| { | |
| "best_metric": 0.6012922525405884, | |
| "best_model_checkpoint": "./wav2vec2-large-xlsr-53-common_voice-ja-demo-kana-only/checkpoint-2600", | |
| "epoch": 15.0, | |
| "eval_steps": 100, | |
| "global_step": 5640, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.26595744680851063, | |
| "eval_cer": 0.9998627637760951, | |
| "eval_loss": 6.830887317657471, | |
| "eval_runtime": 235.9339, | |
| "eval_samples_per_second": 21.027, | |
| "eval_steps_per_second": 2.632, | |
| "eval_wer": 1.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5319148936170213, | |
| "eval_cer": 0.9998627637760951, | |
| "eval_loss": 4.129940986633301, | |
| "eval_runtime": 235.1597, | |
| "eval_samples_per_second": 21.096, | |
| "eval_steps_per_second": 2.641, | |
| "eval_wer": 1.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7978723404255319, | |
| "eval_cer": 0.9869302678528182, | |
| "eval_loss": 3.993030309677124, | |
| "eval_runtime": 234.1893, | |
| "eval_samples_per_second": 21.184, | |
| "eval_steps_per_second": 2.652, | |
| "eval_wer": 1.0, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.0638297872340425, | |
| "eval_cer": 0.5876132198847216, | |
| "eval_loss": 2.0400278568267822, | |
| "eval_runtime": 237.5888, | |
| "eval_samples_per_second": 20.881, | |
| "eval_steps_per_second": 2.614, | |
| "eval_wer": 1.0, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.3297872340425532, | |
| "grad_norm": 3.4516775608062744, | |
| "learning_rate": 0.00029759999999999997, | |
| "loss": 7.1041, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.3297872340425532, | |
| "eval_cer": 0.43090559762339153, | |
| "eval_loss": 1.0610116720199585, | |
| "eval_runtime": 241.7004, | |
| "eval_samples_per_second": 20.525, | |
| "eval_steps_per_second": 2.569, | |
| "eval_wer": 1.0, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.5957446808510638, | |
| "eval_cer": 0.39546636097970517, | |
| "eval_loss": 0.8836929798126221, | |
| "eval_runtime": 237.4265, | |
| "eval_samples_per_second": 20.895, | |
| "eval_steps_per_second": 2.616, | |
| "eval_wer": 1.0, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.8617021276595744, | |
| "eval_cer": 0.3790545231444855, | |
| "eval_loss": 0.7705639004707336, | |
| "eval_runtime": 238.309, | |
| "eval_samples_per_second": 20.818, | |
| "eval_steps_per_second": 2.606, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 2.127659574468085, | |
| "eval_cer": 0.3815893569272002, | |
| "eval_loss": 0.766192615032196, | |
| "eval_runtime": 235.61, | |
| "eval_samples_per_second": 21.056, | |
| "eval_steps_per_second": 2.636, | |
| "eval_wer": 1.0, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 2.393617021276596, | |
| "eval_cer": 0.37896572323489996, | |
| "eval_loss": 0.7620505094528198, | |
| "eval_runtime": 237.8852, | |
| "eval_samples_per_second": 20.855, | |
| "eval_steps_per_second": 2.611, | |
| "eval_wer": 1.0, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.6595744680851063, | |
| "grad_norm": 2.764026165008545, | |
| "learning_rate": 0.00027105058365758754, | |
| "loss": 0.803, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.6595744680851063, | |
| "eval_cer": 0.36259424899494647, | |
| "eval_loss": 0.6968890428543091, | |
| "eval_runtime": 238.5042, | |
| "eval_samples_per_second": 20.8, | |
| "eval_steps_per_second": 2.604, | |
| "eval_wer": 1.0, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.925531914893617, | |
| "eval_cer": 0.3572904725769734, | |
| "eval_loss": 0.6735507249832153, | |
| "eval_runtime": 242.6929, | |
| "eval_samples_per_second": 20.441, | |
| "eval_steps_per_second": 2.559, | |
| "eval_wer": 1.0, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 3.1914893617021276, | |
| "eval_cer": 0.3543762209987568, | |
| "eval_loss": 0.6823433637619019, | |
| "eval_runtime": 250.863, | |
| "eval_samples_per_second": 19.776, | |
| "eval_steps_per_second": 2.475, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 3.4574468085106385, | |
| "eval_cer": 0.3460209567786622, | |
| "eval_loss": 0.6359558701515198, | |
| "eval_runtime": 237.6152, | |
| "eval_samples_per_second": 20.878, | |
| "eval_steps_per_second": 2.613, | |
| "eval_wer": 1.0, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 3.723404255319149, | |
| "eval_cer": 0.34429339490127064, | |
| "eval_loss": 0.6503622531890869, | |
| "eval_runtime": 235.7171, | |
| "eval_samples_per_second": 21.046, | |
| "eval_steps_per_second": 2.635, | |
| "eval_wer": 1.0, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 3.9893617021276597, | |
| "grad_norm": 1.9848517179489136, | |
| "learning_rate": 0.00024186770428015562, | |
| "loss": 0.5675, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 3.9893617021276597, | |
| "eval_cer": 0.34139528876116054, | |
| "eval_loss": 0.6246533393859863, | |
| "eval_runtime": 239.1195, | |
| "eval_samples_per_second": 20.747, | |
| "eval_steps_per_second": 2.597, | |
| "eval_wer": 1.0, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 4.25531914893617, | |
| "eval_cer": 0.3424851058333468, | |
| "eval_loss": 0.6397080421447754, | |
| "eval_runtime": 242.7125, | |
| "eval_samples_per_second": 20.44, | |
| "eval_steps_per_second": 2.559, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 4.5212765957446805, | |
| "eval_cer": 0.3439462679819817, | |
| "eval_loss": 0.6589427590370178, | |
| "eval_runtime": 243.7764, | |
| "eval_samples_per_second": 20.351, | |
| "eval_steps_per_second": 2.547, | |
| "eval_wer": 1.0, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 4.787234042553192, | |
| "eval_cer": 0.3449472851445824, | |
| "eval_loss": 0.6345330476760864, | |
| "eval_runtime": 237.3086, | |
| "eval_samples_per_second": 20.905, | |
| "eval_steps_per_second": 2.617, | |
| "eval_wer": 1.0, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 5.053191489361702, | |
| "eval_cer": 0.3379805286016436, | |
| "eval_loss": 0.652181088924408, | |
| "eval_runtime": 240.2379, | |
| "eval_samples_per_second": 20.65, | |
| "eval_steps_per_second": 2.585, | |
| "eval_wer": 0.999596855472687, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 5.319148936170213, | |
| "grad_norm": 2.756148099899292, | |
| "learning_rate": 0.00021268482490272372, | |
| "loss": 0.4421, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.319148936170213, | |
| "eval_cer": 0.3371732566963205, | |
| "eval_loss": 0.6292724609375, | |
| "eval_runtime": 240.5588, | |
| "eval_samples_per_second": 20.623, | |
| "eval_steps_per_second": 2.581, | |
| "eval_wer": 1.0, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 5.585106382978723, | |
| "eval_cer": 0.3342428596799974, | |
| "eval_loss": 0.6095719337463379, | |
| "eval_runtime": 241.1797, | |
| "eval_samples_per_second": 20.57, | |
| "eval_steps_per_second": 2.575, | |
| "eval_wer": 1.0, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 5.851063829787234, | |
| "eval_cer": 0.3320712982546781, | |
| "eval_loss": 0.6107529401779175, | |
| "eval_runtime": 238.2079, | |
| "eval_samples_per_second": 20.826, | |
| "eval_steps_per_second": 2.607, | |
| "eval_wer": 1.0, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 6.117021276595745, | |
| "eval_cer": 0.3354295493808224, | |
| "eval_loss": 0.6200144290924072, | |
| "eval_runtime": 235.9894, | |
| "eval_samples_per_second": 21.022, | |
| "eval_steps_per_second": 2.631, | |
| "eval_wer": 1.0, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 6.382978723404255, | |
| "eval_cer": 0.33407333257987953, | |
| "eval_loss": 0.6413326263427734, | |
| "eval_runtime": 236.6024, | |
| "eval_samples_per_second": 20.968, | |
| "eval_steps_per_second": 2.625, | |
| "eval_wer": 1.0, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 6.648936170212766, | |
| "grad_norm": 4.183356761932373, | |
| "learning_rate": 0.00018350194552529183, | |
| "loss": 0.3699, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.648936170212766, | |
| "eval_cer": 0.3359462034002293, | |
| "eval_loss": 0.6303403973579407, | |
| "eval_runtime": 237.052, | |
| "eval_samples_per_second": 20.928, | |
| "eval_steps_per_second": 2.62, | |
| "eval_wer": 0.999596855472687, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 6.914893617021277, | |
| "eval_cer": 0.3307796632061611, | |
| "eval_loss": 0.6012922525405884, | |
| "eval_runtime": 233.4251, | |
| "eval_samples_per_second": 21.253, | |
| "eval_steps_per_second": 2.66, | |
| "eval_wer": 1.0, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 7.180851063829787, | |
| "eval_cer": 0.32859195634273536, | |
| "eval_loss": 0.634281575679779, | |
| "eval_runtime": 232.2994, | |
| "eval_samples_per_second": 21.356, | |
| "eval_steps_per_second": 2.673, | |
| "eval_wer": 1.0, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 7.446808510638298, | |
| "eval_cer": 0.3260086862457013, | |
| "eval_loss": 0.6208234429359436, | |
| "eval_runtime": 235.1613, | |
| "eval_samples_per_second": 21.096, | |
| "eval_steps_per_second": 2.641, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 7.712765957446808, | |
| "eval_cer": 0.3287291925666403, | |
| "eval_loss": 0.6095162034034729, | |
| "eval_runtime": 241.6677, | |
| "eval_samples_per_second": 20.528, | |
| "eval_steps_per_second": 2.57, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 7.9787234042553195, | |
| "grad_norm": 1.701768159866333, | |
| "learning_rate": 0.0001543190661478599, | |
| "loss": 0.3146, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 7.9787234042553195, | |
| "eval_cer": 0.3265818492984807, | |
| "eval_loss": 0.6058351397514343, | |
| "eval_runtime": 235.659, | |
| "eval_samples_per_second": 21.052, | |
| "eval_steps_per_second": 2.635, | |
| "eval_wer": 0.999596855472687, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 8.24468085106383, | |
| "eval_cer": 0.3251368325879523, | |
| "eval_loss": 0.6612707376480103, | |
| "eval_runtime": 233.8878, | |
| "eval_samples_per_second": 21.211, | |
| "eval_steps_per_second": 2.655, | |
| "eval_wer": 0.999596855472687, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 8.51063829787234, | |
| "eval_cer": 0.3244022151541082, | |
| "eval_loss": 0.6538846492767334, | |
| "eval_runtime": 235.5702, | |
| "eval_samples_per_second": 21.06, | |
| "eval_steps_per_second": 2.636, | |
| "eval_wer": 1.0, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 8.77659574468085, | |
| "eval_cer": 0.32638810404120316, | |
| "eval_loss": 0.6331284046173096, | |
| "eval_runtime": 236.8675, | |
| "eval_samples_per_second": 20.944, | |
| "eval_steps_per_second": 2.622, | |
| "eval_wer": 1.0, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 9.042553191489361, | |
| "eval_cer": 0.32281996221967485, | |
| "eval_loss": 0.6436325907707214, | |
| "eval_runtime": 236.1998, | |
| "eval_samples_per_second": 21.003, | |
| "eval_steps_per_second": 2.629, | |
| "eval_wer": 1.0, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 9.308510638297872, | |
| "grad_norm": 1.067522406578064, | |
| "learning_rate": 0.000125136186770428, | |
| "loss": 0.2576, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 9.308510638297872, | |
| "eval_cer": 0.32351421605825276, | |
| "eval_loss": 0.6328682899475098, | |
| "eval_runtime": 234.2706, | |
| "eval_samples_per_second": 21.176, | |
| "eval_steps_per_second": 2.651, | |
| "eval_wer": 1.0, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 9.574468085106384, | |
| "eval_cer": 0.3196958199460742, | |
| "eval_loss": 0.6314510703086853, | |
| "eval_runtime": 234.3665, | |
| "eval_samples_per_second": 21.168, | |
| "eval_steps_per_second": 2.65, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 9.840425531914894, | |
| "eval_cer": 0.32033356475127955, | |
| "eval_loss": 0.6280702352523804, | |
| "eval_runtime": 236.442, | |
| "eval_samples_per_second": 20.982, | |
| "eval_steps_per_second": 2.626, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 10.106382978723405, | |
| "eval_cer": 0.3196473836317548, | |
| "eval_loss": 0.6696433424949646, | |
| "eval_runtime": 232.6849, | |
| "eval_samples_per_second": 21.321, | |
| "eval_steps_per_second": 2.669, | |
| "eval_wer": 0.999596855472687, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 10.372340425531915, | |
| "eval_cer": 0.3199218560795647, | |
| "eval_loss": 0.6629988551139832, | |
| "eval_runtime": 233.1379, | |
| "eval_samples_per_second": 21.279, | |
| "eval_steps_per_second": 2.664, | |
| "eval_wer": 0.999596855472687, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 10.638297872340425, | |
| "grad_norm": 1.6601381301879883, | |
| "learning_rate": 9.595330739299609e-05, | |
| "loss": 0.2201, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 10.638297872340425, | |
| "eval_cer": 0.3203093465941198, | |
| "eval_loss": 0.6781216859817505, | |
| "eval_runtime": 232.2432, | |
| "eval_samples_per_second": 21.361, | |
| "eval_steps_per_second": 2.674, | |
| "eval_wer": 1.0, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 10.904255319148936, | |
| "eval_cer": 0.31962316547459513, | |
| "eval_loss": 0.6531046628952026, | |
| "eval_runtime": 239.9955, | |
| "eval_samples_per_second": 20.671, | |
| "eval_steps_per_second": 2.588, | |
| "eval_wer": 1.0, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 11.170212765957446, | |
| "eval_cer": 0.3192598931171997, | |
| "eval_loss": 0.6762946248054504, | |
| "eval_runtime": 235.4369, | |
| "eval_samples_per_second": 21.071, | |
| "eval_steps_per_second": 2.638, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 11.436170212765958, | |
| "eval_cer": 0.3184364757737701, | |
| "eval_loss": 0.6785323023796082, | |
| "eval_runtime": 232.8132, | |
| "eval_samples_per_second": 21.309, | |
| "eval_steps_per_second": 2.667, | |
| "eval_wer": 1.0, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 11.702127659574469, | |
| "eval_cer": 0.31793596719246975, | |
| "eval_loss": 0.666408360004425, | |
| "eval_runtime": 232.0593, | |
| "eval_samples_per_second": 21.378, | |
| "eval_steps_per_second": 2.676, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 11.96808510638298, | |
| "grad_norm": 0.7692495584487915, | |
| "learning_rate": 6.67704280155642e-05, | |
| "loss": 0.1931, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 11.96808510638298, | |
| "eval_cer": 0.31842033033566364, | |
| "eval_loss": 0.6682071089744568, | |
| "eval_runtime": 235.6644, | |
| "eval_samples_per_second": 21.051, | |
| "eval_steps_per_second": 2.635, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 12.23404255319149, | |
| "eval_cer": 0.3168219319631238, | |
| "eval_loss": 0.6799555420875549, | |
| "eval_runtime": 235.3483, | |
| "eval_samples_per_second": 21.079, | |
| "eval_steps_per_second": 2.639, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 12.5, | |
| "eval_cer": 0.3162245507531847, | |
| "eval_loss": 0.6925452351570129, | |
| "eval_runtime": 235.4523, | |
| "eval_samples_per_second": 21.07, | |
| "eval_steps_per_second": 2.637, | |
| "eval_wer": 1.0, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 12.76595744680851, | |
| "eval_cer": 0.3144646979995802, | |
| "eval_loss": 0.7046905159950256, | |
| "eval_runtime": 235.1343, | |
| "eval_samples_per_second": 21.099, | |
| "eval_steps_per_second": 2.641, | |
| "eval_wer": 1.0, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 13.03191489361702, | |
| "eval_cer": 0.3147230250092836, | |
| "eval_loss": 0.6918711066246033, | |
| "eval_runtime": 238.6326, | |
| "eval_samples_per_second": 20.789, | |
| "eval_steps_per_second": 2.602, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 13.297872340425531, | |
| "grad_norm": 1.052759051322937, | |
| "learning_rate": 3.758754863813229e-05, | |
| "loss": 0.1694, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 13.297872340425531, | |
| "eval_cer": 0.31423866186608973, | |
| "eval_loss": 0.699897289276123, | |
| "eval_runtime": 256.2343, | |
| "eval_samples_per_second": 19.361, | |
| "eval_steps_per_second": 2.424, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 13.563829787234042, | |
| "eval_cer": 0.3134394626798198, | |
| "eval_loss": 0.6994884610176086, | |
| "eval_runtime": 236.0872, | |
| "eval_samples_per_second": 21.013, | |
| "eval_steps_per_second": 2.63, | |
| "eval_wer": 1.0, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 13.829787234042554, | |
| "eval_cer": 0.3133829536464472, | |
| "eval_loss": 0.6916852593421936, | |
| "eval_runtime": 234.7745, | |
| "eval_samples_per_second": 21.131, | |
| "eval_steps_per_second": 2.645, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 14.095744680851064, | |
| "eval_cer": 0.3128501541889339, | |
| "eval_loss": 0.6962644457817078, | |
| "eval_runtime": 235.7153, | |
| "eval_samples_per_second": 21.047, | |
| "eval_steps_per_second": 2.635, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 14.361702127659575, | |
| "eval_cer": 0.3128259360317742, | |
| "eval_loss": 0.6961241960525513, | |
| "eval_runtime": 245.639, | |
| "eval_samples_per_second": 20.196, | |
| "eval_steps_per_second": 2.528, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 14.627659574468085, | |
| "grad_norm": 2.195582389831543, | |
| "learning_rate": 8.404669260700388e-06, | |
| "loss": 0.1548, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 14.627659574468085, | |
| "eval_cer": 0.31290666322230654, | |
| "eval_loss": 0.6963828802108765, | |
| "eval_runtime": 237.6797, | |
| "eval_samples_per_second": 20.873, | |
| "eval_steps_per_second": 2.613, | |
| "eval_wer": 1.0, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 14.893617021276595, | |
| "eval_cer": 0.3126725543697628, | |
| "eval_loss": 0.6983669400215149, | |
| "eval_runtime": 245.8138, | |
| "eval_samples_per_second": 20.182, | |
| "eval_steps_per_second": 2.526, | |
| "eval_wer": 0.9997984277363435, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "step": 5640, | |
| "total_flos": 2.6348448154740388e+19, | |
| "train_loss": 0.9431738045198698, | |
| "train_runtime": 36296.3273, | |
| "train_samples_per_second": 4.972, | |
| "train_steps_per_second": 0.155 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 5640, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 15, | |
| "save_steps": 400, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.6348448154740388e+19, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |