BabyLM_2024_Strict_Small_Baseline / trainer_state.json
Qilex's picture
Upload 18 files
c8eb71a verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 49.9001996007984,
"eval_steps": 500,
"global_step": 25000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.998003992015968,
"grad_norm": 1.8999210596084595,
"learning_rate": 3.32667997338656e-06,
"loss": 8.3804,
"step": 500
},
{
"epoch": 1.996007984031936,
"grad_norm": 2.889465093612671,
"learning_rate": 6.65335994677312e-06,
"loss": 7.2559,
"step": 1000
},
{
"epoch": 2.9940119760479043,
"grad_norm": 1.4177864789962769,
"learning_rate": 9.980039920159681e-06,
"loss": 6.3336,
"step": 1500
},
{
"epoch": 3.992015968063872,
"grad_norm": 1.6604845523834229,
"learning_rate": 1.330671989354624e-05,
"loss": 5.7018,
"step": 2000
},
{
"epoch": 4.99001996007984,
"grad_norm": 1.785506248474121,
"learning_rate": 1.6633399866932804e-05,
"loss": 5.3092,
"step": 2500
},
{
"epoch": 5.9880239520958085,
"grad_norm": 1.665967583656311,
"learning_rate": 1.9960079840319362e-05,
"loss": 5.0451,
"step": 3000
},
{
"epoch": 6.986027944111776,
"grad_norm": 2.023294687271118,
"learning_rate": 2.328675981370592e-05,
"loss": 4.84,
"step": 3500
},
{
"epoch": 7.984031936127744,
"grad_norm": 2.2120347023010254,
"learning_rate": 2.661343978709248e-05,
"loss": 4.6636,
"step": 4000
},
{
"epoch": 8.982035928143713,
"grad_norm": 2.0134084224700928,
"learning_rate": 2.994011976047904e-05,
"loss": 4.517,
"step": 4500
},
{
"epoch": 9.980039920159681,
"grad_norm": 1.9846144914627075,
"learning_rate": 3.326679973386561e-05,
"loss": 4.3934,
"step": 5000
},
{
"epoch": 10.978043912175648,
"grad_norm": 2.0299410820007324,
"learning_rate": 3.6593479707252166e-05,
"loss": 4.2831,
"step": 5500
},
{
"epoch": 11.976047904191617,
"grad_norm": 1.7351747751235962,
"learning_rate": 3.9920159680638724e-05,
"loss": 4.1891,
"step": 6000
},
{
"epoch": 12.974051896207584,
"grad_norm": 1.829405665397644,
"learning_rate": 4.324018629407851e-05,
"loss": 4.0984,
"step": 6500
},
{
"epoch": 13.972055888223553,
"grad_norm": 1.727301836013794,
"learning_rate": 4.656686626746507e-05,
"loss": 4.0139,
"step": 7000
},
{
"epoch": 14.970059880239521,
"grad_norm": 1.7156864404678345,
"learning_rate": 4.9893546240851635e-05,
"loss": 3.938,
"step": 7500
},
{
"epoch": 15.968063872255488,
"grad_norm": 1.5628697872161865,
"learning_rate": 5.322022621423819e-05,
"loss": 3.8623,
"step": 8000
},
{
"epoch": 16.96606786427146,
"grad_norm": 1.6095757484436035,
"learning_rate": 5.6540252827677973e-05,
"loss": 3.7939,
"step": 8500
},
{
"epoch": 17.964071856287426,
"grad_norm": 1.695480465888977,
"learning_rate": 5.9866932801064546e-05,
"loss": 3.7259,
"step": 9000
},
{
"epoch": 18.962075848303392,
"grad_norm": 1.6396301984786987,
"learning_rate": 6.319361277445111e-05,
"loss": 3.6648,
"step": 9500
},
{
"epoch": 19.960079840319363,
"grad_norm": 1.6488186120986938,
"learning_rate": 6.652029274783767e-05,
"loss": 3.6029,
"step": 10000
},
{
"epoch": 20.95808383233533,
"grad_norm": 1.7244266271591187,
"learning_rate": 6.984031936127745e-05,
"loss": 3.5493,
"step": 10500
},
{
"epoch": 21.956087824351297,
"grad_norm": 1.5352064371109009,
"learning_rate": 7.316699933466401e-05,
"loss": 3.4955,
"step": 11000
},
{
"epoch": 22.954091816367267,
"grad_norm": 1.5730326175689697,
"learning_rate": 7.649367930805057e-05,
"loss": 3.4487,
"step": 11500
},
{
"epoch": 23.952095808383234,
"grad_norm": 1.5208061933517456,
"learning_rate": 7.982035928143713e-05,
"loss": 3.4063,
"step": 12000
},
{
"epoch": 24.9500998003992,
"grad_norm": 1.4076310396194458,
"learning_rate": 8.314703925482368e-05,
"loss": 3.3677,
"step": 12500
},
{
"epoch": 25.948103792415168,
"grad_norm": 1.5883309841156006,
"learning_rate": 8.646706586826348e-05,
"loss": 3.3283,
"step": 13000
},
{
"epoch": 26.94610778443114,
"grad_norm": 1.5784621238708496,
"learning_rate": 8.979374584165004e-05,
"loss": 3.2934,
"step": 13500
},
{
"epoch": 27.944111776447105,
"grad_norm": 1.432620882987976,
"learning_rate": 9.31204258150366e-05,
"loss": 3.261,
"step": 14000
},
{
"epoch": 28.942115768463076,
"grad_norm": 1.3958067893981934,
"learning_rate": 9.644710578842315e-05,
"loss": 3.23,
"step": 14500
},
{
"epoch": 29.940119760479043,
"grad_norm": 1.3833889961242676,
"learning_rate": 9.977378576180973e-05,
"loss": 3.2001,
"step": 15000
},
{
"epoch": 30.93812375249501,
"grad_norm": 1.3629279136657715,
"learning_rate": 9.995644109160385e-05,
"loss": 3.1728,
"step": 15500
},
{
"epoch": 31.936127744510976,
"grad_norm": 1.4202319383621216,
"learning_rate": 9.981290962387998e-05,
"loss": 3.1431,
"step": 16000
},
{
"epoch": 32.93413173652694,
"grad_norm": 1.3846460580825806,
"learning_rate": 9.956946158420721e-05,
"loss": 3.1126,
"step": 16500
},
{
"epoch": 33.93213572854292,
"grad_norm": 1.3388583660125732,
"learning_rate": 9.92273698475866e-05,
"loss": 3.0906,
"step": 17000
},
{
"epoch": 34.930139720558884,
"grad_norm": 1.2869479656219482,
"learning_rate": 9.878594971476942e-05,
"loss": 3.0625,
"step": 17500
},
{
"epoch": 35.92814371257485,
"grad_norm": 1.3220205307006836,
"learning_rate": 9.824667292407827e-05,
"loss": 3.0418,
"step": 18000
},
{
"epoch": 36.92614770459082,
"grad_norm": 1.2586220502853394,
"learning_rate": 9.761062117679632e-05,
"loss": 3.0155,
"step": 18500
},
{
"epoch": 37.924151696606785,
"grad_norm": 1.3261734247207642,
"learning_rate": 9.688062775520065e-05,
"loss": 2.9964,
"step": 19000
},
{
"epoch": 38.92215568862275,
"grad_norm": 1.2898756265640259,
"learning_rate": 9.605523157182904e-05,
"loss": 2.9767,
"step": 19500
},
{
"epoch": 39.920159680638726,
"grad_norm": 1.3585063219070435,
"learning_rate": 9.513745610578322e-05,
"loss": 2.9549,
"step": 20000
},
{
"epoch": 40.91816367265469,
"grad_norm": 1.3588775396347046,
"learning_rate": 9.412914226495388e-05,
"loss": 2.9349,
"step": 20500
},
{
"epoch": 41.91616766467066,
"grad_norm": 1.2472021579742432,
"learning_rate": 9.303459312750163e-05,
"loss": 2.92,
"step": 21000
},
{
"epoch": 42.91417165668663,
"grad_norm": 1.3725252151489258,
"learning_rate": 9.185161794488783e-05,
"loss": 2.8977,
"step": 21500
},
{
"epoch": 43.91217564870259,
"grad_norm": 1.2629554271697998,
"learning_rate": 9.058469524290322e-05,
"loss": 2.8861,
"step": 22000
},
{
"epoch": 44.91017964071856,
"grad_norm": 1.318297266960144,
"learning_rate": 8.923636626184598e-05,
"loss": 2.8661,
"step": 22500
},
{
"epoch": 45.908183632734534,
"grad_norm": 1.2896426916122437,
"learning_rate": 8.781226625872564e-05,
"loss": 2.8498,
"step": 23000
},
{
"epoch": 46.9061876247505,
"grad_norm": 1.3040919303894043,
"learning_rate": 8.630954488640488e-05,
"loss": 2.8351,
"step": 23500
},
{
"epoch": 47.90419161676647,
"grad_norm": 1.3538358211517334,
"learning_rate": 8.473399248932634e-05,
"loss": 2.8199,
"step": 24000
},
{
"epoch": 48.902195608782435,
"grad_norm": 1.3103379011154175,
"learning_rate": 8.308876936861739e-05,
"loss": 2.8043,
"step": 24500
},
{
"epoch": 49.9001996007984,
"grad_norm": 1.3381751775741577,
"learning_rate": 8.138066273860004e-05,
"loss": 2.7906,
"step": 25000
}
],
"logging_steps": 500,
"max_steps": 50100,
"num_input_tokens_seen": 0,
"num_train_epochs": 100,
"save_steps": 1000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.046659236626432e+17,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}