| { |
| "best_global_step": 8000, |
| "best_metric": 0.09730422496795654, |
| "best_model_checkpoint": "./mt5_latin_punctuator_large/checkpoint-8000", |
| "epoch": 1.6045835213880948, |
| "eval_steps": 1000, |
| "global_step": 8000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.020059174564966652, |
| "grad_norm": 13.09343147277832, |
| "learning_rate": 4.9669073405535504e-05, |
| "loss": 15.4848, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.040118349129933305, |
| "grad_norm": 0.4526735842227936, |
| "learning_rate": 4.9334804118197625e-05, |
| "loss": 0.66, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.060177523694899954, |
| "grad_norm": 0.4390902817249298, |
| "learning_rate": 4.900053483085975e-05, |
| "loss": 0.385, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.08023669825986661, |
| "grad_norm": 0.3624674677848816, |
| "learning_rate": 4.866626554352187e-05, |
| "loss": 0.3017, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.10029587282483325, |
| "grad_norm": 0.2848065197467804, |
| "learning_rate": 4.833199625618399e-05, |
| "loss": 0.2648, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.12035504738979991, |
| "grad_norm": 0.2836224138736725, |
| "learning_rate": 4.7997726968846105e-05, |
| "loss": 0.2419, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.14041422195476655, |
| "grad_norm": 0.3000536561012268, |
| "learning_rate": 4.7663457681508226e-05, |
| "loss": 0.2238, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.16047339651973322, |
| "grad_norm": 0.6995307803153992, |
| "learning_rate": 4.732918839417035e-05, |
| "loss": 0.2157, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.18053257108469986, |
| "grad_norm": 0.1916164755821228, |
| "learning_rate": 4.699491910683247e-05, |
| "loss": 0.2061, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.2005917456496665, |
| "grad_norm": 0.3005019426345825, |
| "learning_rate": 4.666064981949459e-05, |
| "loss": 0.2001, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.2005917456496665, |
| "eval_loss": 0.1447821706533432, |
| "eval_runtime": 687.5913, |
| "eval_samples_per_second": 25.778, |
| "eval_steps_per_second": 6.446, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.22065092021463317, |
| "grad_norm": 0.34013351798057556, |
| "learning_rate": 4.632638053215671e-05, |
| "loss": 0.1911, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.24071009477959981, |
| "grad_norm": 0.19066131114959717, |
| "learning_rate": 4.5992111244818834e-05, |
| "loss": 0.1868, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.26076926934456646, |
| "grad_norm": 0.1935589760541916, |
| "learning_rate": 4.565784195748095e-05, |
| "loss": 0.1828, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.2808284439095331, |
| "grad_norm": 0.31047841906547546, |
| "learning_rate": 4.532357267014307e-05, |
| "loss": 0.1798, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.3008876184744998, |
| "grad_norm": 0.24223153293132782, |
| "learning_rate": 4.498930338280519e-05, |
| "loss": 0.1751, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.32094679303946644, |
| "grad_norm": 1.5393741130828857, |
| "learning_rate": 4.465503409546731e-05, |
| "loss": 0.1704, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.3410059676044331, |
| "grad_norm": 0.21514640748500824, |
| "learning_rate": 4.4320764808129435e-05, |
| "loss": 0.1689, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.3610651421693997, |
| "grad_norm": 0.17480678856372833, |
| "learning_rate": 4.3986495520791556e-05, |
| "loss": 0.1664, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.38112431673436636, |
| "grad_norm": 0.1928788721561432, |
| "learning_rate": 4.365222623345368e-05, |
| "loss": 0.1646, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.401183491299333, |
| "grad_norm": 0.20150336623191833, |
| "learning_rate": 4.331795694611579e-05, |
| "loss": 0.1616, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.401183491299333, |
| "eval_loss": 0.11908746510744095, |
| "eval_runtime": 687.2579, |
| "eval_samples_per_second": 25.791, |
| "eval_steps_per_second": 6.449, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.4212426658642997, |
| "grad_norm": 0.17183753848075867, |
| "learning_rate": 4.2983687658777914e-05, |
| "loss": 0.1632, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.44130184042926635, |
| "grad_norm": 0.2742299735546112, |
| "learning_rate": 4.2649418371440035e-05, |
| "loss": 0.1578, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.461361014994233, |
| "grad_norm": 0.22588330507278442, |
| "learning_rate": 4.231514908410216e-05, |
| "loss": 0.1563, |
| "step": 2300 |
| }, |
| { |
| "epoch": 0.48142018955919963, |
| "grad_norm": 0.25857874751091003, |
| "learning_rate": 4.198087979676428e-05, |
| "loss": 0.1536, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.5014793641241663, |
| "grad_norm": 0.2725016474723816, |
| "learning_rate": 4.16466105094264e-05, |
| "loss": 0.155, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.5215385386891329, |
| "grad_norm": 0.14976142346858978, |
| "learning_rate": 4.131234122208852e-05, |
| "loss": 0.1507, |
| "step": 2600 |
| }, |
| { |
| "epoch": 0.5415977132540996, |
| "grad_norm": 0.16467268764972687, |
| "learning_rate": 4.0978071934750636e-05, |
| "loss": 0.1505, |
| "step": 2700 |
| }, |
| { |
| "epoch": 0.5616568878190662, |
| "grad_norm": 0.16063468158245087, |
| "learning_rate": 4.064380264741276e-05, |
| "loss": 0.147, |
| "step": 2800 |
| }, |
| { |
| "epoch": 0.581716062384033, |
| "grad_norm": 0.23703046143054962, |
| "learning_rate": 4.030953336007488e-05, |
| "loss": 0.1445, |
| "step": 2900 |
| }, |
| { |
| "epoch": 0.6017752369489996, |
| "grad_norm": 0.194139301776886, |
| "learning_rate": 3.9975264072737e-05, |
| "loss": 0.1444, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.6017752369489996, |
| "eval_loss": 0.11365870386362076, |
| "eval_runtime": 687.3052, |
| "eval_samples_per_second": 25.789, |
| "eval_steps_per_second": 6.448, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.6218344115139662, |
| "grad_norm": 0.2936673164367676, |
| "learning_rate": 3.964099478539912e-05, |
| "loss": 0.1443, |
| "step": 3100 |
| }, |
| { |
| "epoch": 0.6418935860789329, |
| "grad_norm": 0.15139873325824738, |
| "learning_rate": 3.9306725498061244e-05, |
| "loss": 0.1415, |
| "step": 3200 |
| }, |
| { |
| "epoch": 0.6619527606438995, |
| "grad_norm": 0.22842614352703094, |
| "learning_rate": 3.8972456210723365e-05, |
| "loss": 0.141, |
| "step": 3300 |
| }, |
| { |
| "epoch": 0.6820119352088662, |
| "grad_norm": 0.17998695373535156, |
| "learning_rate": 3.863818692338548e-05, |
| "loss": 0.1423, |
| "step": 3400 |
| }, |
| { |
| "epoch": 0.7020711097738328, |
| "grad_norm": 0.18952590227127075, |
| "learning_rate": 3.83039176360476e-05, |
| "loss": 0.1388, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.7221302843387994, |
| "grad_norm": 0.11938633769750595, |
| "learning_rate": 3.796964834870972e-05, |
| "loss": 0.1378, |
| "step": 3600 |
| }, |
| { |
| "epoch": 0.7421894589037661, |
| "grad_norm": 0.1671166867017746, |
| "learning_rate": 3.7635379061371845e-05, |
| "loss": 0.1389, |
| "step": 3700 |
| }, |
| { |
| "epoch": 0.7622486334687327, |
| "grad_norm": 0.1272394061088562, |
| "learning_rate": 3.7301109774033966e-05, |
| "loss": 0.1362, |
| "step": 3800 |
| }, |
| { |
| "epoch": 0.7823078080336994, |
| "grad_norm": 0.19626741111278534, |
| "learning_rate": 3.696684048669609e-05, |
| "loss": 0.1377, |
| "step": 3900 |
| }, |
| { |
| "epoch": 0.802366982598666, |
| "grad_norm": 0.3008900284767151, |
| "learning_rate": 3.663257119935821e-05, |
| "loss": 0.1347, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.802366982598666, |
| "eval_loss": 0.10825913399457932, |
| "eval_runtime": 687.2417, |
| "eval_samples_per_second": 25.792, |
| "eval_steps_per_second": 6.449, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.8224261571636328, |
| "grad_norm": 0.45567601919174194, |
| "learning_rate": 3.6298301912020324e-05, |
| "loss": 0.1363, |
| "step": 4100 |
| }, |
| { |
| "epoch": 0.8424853317285994, |
| "grad_norm": 0.17759402096271515, |
| "learning_rate": 3.5964032624682446e-05, |
| "loss": 0.1358, |
| "step": 4200 |
| }, |
| { |
| "epoch": 0.862544506293566, |
| "grad_norm": 0.15186358988285065, |
| "learning_rate": 3.562976333734457e-05, |
| "loss": 0.1365, |
| "step": 4300 |
| }, |
| { |
| "epoch": 0.8826036808585327, |
| "grad_norm": 0.20942702889442444, |
| "learning_rate": 3.529549405000669e-05, |
| "loss": 0.1341, |
| "step": 4400 |
| }, |
| { |
| "epoch": 0.9026628554234993, |
| "grad_norm": 0.37031808495521545, |
| "learning_rate": 3.496122476266881e-05, |
| "loss": 0.1325, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.922722029988466, |
| "grad_norm": 0.13902556896209717, |
| "learning_rate": 3.462695547533093e-05, |
| "loss": 0.1305, |
| "step": 4600 |
| }, |
| { |
| "epoch": 0.9427812045534326, |
| "grad_norm": 0.48744386434555054, |
| "learning_rate": 3.429268618799305e-05, |
| "loss": 0.1315, |
| "step": 4700 |
| }, |
| { |
| "epoch": 0.9628403791183993, |
| "grad_norm": 0.164585679769516, |
| "learning_rate": 3.395841690065517e-05, |
| "loss": 0.1307, |
| "step": 4800 |
| }, |
| { |
| "epoch": 0.9828995536833659, |
| "grad_norm": 0.2665926218032837, |
| "learning_rate": 3.362414761331729e-05, |
| "loss": 0.1295, |
| "step": 4900 |
| }, |
| { |
| "epoch": 1.0028082844390953, |
| "grad_norm": 0.16074395179748535, |
| "learning_rate": 3.328987832597941e-05, |
| "loss": 0.1285, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.0028082844390953, |
| "eval_loss": 0.1043267473578453, |
| "eval_runtime": 687.1542, |
| "eval_samples_per_second": 25.795, |
| "eval_steps_per_second": 6.45, |
| "step": 5000 |
| }, |
| { |
| "epoch": 1.022867459004062, |
| "grad_norm": 0.20015545189380646, |
| "learning_rate": 3.295560903864153e-05, |
| "loss": 0.1275, |
| "step": 5100 |
| }, |
| { |
| "epoch": 1.0429266335690286, |
| "grad_norm": 0.13576115667819977, |
| "learning_rate": 3.2621339751303654e-05, |
| "loss": 0.1269, |
| "step": 5200 |
| }, |
| { |
| "epoch": 1.0629858081339953, |
| "grad_norm": 0.12735939025878906, |
| "learning_rate": 3.2287070463965776e-05, |
| "loss": 0.1265, |
| "step": 5300 |
| }, |
| { |
| "epoch": 1.0830449826989619, |
| "grad_norm": 0.13942281901836395, |
| "learning_rate": 3.19528011766279e-05, |
| "loss": 0.1264, |
| "step": 5400 |
| }, |
| { |
| "epoch": 1.1031041572639286, |
| "grad_norm": 0.15262341499328613, |
| "learning_rate": 3.161853188929001e-05, |
| "loss": 0.1253, |
| "step": 5500 |
| }, |
| { |
| "epoch": 1.1231633318288952, |
| "grad_norm": 0.1289774477481842, |
| "learning_rate": 3.1284262601952133e-05, |
| "loss": 0.1252, |
| "step": 5600 |
| }, |
| { |
| "epoch": 1.143222506393862, |
| "grad_norm": 0.13571390509605408, |
| "learning_rate": 3.0949993314614255e-05, |
| "loss": 0.1239, |
| "step": 5700 |
| }, |
| { |
| "epoch": 1.1632816809588284, |
| "grad_norm": 0.13661526143550873, |
| "learning_rate": 3.0615724027276377e-05, |
| "loss": 0.125, |
| "step": 5800 |
| }, |
| { |
| "epoch": 1.1833408555237952, |
| "grad_norm": 0.20611687004566193, |
| "learning_rate": 3.0281454739938498e-05, |
| "loss": 0.1242, |
| "step": 5900 |
| }, |
| { |
| "epoch": 1.203400030088762, |
| "grad_norm": 0.12380609661340714, |
| "learning_rate": 2.994718545260062e-05, |
| "loss": 0.1231, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.203400030088762, |
| "eval_loss": 0.10073110461235046, |
| "eval_runtime": 687.1346, |
| "eval_samples_per_second": 25.796, |
| "eval_steps_per_second": 6.45, |
| "step": 6000 |
| }, |
| { |
| "epoch": 1.2234592046537285, |
| "grad_norm": 0.1408674120903015, |
| "learning_rate": 2.9612916165262738e-05, |
| "loss": 0.1245, |
| "step": 6100 |
| }, |
| { |
| "epoch": 1.2435183792186952, |
| "grad_norm": 0.14142949879169464, |
| "learning_rate": 2.927864687792486e-05, |
| "loss": 0.1218, |
| "step": 6200 |
| }, |
| { |
| "epoch": 1.2635775537836618, |
| "grad_norm": 0.13047949969768524, |
| "learning_rate": 2.894437759058698e-05, |
| "loss": 0.121, |
| "step": 6300 |
| }, |
| { |
| "epoch": 1.2836367283486285, |
| "grad_norm": 5.7425217628479, |
| "learning_rate": 2.86101083032491e-05, |
| "loss": 0.1207, |
| "step": 6400 |
| }, |
| { |
| "epoch": 1.303695902913595, |
| "grad_norm": 0.28052738308906555, |
| "learning_rate": 2.827583901591122e-05, |
| "loss": 0.12, |
| "step": 6500 |
| }, |
| { |
| "epoch": 1.3237550774785618, |
| "grad_norm": 0.13514311611652374, |
| "learning_rate": 2.7941569728573342e-05, |
| "loss": 0.1199, |
| "step": 6600 |
| }, |
| { |
| "epoch": 1.3438142520435283, |
| "grad_norm": 0.14283640682697296, |
| "learning_rate": 2.7607300441235463e-05, |
| "loss": 0.1197, |
| "step": 6700 |
| }, |
| { |
| "epoch": 1.363873426608495, |
| "grad_norm": 0.14133544266223907, |
| "learning_rate": 2.727303115389758e-05, |
| "loss": 0.1201, |
| "step": 6800 |
| }, |
| { |
| "epoch": 1.3839326011734618, |
| "grad_norm": 0.20595553517341614, |
| "learning_rate": 2.6938761866559703e-05, |
| "loss": 0.1213, |
| "step": 6900 |
| }, |
| { |
| "epoch": 1.4039917757384284, |
| "grad_norm": 0.133372962474823, |
| "learning_rate": 2.6604492579221825e-05, |
| "loss": 0.118, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.4039917757384284, |
| "eval_loss": 0.09819206595420837, |
| "eval_runtime": 687.1022, |
| "eval_samples_per_second": 25.797, |
| "eval_steps_per_second": 6.45, |
| "step": 7000 |
| }, |
| { |
| "epoch": 1.424050950303395, |
| "grad_norm": 0.21542303264141083, |
| "learning_rate": 2.6270223291883943e-05, |
| "loss": 0.1215, |
| "step": 7100 |
| }, |
| { |
| "epoch": 1.4441101248683617, |
| "grad_norm": 0.24275696277618408, |
| "learning_rate": 2.5935954004546064e-05, |
| "loss": 0.1187, |
| "step": 7200 |
| }, |
| { |
| "epoch": 1.4641692994333284, |
| "grad_norm": 0.14183971285820007, |
| "learning_rate": 2.5601684717208186e-05, |
| "loss": 0.1173, |
| "step": 7300 |
| }, |
| { |
| "epoch": 1.484228473998295, |
| "grad_norm": 0.11123021692037582, |
| "learning_rate": 2.5267415429870307e-05, |
| "loss": 0.1167, |
| "step": 7400 |
| }, |
| { |
| "epoch": 1.5042876485632615, |
| "grad_norm": 0.1129390299320221, |
| "learning_rate": 2.4933146142532426e-05, |
| "loss": 0.1196, |
| "step": 7500 |
| }, |
| { |
| "epoch": 1.5243468231282282, |
| "grad_norm": 0.1165638417005539, |
| "learning_rate": 2.4598876855194547e-05, |
| "loss": 0.1186, |
| "step": 7600 |
| }, |
| { |
| "epoch": 1.544405997693195, |
| "grad_norm": 0.3278215527534485, |
| "learning_rate": 2.426460756785667e-05, |
| "loss": 0.1161, |
| "step": 7700 |
| }, |
| { |
| "epoch": 1.5644651722581617, |
| "grad_norm": 0.2158752679824829, |
| "learning_rate": 2.3930338280518787e-05, |
| "loss": 0.1184, |
| "step": 7800 |
| }, |
| { |
| "epoch": 1.5845243468231283, |
| "grad_norm": 0.16784250736236572, |
| "learning_rate": 2.3596068993180908e-05, |
| "loss": 0.118, |
| "step": 7900 |
| }, |
| { |
| "epoch": 1.6045835213880948, |
| "grad_norm": 0.16192170977592468, |
| "learning_rate": 2.326179970584303e-05, |
| "loss": 0.1154, |
| "step": 8000 |
| }, |
| { |
| "epoch": 1.6045835213880948, |
| "eval_loss": 0.09730422496795654, |
| "eval_runtime": 687.1621, |
| "eval_samples_per_second": 25.794, |
| "eval_steps_per_second": 6.45, |
| "step": 8000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 14958, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 1.5259044426479616e+18, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
