bert-large-arabertv02-twitter / trainer_state.json
wissamantoun's picture
First commit
b7bb29b
raw history blame
No virus
72.1 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9999981467376096,
"global_step": 269794,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.446997776130467e-06,
"loss": 4.2339,
"step": 500
},
{
"epoch": 0.0,
"learning_rate": 2.9295774647887324e-06,
"loss": 3.743,
"step": 1000
},
{
"epoch": 0.0,
"learning_rate": 4.4121571534469985e-06,
"loss": 3.5488,
"step": 1500
},
{
"epoch": 0.01,
"learning_rate": 5.8947368421052634e-06,
"loss": 3.441,
"step": 2000
},
{
"epoch": 0.01,
"learning_rate": 7.377316530763528e-06,
"loss": 3.3861,
"step": 2500
},
{
"epoch": 0.01,
"learning_rate": 8.859896219421795e-06,
"loss": 3.3338,
"step": 3000
},
{
"epoch": 0.01,
"learning_rate": 1.034247590808006e-05,
"loss": 3.2739,
"step": 3500
},
{
"epoch": 0.01,
"learning_rate": 1.1825055596738326e-05,
"loss": 3.2384,
"step": 4000
},
{
"epoch": 0.01,
"learning_rate": 1.3307635285396591e-05,
"loss": 3.1955,
"step": 4500
},
{
"epoch": 0.01,
"learning_rate": 1.4790214974054856e-05,
"loss": 3.1733,
"step": 5000
},
{
"epoch": 0.02,
"learning_rate": 1.6272794662713124e-05,
"loss": 3.1648,
"step": 5500
},
{
"epoch": 0.02,
"learning_rate": 1.7755374351371386e-05,
"loss": 3.1262,
"step": 6000
},
{
"epoch": 0.02,
"learning_rate": 1.923795404002965e-05,
"loss": 3.112,
"step": 6500
},
{
"epoch": 0.02,
"learning_rate": 2.072053372868792e-05,
"loss": 3.0858,
"step": 7000
},
{
"epoch": 0.02,
"learning_rate": 2.2203113417346184e-05,
"loss": 3.0709,
"step": 7500
},
{
"epoch": 0.02,
"learning_rate": 2.368569310600445e-05,
"loss": 3.0446,
"step": 8000
},
{
"epoch": 0.03,
"learning_rate": 2.516827279466271e-05,
"loss": 3.0337,
"step": 8500
},
{
"epoch": 0.03,
"learning_rate": 2.6650852483320982e-05,
"loss": 3.0176,
"step": 9000
},
{
"epoch": 0.03,
"learning_rate": 2.8133432171979247e-05,
"loss": 2.9892,
"step": 9500
},
{
"epoch": 0.03,
"learning_rate": 2.9613046701260195e-05,
"loss": 2.9966,
"step": 10000
},
{
"epoch": 0.03,
"learning_rate": 3.1095626389918456e-05,
"loss": 2.9685,
"step": 10500
},
{
"epoch": 0.03,
"learning_rate": 3.257820607857672e-05,
"loss": 2.9461,
"step": 11000
},
{
"epoch": 0.03,
"learning_rate": 3.406078576723499e-05,
"loss": 2.9472,
"step": 11500
},
{
"epoch": 0.04,
"learning_rate": 3.554336545589326e-05,
"loss": 2.9346,
"step": 12000
},
{
"epoch": 0.04,
"learning_rate": 3.7022979985174206e-05,
"loss": 2.9418,
"step": 12500
},
{
"epoch": 0.04,
"learning_rate": 3.850555967383247e-05,
"loss": 2.9088,
"step": 13000
},
{
"epoch": 0.04,
"learning_rate": 3.9988139362490736e-05,
"loss": 2.8908,
"step": 13500
},
{
"epoch": 0.04,
"learning_rate": 4.147071905114901e-05,
"loss": 2.8886,
"step": 14000
},
{
"epoch": 0.04,
"learning_rate": 4.2953298739807265e-05,
"loss": 2.8681,
"step": 14500
},
{
"epoch": 0.04,
"learning_rate": 4.4432913269088213e-05,
"loss": 2.8626,
"step": 15000
},
{
"epoch": 0.05,
"learning_rate": 4.591549295774648e-05,
"loss": 2.8519,
"step": 15500
},
{
"epoch": 0.05,
"learning_rate": 4.739807264640474e-05,
"loss": 2.8402,
"step": 16000
},
{
"epoch": 0.05,
"learning_rate": 4.888065233506301e-05,
"loss": 2.8259,
"step": 16500
},
{
"epoch": 0.05,
"learning_rate": 5.036323202372127e-05,
"loss": 2.836,
"step": 17000
},
{
"epoch": 0.05,
"learning_rate": 5.1845811712379545e-05,
"loss": 2.8166,
"step": 17500
},
{
"epoch": 0.05,
"learning_rate": 5.3328391401037816e-05,
"loss": 2.796,
"step": 18000
},
{
"epoch": 0.05,
"learning_rate": 5.4810971089696074e-05,
"loss": 2.7931,
"step": 18500
},
{
"epoch": 0.06,
"learning_rate": 5.629058561897702e-05,
"loss": 2.7947,
"step": 19000
},
{
"epoch": 0.06,
"learning_rate": 5.777020014825797e-05,
"loss": 2.7701,
"step": 19500
},
{
"epoch": 0.06,
"learning_rate": 5.925277983691624e-05,
"loss": 2.7674,
"step": 20000
},
{
"epoch": 0.06,
"learning_rate": 6.07353595255745e-05,
"loss": 2.7625,
"step": 20500
},
{
"epoch": 0.06,
"learning_rate": 6.221793921423277e-05,
"loss": 2.754,
"step": 21000
},
{
"epoch": 0.06,
"learning_rate": 6.370051890289104e-05,
"loss": 2.7621,
"step": 21500
},
{
"epoch": 0.07,
"learning_rate": 6.51830985915493e-05,
"loss": 2.7329,
"step": 22000
},
{
"epoch": 0.07,
"learning_rate": 6.666567828020757e-05,
"loss": 2.7392,
"step": 22500
},
{
"epoch": 0.07,
"learning_rate": 6.814825796886583e-05,
"loss": 2.7446,
"step": 23000
},
{
"epoch": 0.07,
"learning_rate": 6.96308376575241e-05,
"loss": 2.7346,
"step": 23500
},
{
"epoch": 0.07,
"learning_rate": 7.111341734618236e-05,
"loss": 2.7246,
"step": 24000
},
{
"epoch": 0.07,
"learning_rate": 7.259599703484063e-05,
"loss": 2.7393,
"step": 24500
},
{
"epoch": 0.07,
"learning_rate": 7.407857672349889e-05,
"loss": 2.7271,
"step": 25000
},
{
"epoch": 0.07,
"eval_loss": 2.5492873191833496,
"eval_runtime": 278.1602,
"eval_samples_per_second": 359.505,
"eval_steps_per_second": 44.938,
"step": 25000
},
{
"epoch": 0.08,
"learning_rate": 7.556115641215716e-05,
"loss": 2.7127,
"step": 25500
},
{
"epoch": 0.08,
"learning_rate": 7.704373610081542e-05,
"loss": 2.713,
"step": 26000
},
{
"epoch": 0.08,
"learning_rate": 7.852631578947369e-05,
"loss": 2.7002,
"step": 26500
},
{
"epoch": 0.08,
"learning_rate": 8.000593031875464e-05,
"loss": 2.7042,
"step": 27000
},
{
"epoch": 0.08,
"learning_rate": 8.14885100074129e-05,
"loss": 2.7054,
"step": 27500
},
{
"epoch": 0.08,
"learning_rate": 8.297108969607117e-05,
"loss": 2.6925,
"step": 28000
},
{
"epoch": 0.08,
"learning_rate": 8.445366938472942e-05,
"loss": 2.6927,
"step": 28500
},
{
"epoch": 0.09,
"learning_rate": 8.59362490733877e-05,
"loss": 2.6843,
"step": 29000
},
{
"epoch": 0.09,
"learning_rate": 8.741882876204596e-05,
"loss": 2.6848,
"step": 29500
},
{
"epoch": 0.09,
"learning_rate": 8.890140845070423e-05,
"loss": 2.6851,
"step": 30000
},
{
"epoch": 0.09,
"learning_rate": 9.03839881393625e-05,
"loss": 2.676,
"step": 30500
},
{
"epoch": 0.09,
"learning_rate": 9.186656782802076e-05,
"loss": 2.6811,
"step": 31000
},
{
"epoch": 0.09,
"learning_rate": 9.334914751667902e-05,
"loss": 2.6687,
"step": 31500
},
{
"epoch": 0.09,
"learning_rate": 9.483172720533729e-05,
"loss": 2.6751,
"step": 32000
},
{
"epoch": 0.1,
"learning_rate": 9.631430689399555e-05,
"loss": 2.6746,
"step": 32500
},
{
"epoch": 0.1,
"learning_rate": 9.779688658265382e-05,
"loss": 2.6662,
"step": 33000
},
{
"epoch": 0.1,
"learning_rate": 9.927946627131208e-05,
"loss": 2.6685,
"step": 33500
},
{
"epoch": 0.1,
"learning_rate": 9.999982309633072e-05,
"loss": 2.6702,
"step": 34000
},
{
"epoch": 0.1,
"learning_rate": 9.999846516961786e-05,
"loss": 2.6692,
"step": 34500
},
{
"epoch": 0.1,
"learning_rate": 9.999577483170183e-05,
"loss": 2.6732,
"step": 35000
},
{
"epoch": 0.11,
"learning_rate": 9.9991750774992e-05,
"loss": 2.6676,
"step": 35500
},
{
"epoch": 0.11,
"learning_rate": 9.998638103115459e-05,
"loss": 2.65,
"step": 36000
},
{
"epoch": 0.11,
"learning_rate": 9.997967246921306e-05,
"loss": 2.6493,
"step": 36500
},
{
"epoch": 0.11,
"learning_rate": 9.997162526884725e-05,
"loss": 2.657,
"step": 37000
},
{
"epoch": 0.11,
"learning_rate": 9.996223964559059e-05,
"loss": 2.6521,
"step": 37500
},
{
"epoch": 0.11,
"learning_rate": 9.995151585082442e-05,
"loss": 2.6412,
"step": 38000
},
{
"epoch": 0.11,
"learning_rate": 9.993947963012904e-05,
"loss": 2.6418,
"step": 38500
},
{
"epoch": 0.12,
"learning_rate": 9.992608306462086e-05,
"loss": 2.6442,
"step": 39000
},
{
"epoch": 0.12,
"learning_rate": 9.991134929600863e-05,
"loss": 2.6362,
"step": 39500
},
{
"epoch": 0.12,
"learning_rate": 9.989527871891659e-05,
"loss": 2.6354,
"step": 40000
},
{
"epoch": 0.12,
"learning_rate": 9.987787176377355e-05,
"loss": 2.6167,
"step": 40500
},
{
"epoch": 0.12,
"learning_rate": 9.985912889680143e-05,
"loss": 2.6316,
"step": 41000
},
{
"epoch": 0.12,
"learning_rate": 9.983905062000275e-05,
"loss": 2.6355,
"step": 41500
},
{
"epoch": 0.12,
"learning_rate": 9.981763747114724e-05,
"loss": 2.6183,
"step": 42000
},
{
"epoch": 0.13,
"learning_rate": 9.979493684988302e-05,
"loss": 2.6111,
"step": 42500
},
{
"epoch": 0.13,
"learning_rate": 9.977085837996527e-05,
"loss": 2.6053,
"step": 43000
},
{
"epoch": 0.13,
"learning_rate": 9.97454990173924e-05,
"loss": 2.6019,
"step": 43500
},
{
"epoch": 0.13,
"learning_rate": 9.971875780087649e-05,
"loss": 2.6166,
"step": 44000
},
{
"epoch": 0.13,
"learning_rate": 9.969074240841182e-05,
"loss": 2.6378,
"step": 44500
},
{
"epoch": 0.13,
"learning_rate": 9.966134130446202e-05,
"loss": 2.6069,
"step": 45000
},
{
"epoch": 0.13,
"learning_rate": 9.963067287750436e-05,
"loss": 2.6201,
"step": 45500
},
{
"epoch": 0.14,
"learning_rate": 9.959861502967945e-05,
"loss": 2.5973,
"step": 46000
},
{
"epoch": 0.14,
"learning_rate": 9.956522874954218e-05,
"loss": 2.5926,
"step": 46500
},
{
"epoch": 0.14,
"learning_rate": 9.95305149312992e-05,
"loss": 2.5856,
"step": 47000
},
{
"epoch": 0.14,
"learning_rate": 9.949447450471355e-05,
"loss": 2.5929,
"step": 47500
},
{
"epoch": 0.14,
"learning_rate": 9.945710843507967e-05,
"loss": 2.5851,
"step": 48000
},
{
"epoch": 0.14,
"learning_rate": 9.94184964259314e-05,
"loss": 2.5704,
"step": 48500
},
{
"epoch": 0.15,
"learning_rate": 9.9378484754234e-05,
"loss": 2.5823,
"step": 49000
},
{
"epoch": 0.15,
"learning_rate": 9.933715054611808e-05,
"loss": 2.5716,
"step": 49500
},
{
"epoch": 0.15,
"learning_rate": 9.929458153797284e-05,
"loss": 2.6217,
"step": 50000
},
{
"epoch": 0.15,
"eval_loss": 2.431061267852783,
"eval_runtime": 279.1709,
"eval_samples_per_second": 358.204,
"eval_steps_per_second": 44.775,
"step": 50000
},
{
"epoch": 0.19,
"learning_rate": 9.77079560136976e-05,
"loss": 2.5993,
"step": 50500
},
{
"epoch": 0.19,
"learning_rate": 9.76101478820416e-05,
"loss": 2.5537,
"step": 51000
},
{
"epoch": 0.19,
"learning_rate": 9.751034728712014e-05,
"loss": 2.5581,
"step": 51500
},
{
"epoch": 0.19,
"learning_rate": 9.740855840554321e-05,
"loss": 2.6137,
"step": 52000
},
{
"epoch": 0.19,
"learning_rate": 9.730478549712973e-05,
"loss": 2.5886,
"step": 52500
},
{
"epoch": 0.2,
"learning_rate": 9.719903290472921e-05,
"loss": 2.5534,
"step": 53000
},
{
"epoch": 0.2,
"learning_rate": 9.709130505404002e-05,
"loss": 2.5475,
"step": 53500
},
{
"epoch": 0.2,
"learning_rate": 9.698160645342426e-05,
"loss": 2.5613,
"step": 54000
},
{
"epoch": 0.2,
"learning_rate": 9.686994169371903e-05,
"loss": 2.5487,
"step": 54500
},
{
"epoch": 0.2,
"learning_rate": 9.675631544804424e-05,
"loss": 2.5659,
"step": 55000
},
{
"epoch": 0.21,
"learning_rate": 9.664073247160717e-05,
"loss": 2.5319,
"step": 55500
},
{
"epoch": 0.21,
"learning_rate": 9.652319760150334e-05,
"loss": 2.5536,
"step": 56000
},
{
"epoch": 0.21,
"learning_rate": 9.640371575651422e-05,
"loss": 2.53,
"step": 56500
},
{
"epoch": 0.21,
"learning_rate": 9.628229193690122e-05,
"loss": 2.524,
"step": 57000
},
{
"epoch": 0.21,
"learning_rate": 9.615893122419657e-05,
"loss": 2.5219,
"step": 57500
},
{
"epoch": 0.21,
"learning_rate": 9.60336387809906e-05,
"loss": 2.51,
"step": 58000
},
{
"epoch": 0.22,
"learning_rate": 9.590641985071566e-05,
"loss": 2.5131,
"step": 58500
},
{
"epoch": 0.22,
"learning_rate": 9.577727975742674e-05,
"loss": 2.506,
"step": 59000
},
{
"epoch": 0.22,
"learning_rate": 9.564622390557863e-05,
"loss": 2.5086,
"step": 59500
},
{
"epoch": 0.22,
"learning_rate": 9.551325777979978e-05,
"loss": 2.4997,
"step": 60000
},
{
"epoch": 0.22,
"learning_rate": 9.53783869446627e-05,
"loss": 2.4888,
"step": 60500
},
{
"epoch": 0.23,
"learning_rate": 9.524161704445116e-05,
"loss": 2.4952,
"step": 61000
},
{
"epoch": 0.23,
"learning_rate": 9.510295380292393e-05,
"loss": 2.4868,
"step": 61500
},
{
"epoch": 0.23,
"learning_rate": 9.496240302307531e-05,
"loss": 2.4906,
"step": 62000
},
{
"epoch": 0.23,
"learning_rate": 9.481997058689214e-05,
"loss": 2.4815,
"step": 62500
},
{
"epoch": 0.23,
"learning_rate": 9.467566245510782e-05,
"loss": 2.4772,
"step": 63000
},
{
"epoch": 0.24,
"learning_rate": 9.45294846669527e-05,
"loss": 2.4919,
"step": 63500
},
{
"epoch": 0.24,
"learning_rate": 9.438144333990148e-05,
"loss": 2.4889,
"step": 64000
},
{
"epoch": 0.24,
"learning_rate": 9.423154466941704e-05,
"loss": 2.4811,
"step": 64500
},
{
"epoch": 0.24,
"learning_rate": 9.407979492869132e-05,
"loss": 2.4721,
"step": 65000
},
{
"epoch": 0.24,
"learning_rate": 9.392620046838267e-05,
"loss": 2.4696,
"step": 65500
},
{
"epoch": 0.24,
"learning_rate": 9.377076771635013e-05,
"loss": 2.4739,
"step": 66000
},
{
"epoch": 0.25,
"learning_rate": 9.361350317738446e-05,
"loss": 2.4704,
"step": 66500
},
{
"epoch": 0.25,
"learning_rate": 9.345441343293581e-05,
"loss": 2.4727,
"step": 67000
},
{
"epoch": 0.25,
"learning_rate": 9.329350514083845e-05,
"loss": 2.4649,
"step": 67500
},
{
"epoch": 0.25,
"learning_rate": 9.313078503503196e-05,
"loss": 2.4619,
"step": 68000
},
{
"epoch": 0.25,
"learning_rate": 9.296625992527957e-05,
"loss": 2.4577,
"step": 68500
},
{
"epoch": 0.26,
"learning_rate": 9.279993669688308e-05,
"loss": 2.46,
"step": 69000
},
{
"epoch": 0.26,
"learning_rate": 9.263182231039476e-05,
"loss": 2.4562,
"step": 69500
},
{
"epoch": 0.26,
"learning_rate": 9.246192380132604e-05,
"loss": 2.4431,
"step": 70000
},
{
"epoch": 0.26,
"learning_rate": 9.229024827985306e-05,
"loss": 2.4523,
"step": 70500
},
{
"epoch": 0.26,
"learning_rate": 9.211680293051915e-05,
"loss": 2.4558,
"step": 71000
},
{
"epoch": 0.27,
"learning_rate": 9.194159501193414e-05,
"loss": 2.4508,
"step": 71500
},
{
"epoch": 0.27,
"learning_rate": 9.17646318564706e-05,
"loss": 2.4526,
"step": 72000
},
{
"epoch": 0.27,
"learning_rate": 9.158592086995692e-05,
"loss": 2.4455,
"step": 72500
},
{
"epoch": 0.27,
"learning_rate": 9.140546953136748e-05,
"loss": 2.4423,
"step": 73000
},
{
"epoch": 0.27,
"learning_rate": 9.122328539250962e-05,
"loss": 2.4291,
"step": 73500
},
{
"epoch": 0.27,
"learning_rate": 9.103937607770756e-05,
"loss": 2.4521,
"step": 74000
},
{
"epoch": 0.28,
"learning_rate": 9.085374928348338e-05,
"loss": 2.4427,
"step": 74500
},
{
"epoch": 0.28,
"learning_rate": 9.066641277823487e-05,
"loss": 2.4378,
"step": 75000
},
{
"epoch": 0.28,
"eval_loss": 2.274932622909546,
"eval_runtime": 278.4521,
"eval_samples_per_second": 359.128,
"eval_steps_per_second": 44.891,
"step": 75000
},
{
"epoch": 0.28,
"learning_rate": 9.047737440191048e-05,
"loss": 2.4375,
"step": 75500
},
{
"epoch": 0.28,
"learning_rate": 9.028664206568123e-05,
"loss": 2.4262,
"step": 76000
},
{
"epoch": 0.28,
"learning_rate": 9.009422375160955e-05,
"loss": 2.4342,
"step": 76500
},
{
"epoch": 0.29,
"learning_rate": 8.990012751231527e-05,
"loss": 2.427,
"step": 77000
},
{
"epoch": 0.29,
"learning_rate": 8.970436147063869e-05,
"loss": 2.419,
"step": 77500
},
{
"epoch": 0.29,
"learning_rate": 8.950693381930058e-05,
"loss": 2.4241,
"step": 78000
},
{
"epoch": 0.29,
"learning_rate": 8.930785282055928e-05,
"loss": 2.4192,
"step": 78500
},
{
"epoch": 0.29,
"learning_rate": 8.910712680586502e-05,
"loss": 2.4179,
"step": 79000
},
{
"epoch": 0.29,
"learning_rate": 8.890476417551119e-05,
"loss": 2.4176,
"step": 79500
},
{
"epoch": 0.3,
"learning_rate": 8.870077339828284e-05,
"loss": 2.4179,
"step": 80000
},
{
"epoch": 0.3,
"learning_rate": 8.849516301110216e-05,
"loss": 2.418,
"step": 80500
},
{
"epoch": 0.3,
"learning_rate": 8.828794161867136e-05,
"loss": 2.4116,
"step": 81000
},
{
"epoch": 0.3,
"learning_rate": 8.807911789311245e-05,
"loss": 2.4114,
"step": 81500
},
{
"epoch": 0.3,
"learning_rate": 8.786870057360441e-05,
"loss": 2.4091,
"step": 82000
},
{
"epoch": 0.31,
"learning_rate": 8.765669846601735e-05,
"loss": 2.4125,
"step": 82500
},
{
"epoch": 0.31,
"learning_rate": 8.744312044254409e-05,
"loss": 2.4115,
"step": 83000
},
{
"epoch": 0.31,
"learning_rate": 8.722797544132881e-05,
"loss": 2.4195,
"step": 83500
},
{
"epoch": 0.31,
"learning_rate": 8.701127246609299e-05,
"loss": 2.4048,
"step": 84000
},
{
"epoch": 0.31,
"learning_rate": 8.679302058575865e-05,
"loss": 2.4075,
"step": 84500
},
{
"epoch": 0.32,
"learning_rate": 8.657322893406876e-05,
"loss": 2.3983,
"step": 85000
},
{
"epoch": 0.32,
"learning_rate": 8.635190670920503e-05,
"loss": 2.3999,
"step": 85500
},
{
"epoch": 0.32,
"learning_rate": 8.6129063173403e-05,
"loss": 2.4055,
"step": 86000
},
{
"epoch": 0.32,
"learning_rate": 8.590470765256439e-05,
"loss": 2.3899,
"step": 86500
},
{
"epoch": 0.32,
"learning_rate": 8.567884953586675e-05,
"loss": 2.3935,
"step": 87000
},
{
"epoch": 0.32,
"learning_rate": 8.545149827537065e-05,
"loss": 2.3872,
"step": 87500
},
{
"epoch": 0.33,
"learning_rate": 8.522266338562404e-05,
"loss": 2.3877,
"step": 88000
},
{
"epoch": 0.33,
"learning_rate": 8.499235444326407e-05,
"loss": 2.3939,
"step": 88500
},
{
"epoch": 0.33,
"learning_rate": 8.476058108661639e-05,
"loss": 2.3855,
"step": 89000
},
{
"epoch": 0.33,
"learning_rate": 8.452735301529164e-05,
"loss": 2.388,
"step": 89500
},
{
"epoch": 0.33,
"learning_rate": 8.429267998977967e-05,
"loss": 2.3801,
"step": 90000
},
{
"epoch": 0.34,
"learning_rate": 8.4056571831041e-05,
"loss": 2.3723,
"step": 90500
},
{
"epoch": 0.34,
"learning_rate": 8.381903842009583e-05,
"loss": 2.3838,
"step": 91000
},
{
"epoch": 0.34,
"learning_rate": 8.358008969761053e-05,
"loss": 2.3857,
"step": 91500
},
{
"epoch": 0.34,
"learning_rate": 8.333973566348161e-05,
"loss": 2.3678,
"step": 92000
},
{
"epoch": 0.34,
"learning_rate": 8.309798637641725e-05,
"loss": 2.3804,
"step": 92500
},
{
"epoch": 0.34,
"learning_rate": 8.285485195351632e-05,
"loss": 2.3667,
"step": 93000
},
{
"epoch": 0.35,
"learning_rate": 8.261034256984503e-05,
"loss": 2.3648,
"step": 93500
},
{
"epoch": 0.35,
"learning_rate": 8.236446845801104e-05,
"loss": 2.4219,
"step": 94000
},
{
"epoch": 0.35,
"learning_rate": 8.211723990773533e-05,
"loss": 2.4274,
"step": 94500
},
{
"epoch": 0.35,
"learning_rate": 8.186866726542143e-05,
"loss": 2.4006,
"step": 95000
},
{
"epoch": 0.35,
"learning_rate": 8.161876093372264e-05,
"loss": 2.3849,
"step": 95500
},
{
"epoch": 0.36,
"learning_rate": 8.136753137110643e-05,
"loss": 2.3937,
"step": 96000
},
{
"epoch": 0.36,
"learning_rate": 8.111498909141696e-05,
"loss": 2.3867,
"step": 96500
},
{
"epoch": 0.36,
"learning_rate": 8.086114466343502e-05,
"loss": 2.3914,
"step": 97000
},
{
"epoch": 0.36,
"learning_rate": 8.060600871043566e-05,
"loss": 2.3946,
"step": 97500
},
{
"epoch": 0.36,
"learning_rate": 8.034959190974374e-05,
"loss": 2.397,
"step": 98000
},
{
"epoch": 0.37,
"learning_rate": 8.009190499228698e-05,
"loss": 2.3854,
"step": 98500
},
{
"epoch": 0.37,
"learning_rate": 7.983295874214692e-05,
"loss": 2.4079,
"step": 99000
},
{
"epoch": 0.37,
"learning_rate": 7.95727639961076e-05,
"loss": 2.394,
"step": 99500
},
{
"epoch": 0.37,
"learning_rate": 7.931133164320208e-05,
"loss": 2.394,
"step": 100000
},
{
"epoch": 0.37,
"eval_loss": 2.2282919883728027,
"eval_runtime": 285.8926,
"eval_samples_per_second": 349.782,
"eval_steps_per_second": 43.723,
"step": 100000
},
{
"epoch": 0.37,
"learning_rate": 7.904867262425669e-05,
"loss": 2.3871,
"step": 100500
},
{
"epoch": 0.37,
"learning_rate": 7.878479793143314e-05,
"loss": 2.3768,
"step": 101000
},
{
"epoch": 0.38,
"learning_rate": 7.851971860776864e-05,
"loss": 2.3783,
"step": 101500
},
{
"epoch": 0.38,
"learning_rate": 7.82534457467136e-05,
"loss": 2.3733,
"step": 102000
},
{
"epoch": 0.38,
"learning_rate": 7.798599049166741e-05,
"loss": 2.3717,
"step": 102500
},
{
"epoch": 0.38,
"learning_rate": 7.771736403551216e-05,
"loss": 2.3689,
"step": 103000
},
{
"epoch": 0.38,
"learning_rate": 7.744757762014416e-05,
"loss": 2.3714,
"step": 103500
},
{
"epoch": 0.39,
"learning_rate": 7.717664253600352e-05,
"loss": 2.3792,
"step": 104000
},
{
"epoch": 0.39,
"learning_rate": 7.690457012160156e-05,
"loss": 2.3711,
"step": 104500
},
{
"epoch": 0.39,
"learning_rate": 7.663137176304642e-05,
"loss": 2.3829,
"step": 105000
},
{
"epoch": 0.39,
"learning_rate": 7.635705889356646e-05,
"loss": 2.4541,
"step": 105500
},
{
"epoch": 0.39,
"learning_rate": 7.608164299303187e-05,
"loss": 2.386,
"step": 106000
},
{
"epoch": 0.39,
"learning_rate": 7.580513558747409e-05,
"loss": 2.3839,
"step": 106500
},
{
"epoch": 0.4,
"learning_rate": 7.552754824860368e-05,
"loss": 2.3896,
"step": 107000
},
{
"epoch": 0.4,
"learning_rate": 7.524889259332584e-05,
"loss": 2.3839,
"step": 107500
},
{
"epoch": 0.4,
"learning_rate": 7.496918028325434e-05,
"loss": 2.3821,
"step": 108000
},
{
"epoch": 0.4,
"learning_rate": 7.468842302422355e-05,
"loss": 2.3797,
"step": 108500
},
{
"epoch": 0.4,
"learning_rate": 7.440663256579836e-05,
"loss": 2.348,
"step": 109000
},
{
"epoch": 0.41,
"learning_rate": 7.412382070078269e-05,
"loss": 2.3413,
"step": 109500
},
{
"epoch": 0.41,
"learning_rate": 7.383999926472585e-05,
"loss": 2.3497,
"step": 110000
},
{
"epoch": 0.41,
"learning_rate": 7.355518013542717e-05,
"loss": 2.3303,
"step": 110500
},
{
"epoch": 0.41,
"learning_rate": 7.326937523243908e-05,
"loss": 2.3348,
"step": 111000
},
{
"epoch": 0.41,
"learning_rate": 7.29825965165682e-05,
"loss": 2.3375,
"step": 111500
},
{
"epoch": 0.42,
"learning_rate": 7.269485598937468e-05,
"loss": 2.3271,
"step": 112000
},
{
"epoch": 0.42,
"learning_rate": 7.240616569267015e-05,
"loss": 2.3184,
"step": 112500
},
{
"epoch": 0.42,
"learning_rate": 7.211653770801363e-05,
"loss": 2.333,
"step": 113000
},
{
"epoch": 0.42,
"learning_rate": 7.182598415620591e-05,
"loss": 2.3712,
"step": 113500
},
{
"epoch": 0.42,
"learning_rate": 7.153451719678243e-05,
"loss": 2.3387,
"step": 114000
},
{
"epoch": 0.42,
"learning_rate": 7.124214902750428e-05,
"loss": 2.3274,
"step": 114500
},
{
"epoch": 0.43,
"learning_rate": 7.094889188384774e-05,
"loss": 2.326,
"step": 115000
},
{
"epoch": 0.43,
"learning_rate": 7.065475803849241e-05,
"loss": 2.3131,
"step": 115500
},
{
"epoch": 0.43,
"learning_rate": 7.035975980080728e-05,
"loss": 2.3186,
"step": 116000
},
{
"epoch": 0.43,
"learning_rate": 7.006390951633589e-05,
"loss": 2.3156,
"step": 116500
},
{
"epoch": 0.43,
"learning_rate": 6.976721956627952e-05,
"loss": 2.3211,
"step": 117000
},
{
"epoch": 0.44,
"learning_rate": 6.946970236697905e-05,
"loss": 2.3116,
"step": 117500
},
{
"epoch": 0.44,
"learning_rate": 6.917137036939542e-05,
"loss": 2.3189,
"step": 118000
},
{
"epoch": 0.44,
"learning_rate": 6.88722360585885e-05,
"loss": 2.3286,
"step": 118500
},
{
"epoch": 0.44,
"learning_rate": 6.857231195319457e-05,
"loss": 2.3186,
"step": 119000
},
{
"epoch": 0.44,
"learning_rate": 6.827161060490248e-05,
"loss": 2.3102,
"step": 119500
},
{
"epoch": 0.44,
"learning_rate": 6.797014459792836e-05,
"loss": 2.3146,
"step": 120000
},
{
"epoch": 0.45,
"learning_rate": 6.766792654848896e-05,
"loss": 2.2962,
"step": 120500
},
{
"epoch": 0.45,
"learning_rate": 6.736496910427364e-05,
"loss": 2.2984,
"step": 121000
},
{
"epoch": 0.45,
"learning_rate": 6.70612849439151e-05,
"loss": 2.308,
"step": 121500
},
{
"epoch": 0.45,
"learning_rate": 6.675688677645883e-05,
"loss": 2.3029,
"step": 122000
},
{
"epoch": 0.45,
"learning_rate": 6.645178734083117e-05,
"loss": 2.2933,
"step": 122500
},
{
"epoch": 0.46,
"learning_rate": 6.614599940530619e-05,
"loss": 2.3026,
"step": 123000
},
{
"epoch": 0.46,
"learning_rate": 6.583953576697141e-05,
"loss": 2.3084,
"step": 123500
},
{
"epoch": 0.46,
"learning_rate": 6.553240925119219e-05,
"loss": 2.2985,
"step": 124000
},
{
"epoch": 0.46,
"learning_rate": 6.522463271107502e-05,
"loss": 2.3035,
"step": 124500
},
{
"epoch": 0.46,
"learning_rate": 6.49162190269296e-05,
"loss": 2.2891,
"step": 125000
},
{
"epoch": 0.46,
"eval_loss": 2.1396679878234863,
"eval_runtime": 305.6778,
"eval_samples_per_second": 327.142,
"eval_steps_per_second": 40.893,
"step": 125000
},
{
"epoch": 0.47,
"learning_rate": 6.460718110572983e-05,
"loss": 2.2987,
"step": 125500
},
{
"epoch": 0.47,
"learning_rate": 6.429753188057368e-05,
"loss": 2.2899,
"step": 126000
},
{
"epoch": 0.47,
"learning_rate": 6.398728431014187e-05,
"loss": 2.2919,
"step": 126500
},
{
"epoch": 0.47,
"learning_rate": 6.367645137815561e-05,
"loss": 2.2878,
"step": 127000
},
{
"epoch": 0.47,
"learning_rate": 6.336504609283325e-05,
"loss": 2.2848,
"step": 127500
},
{
"epoch": 0.47,
"learning_rate": 6.305308148634585e-05,
"loss": 2.2813,
"step": 128000
},
{
"epoch": 0.48,
"learning_rate": 6.274057061427182e-05,
"loss": 2.2804,
"step": 128500
},
{
"epoch": 0.48,
"learning_rate": 6.242752655505053e-05,
"loss": 2.2888,
"step": 129000
},
{
"epoch": 0.48,
"learning_rate": 6.211396240943499e-05,
"loss": 2.2884,
"step": 129500
},
{
"epoch": 0.48,
"learning_rate": 6.17998912999436e-05,
"loss": 2.28,
"step": 130000
},
{
"epoch": 0.48,
"learning_rate": 6.148532637031098e-05,
"loss": 2.2855,
"step": 130500
},
{
"epoch": 0.49,
"learning_rate": 6.117028078493787e-05,
"loss": 2.3124,
"step": 131000
},
{
"epoch": 0.49,
"learning_rate": 6.085476772834029e-05,
"loss": 2.2886,
"step": 131500
},
{
"epoch": 0.49,
"learning_rate": 6.053880040459764e-05,
"loss": 2.3043,
"step": 132000
},
{
"epoch": 0.49,
"learning_rate": 6.022239203680027e-05,
"loss": 2.3534,
"step": 132500
},
{
"epoch": 0.49,
"learning_rate": 5.990555586649599e-05,
"loss": 2.569,
"step": 133000
},
{
"epoch": 0.49,
"learning_rate": 5.958830515313596e-05,
"loss": 2.341,
"step": 133500
},
{
"epoch": 0.5,
"learning_rate": 5.927065317351976e-05,
"loss": 2.2866,
"step": 134000
},
{
"epoch": 0.5,
"learning_rate": 5.8952613221239826e-05,
"loss": 2.2786,
"step": 134500
},
{
"epoch": 0.5,
"learning_rate": 5.863419860612506e-05,
"loss": 2.2707,
"step": 135000
},
{
"epoch": 0.5,
"learning_rate": 5.831542265368378e-05,
"loss": 2.277,
"step": 135500
},
{
"epoch": 0.5,
"learning_rate": 5.799629870454619e-05,
"loss": 2.2702,
"step": 136000
},
{
"epoch": 0.51,
"learning_rate": 5.7676840113905974e-05,
"loss": 2.2673,
"step": 136500
},
{
"epoch": 0.51,
"learning_rate": 5.735706025096136e-05,
"loss": 2.2517,
"step": 137000
},
{
"epoch": 0.51,
"learning_rate": 5.7036972498355744e-05,
"loss": 2.2768,
"step": 137500
},
{
"epoch": 0.51,
"learning_rate": 5.671659025161755e-05,
"loss": 2.2569,
"step": 138000
},
{
"epoch": 0.51,
"learning_rate": 5.6395926918599606e-05,
"loss": 2.2527,
"step": 138500
},
{
"epoch": 0.52,
"learning_rate": 5.607499591891816e-05,
"loss": 2.2662,
"step": 139000
},
{
"epoch": 0.52,
"learning_rate": 5.5753810683391104e-05,
"loss": 2.2446,
"step": 139500
},
{
"epoch": 0.52,
"learning_rate": 5.5432384653476e-05,
"loss": 2.2506,
"step": 140000
},
{
"epoch": 0.52,
"learning_rate": 5.5110731280707605e-05,
"loss": 2.2495,
"step": 140500
},
{
"epoch": 0.52,
"learning_rate": 5.4788864026134824e-05,
"loss": 2.2513,
"step": 141000
},
{
"epoch": 0.52,
"learning_rate": 5.446679635975741e-05,
"loss": 2.2512,
"step": 141500
},
{
"epoch": 0.53,
"learning_rate": 5.41445417599623e-05,
"loss": 2.2497,
"step": 142000
},
{
"epoch": 0.53,
"learning_rate": 5.3822113712959466e-05,
"loss": 2.2491,
"step": 142500
},
{
"epoch": 0.53,
"learning_rate": 5.349952571221761e-05,
"loss": 2.2425,
"step": 143000
},
{
"epoch": 0.53,
"learning_rate": 5.3176791257899405e-05,
"loss": 2.2491,
"step": 143500
},
{
"epoch": 0.53,
"learning_rate": 5.285392385629653e-05,
"loss": 2.2542,
"step": 144000
},
{
"epoch": 0.54,
"learning_rate": 5.253093701926446e-05,
"loss": 2.2498,
"step": 144500
},
{
"epoch": 0.54,
"learning_rate": 5.2207844263657e-05,
"loss": 2.2456,
"step": 145000
},
{
"epoch": 0.54,
"learning_rate": 5.188465911076059e-05,
"loss": 2.235,
"step": 145500
},
{
"epoch": 0.54,
"learning_rate": 5.156139508572844e-05,
"loss": 2.2463,
"step": 146000
},
{
"epoch": 0.54,
"learning_rate": 5.1238065717014526e-05,
"loss": 2.232,
"step": 146500
},
{
"epoch": 0.54,
"learning_rate": 5.091468453580748e-05,
"loss": 2.227,
"step": 147000
},
{
"epoch": 0.55,
"learning_rate": 5.0591265075464167e-05,
"loss": 2.2354,
"step": 147500
},
{
"epoch": 0.55,
"learning_rate": 5.026782087094353e-05,
"loss": 2.2266,
"step": 148000
},
{
"epoch": 0.55,
"learning_rate": 4.9944365458239946e-05,
"loss": 2.2319,
"step": 148500
},
{
"epoch": 0.55,
"learning_rate": 4.9620912373816894e-05,
"loss": 2.2383,
"step": 149000
},
{
"epoch": 0.55,
"learning_rate": 4.929747515404043e-05,
"loss": 2.2315,
"step": 149500
},
{
"epoch": 0.56,
"learning_rate": 4.897406733461264e-05,
"loss": 2.2286,
"step": 150000
},
{
"epoch": 0.56,
"eval_loss": 2.0796430110931396,
"eval_runtime": 286.5966,
"eval_samples_per_second": 348.923,
"eval_steps_per_second": 43.615,
"step": 150000
},
{
"epoch": 0.56,
"learning_rate": 4.8650702450005264e-05,
"loss": 2.2269,
"step": 150500
},
{
"epoch": 0.56,
"learning_rate": 4.832739403289318e-05,
"loss": 2.2294,
"step": 151000
},
{
"epoch": 0.56,
"learning_rate": 4.8004155613588214e-05,
"loss": 2.216,
"step": 151500
},
{
"epoch": 0.56,
"learning_rate": 4.7681000719472726e-05,
"loss": 2.2128,
"step": 152000
},
{
"epoch": 0.57,
"learning_rate": 4.7357942874433634e-05,
"loss": 2.2088,
"step": 152500
},
{
"epoch": 0.57,
"learning_rate": 4.703499559829639e-05,
"loss": 2.2112,
"step": 153000
},
{
"epoch": 0.57,
"learning_rate": 4.671217240625916e-05,
"loss": 2.2168,
"step": 153500
},
{
"epoch": 0.57,
"learning_rate": 4.6389486808327304e-05,
"loss": 2.2034,
"step": 154000
},
{
"epoch": 0.57,
"learning_rate": 4.606695230874788e-05,
"loss": 2.2045,
"step": 154500
},
{
"epoch": 0.57,
"learning_rate": 4.5744582405444544e-05,
"loss": 2.2043,
"step": 155000
},
{
"epoch": 0.58,
"learning_rate": 4.542239058945272e-05,
"loss": 2.2116,
"step": 155500
},
{
"epoch": 0.58,
"learning_rate": 4.51003903443549e-05,
"loss": 2.2046,
"step": 156000
},
{
"epoch": 0.58,
"learning_rate": 4.4778595145716465e-05,
"loss": 2.1967,
"step": 156500
},
{
"epoch": 0.58,
"learning_rate": 4.4457018460521684e-05,
"loss": 2.2046,
"step": 157000
},
{
"epoch": 0.58,
"learning_rate": 4.4135673746610115e-05,
"loss": 2.1952,
"step": 157500
},
{
"epoch": 0.59,
"learning_rate": 4.381457445211346e-05,
"loss": 2.2071,
"step": 158000
},
{
"epoch": 0.59,
"learning_rate": 4.349373401489269e-05,
"loss": 2.1993,
"step": 158500
},
{
"epoch": 0.59,
"learning_rate": 4.317316586197571e-05,
"loss": 2.1998,
"step": 159000
},
{
"epoch": 0.59,
"learning_rate": 4.2852883408995515e-05,
"loss": 2.1938,
"step": 159500
},
{
"epoch": 0.59,
"learning_rate": 4.253290005962863e-05,
"loss": 2.1901,
"step": 160000
},
{
"epoch": 0.59,
"learning_rate": 4.221322920503423e-05,
"loss": 2.1933,
"step": 160500
},
{
"epoch": 0.6,
"learning_rate": 4.1893884223293746e-05,
"loss": 2.1884,
"step": 161000
},
{
"epoch": 0.6,
"learning_rate": 4.157487847885094e-05,
"loss": 2.1855,
"step": 161500
},
{
"epoch": 0.6,
"learning_rate": 4.1256225321952705e-05,
"loss": 2.1968,
"step": 162000
},
{
"epoch": 0.6,
"learning_rate": 4.093793808809028e-05,
"loss": 2.186,
"step": 162500
},
{
"epoch": 0.6,
"learning_rate": 4.062003009744115e-05,
"loss": 2.1905,
"step": 163000
},
{
"epoch": 0.61,
"learning_rate": 4.0302514654311675e-05,
"loss": 2.1828,
"step": 163500
},
{
"epoch": 0.61,
"learning_rate": 3.998540504658027e-05,
"loss": 2.1878,
"step": 164000
},
{
"epoch": 0.61,
"learning_rate": 3.966871454514137e-05,
"loss": 2.1918,
"step": 164500
},
{
"epoch": 0.61,
"learning_rate": 3.935245640334991e-05,
"loss": 2.182,
"step": 165000
},
{
"epoch": 0.61,
"learning_rate": 3.903664385646685e-05,
"loss": 2.1872,
"step": 165500
},
{
"epoch": 0.62,
"learning_rate": 3.872129012110515e-05,
"loss": 2.18,
"step": 166000
},
{
"epoch": 0.62,
"learning_rate": 3.8406408394676724e-05,
"loss": 2.1794,
"step": 166500
},
{
"epoch": 0.62,
"learning_rate": 3.8092011854840135e-05,
"loss": 2.1778,
"step": 167000
},
{
"epoch": 0.62,
"learning_rate": 3.7778113658949145e-05,
"loss": 2.1764,
"step": 167500
},
{
"epoch": 0.62,
"learning_rate": 3.7464726943501955e-05,
"loss": 2.1727,
"step": 168000
},
{
"epoch": 0.62,
"learning_rate": 3.715186482359162e-05,
"loss": 2.1718,
"step": 168500
},
{
"epoch": 0.63,
"learning_rate": 3.683954039235707e-05,
"loss": 2.1766,
"step": 169000
},
{
"epoch": 0.63,
"learning_rate": 3.6527766720435186e-05,
"loss": 2.1838,
"step": 169500
},
{
"epoch": 0.63,
"learning_rate": 3.6216556855413906e-05,
"loss": 2.1786,
"step": 170000
},
{
"epoch": 0.63,
"learning_rate": 3.5905923821286006e-05,
"loss": 2.1748,
"step": 170500
},
{
"epoch": 0.63,
"learning_rate": 3.559588061790419e-05,
"loss": 2.1708,
"step": 171000
},
{
"epoch": 0.64,
"learning_rate": 3.528644022043701e-05,
"loss": 2.1749,
"step": 171500
},
{
"epoch": 0.64,
"learning_rate": 3.497761557882584e-05,
"loss": 2.1668,
"step": 172000
},
{
"epoch": 0.64,
"learning_rate": 3.466941961724301e-05,
"loss": 2.1703,
"step": 172500
},
{
"epoch": 0.64,
"learning_rate": 3.4361865233550814e-05,
"loss": 2.1682,
"step": 173000
},
{
"epoch": 0.64,
"learning_rate": 3.40549652987618e-05,
"loss": 2.1705,
"step": 173500
},
{
"epoch": 0.64,
"learning_rate": 3.374873265650016e-05,
"loss": 2.1671,
"step": 174000
},
{
"epoch": 0.65,
"learning_rate": 3.3443180122464156e-05,
"loss": 2.16,
"step": 174500
},
{
"epoch": 0.65,
"learning_rate": 3.3138320483889874e-05,
"loss": 2.1536,
"step": 175000
},
{
"epoch": 0.65,
"eval_loss": 2.0123212337493896,
"eval_runtime": 294.337,
"eval_samples_per_second": 339.747,
"eval_steps_per_second": 42.468,
"step": 175000
},
{
"epoch": 0.65,
"learning_rate": 3.283416649901599e-05,
"loss": 2.152,
"step": 175500
},
{
"epoch": 0.65,
"learning_rate": 3.253073089654992e-05,
"loss": 2.1519,
"step": 176000
},
{
"epoch": 0.65,
"learning_rate": 3.222802637513508e-05,
"loss": 2.1638,
"step": 176500
},
{
"epoch": 0.66,
"learning_rate": 3.192606560281948e-05,
"loss": 2.1527,
"step": 177000
},
{
"epoch": 0.66,
"learning_rate": 3.162486121652556e-05,
"loss": 2.1499,
"step": 177500
},
{
"epoch": 0.66,
"learning_rate": 3.1324425821521375e-05,
"loss": 2.1614,
"step": 178000
},
{
"epoch": 0.66,
"learning_rate": 3.1024771990893e-05,
"loss": 2.1556,
"step": 178500
},
{
"epoch": 0.66,
"learning_rate": 3.072591226501842e-05,
"loss": 2.1514,
"step": 179000
},
{
"epoch": 0.67,
"learning_rate": 3.042785915104267e-05,
"loss": 2.1533,
"step": 179500
},
{
"epoch": 0.67,
"learning_rate": 3.013062512235445e-05,
"loss": 2.1413,
"step": 180000
},
{
"epoch": 0.67,
"learning_rate": 2.9834222618064146e-05,
"loss": 2.1461,
"step": 180500
},
{
"epoch": 0.67,
"learning_rate": 2.9538664042483145e-05,
"loss": 2.1475,
"step": 181000
},
{
"epoch": 0.67,
"learning_rate": 2.9243961764604878e-05,
"loss": 2.1452,
"step": 181500
},
{
"epoch": 0.67,
"learning_rate": 2.895012811758705e-05,
"loss": 2.1488,
"step": 182000
},
{
"epoch": 0.68,
"learning_rate": 2.8657175398235548e-05,
"loss": 2.1496,
"step": 182500
},
{
"epoch": 0.68,
"learning_rate": 2.8365115866489895e-05,
"loss": 2.1348,
"step": 183000
},
{
"epoch": 0.68,
"learning_rate": 2.8073961744910036e-05,
"loss": 2.1406,
"step": 183500
},
{
"epoch": 0.68,
"learning_rate": 2.7783725218164992e-05,
"loss": 2.1484,
"step": 184000
},
{
"epoch": 0.68,
"learning_rate": 2.7494418432522773e-05,
"loss": 2.1482,
"step": 184500
},
{
"epoch": 0.69,
"learning_rate": 2.7206053495342176e-05,
"loss": 2.1491,
"step": 185000
},
{
"epoch": 0.69,
"learning_rate": 2.691864247456609e-05,
"loss": 2.1316,
"step": 185500
},
{
"epoch": 0.69,
"learning_rate": 2.6632197398216403e-05,
"loss": 2.1459,
"step": 186000
},
{
"epoch": 0.69,
"learning_rate": 2.6346730253890626e-05,
"loss": 2.1308,
"step": 186500
},
{
"epoch": 0.69,
"learning_rate": 2.6062252988260348e-05,
"loss": 2.1389,
"step": 187000
},
{
"epoch": 0.69,
"learning_rate": 2.5778777506571112e-05,
"loss": 2.1374,
"step": 187500
},
{
"epoch": 0.7,
"learning_rate": 2.5496315672144238e-05,
"loss": 2.1322,
"step": 188000
},
{
"epoch": 0.7,
"learning_rate": 2.521487930588044e-05,
"loss": 2.1235,
"step": 188500
},
{
"epoch": 0.7,
"learning_rate": 2.4934480185764976e-05,
"loss": 2.1291,
"step": 189000
},
{
"epoch": 0.7,
"learning_rate": 2.465513004637487e-05,
"loss": 2.1366,
"step": 189500
},
{
"epoch": 0.7,
"learning_rate": 2.4376840578387754e-05,
"loss": 2.1256,
"step": 190000
},
{
"epoch": 0.71,
"learning_rate": 2.409962342809261e-05,
"loss": 2.1304,
"step": 190500
},
{
"epoch": 0.71,
"learning_rate": 2.382349019690248e-05,
"loss": 2.1229,
"step": 191000
},
{
"epoch": 0.71,
"learning_rate": 2.3548452440868816e-05,
"loss": 2.1268,
"step": 191500
},
{
"epoch": 0.71,
"learning_rate": 2.3274521670197923e-05,
"loss": 2.1278,
"step": 192000
},
{
"epoch": 0.71,
"learning_rate": 2.300170934876934e-05,
"loss": 2.1277,
"step": 192500
},
{
"epoch": 0.72,
"learning_rate": 2.2730026893655916e-05,
"loss": 2.1195,
"step": 193000
},
{
"epoch": 0.72,
"learning_rate": 2.2459485674646187e-05,
"loss": 2.1253,
"step": 193500
},
{
"epoch": 0.72,
"learning_rate": 2.2190097013768403e-05,
"loss": 2.1252,
"step": 194000
},
{
"epoch": 0.72,
"learning_rate": 2.1921872184816817e-05,
"loss": 2.1168,
"step": 194500
},
{
"epoch": 0.72,
"learning_rate": 2.1654822412879798e-05,
"loss": 2.1288,
"step": 195000
},
{
"epoch": 0.72,
"learning_rate": 2.138895887387018e-05,
"loss": 2.1195,
"step": 195500
},
{
"epoch": 0.73,
"learning_rate": 2.112429269405739e-05,
"loss": 2.1196,
"step": 196000
},
{
"epoch": 0.73,
"learning_rate": 2.0860834949602015e-05,
"loss": 2.1175,
"step": 196500
},
{
"epoch": 0.73,
"learning_rate": 2.0598596666092075e-05,
"loss": 2.1234,
"step": 197000
},
{
"epoch": 0.73,
"learning_rate": 2.0337588818081744e-05,
"loss": 2.1122,
"step": 197500
},
{
"epoch": 0.73,
"learning_rate": 2.007782232863199e-05,
"loss": 2.1185,
"step": 198000
},
{
"epoch": 0.74,
"learning_rate": 1.9819308068853526e-05,
"loss": 2.1201,
"step": 198500
},
{
"epoch": 0.74,
"learning_rate": 1.956205685745183e-05,
"loss": 2.1079,
"step": 199000
},
{
"epoch": 0.74,
"learning_rate": 1.9306079460274302e-05,
"loss": 2.1137,
"step": 199500
},
{
"epoch": 0.74,
"learning_rate": 1.9051386589859843e-05,
"loss": 2.114,
"step": 200000
},
{
"epoch": 0.74,
"eval_loss": 1.9818874597549438,
"eval_runtime": 287.1851,
"eval_samples_per_second": 348.208,
"eval_steps_per_second": 43.526,
"step": 200000
},
{
"epoch": 0.74,
"learning_rate": 1.879798890499046e-05,
"loss": 2.1094,
"step": 200500
},
{
"epoch": 0.75,
"learning_rate": 1.8545897010245273e-05,
"loss": 2.1185,
"step": 201000
},
{
"epoch": 0.75,
"learning_rate": 1.8295121455556607e-05,
"loss": 2.1187,
"step": 201500
},
{
"epoch": 0.75,
"learning_rate": 1.8045672735768616e-05,
"loss": 2.1096,
"step": 202000
},
{
"epoch": 0.75,
"learning_rate": 1.7797561290197957e-05,
"loss": 2.1058,
"step": 202500
},
{
"epoch": 0.75,
"learning_rate": 1.755079750219699e-05,
"loss": 2.1065,
"step": 203000
},
{
"epoch": 0.75,
"learning_rate": 1.7305391698719187e-05,
"loss": 2.104,
"step": 203500
},
{
"epoch": 0.76,
"learning_rate": 1.706135414988701e-05,
"loss": 2.1047,
"step": 204000
},
{
"epoch": 0.76,
"learning_rate": 1.6818695068562084e-05,
"loss": 2.1033,
"step": 204500
},
{
"epoch": 0.76,
"learning_rate": 1.6577424609917756e-05,
"loss": 2.1106,
"step": 205000
},
{
"epoch": 0.76,
"learning_rate": 1.633755287101416e-05,
"loss": 2.1068,
"step": 205500
},
{
"epoch": 0.76,
"learning_rate": 1.6099089890375623e-05,
"loss": 2.1013,
"step": 206000
},
{
"epoch": 0.77,
"learning_rate": 1.5862045647570574e-05,
"loss": 2.1019,
"step": 206500
},
{
"epoch": 0.77,
"learning_rate": 1.562643006279392e-05,
"loss": 2.0999,
"step": 207000
},
{
"epoch": 0.77,
"learning_rate": 1.5392252996451884e-05,
"loss": 2.1059,
"step": 207500
},
{
"epoch": 0.77,
"learning_rate": 1.5159524248749296e-05,
"loss": 2.1054,
"step": 208000
},
{
"epoch": 0.77,
"learning_rate": 1.4928253559279532e-05,
"loss": 2.1043,
"step": 208500
},
{
"epoch": 0.77,
"learning_rate": 1.469845060661686e-05,
"loss": 2.105,
"step": 209000
},
{
"epoch": 0.78,
"learning_rate": 1.4470125007911478e-05,
"loss": 2.1091,
"step": 209500
},
{
"epoch": 0.78,
"learning_rate": 1.4243286318486915e-05,
"loss": 2.101,
"step": 210000
},
{
"epoch": 0.78,
"learning_rate": 1.4017944031440283e-05,
"loss": 2.1054,
"step": 210500
},
{
"epoch": 0.78,
"learning_rate": 1.3794107577244886e-05,
"loss": 2.0959,
"step": 211000
},
{
"epoch": 0.78,
"learning_rate": 1.3571786323355596e-05,
"loss": 2.0913,
"step": 211500
},
{
"epoch": 0.79,
"learning_rate": 1.335098957381687e-05,
"loss": 2.0924,
"step": 212000
},
{
"epoch": 0.79,
"learning_rate": 1.3131726568873315e-05,
"loss": 2.0939,
"step": 212500
},
{
"epoch": 0.79,
"learning_rate": 1.2914006484583013e-05,
"loss": 2.0917,
"step": 213000
},
{
"epoch": 0.79,
"learning_rate": 1.2697838432433545e-05,
"loss": 2.0899,
"step": 213500
},
{
"epoch": 0.79,
"learning_rate": 1.2483231458960599e-05,
"loss": 2.0961,
"step": 214000
},
{
"epoch": 0.8,
"learning_rate": 1.2270194545369473e-05,
"loss": 2.0955,
"step": 214500
},
{
"epoch": 0.8,
"learning_rate": 1.2058736607159133e-05,
"loss": 2.0848,
"step": 215000
},
{
"epoch": 0.8,
"learning_rate": 1.1848866493749111e-05,
"loss": 2.0841,
"step": 215500
},
{
"epoch": 0.8,
"learning_rate": 1.1640592988109261e-05,
"loss": 2.088,
"step": 216000
},
{
"epoch": 0.8,
"learning_rate": 1.1433924806392054e-05,
"loss": 2.092,
"step": 216500
},
{
"epoch": 0.8,
"learning_rate": 1.1228870597567887e-05,
"loss": 2.0807,
"step": 217000
},
{
"epoch": 0.81,
"learning_rate": 1.102543894306316e-05,
"loss": 2.0881,
"step": 217500
},
{
"epoch": 0.81,
"learning_rate": 1.0823638356401056e-05,
"loss": 2.084,
"step": 218000
},
{
"epoch": 0.81,
"learning_rate": 1.0623477282845312e-05,
"loss": 2.0816,
"step": 218500
},
{
"epoch": 0.81,
"learning_rate": 1.0424964099046813e-05,
"loss": 2.0868,
"step": 219000
},
{
"epoch": 0.81,
"learning_rate": 1.0228107112692953e-05,
"loss": 2.0883,
"step": 219500
},
{
"epoch": 0.82,
"learning_rate": 1.0032914562160051e-05,
"loss": 2.0836,
"step": 220000
},
{
"epoch": 0.82,
"learning_rate": 9.839394616168506e-06,
"loss": 2.0877,
"step": 220500
},
{
"epoch": 0.82,
"learning_rate": 9.647555373440976e-06,
"loss": 2.082,
"step": 221000
},
{
"epoch": 0.82,
"learning_rate": 9.457404862363428e-06,
"loss": 2.0798,
"step": 221500
},
{
"epoch": 0.82,
"learning_rate": 9.26895104064921e-06,
"loss": 2.0855,
"step": 222000
},
{
"epoch": 0.82,
"learning_rate": 9.082201795005968e-06,
"loss": 2.0892,
"step": 222500
},
{
"epoch": 0.83,
"learning_rate": 8.897164940805591e-06,
"loss": 2.0816,
"step": 223000
},
{
"epoch": 0.83,
"learning_rate": 8.71384822175716e-06,
"loss": 2.0886,
"step": 223500
},
{
"epoch": 0.83,
"learning_rate": 8.532259309582886e-06,
"loss": 2.0848,
"step": 224000
},
{
"epoch": 0.83,
"learning_rate": 8.35240580369701e-06,
"loss": 2.0806,
"step": 224500
},
{
"epoch": 0.83,
"learning_rate": 8.174295230887846e-06,
"loss": 2.0845,
"step": 225000
},
{
"epoch": 0.83,
"eval_loss": 1.9471186399459839,
"eval_runtime": 284.8288,
"eval_samples_per_second": 351.088,
"eval_steps_per_second": 43.886,
"step": 225000
},
{
"epoch": 0.84,
"learning_rate": 7.997935045002724e-06,
"loss": 2.0879,
"step": 225500
},
{
"epoch": 0.84,
"learning_rate": 7.823332626636065e-06,
"loss": 2.0804,
"step": 226000
},
{
"epoch": 0.84,
"learning_rate": 7.650495282820502e-06,
"loss": 2.0835,
"step": 226500
},
{
"epoch": 0.84,
"learning_rate": 7.479430246721092e-06,
"loss": 2.0834,
"step": 227000
},
{
"epoch": 0.84,
"learning_rate": 7.310144677332631e-06,
"loss": 2.0755,
"step": 227500
},
{
"epoch": 0.85,
"learning_rate": 7.142645659180036e-06,
"loss": 2.0744,
"step": 228000
},
{
"epoch": 0.85,
"learning_rate": 6.9769402020218314e-06,
"loss": 2.073,
"step": 228500
},
{
"epoch": 0.85,
"learning_rate": 6.813035240556842e-06,
"loss": 2.075,
"step": 229000
},
{
"epoch": 0.85,
"learning_rate": 6.650937634133952e-06,
"loss": 2.0767,
"step": 229500
},
{
"epoch": 0.85,
"learning_rate": 6.4906541664650325e-06,
"loss": 2.0683,
"step": 230000
},
{
"epoch": 0.85,
"learning_rate": 6.332191545341093e-06,
"loss": 2.0783,
"step": 230500
},
{
"epoch": 0.86,
"learning_rate": 6.175556402351546e-06,
"loss": 2.0665,
"step": 231000
},
{
"epoch": 0.86,
"learning_rate": 6.020755292606617e-06,
"loss": 2.0818,
"step": 231500
},
{
"epoch": 0.86,
"learning_rate": 5.867794694463102e-06,
"loss": 2.0693,
"step": 232000
},
{
"epoch": 0.86,
"learning_rate": 5.716681009253189e-06,
"loss": 2.0705,
"step": 232500
},
{
"epoch": 0.86,
"learning_rate": 5.567420561016629e-06,
"loss": 2.0818,
"step": 233000
},
{
"epoch": 0.87,
"learning_rate": 5.420019596236003e-06,
"loss": 2.0723,
"step": 233500
},
{
"epoch": 0.87,
"learning_rate": 5.274484283575371e-06,
"loss": 2.0833,
"step": 234000
},
{
"epoch": 0.87,
"learning_rate": 5.1308207136220755e-06,
"loss": 2.0764,
"step": 234500
},
{
"epoch": 0.87,
"learning_rate": 4.989034898631872e-06,
"loss": 2.0724,
"step": 235000
},
{
"epoch": 0.87,
"learning_rate": 4.84913277227731e-06,
"loss": 2.0718,
"step": 235500
},
{
"epoch": 0.87,
"learning_rate": 4.711120189399443e-06,
"loss": 2.0752,
"step": 236000
},
{
"epoch": 0.88,
"learning_rate": 4.575002925762739e-06,
"loss": 2.0718,
"step": 236500
},
{
"epoch": 0.88,
"learning_rate": 4.440786677813458e-06,
"loss": 2.0747,
"step": 237000
},
{
"epoch": 0.88,
"learning_rate": 4.308477062441168e-06,
"loss": 2.0714,
"step": 237500
},
{
"epoch": 0.88,
"learning_rate": 4.17807961674373e-06,
"loss": 2.0652,
"step": 238000
},
{
"epoch": 0.88,
"learning_rate": 4.049599797795589e-06,
"loss": 2.0726,
"step": 238500
},
{
"epoch": 0.89,
"learning_rate": 3.923042982419334e-06,
"loss": 2.0692,
"step": 239000
},
{
"epoch": 0.89,
"learning_rate": 3.798414466960759e-06,
"loss": 2.076,
"step": 239500
},
{
"epoch": 0.89,
"learning_rate": 3.6757194670671513e-06,
"loss": 2.0695,
"step": 240000
},
{
"epoch": 0.89,
"learning_rate": 3.55496311746904e-06,
"loss": 2.066,
"step": 240500
},
{
"epoch": 0.89,
"learning_rate": 3.436150471765326e-06,
"loss": 2.0671,
"step": 241000
},
{
"epoch": 0.9,
"learning_rate": 3.319286502211766e-06,
"loss": 2.0682,
"step": 241500
},
{
"epoch": 0.9,
"learning_rate": 3.2043760995128903e-06,
"loss": 2.0716,
"step": 242000
},
{
"epoch": 0.9,
"learning_rate": 3.091424072617366e-06,
"loss": 2.0684,
"step": 242500
},
{
"epoch": 0.9,
"learning_rate": 2.9804351485166747e-06,
"loss": 2.0631,
"step": 243000
},
{
"epoch": 0.9,
"learning_rate": 2.8714139720473597e-06,
"loss": 2.0686,
"step": 243500
},
{
"epoch": 0.9,
"learning_rate": 2.7643651056965924e-06,
"loss": 2.0651,
"step": 244000
},
{
"epoch": 0.91,
"learning_rate": 2.659293029411264e-06,
"loss": 2.0695,
"step": 244500
},
{
"epoch": 0.91,
"learning_rate": 2.556202140410474e-06,
"loss": 2.0704,
"step": 245000
},
{
"epoch": 0.91,
"learning_rate": 2.4550967530015623e-06,
"loss": 2.0668,
"step": 245500
},
{
"epoch": 0.91,
"learning_rate": 2.3559810983994732e-06,
"loss": 2.0656,
"step": 246000
},
{
"epoch": 0.91,
"learning_rate": 2.258859324549778e-06,
"loss": 2.0691,
"step": 246500
},
{
"epoch": 0.92,
"learning_rate": 2.1637354959549884e-06,
"loss": 2.0589,
"step": 247000
},
{
"epoch": 0.92,
"learning_rate": 2.0706135935045333e-06,
"loss": 2.067,
"step": 247500
},
{
"epoch": 0.92,
"learning_rate": 1.9794975143081264e-06,
"loss": 2.0654,
"step": 248000
},
{
"epoch": 0.92,
"learning_rate": 1.8903910715326823e-06,
"loss": 2.0635,
"step": 248500
},
{
"epoch": 0.92,
"learning_rate": 1.8032979942427475e-06,
"loss": 2.0673,
"step": 249000
},
{
"epoch": 0.92,
"learning_rate": 1.7182219272444011e-06,
"loss": 2.0662,
"step": 249500
},
{
"epoch": 0.93,
"learning_rate": 1.635166430932772e-06,
"loss": 2.0697,
"step": 250000
},
{
"epoch": 0.93,
"eval_loss": 1.9344754219055176,
"eval_runtime": 284.7729,
"eval_samples_per_second": 351.157,
"eval_steps_per_second": 43.895,
"step": 250000
},
{
"epoch": 0.93,
"learning_rate": 1.5541349811430016e-06,
"loss": 2.061,
"step": 250500
},
{
"epoch": 0.93,
"learning_rate": 1.475130969004812e-06,
"loss": 2.0696,
"step": 251000
},
{
"epoch": 0.93,
"learning_rate": 1.3981577008005563e-06,
"loss": 2.0691,
"step": 251500
},
{
"epoch": 0.93,
"learning_rate": 1.3232183978268698e-06,
"loss": 2.0622,
"step": 252000
},
{
"epoch": 0.94,
"learning_rate": 1.2503161962598653e-06,
"loss": 2.0714,
"step": 252500
},
{
"epoch": 0.94,
"learning_rate": 1.1794541470238729e-06,
"loss": 2.0664,
"step": 253000
},
{
"epoch": 0.94,
"learning_rate": 1.1106352156637633e-06,
"loss": 2.0606,
"step": 253500
},
{
"epoch": 0.94,
"learning_rate": 1.0438622822208478e-06,
"loss": 2.0645,
"step": 254000
},
{
"epoch": 0.94,
"learning_rate": 9.791381411123513e-07,
"loss": 2.0724,
"step": 254500
},
{
"epoch": 0.95,
"learning_rate": 9.164655010144518e-07,
"loss": 2.0629,
"step": 255000
},
{
"epoch": 0.95,
"learning_rate": 8.558469847489314e-07,
"loss": 2.0688,
"step": 255500
},
{
"epoch": 0.95,
"learning_rate": 7.972851291734252e-07,
"loss": 2.0566,
"step": 256000
},
{
"epoch": 0.95,
"learning_rate": 7.407823850752338e-07,
"loss": 2.0689,
"step": 256500
},
{
"epoch": 0.95,
"learning_rate": 6.863411170687673e-07,
"loss": 2.071,
"step": 257000
},
{
"epoch": 0.95,
"learning_rate": 6.339636034966123e-07,
"loss": 2.0665,
"step": 257500
},
{
"epoch": 0.96,
"learning_rate": 5.836520363341258e-07,
"loss": 2.0606,
"step": 258000
},
{
"epoch": 0.96,
"learning_rate": 5.354085210977633e-07,
"loss": 2.0646,
"step": 258500
},
{
"epoch": 0.96,
"learning_rate": 4.892350767569276e-07,
"loss": 2.0663,
"step": 259000
},
{
"epoch": 0.96,
"learning_rate": 4.451336356494862e-07,
"loss": 2.0683,
"step": 259500
},
{
"epoch": 0.96,
"learning_rate": 4.031060434009026e-07,
"loss": 2.0595,
"step": 260000
},
{
"epoch": 0.97,
"learning_rate": 3.631540588470039e-07,
"loss": 2.0691,
"step": 260500
},
{
"epoch": 0.97,
"learning_rate": 3.252793539603671e-07,
"loss": 2.0651,
"step": 261000
},
{
"epoch": 0.97,
"learning_rate": 2.8948351378034753e-07,
"loss": 2.0611,
"step": 261500
},
{
"epoch": 0.97,
"learning_rate": 2.557680363467485e-07,
"loss": 2.0733,
"step": 262000
},
{
"epoch": 0.97,
"learning_rate": 2.2413433263713257e-07,
"loss": 2.0591,
"step": 262500
},
{
"epoch": 0.97,
"learning_rate": 1.9458372650776325e-07,
"loss": 2.0626,
"step": 263000
},
{
"epoch": 0.98,
"learning_rate": 1.6711745463821593e-07,
"loss": 2.0669,
"step": 263500
},
{
"epoch": 0.98,
"learning_rate": 1.4173666647959715e-07,
"loss": 2.0701,
"step": 264000
},
{
"epoch": 0.98,
"learning_rate": 1.1844242420647745e-07,
"loss": 2.0679,
"step": 264500
},
{
"epoch": 0.98,
"learning_rate": 9.723570267241577e-08,
"loss": 2.0679,
"step": 265000
},
{
"epoch": 0.98,
"learning_rate": 7.811738936916447e-08,
"loss": 2.0643,
"step": 265500
},
{
"epoch": 0.99,
"learning_rate": 6.108828438952663e-08,
"loss": 2.0615,
"step": 266000
},
{
"epoch": 0.99,
"learning_rate": 4.614910039389409e-08,
"loss": 2.0511,
"step": 266500
},
{
"epoch": 0.99,
"learning_rate": 3.3300462580387884e-08,
"loss": 2.0594,
"step": 267000
},
{
"epoch": 0.99,
"learning_rate": 2.254290865871811e-08,
"loss": 2.0665,
"step": 267500
},
{
"epoch": 0.99,
"learning_rate": 1.3876888827679679e-08,
"loss": 2.0572,
"step": 268000
},
{
"epoch": 1.0,
"learning_rate": 7.302765756300733e-09,
"loss": 2.0682,
"step": 268500
},
{
"epoch": 1.0,
"learning_rate": 2.820814568671448e-09,
"loss": 2.0611,
"step": 269000
},
{
"epoch": 1.0,
"learning_rate": 4.31222832436573e-10,
"loss": 2.0658,
"step": 269500
},
{
"epoch": 1.0,
"step": 269794,
"total_flos": 7.264837577610363e+18,
"train_loss": 1.8196985500431868,
"train_runtime": 434920.5349,
"train_samples_per_second": 148.879,
"train_steps_per_second": 0.62
}
],
"max_steps": 269794,
"num_train_epochs": 1,
"total_flos": 7.264837577610363e+18,
"trial_name": null,
"trial_params": null
}