esm3_ddg_v2 / trainer_state.json
hazemessam's picture
Upload trainer_state.json with huggingface_hub
2729feb verified
{
"best_metric": 0.8526459553649132,
"best_model_checkpoint": "stability_weights_dora_norm_swap_v2/checkpoint-1820",
"epoch": 10.996978851963746,
"eval_steps": 500,
"global_step": 1820,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.06042296072507553,
"grad_norm": 42.27948760986328,
"learning_rate": 2.5e-06,
"loss": 3.9615,
"step": 10
},
{
"epoch": 0.12084592145015106,
"grad_norm": 45.654972076416016,
"learning_rate": 5e-06,
"loss": 2.8167,
"step": 20
},
{
"epoch": 0.18126888217522658,
"grad_norm": 33.64224624633789,
"learning_rate": 7.5e-06,
"loss": 3.9832,
"step": 30
},
{
"epoch": 0.24169184290030213,
"grad_norm": 38.766605377197266,
"learning_rate": 1e-05,
"loss": 3.483,
"step": 40
},
{
"epoch": 0.3021148036253776,
"grad_norm": 36.45051574707031,
"learning_rate": 1.25e-05,
"loss": 2.6488,
"step": 50
},
{
"epoch": 0.36253776435045315,
"grad_norm": 31.120370864868164,
"learning_rate": 1.5e-05,
"loss": 2.7824,
"step": 60
},
{
"epoch": 0.4229607250755287,
"grad_norm": 40.57133865356445,
"learning_rate": 1.75e-05,
"loss": 3.4959,
"step": 70
},
{
"epoch": 0.48338368580060426,
"grad_norm": 39.07503890991211,
"learning_rate": 2e-05,
"loss": 2.7043,
"step": 80
},
{
"epoch": 0.5438066465256798,
"grad_norm": 27.892555236816406,
"learning_rate": 2.25e-05,
"loss": 2.3916,
"step": 90
},
{
"epoch": 0.6042296072507553,
"grad_norm": 35.324249267578125,
"learning_rate": 2.5e-05,
"loss": 3.5084,
"step": 100
},
{
"epoch": 0.6646525679758308,
"grad_norm": 34.17033386230469,
"learning_rate": 2.7500000000000004e-05,
"loss": 2.15,
"step": 110
},
{
"epoch": 0.7250755287009063,
"grad_norm": 28.871646881103516,
"learning_rate": 3e-05,
"loss": 2.4973,
"step": 120
},
{
"epoch": 0.7854984894259819,
"grad_norm": 34.328651428222656,
"learning_rate": 3.2500000000000004e-05,
"loss": 2.2425,
"step": 130
},
{
"epoch": 0.8459214501510574,
"grad_norm": 27.76066017150879,
"learning_rate": 3.5e-05,
"loss": 2.4867,
"step": 140
},
{
"epoch": 0.9063444108761329,
"grad_norm": 46.40857696533203,
"learning_rate": 3.7500000000000003e-05,
"loss": 2.3429,
"step": 150
},
{
"epoch": 0.9667673716012085,
"grad_norm": 24.273012161254883,
"learning_rate": 4e-05,
"loss": 1.8543,
"step": 160
},
{
"epoch": 0.9969788519637462,
"eval_validation_loss": 2.0505075454711914,
"eval_validation_mae": 1.01314377784729,
"eval_validation_mse": 2.0505075454711914,
"eval_validation_pearson": 0.46795711140864427,
"eval_validation_rmse": 1.4319593906402588,
"eval_validation_runtime": 129.1022,
"eval_validation_samples_per_second": 2.649,
"eval_validation_spearman": 0.5000603914960909,
"eval_validation_steps_per_second": 2.649,
"step": 165
},
{
"epoch": 0.9969788519637462,
"eval_test_loss": 2.0498456954956055,
"eval_test_mae": 1.0129708051681519,
"eval_test_mse": 2.0498456954956055,
"eval_test_pearson": 0.4678271674806638,
"eval_test_rmse": 1.4317282438278198,
"eval_test_runtime": 128.8868,
"eval_test_samples_per_second": 2.653,
"eval_test_spearman": 0.49953701661422967,
"eval_test_steps_per_second": 2.653,
"step": 165
},
{
"epoch": 0.9969788519637462,
"eval_myoglobin_loss": 1.1084952354431152,
"eval_myoglobin_mae": 0.7779242396354675,
"eval_myoglobin_mse": 1.1084952354431152,
"eval_myoglobin_pearson": 0.3155295627311716,
"eval_myoglobin_rmse": 1.0528509616851807,
"eval_myoglobin_runtime": 50.3681,
"eval_myoglobin_samples_per_second": 2.66,
"eval_myoglobin_spearman": 0.3150316299942073,
"eval_myoglobin_steps_per_second": 2.66,
"step": 165
},
{
"epoch": 0.9969788519637462,
"eval_myoglobin_r_loss": 1.1083894968032837,
"eval_myoglobin_r_mae": 0.778092622756958,
"eval_myoglobin_r_mse": 1.1083894968032837,
"eval_myoglobin_r_pearson": 0.315758311809077,
"eval_myoglobin_r_rmse": 1.0528007745742798,
"eval_myoglobin_r_runtime": 50.3077,
"eval_myoglobin_r_samples_per_second": 2.664,
"eval_myoglobin_r_spearman": 0.3167998663343996,
"eval_myoglobin_r_steps_per_second": 2.664,
"step": 165
},
{
"epoch": 0.9969788519637462,
"eval_p53_loss": 4.773194789886475,
"eval_p53_mae": 1.6836440563201904,
"eval_p53_mse": 4.773194789886475,
"eval_p53_pearson": 0.260329486693081,
"eval_p53_rmse": 2.1847641468048096,
"eval_p53_runtime": 17.5157,
"eval_p53_samples_per_second": 2.398,
"eval_p53_spearman": 0.1950488231413393,
"eval_p53_steps_per_second": 2.398,
"step": 165
},
{
"epoch": 1.027190332326284,
"grad_norm": 25.500028610229492,
"learning_rate": 4.25e-05,
"loss": 2.1163,
"step": 170
},
{
"epoch": 1.0876132930513596,
"grad_norm": 31.47431755065918,
"learning_rate": 4.5e-05,
"loss": 1.7539,
"step": 180
},
{
"epoch": 1.148036253776435,
"grad_norm": 22.619182586669922,
"learning_rate": 4.75e-05,
"loss": 1.4633,
"step": 190
},
{
"epoch": 1.2084592145015105,
"grad_norm": 38.80492401123047,
"learning_rate": 5e-05,
"loss": 1.4391,
"step": 200
},
{
"epoch": 1.2688821752265862,
"grad_norm": 22.946945190429688,
"learning_rate": 5.25e-05,
"loss": 1.3334,
"step": 210
},
{
"epoch": 1.3293051359516617,
"grad_norm": 14.94211483001709,
"learning_rate": 5.500000000000001e-05,
"loss": 1.1311,
"step": 220
},
{
"epoch": 1.3897280966767371,
"grad_norm": 27.56308364868164,
"learning_rate": 5.7499999999999995e-05,
"loss": 1.6216,
"step": 230
},
{
"epoch": 1.4501510574018126,
"grad_norm": 19.250564575195312,
"learning_rate": 6e-05,
"loss": 1.273,
"step": 240
},
{
"epoch": 1.510574018126888,
"grad_norm": 19.437816619873047,
"learning_rate": 6.25e-05,
"loss": 0.9644,
"step": 250
},
{
"epoch": 1.5709969788519638,
"grad_norm": 31.529216766357422,
"learning_rate": 6.500000000000001e-05,
"loss": 1.7949,
"step": 260
},
{
"epoch": 1.6314199395770392,
"grad_norm": 32.55619430541992,
"learning_rate": 6.750000000000001e-05,
"loss": 1.241,
"step": 270
},
{
"epoch": 1.691842900302115,
"grad_norm": 26.349998474121094,
"learning_rate": 7e-05,
"loss": 1.3735,
"step": 280
},
{
"epoch": 1.7522658610271904,
"grad_norm": 29.46245002746582,
"learning_rate": 7.25e-05,
"loss": 1.4623,
"step": 290
},
{
"epoch": 1.8126888217522659,
"grad_norm": 14.214956283569336,
"learning_rate": 7.500000000000001e-05,
"loss": 0.8406,
"step": 300
},
{
"epoch": 1.8731117824773413,
"grad_norm": 16.597463607788086,
"learning_rate": 7.75e-05,
"loss": 0.9432,
"step": 310
},
{
"epoch": 1.9335347432024168,
"grad_norm": 17.1890869140625,
"learning_rate": 8e-05,
"loss": 1.195,
"step": 320
},
{
"epoch": 1.9939577039274925,
"grad_norm": 17.546321868896484,
"learning_rate": 8.25e-05,
"loss": 1.0398,
"step": 330
},
{
"epoch": 2.0,
"eval_validation_loss": 0.9950127005577087,
"eval_validation_mae": 0.6999762654304504,
"eval_validation_mse": 0.9950127005577087,
"eval_validation_pearson": 0.7727618943702055,
"eval_validation_rmse": 0.9975032210350037,
"eval_validation_runtime": 129.1954,
"eval_validation_samples_per_second": 2.647,
"eval_validation_spearman": 0.7928617789227591,
"eval_validation_steps_per_second": 2.647,
"step": 331
},
{
"epoch": 2.0,
"eval_test_loss": 0.9929149150848389,
"eval_test_mae": 0.7004790306091309,
"eval_test_mse": 0.9929149150848389,
"eval_test_pearson": 0.7726932487807971,
"eval_test_rmse": 0.9964511394500732,
"eval_test_runtime": 129.0193,
"eval_test_samples_per_second": 2.651,
"eval_test_spearman": 0.7933636966348652,
"eval_test_steps_per_second": 2.651,
"step": 331
},
{
"epoch": 2.0,
"eval_myoglobin_loss": 0.934596061706543,
"eval_myoglobin_mae": 0.7355605959892273,
"eval_myoglobin_mse": 0.934596061706543,
"eval_myoglobin_pearson": 0.5740624022673728,
"eval_myoglobin_rmse": 0.9667450785636902,
"eval_myoglobin_runtime": 50.363,
"eval_myoglobin_samples_per_second": 2.661,
"eval_myoglobin_spearman": 0.5940538377065167,
"eval_myoglobin_steps_per_second": 2.661,
"step": 331
},
{
"epoch": 2.0,
"eval_myoglobin_r_loss": 0.9417540431022644,
"eval_myoglobin_r_mae": 0.7385311722755432,
"eval_myoglobin_r_mse": 0.9417540431022644,
"eval_myoglobin_r_pearson": 0.5734044991540941,
"eval_myoglobin_r_rmse": 0.970440149307251,
"eval_myoglobin_r_runtime": 50.3941,
"eval_myoglobin_r_samples_per_second": 2.659,
"eval_myoglobin_r_spearman": 0.5919040214508811,
"eval_myoglobin_r_steps_per_second": 2.659,
"step": 331
},
{
"epoch": 2.0,
"eval_p53_loss": 4.290196895599365,
"eval_p53_mae": 1.622589349746704,
"eval_p53_mse": 4.290196895599365,
"eval_p53_pearson": 0.29006131482310593,
"eval_p53_rmse": 2.0712790489196777,
"eval_p53_runtime": 17.523,
"eval_p53_samples_per_second": 2.397,
"eval_p53_spearman": 0.26692597566579634,
"eval_p53_steps_per_second": 2.397,
"step": 331
},
{
"epoch": 2.054380664652568,
"grad_norm": 13.338666915893555,
"learning_rate": 8.5e-05,
"loss": 0.6917,
"step": 340
},
{
"epoch": 2.1148036253776437,
"grad_norm": 21.178325653076172,
"learning_rate": 8.75e-05,
"loss": 0.8003,
"step": 350
},
{
"epoch": 2.175226586102719,
"grad_norm": 14.95538330078125,
"learning_rate": 9e-05,
"loss": 0.6155,
"step": 360
},
{
"epoch": 2.2356495468277946,
"grad_norm": 10.555205345153809,
"learning_rate": 9.250000000000001e-05,
"loss": 0.6111,
"step": 370
},
{
"epoch": 2.29607250755287,
"grad_norm": 11.569594383239746,
"learning_rate": 9.5e-05,
"loss": 0.8681,
"step": 380
},
{
"epoch": 2.3564954682779455,
"grad_norm": 18.517148971557617,
"learning_rate": 9.75e-05,
"loss": 0.6754,
"step": 390
},
{
"epoch": 2.416918429003021,
"grad_norm": 21.002437591552734,
"learning_rate": 0.0001,
"loss": 0.5359,
"step": 400
},
{
"epoch": 2.477341389728097,
"grad_norm": 17.249919891357422,
"learning_rate": 9.999706613915566e-05,
"loss": 0.8332,
"step": 410
},
{
"epoch": 2.5377643504531724,
"grad_norm": 10.25106143951416,
"learning_rate": 9.998826490092421e-05,
"loss": 0.496,
"step": 420
},
{
"epoch": 2.598187311178248,
"grad_norm": 18.843320846557617,
"learning_rate": 9.997359731816998e-05,
"loss": 0.7244,
"step": 430
},
{
"epoch": 2.6586102719033233,
"grad_norm": 11.991676330566406,
"learning_rate": 9.995306511219885e-05,
"loss": 0.5112,
"step": 440
},
{
"epoch": 2.719033232628399,
"grad_norm": 21.79170036315918,
"learning_rate": 9.992667069255619e-05,
"loss": 0.5307,
"step": 450
},
{
"epoch": 2.7794561933534743,
"grad_norm": 9.106186866760254,
"learning_rate": 9.989441715674422e-05,
"loss": 0.4371,
"step": 460
},
{
"epoch": 2.8398791540785497,
"grad_norm": 10.968169212341309,
"learning_rate": 9.985630828985835e-05,
"loss": 0.5922,
"step": 470
},
{
"epoch": 2.900302114803625,
"grad_norm": 14.699440002441406,
"learning_rate": 9.981234856414307e-05,
"loss": 0.5858,
"step": 480
},
{
"epoch": 2.9607250755287007,
"grad_norm": 13.304734230041504,
"learning_rate": 9.97625431384671e-05,
"loss": 0.6854,
"step": 490
},
{
"epoch": 2.996978851963746,
"eval_validation_loss": 0.8451957702636719,
"eval_validation_mae": 0.6374915242195129,
"eval_validation_mse": 0.8451957702636719,
"eval_validation_pearson": 0.8118986310850005,
"eval_validation_rmse": 0.9193453192710876,
"eval_validation_runtime": 128.9657,
"eval_validation_samples_per_second": 2.652,
"eval_validation_spearman": 0.8191585157836645,
"eval_validation_steps_per_second": 2.652,
"step": 496
},
{
"epoch": 2.996978851963746,
"eval_test_loss": 0.8352708220481873,
"eval_test_mae": 0.6319109201431274,
"eval_test_mse": 0.8352708220481873,
"eval_test_pearson": 0.8117305964358366,
"eval_test_rmse": 0.9139315485954285,
"eval_test_runtime": 129.0007,
"eval_test_samples_per_second": 2.651,
"eval_test_spearman": 0.8192730040390717,
"eval_test_steps_per_second": 2.651,
"step": 496
},
{
"epoch": 2.996978851963746,
"eval_myoglobin_loss": 0.8053471446037292,
"eval_myoglobin_mae": 0.6675698757171631,
"eval_myoglobin_mse": 0.8053471446037292,
"eval_myoglobin_pearson": 0.6029393659750895,
"eval_myoglobin_rmse": 0.8974113464355469,
"eval_myoglobin_runtime": 50.3201,
"eval_myoglobin_samples_per_second": 2.663,
"eval_myoglobin_spearman": 0.6248470874841663,
"eval_myoglobin_steps_per_second": 2.663,
"step": 496
},
{
"epoch": 2.996978851963746,
"eval_myoglobin_r_loss": 0.8195508122444153,
"eval_myoglobin_r_mae": 0.6755225658416748,
"eval_myoglobin_r_mse": 0.8195508122444153,
"eval_myoglobin_r_pearson": 0.6011248022884956,
"eval_myoglobin_r_rmse": 0.9052904844284058,
"eval_myoglobin_r_runtime": 50.3351,
"eval_myoglobin_r_samples_per_second": 2.662,
"eval_myoglobin_r_spearman": 0.6238021071928538,
"eval_myoglobin_r_steps_per_second": 2.662,
"step": 496
},
{
"epoch": 2.996978851963746,
"eval_p53_loss": 4.1966938972473145,
"eval_p53_mae": 1.6126927137374878,
"eval_p53_mse": 4.1966938972473145,
"eval_p53_pearson": 0.3033285839483142,
"eval_p53_rmse": 2.0485832691192627,
"eval_p53_runtime": 17.5229,
"eval_p53_samples_per_second": 2.397,
"eval_p53_spearman": 0.2764069529435432,
"eval_p53_steps_per_second": 2.397,
"step": 496
},
{
"epoch": 3.0211480362537766,
"grad_norm": 7.5384063720703125,
"learning_rate": 9.970689785771798e-05,
"loss": 0.4402,
"step": 500
},
{
"epoch": 3.081570996978852,
"grad_norm": 13.131170272827148,
"learning_rate": 9.964541925211612e-05,
"loss": 0.3957,
"step": 510
},
{
"epoch": 3.1419939577039275,
"grad_norm": 5.908936977386475,
"learning_rate": 9.957811453644847e-05,
"loss": 0.2294,
"step": 520
},
{
"epoch": 3.202416918429003,
"grad_norm": 7.813998699188232,
"learning_rate": 9.950499160922183e-05,
"loss": 0.2424,
"step": 530
},
{
"epoch": 3.2628398791540785,
"grad_norm": 9.31921100616455,
"learning_rate": 9.942605905173592e-05,
"loss": 0.3864,
"step": 540
},
{
"epoch": 3.323262839879154,
"grad_norm": 6.702413558959961,
"learning_rate": 9.934132612707632e-05,
"loss": 0.3761,
"step": 550
},
{
"epoch": 3.38368580060423,
"grad_norm": 9.235360145568848,
"learning_rate": 9.925080277902743e-05,
"loss": 0.2577,
"step": 560
},
{
"epoch": 3.4441087613293053,
"grad_norm": 10.142770767211914,
"learning_rate": 9.91544996309055e-05,
"loss": 0.322,
"step": 570
},
{
"epoch": 3.504531722054381,
"grad_norm": 12.021828651428223,
"learning_rate": 9.905242798431196e-05,
"loss": 0.2585,
"step": 580
},
{
"epoch": 3.5649546827794563,
"grad_norm": 7.120593070983887,
"learning_rate": 9.894459981780711e-05,
"loss": 0.3731,
"step": 590
},
{
"epoch": 3.6253776435045317,
"grad_norm": 9.525044441223145,
"learning_rate": 9.883102778550434e-05,
"loss": 0.3116,
"step": 600
},
{
"epoch": 3.685800604229607,
"grad_norm": 13.72534465789795,
"learning_rate": 9.871172521558523e-05,
"loss": 0.3361,
"step": 610
},
{
"epoch": 3.7462235649546827,
"grad_norm": 12.432317733764648,
"learning_rate": 9.858670610873528e-05,
"loss": 0.2497,
"step": 620
},
{
"epoch": 3.806646525679758,
"grad_norm": 7.066479206085205,
"learning_rate": 9.845598513650103e-05,
"loss": 0.3698,
"step": 630
},
{
"epoch": 3.8670694864048336,
"grad_norm": 9.628741264343262,
"learning_rate": 9.831957763956813e-05,
"loss": 0.3154,
"step": 640
},
{
"epoch": 3.9274924471299095,
"grad_norm": 11.99616813659668,
"learning_rate": 9.817749962596115e-05,
"loss": 0.3181,
"step": 650
},
{
"epoch": 3.987915407854985,
"grad_norm": 9.52004623413086,
"learning_rate": 9.802976776916494e-05,
"loss": 0.2454,
"step": 660
},
{
"epoch": 4.0,
"eval_validation_loss": 0.7796794772148132,
"eval_validation_mae": 0.6025121808052063,
"eval_validation_mse": 0.7796794772148132,
"eval_validation_pearson": 0.8275993492481604,
"eval_validation_rmse": 0.8829945921897888,
"eval_validation_runtime": 128.9701,
"eval_validation_samples_per_second": 2.652,
"eval_validation_spearman": 0.8297559568405268,
"eval_validation_steps_per_second": 2.652,
"step": 662
},
{
"epoch": 4.0,
"eval_test_loss": 0.7812950015068054,
"eval_test_mae": 0.6039361953735352,
"eval_test_mse": 0.7812950015068054,
"eval_test_pearson": 0.8269227759203943,
"eval_test_rmse": 0.8839089274406433,
"eval_test_runtime": 128.9749,
"eval_test_samples_per_second": 2.652,
"eval_test_spearman": 0.8285234450057767,
"eval_test_steps_per_second": 2.652,
"step": 662
},
{
"epoch": 4.0,
"eval_myoglobin_loss": 0.8277855515480042,
"eval_myoglobin_mae": 0.670007050037384,
"eval_myoglobin_mse": 0.8277855515480042,
"eval_myoglobin_pearson": 0.6006203565841588,
"eval_myoglobin_rmse": 0.9098272323608398,
"eval_myoglobin_runtime": 50.3879,
"eval_myoglobin_samples_per_second": 2.659,
"eval_myoglobin_spearman": 0.6452977757628354,
"eval_myoglobin_steps_per_second": 2.659,
"step": 662
},
{
"epoch": 4.0,
"eval_myoglobin_r_loss": 0.8345361948013306,
"eval_myoglobin_r_mae": 0.6731795072555542,
"eval_myoglobin_r_mse": 0.8345361948013306,
"eval_myoglobin_r_pearson": 0.5986034577274495,
"eval_myoglobin_r_rmse": 0.9135295152664185,
"eval_myoglobin_r_runtime": 50.4043,
"eval_myoglobin_r_samples_per_second": 2.659,
"eval_myoglobin_r_spearman": 0.6437390342781807,
"eval_myoglobin_r_steps_per_second": 2.659,
"step": 662
},
{
"epoch": 4.0,
"eval_p53_loss": 3.8773045539855957,
"eval_p53_mae": 1.5222440958023071,
"eval_p53_mse": 3.8773045539855957,
"eval_p53_pearson": 0.3431499426951632,
"eval_p53_rmse": 1.9690872430801392,
"eval_p53_runtime": 17.5208,
"eval_p53_samples_per_second": 2.397,
"eval_p53_spearman": 0.3029050689249383,
"eval_p53_steps_per_second": 2.397,
"step": 662
},
{
"epoch": 4.04833836858006,
"grad_norm": 7.301741123199463,
"learning_rate": 9.787639940616788e-05,
"loss": 0.1719,
"step": 670
},
{
"epoch": 4.108761329305136,
"grad_norm": 7.330774784088135,
"learning_rate": 9.771741253542741e-05,
"loss": 0.2217,
"step": 680
},
{
"epoch": 4.169184290030212,
"grad_norm": 4.552008152008057,
"learning_rate": 9.755282581475769e-05,
"loss": 0.2123,
"step": 690
},
{
"epoch": 4.229607250755287,
"grad_norm": 4.030465126037598,
"learning_rate": 9.738265855914013e-05,
"loss": 0.1504,
"step": 700
},
{
"epoch": 4.290030211480363,
"grad_norm": 13.193011283874512,
"learning_rate": 9.720693073845667e-05,
"loss": 0.1922,
"step": 710
},
{
"epoch": 4.350453172205438,
"grad_norm": 7.253832817077637,
"learning_rate": 9.70256629751462e-05,
"loss": 0.1163,
"step": 720
},
{
"epoch": 4.410876132930514,
"grad_norm": 4.736353874206543,
"learning_rate": 9.683887654178445e-05,
"loss": 0.1391,
"step": 730
},
{
"epoch": 4.471299093655589,
"grad_norm": 8.901742935180664,
"learning_rate": 9.664659335858755e-05,
"loss": 0.1764,
"step": 740
},
{
"epoch": 4.531722054380665,
"grad_norm": 6.86702299118042,
"learning_rate": 9.644883599083958e-05,
"loss": 0.2754,
"step": 750
},
{
"epoch": 4.59214501510574,
"grad_norm": 7.574690818786621,
"learning_rate": 9.624562764624445e-05,
"loss": 0.1909,
"step": 760
},
{
"epoch": 4.652567975830816,
"grad_norm": 7.513609409332275,
"learning_rate": 9.603699217220239e-05,
"loss": 0.1752,
"step": 770
},
{
"epoch": 4.712990936555891,
"grad_norm": 6.482759475708008,
"learning_rate": 9.582295405301131e-05,
"loss": 0.1733,
"step": 780
},
{
"epoch": 4.7734138972809665,
"grad_norm": 12.048788070678711,
"learning_rate": 9.56035384069935e-05,
"loss": 0.1986,
"step": 790
},
{
"epoch": 4.833836858006042,
"grad_norm": 10.056185722351074,
"learning_rate": 9.537877098354786e-05,
"loss": 0.1798,
"step": 800
},
{
"epoch": 4.8942598187311175,
"grad_norm": 11.082551956176758,
"learning_rate": 9.514867816012809e-05,
"loss": 0.2064,
"step": 810
},
{
"epoch": 4.954682779456194,
"grad_norm": 11.846305847167969,
"learning_rate": 9.491328693914722e-05,
"loss": 0.1868,
"step": 820
},
{
"epoch": 4.996978851963746,
"eval_validation_loss": 0.7762272953987122,
"eval_validation_mae": 0.5832256078720093,
"eval_validation_mse": 0.7762272953987122,
"eval_validation_pearson": 0.8296356628068153,
"eval_validation_rmse": 0.8810376524925232,
"eval_validation_runtime": 129.148,
"eval_validation_samples_per_second": 2.648,
"eval_validation_spearman": 0.8313329837924658,
"eval_validation_steps_per_second": 2.648,
"step": 827
},
{
"epoch": 4.996978851963746,
"eval_test_loss": 0.7746825814247131,
"eval_test_mae": 0.5824557542800903,
"eval_test_mse": 0.7746825814247131,
"eval_test_pearson": 0.8289941215708723,
"eval_test_rmse": 0.8801605701446533,
"eval_test_runtime": 129.0007,
"eval_test_samples_per_second": 2.651,
"eval_test_spearman": 0.83056037563114,
"eval_test_steps_per_second": 2.651,
"step": 827
},
{
"epoch": 4.996978851963746,
"eval_myoglobin_loss": 0.7784543037414551,
"eval_myoglobin_mae": 0.6274142265319824,
"eval_myoglobin_mse": 0.7784543037414551,
"eval_myoglobin_pearson": 0.6119697266512958,
"eval_myoglobin_rmse": 0.8823005557060242,
"eval_myoglobin_runtime": 50.3439,
"eval_myoglobin_samples_per_second": 2.662,
"eval_myoglobin_spearman": 0.6659828987607965,
"eval_myoglobin_steps_per_second": 2.662,
"step": 827
},
{
"epoch": 4.996978851963746,
"eval_myoglobin_r_loss": 0.7818257212638855,
"eval_myoglobin_r_mae": 0.6293807625770569,
"eval_myoglobin_r_mse": 0.7818257212638855,
"eval_myoglobin_r_pearson": 0.6113029738762634,
"eval_myoglobin_r_rmse": 0.8842090964317322,
"eval_myoglobin_r_runtime": 50.3816,
"eval_myoglobin_r_samples_per_second": 2.66,
"eval_myoglobin_r_spearman": 0.6645264107175352,
"eval_myoglobin_r_steps_per_second": 2.66,
"step": 827
},
{
"epoch": 4.996978851963746,
"eval_p53_loss": 3.965853452682495,
"eval_p53_mae": 1.5425353050231934,
"eval_p53_mse": 3.965853452682495,
"eval_p53_pearson": 0.33295329636894166,
"eval_p53_rmse": 1.9914450645446777,
"eval_p53_runtime": 17.5238,
"eval_p53_samples_per_second": 2.397,
"eval_p53_spearman": 0.2773793608694659,
"eval_p53_steps_per_second": 2.397,
"step": 827
},
{
"epoch": 5.015105740181269,
"grad_norm": 6.842067241668701,
"learning_rate": 9.467262494480869e-05,
"loss": 0.1314,
"step": 830
},
{
"epoch": 5.075528700906345,
"grad_norm": 3.0206170082092285,
"learning_rate": 9.442672041986457e-05,
"loss": 0.077,
"step": 840
},
{
"epoch": 5.13595166163142,
"grad_norm": 4.4932355880737305,
"learning_rate": 9.417560222230115e-05,
"loss": 0.124,
"step": 850
},
{
"epoch": 5.196374622356496,
"grad_norm": 6.419702053070068,
"learning_rate": 9.391929982195232e-05,
"loss": 0.0903,
"step": 860
},
{
"epoch": 5.256797583081571,
"grad_norm": 5.199291229248047,
"learning_rate": 9.365784329704115e-05,
"loss": 0.117,
"step": 870
},
{
"epoch": 5.317220543806647,
"grad_norm": 6.824092864990234,
"learning_rate": 9.339126333065007e-05,
"loss": 0.1264,
"step": 880
},
{
"epoch": 5.377643504531722,
"grad_norm": 7.177854061126709,
"learning_rate": 9.31195912071201e-05,
"loss": 0.1153,
"step": 890
},
{
"epoch": 5.438066465256798,
"grad_norm": 6.354623317718506,
"learning_rate": 9.284285880837946e-05,
"loss": 0.1371,
"step": 900
},
{
"epoch": 5.498489425981873,
"grad_norm": 7.266890525817871,
"learning_rate": 9.256109861020213e-05,
"loss": 0.1253,
"step": 910
},
{
"epoch": 5.5589123867069485,
"grad_norm": 5.081086158752441,
"learning_rate": 9.22743436783966e-05,
"loss": 0.0986,
"step": 920
},
{
"epoch": 5.619335347432024,
"grad_norm": 4.2226762771606445,
"learning_rate": 9.198262766492554e-05,
"loss": 0.0786,
"step": 930
},
{
"epoch": 5.6797583081570995,
"grad_norm": 5.185201168060303,
"learning_rate": 9.168598480395651e-05,
"loss": 0.1014,
"step": 940
},
{
"epoch": 5.740181268882175,
"grad_norm": 8.60638427734375,
"learning_rate": 9.138444990784453e-05,
"loss": 0.1176,
"step": 950
},
{
"epoch": 5.80060422960725,
"grad_norm": 7.529942989349365,
"learning_rate": 9.107805836304658e-05,
"loss": 0.1253,
"step": 960
},
{
"epoch": 5.861027190332326,
"grad_norm": 13.042976379394531,
"learning_rate": 9.076684612596891e-05,
"loss": 0.1317,
"step": 970
},
{
"epoch": 5.921450151057401,
"grad_norm": 6.046395778656006,
"learning_rate": 9.045084971874738e-05,
"loss": 0.137,
"step": 980
},
{
"epoch": 5.981873111782478,
"grad_norm": 7.686984062194824,
"learning_rate": 9.013010622496144e-05,
"loss": 0.116,
"step": 990
},
{
"epoch": 6.0,
"eval_validation_loss": 0.7437558770179749,
"eval_validation_mae": 0.560340940952301,
"eval_validation_mse": 0.7437558770179749,
"eval_validation_pearson": 0.8386764926773793,
"eval_validation_rmse": 0.8624128103256226,
"eval_validation_runtime": 128.9359,
"eval_validation_samples_per_second": 2.652,
"eval_validation_spearman": 0.8401724374307825,
"eval_validation_steps_per_second": 2.652,
"step": 993
},
{
"epoch": 6.0,
"eval_test_loss": 0.7406001091003418,
"eval_test_mae": 0.558407723903656,
"eval_test_mse": 0.7406001091003418,
"eval_test_pearson": 0.8379222565005193,
"eval_test_rmse": 0.8605812788009644,
"eval_test_runtime": 128.8915,
"eval_test_samples_per_second": 2.653,
"eval_test_spearman": 0.8392344740172174,
"eval_test_steps_per_second": 2.653,
"step": 993
},
{
"epoch": 6.0,
"eval_myoglobin_loss": 0.7151281833648682,
"eval_myoglobin_mae": 0.6059358716011047,
"eval_myoglobin_mse": 0.7151281833648682,
"eval_myoglobin_pearson": 0.6404604400648282,
"eval_myoglobin_rmse": 0.8456525206565857,
"eval_myoglobin_runtime": 50.3332,
"eval_myoglobin_samples_per_second": 2.662,
"eval_myoglobin_spearman": 0.695120141585149,
"eval_myoglobin_steps_per_second": 2.662,
"step": 993
},
{
"epoch": 6.0,
"eval_myoglobin_r_loss": 0.718505322933197,
"eval_myoglobin_r_mae": 0.6069437861442566,
"eval_myoglobin_r_mse": 0.718505322933197,
"eval_myoglobin_r_pearson": 0.6396679973590835,
"eval_myoglobin_r_rmse": 0.847646951675415,
"eval_myoglobin_r_runtime": 50.3333,
"eval_myoglobin_r_samples_per_second": 2.662,
"eval_myoglobin_r_spearman": 0.6941175590622191,
"eval_myoglobin_r_steps_per_second": 2.662,
"step": 993
},
{
"epoch": 6.0,
"eval_p53_loss": 3.9644815921783447,
"eval_p53_mae": 1.5399214029312134,
"eval_p53_mse": 3.9644815921783447,
"eval_p53_pearson": 0.3275408804183826,
"eval_p53_rmse": 1.991100549697876,
"eval_p53_runtime": 17.5252,
"eval_p53_samples_per_second": 2.397,
"eval_p53_spearman": 0.2655483977707391,
"eval_p53_steps_per_second": 2.397,
"step": 993
},
{
"epoch": 6.042296072507553,
"grad_norm": 4.583357334136963,
"learning_rate": 8.980465328528219e-05,
"loss": 0.0736,
"step": 1000
},
{
"epoch": 6.102719033232629,
"grad_norm": 4.502609729766846,
"learning_rate": 8.94745290930551e-05,
"loss": 0.0453,
"step": 1010
},
{
"epoch": 6.163141993957704,
"grad_norm": 4.533963203430176,
"learning_rate": 8.913977238981778e-05,
"loss": 0.0728,
"step": 1020
},
{
"epoch": 6.22356495468278,
"grad_norm": 3.250356912612915,
"learning_rate": 8.880042246075365e-05,
"loss": 0.0644,
"step": 1030
},
{
"epoch": 6.283987915407855,
"grad_norm": 5.3714470863342285,
"learning_rate": 8.845651913008145e-05,
"loss": 0.0654,
"step": 1040
},
{
"epoch": 6.3444108761329305,
"grad_norm": 4.90172815322876,
"learning_rate": 8.810810275638183e-05,
"loss": 0.0976,
"step": 1050
},
{
"epoch": 6.404833836858006,
"grad_norm": 4.008552551269531,
"learning_rate": 8.775521422786104e-05,
"loss": 0.0821,
"step": 1060
},
{
"epoch": 6.4652567975830815,
"grad_norm": 6.362269878387451,
"learning_rate": 8.739789495755253e-05,
"loss": 0.0668,
"step": 1070
},
{
"epoch": 6.525679758308157,
"grad_norm": 3.8847382068634033,
"learning_rate": 8.703618687845696e-05,
"loss": 0.0964,
"step": 1080
},
{
"epoch": 6.586102719033232,
"grad_norm": 6.632302761077881,
"learning_rate": 8.667013243862113e-05,
"loss": 0.0588,
"step": 1090
},
{
"epoch": 6.646525679758308,
"grad_norm": 4.578704833984375,
"learning_rate": 8.629977459615655e-05,
"loss": 0.1196,
"step": 1100
},
{
"epoch": 6.706948640483383,
"grad_norm": 3.4470386505126953,
"learning_rate": 8.592515681419813e-05,
"loss": 0.099,
"step": 1110
},
{
"epoch": 6.76737160120846,
"grad_norm": 5.420199871063232,
"learning_rate": 8.554632305580354e-05,
"loss": 0.08,
"step": 1120
},
{
"epoch": 6.827794561933535,
"grad_norm": 2.7681386470794678,
"learning_rate": 8.5163317778794e-05,
"loss": 0.0618,
"step": 1130
},
{
"epoch": 6.888217522658611,
"grad_norm": 6.834138870239258,
"learning_rate": 8.477618593053693e-05,
"loss": 0.1016,
"step": 1140
},
{
"epoch": 6.948640483383686,
"grad_norm": 3.5948920249938965,
"learning_rate": 8.438497294267117e-05,
"loss": 0.0986,
"step": 1150
},
{
"epoch": 6.996978851963746,
"eval_validation_loss": 0.7183637619018555,
"eval_validation_mae": 0.546740710735321,
"eval_validation_mse": 0.7183637619018555,
"eval_validation_pearson": 0.8431698872855691,
"eval_validation_rmse": 0.8475634455680847,
"eval_validation_runtime": 129.0329,
"eval_validation_samples_per_second": 2.65,
"eval_validation_spearman": 0.8431269246509225,
"eval_validation_steps_per_second": 2.65,
"step": 1158
},
{
"epoch": 6.996978851963746,
"eval_test_loss": 0.7154301404953003,
"eval_test_mae": 0.5448740720748901,
"eval_test_mse": 0.7154301404953003,
"eval_test_pearson": 0.8424761229464366,
"eval_test_rmse": 0.845831036567688,
"eval_test_runtime": 128.9049,
"eval_test_samples_per_second": 2.653,
"eval_test_spearman": 0.8418909616629952,
"eval_test_steps_per_second": 2.653,
"step": 1158
},
{
"epoch": 6.996978851963746,
"eval_myoglobin_loss": 0.7281521558761597,
"eval_myoglobin_mae": 0.6114689707756042,
"eval_myoglobin_mse": 0.7281521558761597,
"eval_myoglobin_pearson": 0.6346894753809238,
"eval_myoglobin_rmse": 0.8533183336257935,
"eval_myoglobin_runtime": 50.3288,
"eval_myoglobin_samples_per_second": 2.662,
"eval_myoglobin_spearman": 0.6774278022377248,
"eval_myoglobin_steps_per_second": 2.662,
"step": 1158
},
{
"epoch": 6.996978851963746,
"eval_myoglobin_r_loss": 0.7321227192878723,
"eval_myoglobin_r_mae": 0.6134014129638672,
"eval_myoglobin_r_mse": 0.7321227192878723,
"eval_myoglobin_r_pearson": 0.633906508155178,
"eval_myoglobin_r_rmse": 0.8556417226791382,
"eval_myoglobin_r_runtime": 50.3016,
"eval_myoglobin_r_samples_per_second": 2.664,
"eval_myoglobin_r_spearman": 0.6763329422189034,
"eval_myoglobin_r_steps_per_second": 2.664,
"step": 1158
},
{
"epoch": 6.996978851963746,
"eval_p53_loss": 4.01906156539917,
"eval_p53_mae": 1.5535447597503662,
"eval_p53_mse": 4.01906156539917,
"eval_p53_pearson": 0.3308597233844921,
"eval_p53_rmse": 2.0047597885131836,
"eval_p53_runtime": 17.5174,
"eval_p53_samples_per_second": 2.398,
"eval_p53_spearman": 0.3005550831039583,
"eval_p53_steps_per_second": 2.398,
"step": 1158
},
{
"epoch": 7.009063444108762,
"grad_norm": 1.746163010597229,
"learning_rate": 8.39897247257754e-05,
"loss": 0.0779,
"step": 1160
},
{
"epoch": 7.069486404833837,
"grad_norm": 3.740064859390259,
"learning_rate": 8.359048766398031e-05,
"loss": 0.0478,
"step": 1170
},
{
"epoch": 7.1299093655589125,
"grad_norm": 3.6287150382995605,
"learning_rate": 8.318730860952522e-05,
"loss": 0.0989,
"step": 1180
},
{
"epoch": 7.190332326283988,
"grad_norm": 5.2572784423828125,
"learning_rate": 8.278023487725982e-05,
"loss": 0.0487,
"step": 1190
},
{
"epoch": 7.2507552870090635,
"grad_norm": 6.087055206298828,
"learning_rate": 8.236931423909138e-05,
"loss": 0.0552,
"step": 1200
},
{
"epoch": 7.311178247734139,
"grad_norm": 4.305581092834473,
"learning_rate": 8.19545949183788e-05,
"loss": 0.0553,
"step": 1210
},
{
"epoch": 7.371601208459214,
"grad_norm": 4.056112289428711,
"learning_rate": 8.153612558427311e-05,
"loss": 0.0463,
"step": 1220
},
{
"epoch": 7.43202416918429,
"grad_norm": 2.302788734436035,
"learning_rate": 8.111395534600603e-05,
"loss": 0.0461,
"step": 1230
},
{
"epoch": 7.492447129909365,
"grad_norm": 4.409842491149902,
"learning_rate": 8.068813374712688e-05,
"loss": 0.0692,
"step": 1240
},
{
"epoch": 7.552870090634441,
"grad_norm": 5.059557914733887,
"learning_rate": 8.025871075968828e-05,
"loss": 0.0462,
"step": 1250
},
{
"epoch": 7.613293051359516,
"grad_norm": 3.1334400177001953,
"learning_rate": 7.982573677838172e-05,
"loss": 0.0729,
"step": 1260
},
{
"epoch": 7.673716012084592,
"grad_norm": 5.167521953582764,
"learning_rate": 7.938926261462366e-05,
"loss": 0.0728,
"step": 1270
},
{
"epoch": 7.734138972809667,
"grad_norm": 7.676636219024658,
"learning_rate": 7.894933949059245e-05,
"loss": 0.0484,
"step": 1280
},
{
"epoch": 7.794561933534744,
"grad_norm": 6.20352029800415,
"learning_rate": 7.850601903321716e-05,
"loss": 0.067,
"step": 1290
},
{
"epoch": 7.854984894259819,
"grad_norm": 5.005100727081299,
"learning_rate": 7.805935326811912e-05,
"loss": 0.0519,
"step": 1300
},
{
"epoch": 7.9154078549848945,
"grad_norm": 3.7345407009124756,
"learning_rate": 7.760939461350623e-05,
"loss": 0.0603,
"step": 1310
},
{
"epoch": 7.97583081570997,
"grad_norm": 4.5358781814575195,
"learning_rate": 7.715619587402164e-05,
"loss": 0.0591,
"step": 1320
},
{
"epoch": 8.0,
"eval_validation_loss": 0.7083848118782043,
"eval_validation_mae": 0.5314592719078064,
"eval_validation_mse": 0.7083848118782043,
"eval_validation_pearson": 0.8431805287577845,
"eval_validation_rmse": 0.841655969619751,
"eval_validation_runtime": 129.0006,
"eval_validation_samples_per_second": 2.651,
"eval_validation_spearman": 0.8425645367331428,
"eval_validation_steps_per_second": 2.651,
"step": 1324
},
{
"epoch": 8.0,
"eval_test_loss": 0.7102228999137878,
"eval_test_mae": 0.5320845246315002,
"eval_test_mse": 0.7102228999137878,
"eval_test_pearson": 0.8422782344343887,
"eval_test_rmse": 0.8427472114562988,
"eval_test_runtime": 129.0009,
"eval_test_samples_per_second": 2.651,
"eval_test_spearman": 0.841548097097326,
"eval_test_steps_per_second": 2.651,
"step": 1324
},
{
"epoch": 8.0,
"eval_myoglobin_loss": 0.7520159482955933,
"eval_myoglobin_mae": 0.6083745956420898,
"eval_myoglobin_mse": 0.7520159482955933,
"eval_myoglobin_pearson": 0.6194230091693953,
"eval_myoglobin_rmse": 0.8671885132789612,
"eval_myoglobin_runtime": 50.3253,
"eval_myoglobin_samples_per_second": 2.663,
"eval_myoglobin_spearman": 0.6743252831866682,
"eval_myoglobin_steps_per_second": 2.663,
"step": 1324
},
{
"epoch": 8.0,
"eval_myoglobin_r_loss": 0.753574013710022,
"eval_myoglobin_r_mae": 0.6102104783058167,
"eval_myoglobin_r_mse": 0.753574013710022,
"eval_myoglobin_r_pearson": 0.6190984211925752,
"eval_myoglobin_r_rmse": 0.8680863976478577,
"eval_myoglobin_r_runtime": 50.3474,
"eval_myoglobin_r_samples_per_second": 2.662,
"eval_myoglobin_r_spearman": 0.6751208648404359,
"eval_myoglobin_r_steps_per_second": 2.662,
"step": 1324
},
{
"epoch": 8.0,
"eval_p53_loss": 3.998952627182007,
"eval_p53_mae": 1.5620994567871094,
"eval_p53_mse": 3.998952627182007,
"eval_p53_pearson": 0.32915902114473283,
"eval_p53_rmse": 1.999738097190857,
"eval_p53_runtime": 17.5293,
"eval_p53_samples_per_second": 2.396,
"eval_p53_spearman": 0.2918034117706535,
"eval_p53_steps_per_second": 2.396,
"step": 1324
},
{
"epoch": 8.036253776435045,
"grad_norm": 2.709134101867676,
"learning_rate": 7.669981023454682e-05,
"loss": 0.0448,
"step": 1330
},
{
"epoch": 8.09667673716012,
"grad_norm": 3.791492223739624,
"learning_rate": 7.624029125396004e-05,
"loss": 0.0381,
"step": 1340
},
{
"epoch": 8.157099697885196,
"grad_norm": 2.499840259552002,
"learning_rate": 7.577769285885109e-05,
"loss": 0.0399,
"step": 1350
},
{
"epoch": 8.217522658610273,
"grad_norm": 4.001781463623047,
"learning_rate": 7.53120693371927e-05,
"loss": 0.0473,
"step": 1360
},
{
"epoch": 8.277945619335348,
"grad_norm": 4.293058395385742,
"learning_rate": 7.484347533196961e-05,
"loss": 0.0423,
"step": 1370
},
{
"epoch": 8.338368580060424,
"grad_norm": 6.312211990356445,
"learning_rate": 7.437196583476596e-05,
"loss": 0.0607,
"step": 1380
},
{
"epoch": 8.3987915407855,
"grad_norm": 5.174694538116455,
"learning_rate": 7.389759617931182e-05,
"loss": 0.0513,
"step": 1390
},
{
"epoch": 8.459214501510575,
"grad_norm": 3.2399227619171143,
"learning_rate": 7.342042203498951e-05,
"loss": 0.0264,
"step": 1400
},
{
"epoch": 8.51963746223565,
"grad_norm": 3.2468111515045166,
"learning_rate": 7.294049940030055e-05,
"loss": 0.0397,
"step": 1410
},
{
"epoch": 8.580060422960726,
"grad_norm": 4.853147983551025,
"learning_rate": 7.245788459629396e-05,
"loss": 0.0504,
"step": 1420
},
{
"epoch": 8.640483383685801,
"grad_norm": 3.306142568588257,
"learning_rate": 7.197263425995682e-05,
"loss": 0.0405,
"step": 1430
},
{
"epoch": 8.700906344410877,
"grad_norm": 3.277174711227417,
"learning_rate": 7.14848053375676e-05,
"loss": 0.0382,
"step": 1440
},
{
"epoch": 8.761329305135952,
"grad_norm": 3.5067923069000244,
"learning_rate": 7.099445507801323e-05,
"loss": 0.0402,
"step": 1450
},
{
"epoch": 8.821752265861027,
"grad_norm": 4.621323108673096,
"learning_rate": 7.05016410260708e-05,
"loss": 0.0601,
"step": 1460
},
{
"epoch": 8.882175226586103,
"grad_norm": 2.868621587753296,
"learning_rate": 7.000642101565434e-05,
"loss": 0.0389,
"step": 1470
},
{
"epoch": 8.942598187311178,
"grad_norm": 3.935192584991455,
"learning_rate": 6.950885316302773e-05,
"loss": 0.0809,
"step": 1480
},
{
"epoch": 8.996978851963746,
"eval_validation_loss": 0.7205836176872253,
"eval_validation_mae": 0.5384864807128906,
"eval_validation_mse": 0.7205836176872253,
"eval_validation_pearson": 0.8410535584549592,
"eval_validation_rmse": 0.8488719463348389,
"eval_validation_runtime": 129.1697,
"eval_validation_samples_per_second": 2.648,
"eval_validation_spearman": 0.8456297609552365,
"eval_validation_steps_per_second": 2.648,
"step": 1489
},
{
"epoch": 8.996978851963746,
"eval_test_loss": 0.7227678298950195,
"eval_test_mae": 0.5399196743965149,
"eval_test_mse": 0.7227678298950195,
"eval_test_pearson": 0.8400645100430921,
"eval_test_rmse": 0.8501575589179993,
"eval_test_runtime": 129.1979,
"eval_test_samples_per_second": 2.647,
"eval_test_spearman": 0.8440572355074423,
"eval_test_steps_per_second": 2.647,
"step": 1489
},
{
"epoch": 8.996978851963746,
"eval_myoglobin_loss": 0.7287605404853821,
"eval_myoglobin_mae": 0.611557126045227,
"eval_myoglobin_mse": 0.7287605404853821,
"eval_myoglobin_pearson": 0.6309798982049415,
"eval_myoglobin_rmse": 0.8536747097969055,
"eval_myoglobin_runtime": 50.4254,
"eval_myoglobin_samples_per_second": 2.657,
"eval_myoglobin_spearman": 0.6759837841263407,
"eval_myoglobin_steps_per_second": 2.657,
"step": 1489
},
{
"epoch": 8.996978851963746,
"eval_myoglobin_r_loss": 0.7296391725540161,
"eval_myoglobin_r_mae": 0.6120913028717041,
"eval_myoglobin_r_mse": 0.7296391725540161,
"eval_myoglobin_r_pearson": 0.63082406938247,
"eval_myoglobin_r_rmse": 0.8541892170906067,
"eval_myoglobin_r_runtime": 50.4386,
"eval_myoglobin_r_samples_per_second": 2.657,
"eval_myoglobin_r_spearman": 0.6778293340441719,
"eval_myoglobin_r_steps_per_second": 2.657,
"step": 1489
},
{
"epoch": 8.996978851963746,
"eval_p53_loss": 3.9503331184387207,
"eval_p53_mae": 1.5360697507858276,
"eval_p53_mse": 3.9503331184387207,
"eval_p53_pearson": 0.32911657672957517,
"eval_p53_rmse": 1.9875445365905762,
"eval_p53_runtime": 17.5407,
"eval_p53_samples_per_second": 2.394,
"eval_p53_spearman": 0.2984481992644589,
"eval_p53_steps_per_second": 2.394,
"step": 1489
},
{
"epoch": 9.003021148036254,
"grad_norm": 3.8243162631988525,
"learning_rate": 6.90089958599846e-05,
"loss": 0.0256,
"step": 1490
},
{
"epoch": 9.06344410876133,
"grad_norm": 1.7380579710006714,
"learning_rate": 6.850690776699573e-05,
"loss": 0.0361,
"step": 1500
},
{
"epoch": 9.123867069486405,
"grad_norm": 3.18019962310791,
"learning_rate": 6.800264780632494e-05,
"loss": 0.0318,
"step": 1510
},
{
"epoch": 9.18429003021148,
"grad_norm": 3.6475789546966553,
"learning_rate": 6.749627515511442e-05,
"loss": 0.0308,
"step": 1520
},
{
"epoch": 9.244712990936556,
"grad_norm": 2.547883987426758,
"learning_rate": 6.698784923843992e-05,
"loss": 0.0266,
"step": 1530
},
{
"epoch": 9.305135951661631,
"grad_norm": 2.434000015258789,
"learning_rate": 6.647742972233703e-05,
"loss": 0.0302,
"step": 1540
},
{
"epoch": 9.365558912386707,
"grad_norm": 5.521008014678955,
"learning_rate": 6.5965076506799e-05,
"loss": 0.0358,
"step": 1550
},
{
"epoch": 9.425981873111782,
"grad_norm": 3.3292031288146973,
"learning_rate": 6.545084971874738e-05,
"loss": 0.037,
"step": 1560
},
{
"epoch": 9.486404833836858,
"grad_norm": 3.638929605484009,
"learning_rate": 6.493480970497569e-05,
"loss": 0.0422,
"step": 1570
},
{
"epoch": 9.546827794561933,
"grad_norm": 2.6074700355529785,
"learning_rate": 6.441701702506754e-05,
"loss": 0.0292,
"step": 1580
},
{
"epoch": 9.607250755287009,
"grad_norm": 2.0434532165527344,
"learning_rate": 6.389753244428972e-05,
"loss": 0.021,
"step": 1590
},
{
"epoch": 9.667673716012084,
"grad_norm": 4.6780524253845215,
"learning_rate": 6.337641692646106e-05,
"loss": 0.0366,
"step": 1600
},
{
"epoch": 9.72809667673716,
"grad_norm": 3.076948642730713,
"learning_rate": 6.285373162679803e-05,
"loss": 0.0295,
"step": 1610
},
{
"epoch": 9.788519637462235,
"grad_norm": 4.26541805267334,
"learning_rate": 6.232953788473811e-05,
"loss": 0.0274,
"step": 1620
},
{
"epoch": 9.84894259818731,
"grad_norm": 2.9073691368103027,
"learning_rate": 6.1803897216741e-05,
"loss": 0.0324,
"step": 1630
},
{
"epoch": 9.909365558912386,
"grad_norm": 4.8707990646362305,
"learning_rate": 6.127687130906972e-05,
"loss": 0.0401,
"step": 1640
},
{
"epoch": 9.969788519637461,
"grad_norm": 4.892948150634766,
"learning_rate": 6.0748522010551215e-05,
"loss": 0.0461,
"step": 1650
},
{
"epoch": 10.0,
"eval_validation_loss": 0.7096761465072632,
"eval_validation_mae": 0.5233484506607056,
"eval_validation_mse": 0.7096761465072632,
"eval_validation_pearson": 0.8435451256537725,
"eval_validation_rmse": 0.8424227833747864,
"eval_validation_runtime": 128.988,
"eval_validation_samples_per_second": 2.651,
"eval_validation_spearman": 0.8466052369033387,
"eval_validation_steps_per_second": 2.651,
"step": 1655
},
{
"epoch": 10.0,
"eval_test_loss": 0.7089855074882507,
"eval_test_mae": 0.5238877534866333,
"eval_test_mse": 0.7089855074882507,
"eval_test_pearson": 0.8428611030663262,
"eval_test_rmse": 0.8420127630233765,
"eval_test_runtime": 128.948,
"eval_test_samples_per_second": 2.652,
"eval_test_spearman": 0.8455169232513489,
"eval_test_steps_per_second": 2.652,
"step": 1655
},
{
"epoch": 10.0,
"eval_myoglobin_loss": 0.7252078056335449,
"eval_myoglobin_mae": 0.6012104749679565,
"eval_myoglobin_mse": 0.7252078056335449,
"eval_myoglobin_pearson": 0.636367763746648,
"eval_myoglobin_rmse": 0.8515913486480713,
"eval_myoglobin_runtime": 50.3593,
"eval_myoglobin_samples_per_second": 2.661,
"eval_myoglobin_spearman": 0.6746395254699745,
"eval_myoglobin_steps_per_second": 2.661,
"step": 1655
},
{
"epoch": 10.0,
"eval_myoglobin_r_loss": 0.726817786693573,
"eval_myoglobin_r_mae": 0.6012217402458191,
"eval_myoglobin_r_mse": 0.726817786693573,
"eval_myoglobin_r_pearson": 0.6361235811248207,
"eval_myoglobin_r_rmse": 0.8525360822677612,
"eval_myoglobin_r_runtime": 50.3696,
"eval_myoglobin_r_samples_per_second": 2.66,
"eval_myoglobin_r_spearman": 0.6742305117044012,
"eval_myoglobin_r_steps_per_second": 2.66,
"step": 1655
},
{
"epoch": 10.0,
"eval_p53_loss": 3.99676775932312,
"eval_p53_mae": 1.5769025087356567,
"eval_p53_mse": 3.99676775932312,
"eval_p53_pearson": 0.3403924251906574,
"eval_p53_rmse": 1.9991917610168457,
"eval_p53_runtime": 17.5283,
"eval_p53_samples_per_second": 2.396,
"eval_p53_spearman": 0.2857258622336363,
"eval_p53_steps_per_second": 2.396,
"step": 1655
},
{
"epoch": 10.030211480362539,
"grad_norm": 2.2076847553253174,
"learning_rate": 6.021891132531825e-05,
"loss": 0.0307,
"step": 1660
},
{
"epoch": 10.090634441087614,
"grad_norm": 2.394089937210083,
"learning_rate": 5.9688101405532925e-05,
"loss": 0.0187,
"step": 1670
},
{
"epoch": 10.15105740181269,
"grad_norm": 2.8219094276428223,
"learning_rate": 5.9156154544092815e-05,
"loss": 0.0259,
"step": 1680
},
{
"epoch": 10.211480362537765,
"grad_norm": 2.308112144470215,
"learning_rate": 5.862313316732063e-05,
"loss": 0.027,
"step": 1690
},
{
"epoch": 10.27190332326284,
"grad_norm": 2.3153975009918213,
"learning_rate": 5.808909982763825e-05,
"loss": 0.0238,
"step": 1700
},
{
"epoch": 10.332326283987916,
"grad_norm": 3.1248135566711426,
"learning_rate": 5.7554117196225846e-05,
"loss": 0.0228,
"step": 1710
},
{
"epoch": 10.392749244712991,
"grad_norm": 3.748237371444702,
"learning_rate": 5.701824805566722e-05,
"loss": 0.024,
"step": 1720
},
{
"epoch": 10.453172205438067,
"grad_norm": 3.601746082305908,
"learning_rate": 5.6481555292581946e-05,
"loss": 0.0227,
"step": 1730
},
{
"epoch": 10.513595166163142,
"grad_norm": 2.709296703338623,
"learning_rate": 5.5944101890245324e-05,
"loss": 0.0174,
"step": 1740
},
{
"epoch": 10.574018126888218,
"grad_norm": 2.704521656036377,
"learning_rate": 5.540595092119709e-05,
"loss": 0.0315,
"step": 1750
},
{
"epoch": 10.634441087613293,
"grad_norm": 3.2573423385620117,
"learning_rate": 5.486716553983951e-05,
"loss": 0.0287,
"step": 1760
},
{
"epoch": 10.694864048338369,
"grad_norm": 4.1254682540893555,
"learning_rate": 5.432780897502589e-05,
"loss": 0.0311,
"step": 1770
},
{
"epoch": 10.755287009063444,
"grad_norm": 4.715117454528809,
"learning_rate": 5.378794452264053e-05,
"loss": 0.022,
"step": 1780
},
{
"epoch": 10.81570996978852,
"grad_norm": 2.1660892963409424,
"learning_rate": 5.324763553817054e-05,
"loss": 0.0211,
"step": 1790
},
{
"epoch": 10.876132930513595,
"grad_norm": 3.1040217876434326,
"learning_rate": 5.270694542927088e-05,
"loss": 0.0347,
"step": 1800
},
{
"epoch": 10.93655589123867,
"grad_norm": 2.742941379547119,
"learning_rate": 5.216593764832311e-05,
"loss": 0.0226,
"step": 1810
},
{
"epoch": 10.996978851963746,
"grad_norm": 3.172571897506714,
"learning_rate": 5.162467568498903e-05,
"loss": 0.025,
"step": 1820
},
{
"epoch": 10.996978851963746,
"eval_validation_loss": 0.6895685195922852,
"eval_validation_mae": 0.5120286345481873,
"eval_validation_mse": 0.6895685195922852,
"eval_validation_pearson": 0.8489549431017167,
"eval_validation_rmse": 0.8304026126861572,
"eval_validation_runtime": 128.9581,
"eval_validation_samples_per_second": 2.652,
"eval_validation_spearman": 0.8526459553649132,
"eval_validation_steps_per_second": 2.652,
"step": 1820
},
{
"epoch": 10.996978851963746,
"eval_test_loss": 0.6883087158203125,
"eval_test_mae": 0.5119835734367371,
"eval_test_mse": 0.6883087158203125,
"eval_test_pearson": 0.848377152226476,
"eval_test_rmse": 0.829643726348877,
"eval_test_runtime": 128.9938,
"eval_test_samples_per_second": 2.651,
"eval_test_spearman": 0.8513768312964548,
"eval_test_steps_per_second": 2.651,
"step": 1820
},
{
"epoch": 10.996978851963746,
"eval_myoglobin_loss": 0.7179906368255615,
"eval_myoglobin_mae": 0.5888025760650635,
"eval_myoglobin_mse": 0.7179906368255615,
"eval_myoglobin_pearson": 0.6391641538657495,
"eval_myoglobin_rmse": 0.8473432660102844,
"eval_myoglobin_runtime": 50.3591,
"eval_myoglobin_samples_per_second": 2.661,
"eval_myoglobin_spearman": 0.6862166102248016,
"eval_myoglobin_steps_per_second": 2.661,
"step": 1820
},
{
"epoch": 10.996978851963746,
"eval_myoglobin_r_loss": 0.7204333543777466,
"eval_myoglobin_r_mae": 0.5895242691040039,
"eval_myoglobin_r_mse": 0.7204333543777466,
"eval_myoglobin_r_pearson": 0.6383291059933072,
"eval_myoglobin_r_rmse": 0.8487834334373474,
"eval_myoglobin_r_runtime": 50.3628,
"eval_myoglobin_r_samples_per_second": 2.661,
"eval_myoglobin_r_spearman": 0.683303634138279,
"eval_myoglobin_r_steps_per_second": 2.661,
"step": 1820
},
{
"epoch": 10.996978851963746,
"eval_p53_loss": 4.048507213592529,
"eval_p53_mae": 1.5837998390197754,
"eval_p53_mse": 4.048507213592529,
"eval_p53_pearson": 0.3178191790357232,
"eval_p53_rmse": 2.0120902061462402,
"eval_p53_runtime": 17.5292,
"eval_p53_samples_per_second": 2.396,
"eval_p53_spearman": 0.2873465421101742,
"eval_p53_steps_per_second": 2.396,
"step": 1820
}
],
"logging_steps": 10,
"max_steps": 3300,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}