"step": 40500
},
{
"epoch": 1.67,
"learning_rate": 3.329530638852673e-05,
"loss": 0.5977,
"step": 41000
},
{
"epoch": 1.69,
"learning_rate": 3.3091590612777054e-05,
"loss": 0.5925,
"step": 41500
},
{
"epoch": 1.71,
"learning_rate": 3.2887874837027384e-05,
"loss": 0.6036,
"step": 42000
},
{
"epoch": 1.73,
"learning_rate": 3.2684159061277707e-05,
"loss": 0.5846,
"step": 42500
},
{
"epoch": 1.75,
"learning_rate": 3.2480443285528036e-05,
"loss": 0.5828,
"step": 43000
},
{
"epoch": 1.77,
"learning_rate": 3.227672750977836e-05,
"loss": 0.5902,
"step": 43500
},
{
"epoch": 1.79,
"learning_rate": 3.207301173402868e-05,
"loss": 0.5804,
"step": 44000
},
{
"epoch": 1.81,
"learning_rate": 3.186929595827901e-05,
"loss": 0.5864,
"step": 44500
},
{
"epoch": 1.83,
"learning_rate": 3.1665580182529335e-05,
"loss": 0.5894,
"step": 45000
},
{
"epoch": 1.85,
"learning_rate": 3.1461864406779664e-05,
"loss": 0.5866,
"step": 45500
},
{
"epoch": 1.87,
"learning_rate": 3.125814863102999e-05,
"loss": 0.5756,
"step": 46000
},
{
"epoch": 1.89,
"learning_rate": 3.105443285528031e-05,
"loss": 0.5893,
"step": 46500
},
{
"epoch": 1.91,
"learning_rate": 3.085071707953064e-05,
"loss": 0.5843,
"step": 47000
},
{
"epoch": 1.94,
"learning_rate": 3.064700130378096e-05,
"loss": 0.5769,
"step": 47500
},
{
"epoch": 1.96,
"learning_rate": 3.044328552803129e-05,
"loss": 0.572,
"step": 48000
},
{
"epoch": 1.98,
"learning_rate": 3.0239569752281615e-05,
"loss": 0.582,
"step": 48500
},
{
"epoch": 2.0,
"learning_rate": 3.003585397653194e-05,
"loss": 0.5967,
"step": 49000
},
{
"epoch": 2.02,
"learning_rate": 2.983213820078227e-05,
"loss": 0.5134,
"step": 49500
},
{
"epoch": 2.04,
"learning_rate": 2.9628422425032598e-05,
"loss": 0.5122,
"step": 50000
},
{
"epoch": 2.06,
"learning_rate": 2.9424706649282924e-05,
"loss": 0.4969,
"step": 50500
},
{
"epoch": 2.08,
"learning_rate": 2.922099087353325e-05,
"loss": 0.5032,
"step": 51000
},
{
"epoch": 2.1,
"learning_rate": 2.9017275097783576e-05,
"loss": 0.5039,
"step": 51500
},
{
"epoch": 2.12,
"learning_rate": 2.88135593220339e-05,
"loss": 0.4981,
"step": 52000
},
{
"epoch": 2.14,
"learning_rate": 2.8609843546284226e-05,
"loss": 0.5063,
"step": 52500
},
{
"epoch": 2.16,
"learning_rate": 2.8406127770534552e-05,
"loss": 0.478,
"step": 53000
},
{
"epoch": 2.18,
"learning_rate": 2.8202411994784878e-05,
"loss": 0.5014,
"step": 53500
},
{
"epoch": 2.2,
"learning_rate": 2.7998696219035204e-05,
"loss": 0.4999,
"step": 54000
},
{
"epoch": 2.22,
"learning_rate": 2.7794980443285527e-05,
"loss": 0.5096,
"step": 54500
},
{
"epoch": 2.24,
"learning_rate": 2.7591264667535854e-05,
"loss": 0.4982,
"step": 55000
},
{
"epoch": 2.26,
"learning_rate": 2.738754889178618e-05,
"loss": 0.4927,
"step": 55500
},
{
"epoch": 2.28,
"learning_rate": 2.7183833116036506e-05,
"loss": 0.4963,
"step": 56000
},
{
"epoch": 2.3,
"learning_rate": 2.6980117340286833e-05,
"loss": 0.4983,
"step": 56500
},
{
"epoch": 2.32,
"learning_rate": 2.6776401564537155e-05,
"loss": 0.5004,
"step": 57000
},
{
"epoch": 2.34,
"learning_rate": 2.6572685788787482e-05,
"loss": 0.5059,
"step": 57500
},
{
"epoch": 2.36,
"learning_rate": 2.6368970013037815e-05,
"loss": 0.5045,
"step": 58000
},
{
"epoch": 2.38,
"learning_rate": 2.6165254237288138e-05,
"loss": 0.5062,
"step": 58500
},
{
"epoch": 2.4,
"learning_rate": 2.5961538461538464e-05,
"loss": 0.5077,
"step": 59000
},
{
"epoch": 2.42,
"learning_rate": 2.575782268578879e-05,
"loss": 0.4997,
"step": 59500
},
{
"epoch": 2.44,
"learning_rate": 2.5554106910039117e-05,
"loss": 0.4998,
"step": 60000
},
{
"epoch": 2.46,
"learning_rate": 2.5350391134289443e-05,
"loss": 0.5074,
"step": 60500
},
{
"epoch": 2.49,
"learning_rate": 2.5146675358539766e-05,
"loss": 0.4928,
"step": 61000
},
{
"epoch": 2.51,
"learning_rate": 2.4942959582790092e-05,
"loss": 0.5026,
"step": 61500
},
{
"epoch": 2.53,
"learning_rate": 2.473924380704042e-05,
"loss": 0.5058,
"step": 62000
},
{
"epoch": 2.55,
"learning_rate": 2.4535528031290745e-05,
"loss": 0.4982,
"step": 62500
},
{
"epoch": 2.57,
"learning_rate": 2.433181225554107e-05,
"loss": 0.4874,
"step": 63000
},
{
"epoch": 2.59,
"learning_rate": 2.4128096479791397e-05,
"loss": 0.5095,
"step": 63500
},
{
"epoch": 2.61,
"learning_rate": 2.392438070404172e-05,
"loss": 0.501,
"step": 64000
},
{
"epoch": 2.63,
"learning_rate": 2.3720664928292046e-05,
"loss": 0.5076,
"step": 64500
},
{
"epoch": 2.65,
"learning_rate": 2.3516949152542376e-05,
"loss": 0.4894,
"step": 65000
},
{
"epoch": 2.67,
"learning_rate": 2.3313233376792702e-05,
"loss": 0.5081,
"step": 65500
},
{
"epoch": 2.69,
"learning_rate": 2.3109517601043025e-05,
"loss": 0.5117,
"step": 66000
},
{
"epoch": 2.71,
"learning_rate": 2.290580182529335e-05,
"loss": 0.4996,
"step": 66500
},
{
"epoch": 2.73,
"learning_rate": 2.2702086049543678e-05,
"loss": 0.4968,
"step": 67000
},
{
"epoch": 2.75,
"learning_rate": 2.2498370273794004e-05,
"loss": 0.5117,
"step": 67500
},
{
"epoch": 2.77,
"learning_rate": 2.229465449804433e-05,
"loss": 0.5034,
"step": 68000
},
{
"epoch": 2.79,
"learning_rate": 2.2090938722294653e-05,
"loss": 0.493,
"step": 68500
},
{
"epoch": 2.81,
"learning_rate": 2.188722294654498e-05,
"loss": 0.5027,
"step": 69000
},
{
"epoch": 2.83,
"learning_rate": 2.168350717079531e-05,
"loss": 0.5018,
"step": 69500
},
{
"epoch": 2.85,
"learning_rate": 2.1479791395045636e-05,
"loss": 0.5055,
"step": 70000
},
{
"epoch": 2.87,
"learning_rate": 2.127607561929596e-05,
"loss": 0.5008,
"step": 70500
},
{
"epoch": 2.89,
"learning_rate": 2.1072359843546285e-05,
"loss": 0.4957,
"step": 71000
},
{
"epoch": 2.91,
"learning_rate": 2.086864406779661e-05,
"loss": 0.4935,
"step": 71500
},
{
"epoch": 2.93,
"learning_rate": 2.0664928292046937e-05,
"loss": 0.4841,
"step": 72000
},
{
"epoch": 2.95,
"learning_rate": 2.0461212516297264e-05,
"loss": 0.5075,
"step": 72500
},
{
"epoch": 2.97,
"learning_rate": 2.0257496740547587e-05,
"loss": 0.4854,
"step": 73000
},
{
"epoch": 2.99,
"learning_rate": 2.0053780964797913e-05,
"loss": 0.5015,
"step": 73500
},
{
"epoch": 3.01,
"learning_rate": 1.9850065189048242e-05,
"loss": 0.431,
"step": 74000
},
{
"epoch": 3.04,
"learning_rate": 1.964634941329857e-05,
"loss": 0.4067,
"step": 74500
},
{
"epoch": 3.06,
"learning_rate": 1.944263363754889e-05,
"loss": 0.4033,
"step": 75000
},
{
"epoch": 3.08,
"learning_rate": 1.9238917861799218e-05,
"loss": 0.419,
"step": 75500
},
{
"epoch": 3.1,
"learning_rate": 1.9035202086049544e-05,
"loss": 0.4173,
"step": 76000
},
{
"epoch": 3.12,
"learning_rate": 1.883148631029987e-05,
"loss": 0.4218,
"step": 76500
},
{
"epoch": 3.14,
"learning_rate": 1.8627770534550197e-05,
"loss": 0.4125,
"step": 77000
},
{
"epoch": 3.16,
"learning_rate": 1.842405475880052e-05,
"loss": 0.4158,
"step": 77500
},
{
"epoch": 3.18,
"learning_rate": 1.8220338983050846e-05,
"loss": 0.419,
"step": 78000
},
{
"epoch": 3.2,
"learning_rate": 1.8016623207301176e-05,
"loss": 0.4233,
"step": 78500
},
{
"epoch": 3.22,
"learning_rate": 1.7812907431551502e-05,
"loss": 0.4332,
"step": 79000
},
{
"epoch": 3.24,
"learning_rate": 1.7609191655801828e-05,
"loss": 0.4099,
"step": 79500
},
{
"epoch": 3.26,
"learning_rate": 1.740547588005215e-05,
"loss": 0.4054,
"step": 80000
},
{
"epoch": 3.28,
"learning_rate": 1.7201760104302477e-05,
"loss": 0.4164,
"step": 80500
},
{
"epoch": 3.3,
"learning_rate": 1.6998044328552804e-05,
"loss": 0.3949,
"step": 81000
},
{
"epoch": 3.32,
"learning_rate": 1.679432855280313e-05,
"loss": 0.4216,
"step": 81500
},
{
"epoch": 3.34,
"learning_rate": 1.6590612777053456e-05,
"loss": 0.4062,
"step": 82000
},
{
"epoch": 3.36,
"learning_rate": 1.6386897001303783e-05,
"loss": 0.421,
"step": 82500
},
{
"epoch": 3.38,
"learning_rate": 1.618318122555411e-05,
"loss": 0.4159,
"step": 83000
},
{
"epoch": 3.4,
"learning_rate": 1.5979465449804435e-05,
"loss": 0.4096,
"step": 83500
},
{
"epoch": 3.42,
"learning_rate": 1.577574967405476e-05,
"loss": 0.4117,
"step": 84000
},
{
"epoch": 3.44,
"learning_rate": 1.5572033898305084e-05,
"loss": 0.4118,
"step": 84500
},
{
"epoch": 3.46,
"learning_rate": 1.536831812255541e-05,
"loss": 0.4278,
"step": 85000
},
{
"epoch": 3.48,
"learning_rate": 1.5164602346805737e-05,
"loss": 0.4214,
"step": 85500
},
{
"epoch": 3.5,
"learning_rate": 1.4960886571056063e-05,
"loss": 0.4114,
"step": 86000
},
{
"epoch": 3.52,
"learning_rate": 1.4757170795306388e-05,
"loss": 0.415,
"step": 86500
},
{
"epoch": 3.54,
"learning_rate": 1.4553455019556716e-05,
"loss": 0.409,
"step": 87000
},
{
"epoch": 3.57,
"learning_rate": 1.4349739243807042e-05,
"loss": 0.4045,
"step": 87500
},
{
"epoch": 3.59,
"learning_rate": 1.4146023468057368e-05,
"loss": 0.4225,
"step": 88000
},
{
"epoch": 3.61,
"learning_rate": 1.3942307692307693e-05,
"loss": 0.4046,
"step": 88500
},
{
"epoch": 3.63,
"learning_rate": 1.373859191655802e-05,
"loss": 0.409,
"step": 89000
},
{
"epoch": 3.65,
"learning_rate": 1.3534876140808344e-05,
"loss": 0.3952,
"step": 89500
},
{
"epoch": 3.67,
"learning_rate": 1.333116036505867e-05,
"loss": 0.397,
"step": 90000
},
{
"epoch": 3.69,
"learning_rate": 1.3127444589308997e-05,
"loss": 0.4099,
"step": 90500
},
{
"epoch": 3.71,
"learning_rate": 1.2923728813559321e-05,
"loss": 0.4029,
"step": 91000
},
{
"epoch": 3.73,
"learning_rate": 1.2720013037809649e-05,
"loss": 0.4022,
"step": 91500
},
{
"epoch": 3.75,
"learning_rate": 1.2516297262059975e-05,
"loss": 0.4129,
"step": 92000
},
{
"epoch": 3.77,
"learning_rate": 1.23125814863103e-05,
"loss": 0.4078,
"step": 92500
},
{
"epoch": 3.79,
"learning_rate": 1.2108865710560626e-05,
"loss": 0.4034,
"step": 93000
},
{
"epoch": 3.81,
"learning_rate": 1.1905149934810953e-05,
"loss": 0.4092,
"step": 93500
},
{
"epoch": 3.83,
"learning_rate": 1.1701434159061279e-05,
"loss": 0.4102,
"step": 94000
},
{
"epoch": 3.85,
"learning_rate": 1.1497718383311603e-05,
"loss": 0.3949,
"step": 94500
},
{
"epoch": 3.87,
"learning_rate": 1.1294002607561931e-05,
"loss": 0.3935,
"step": 95000
},
{
"epoch": 3.89,
"learning_rate": 1.1090286831812256e-05,
"loss": 0.4042,
"step": 95500
},
{
"epoch": 3.91,
"learning_rate": 1.0886571056062582e-05,
"loss": 0.4073,
"step": 96000
},
{
"epoch": 3.93,
"learning_rate": 1.0682855280312907e-05,
"loss": 0.4072,
"step": 96500
},
{
"epoch": 3.95,
"learning_rate": 1.0479139504563235e-05,
"loss": 0.4094,
"step": 97000
},
{
"epoch": 3.97,
"learning_rate": 1.027542372881356e-05,
"loss": 0.3862,
"step": 97500
},
{
"epoch": 3.99,
"learning_rate": 1.0071707953063886e-05,
"loss": 0.3995,
"step": 98000
},
{
"epoch": 4.01,
"learning_rate": 9.867992177314212e-06,
"loss": 0.3644,
"step": 98500
},
{
"epoch": 4.03,
"learning_rate": 9.664276401564537e-06,
"loss": 0.3292,
"step": 99000
},
{
"epoch": 4.05,
"learning_rate": 9.460560625814865e-06,
"loss": 0.3353,
"step": 99500
},
{
"epoch": 4.07,
"learning_rate": 9.25684485006519e-06,
"loss": 0.3445,
"step": 100000
},
{
"epoch": 4.09,
"learning_rate": 9.053129074315516e-06,
"loss": 0.3365,
"step": 100500
},
{
"epoch": 4.12,
"learning_rate": 8.84941329856584e-06,
"loss": 0.3293,
"step": 101000
},
{
"epoch": 4.14,
"learning_rate": 8.645697522816168e-06,
"loss": 0.334,
"step": 101500
},
{
"epoch": 4.16,
"learning_rate": 8.441981747066494e-06,
"loss": 0.3337,
"step": 102000
},
{
"epoch": 4.18,
"learning_rate": 8.238265971316819e-06,
"loss": 0.3328,
"step": 102500
},
{
"epoch": 4.2,
"learning_rate": 8.034550195567145e-06,
"loss": 0.343,
"step": 103000
},
{
"epoch": 4.22,
"learning_rate": 7.83083441981747e-06,
"loss": 0.334,
"step": 103500
},
{
"epoch": 4.24,
"learning_rate": 7.627118644067798e-06,
"loss": 0.3356,
"step": 104000
},
{
"epoch": 4.26,
"learning_rate": 7.423402868318123e-06,
"loss": 0.3407,
"step": 104500
},
{
"epoch": 4.28,
"learning_rate": 7.219687092568449e-06,
"loss": 0.3453,
"step": 105000
},
{
"epoch": 4.3,
"learning_rate": 7.015971316818774e-06,
"loss": 0.3323,
"step": 105500
},
{
"epoch": 4.32,
"learning_rate": 6.812255541069101e-06,
"loss": 0.3185,
"step": 106000
},
{
"epoch": 4.34,
"learning_rate": 6.608539765319427e-06,
"loss": 0.3346,
"step": 106500
},
{
"epoch": 4.36,
"learning_rate": 6.404823989569752e-06,
"loss": 0.3324,
"step": 107000
},
{
"epoch": 4.38,
"learning_rate": 6.2011082138200785e-06,
"loss": 0.3235,
"step": 107500
},
{
"epoch": 4.4,
"learning_rate": 5.997392438070405e-06,
"loss": 0.3567,
"step": 108000
},
{
"epoch": 4.42,
"learning_rate": 5.79367666232073e-06,
"loss": 0.3406,
"step": 108500
},
{
"epoch": 4.44,
"learning_rate": 5.5899608865710565e-06,
"loss": 0.3411,
"step": 109000
},
{
"epoch": 4.46,
"learning_rate": 5.386245110821382e-06,
"loss": 0.3363,
"step": 109500
},
{
"epoch": 4.48,
"learning_rate": 5.182529335071708e-06,
"loss": 0.3427,
"step": 110000
},
{
"epoch": 4.5,
"learning_rate": 4.978813559322034e-06,
"loss": 0.3367,
"step": 110500
},
{
"epoch": 4.52,
"learning_rate": 4.77509778357236e-06,
"loss": 0.3244,
"step": 111000
},
{
"epoch": 4.54,
"learning_rate": 4.571382007822686e-06,
"loss": 0.3283,
"step": 111500
},
{
"epoch": 4.56,
"learning_rate": 4.367666232073012e-06,
"loss": 0.3226,
"step": 112000
},
{
"epoch": 4.58,
"learning_rate": 4.163950456323338e-06,
"loss": 0.3273,
"step": 112500
},
{
"epoch": 4.6,
"learning_rate": 3.9602346805736635e-06,
"loss": 0.3232,
"step": 113000
},
{
"epoch": 4.62,
"learning_rate": 3.7565189048239898e-06,
"loss": 0.321,
"step": 113500
},
{
"epoch": 4.64,
"learning_rate": 3.5528031290743156e-06,
"loss": 0.3204,
"step": 114000
},
{
"epoch": 4.67,
"learning_rate": 3.349087353324642e-06,
"loss": 0.33,
"step": 114500
},
{
"epoch": 4.69,
"learning_rate": 3.1453715775749674e-06,
"loss": 0.3262,
"step": 115000
},
{
"epoch": 4.71,
"learning_rate": 2.9416558018252932e-06,
"loss": 0.3223,
"step": 115500
},
{
"epoch": 4.73,
"learning_rate": 2.7379400260756195e-06,
"loss": 0.3151,
"step": 116000
},
{
"epoch": 4.75,
"learning_rate": 2.5342242503259454e-06,
"loss": 0.3285,
"step": 116500
},
{
"epoch": 4.77,
"learning_rate": 2.3305084745762712e-06,
"loss": 0.3177,
"step": 117000
},
{
"epoch": 4.79,
"learning_rate": 2.126792698826597e-06,
"loss": 0.3344,
"step": 117500
},
{
"epoch": 4.81,
"learning_rate": 1.9230769230769234e-06,
"loss": 0.3373,
"step": 118000
},
{
"epoch": 4.83,
"learning_rate": 1.7193611473272493e-06,
"loss": 0.3283,
"step": 118500
},
{
"epoch": 4.85,
"learning_rate": 1.5156453715775751e-06,
"loss": 0.3282,
"step": 119000
},
{
"epoch": 4.87,
"learning_rate": 1.311929595827901e-06,
"loss": 0.3243,
"step": 119500
},
{
"epoch": 4.89,
"learning_rate": 1.108213820078227e-06,
"loss": 0.3322,
"step": 120000
},
{
"epoch": 4.91,
"learning_rate": 9.044980443285528e-07,
"loss": 0.3164,
"step": 120500
},
{
"epoch": 4.93,
"learning_rate": 7.007822685788788e-07,
"loss": 0.3215,
"step": 121000
},
{
"epoch": 4.95,
"learning_rate": 4.970664928292048e-07,
"loss": 0.3203,
"step": 121500
},
{
"epoch": 4.97,
"learning_rate": 2.9335071707953065e-07,
"loss": 0.3216,
"step": 122000
},
{
"epoch": 4.99,
"learning_rate": 8.963494132985658e-08,
"loss": 0.332,
"step": 122500
},
{
"epoch": 5.0,
"step": 122720,
"total_flos": 5.166258268431053e+17,
"train_loss": 0.5170908811661225,
"train_runtime": 67360.5161,
"train_samples_per_second": 29.149,
"train_steps_per_second": 1.822
}
],
"max_steps": 122720,
"num_train_epochs": 5,
"total_flos": 5.166258268431053e+17,
"trial_name": null,
"trial_params": null
}