| { | |
| "best_metric": 6.002164840698242, | |
| "best_model_checkpoint": "distilbert_lda_100_v1/checkpoint-50000", | |
| "epoch": 25.0, | |
| "eval_steps": 10000, | |
| "global_step": 59550, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.20990764063811923, | |
| "grad_norm": 1.8170679807662964, | |
| "learning_rate": 5e-06, | |
| "loss": 13.8015, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.41981528127623846, | |
| "grad_norm": 1.1163582801818848, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9821, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6297229219143576, | |
| "grad_norm": 0.9382531642913818, | |
| "learning_rate": 1.5e-05, | |
| "loss": 11.5028, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.8396305625524769, | |
| "grad_norm": 0.9157293438911438, | |
| "learning_rate": 2e-05, | |
| "loss": 11.3516, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0495382031905962, | |
| "grad_norm": 1.1400713920593262, | |
| "learning_rate": 2.5e-05, | |
| "loss": 11.2469, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.2594458438287153, | |
| "grad_norm": 1.0431565046310425, | |
| "learning_rate": 3e-05, | |
| "loss": 11.1525, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.4693534844668346, | |
| "grad_norm": 0.9461675882339478, | |
| "learning_rate": 3.5e-05, | |
| "loss": 11.0751, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.6792611251049538, | |
| "grad_norm": 0.9238805770874023, | |
| "learning_rate": 4e-05, | |
| "loss": 11.0176, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.8891687657430731, | |
| "grad_norm": 0.9048447012901306, | |
| "learning_rate": 4.5e-05, | |
| "loss": 10.9682, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.0990764063811924, | |
| "grad_norm": 0.8827895522117615, | |
| "learning_rate": 5e-05, | |
| "loss": 10.922, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.3089840470193117, | |
| "grad_norm": 0.8999706506729126, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 10.8833, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 2.5188916876574305, | |
| "grad_norm": 0.8498984575271606, | |
| "learning_rate": 6e-05, | |
| "loss": 10.8491, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.72879932829555, | |
| "grad_norm": 0.828645646572113, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 10.8167, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.938706968933669, | |
| "grad_norm": 0.8627983331680298, | |
| "learning_rate": 7e-05, | |
| "loss": 10.7889, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 3.1486146095717884, | |
| "grad_norm": 0.7841621041297913, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.7629, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 3.3585222502099077, | |
| "grad_norm": 0.8292039036750793, | |
| "learning_rate": 8e-05, | |
| "loss": 10.7422, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 3.568429890848027, | |
| "grad_norm": 0.8942447304725647, | |
| "learning_rate": 8.5e-05, | |
| "loss": 10.7272, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 3.7783375314861463, | |
| "grad_norm": 0.7622050642967224, | |
| "learning_rate": 9e-05, | |
| "loss": 10.7021, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.988245172124265, | |
| "grad_norm": 0.802660346031189, | |
| "learning_rate": 9.5e-05, | |
| "loss": 10.6744, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 4.198152812762385, | |
| "grad_norm": 0.7919928431510925, | |
| "learning_rate": 0.0001, | |
| "loss": 10.6393, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.198152812762385, | |
| "eval_accuracy": 0.15217451793316453, | |
| "eval_loss": 10.570717811584473, | |
| "eval_runtime": 1.3215, | |
| "eval_samples_per_second": 362.455, | |
| "eval_steps_per_second": 3.783, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 4.408060453400504, | |
| "grad_norm": 0.8470991253852844, | |
| "learning_rate": 9.899091826437942e-05, | |
| "loss": 10.5992, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 4.617968094038623, | |
| "grad_norm": 0.8414509892463684, | |
| "learning_rate": 9.798183652875883e-05, | |
| "loss": 10.5451, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 4.827875734676742, | |
| "grad_norm": 0.889491856098175, | |
| "learning_rate": 9.697275479313825e-05, | |
| "loss": 10.4816, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 5.037783375314861, | |
| "grad_norm": 0.9530637264251709, | |
| "learning_rate": 9.596367305751767e-05, | |
| "loss": 10.3501, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 5.247691015952981, | |
| "grad_norm": 0.9737921357154846, | |
| "learning_rate": 9.495459132189707e-05, | |
| "loss": 10.2059, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 5.4575986565911, | |
| "grad_norm": 0.990348756313324, | |
| "learning_rate": 9.394550958627649e-05, | |
| "loss": 10.0769, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 5.667506297229219, | |
| "grad_norm": 1.0464961528778076, | |
| "learning_rate": 9.293642785065591e-05, | |
| "loss": 9.9826, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 5.877413937867338, | |
| "grad_norm": 1.11197030544281, | |
| "learning_rate": 9.192734611503532e-05, | |
| "loss": 9.9089, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 6.087321578505458, | |
| "grad_norm": 1.1564216613769531, | |
| "learning_rate": 9.091826437941474e-05, | |
| "loss": 9.7827, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 6.297229219143577, | |
| "grad_norm": 1.2141942977905273, | |
| "learning_rate": 8.990918264379415e-05, | |
| "loss": 9.6616, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 6.507136859781696, | |
| "grad_norm": 1.3060942888259888, | |
| "learning_rate": 8.890010090817356e-05, | |
| "loss": 9.5685, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 6.717044500419815, | |
| "grad_norm": 1.6777979135513306, | |
| "learning_rate": 8.789101917255298e-05, | |
| "loss": 9.3509, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 6.926952141057934, | |
| "grad_norm": 2.0054266452789307, | |
| "learning_rate": 8.68819374369324e-05, | |
| "loss": 9.0596, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 7.136859781696054, | |
| "grad_norm": 2.0553789138793945, | |
| "learning_rate": 8.58728557013118e-05, | |
| "loss": 8.8332, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 7.346767422334173, | |
| "grad_norm": 2.319114923477173, | |
| "learning_rate": 8.486377396569122e-05, | |
| "loss": 8.6454, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 7.5566750629722925, | |
| "grad_norm": 2.0394012928009033, | |
| "learning_rate": 8.385469223007064e-05, | |
| "loss": 8.4056, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 7.766582703610411, | |
| "grad_norm": 1.827172040939331, | |
| "learning_rate": 8.284561049445006e-05, | |
| "loss": 8.1372, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 7.97649034424853, | |
| "grad_norm": 1.8120529651641846, | |
| "learning_rate": 8.183652875882947e-05, | |
| "loss": 7.9441, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 8.18639798488665, | |
| "grad_norm": 1.765929102897644, | |
| "learning_rate": 8.082744702320889e-05, | |
| "loss": 7.7749, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 8.39630562552477, | |
| "grad_norm": 1.7692029476165771, | |
| "learning_rate": 7.98183652875883e-05, | |
| "loss": 7.6607, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 8.39630562552477, | |
| "eval_accuracy": 0.3923791352170375, | |
| "eval_loss": 7.453896999359131, | |
| "eval_runtime": 1.2949, | |
| "eval_samples_per_second": 369.905, | |
| "eval_steps_per_second": 3.861, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 8.606213266162888, | |
| "grad_norm": 1.6693313121795654, | |
| "learning_rate": 7.880928355196771e-05, | |
| "loss": 7.5532, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 8.816120906801007, | |
| "grad_norm": 1.7346302270889282, | |
| "learning_rate": 7.780020181634713e-05, | |
| "loss": 7.4595, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 9.026028547439127, | |
| "grad_norm": 1.7092608213424683, | |
| "learning_rate": 7.679112008072655e-05, | |
| "loss": 7.3627, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 9.235936188077247, | |
| "grad_norm": 1.6401524543762207, | |
| "learning_rate": 7.578203834510595e-05, | |
| "loss": 7.2618, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 9.445843828715365, | |
| "grad_norm": 1.6252995729446411, | |
| "learning_rate": 7.477295660948537e-05, | |
| "loss": 7.1712, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 9.655751469353484, | |
| "grad_norm": 1.6538236141204834, | |
| "learning_rate": 7.376387487386479e-05, | |
| "loss": 7.0902, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 9.865659109991604, | |
| "grad_norm": 1.584236979484558, | |
| "learning_rate": 7.27547931382442e-05, | |
| "loss": 7.0174, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 10.075566750629722, | |
| "grad_norm": 1.5742157697677612, | |
| "learning_rate": 7.174571140262362e-05, | |
| "loss": 6.9503, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 10.285474391267842, | |
| "grad_norm": 1.5693203210830688, | |
| "learning_rate": 7.073662966700304e-05, | |
| "loss": 6.8978, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 10.495382031905962, | |
| "grad_norm": 1.5250983238220215, | |
| "learning_rate": 6.972754793138244e-05, | |
| "loss": 6.8494, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 10.705289672544081, | |
| "grad_norm": 1.578021764755249, | |
| "learning_rate": 6.871846619576186e-05, | |
| "loss": 6.8117, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 10.9151973131822, | |
| "grad_norm": 1.5614759922027588, | |
| "learning_rate": 6.770938446014128e-05, | |
| "loss": 6.7742, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 11.125104953820319, | |
| "grad_norm": 1.565773844718933, | |
| "learning_rate": 6.670030272452068e-05, | |
| "loss": 6.7246, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 11.335012594458439, | |
| "grad_norm": 1.5502065420150757, | |
| "learning_rate": 6.56912209889001e-05, | |
| "loss": 6.6824, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 11.544920235096557, | |
| "grad_norm": 1.5737782716751099, | |
| "learning_rate": 6.468213925327952e-05, | |
| "loss": 6.6518, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 11.754827875734676, | |
| "grad_norm": 1.5565502643585205, | |
| "learning_rate": 6.367305751765893e-05, | |
| "loss": 6.6237, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 11.964735516372796, | |
| "grad_norm": 1.54232919216156, | |
| "learning_rate": 6.266397578203835e-05, | |
| "loss": 6.5983, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 12.174643157010916, | |
| "grad_norm": 1.520557165145874, | |
| "learning_rate": 6.165489404641777e-05, | |
| "loss": 6.5678, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 12.384550797649034, | |
| "grad_norm": 1.528678059577942, | |
| "learning_rate": 6.064581231079718e-05, | |
| "loss": 6.5374, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 12.594458438287154, | |
| "grad_norm": 1.5926470756530762, | |
| "learning_rate": 5.963673057517659e-05, | |
| "loss": 6.5199, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 12.594458438287154, | |
| "eval_accuracy": 0.5232392198561715, | |
| "eval_loss": 6.410386562347412, | |
| "eval_runtime": 1.2939, | |
| "eval_samples_per_second": 370.187, | |
| "eval_steps_per_second": 3.864, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 12.804366078925273, | |
| "grad_norm": 1.5785082578659058, | |
| "learning_rate": 5.8627648839556e-05, | |
| "loss": 6.4986, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 13.014273719563391, | |
| "grad_norm": 1.4924007654190063, | |
| "learning_rate": 5.7618567103935416e-05, | |
| "loss": 6.482, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 13.224181360201511, | |
| "grad_norm": 1.601302146911621, | |
| "learning_rate": 5.660948536831484e-05, | |
| "loss": 6.4517, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 13.43408900083963, | |
| "grad_norm": 1.5700117349624634, | |
| "learning_rate": 5.5600403632694254e-05, | |
| "loss": 6.4361, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 13.64399664147775, | |
| "grad_norm": 1.4894846677780151, | |
| "learning_rate": 5.4591321897073666e-05, | |
| "loss": 6.4214, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 13.853904282115868, | |
| "grad_norm": 1.5325466394424438, | |
| "learning_rate": 5.358224016145308e-05, | |
| "loss": 6.4034, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 14.063811922753988, | |
| "grad_norm": 1.5216163396835327, | |
| "learning_rate": 5.257315842583249e-05, | |
| "loss": 6.3849, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 14.273719563392108, | |
| "grad_norm": 1.565855622291565, | |
| "learning_rate": 5.15640766902119e-05, | |
| "loss": 6.3655, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 14.483627204030226, | |
| "grad_norm": 1.5256385803222656, | |
| "learning_rate": 5.055499495459133e-05, | |
| "loss": 6.354, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 14.693534844668346, | |
| "grad_norm": 1.536907434463501, | |
| "learning_rate": 4.954591321897074e-05, | |
| "loss": 6.34, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 14.903442485306465, | |
| "grad_norm": 1.5488026142120361, | |
| "learning_rate": 4.853683148335015e-05, | |
| "loss": 6.3302, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 15.113350125944585, | |
| "grad_norm": 1.5399444103240967, | |
| "learning_rate": 4.7527749747729566e-05, | |
| "loss": 6.3108, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 15.323257766582703, | |
| "grad_norm": 1.5056838989257812, | |
| "learning_rate": 4.6518668012108985e-05, | |
| "loss": 6.295, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 15.533165407220823, | |
| "grad_norm": 1.5070394277572632, | |
| "learning_rate": 4.55095862764884e-05, | |
| "loss": 6.2855, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 15.743073047858942, | |
| "grad_norm": 1.557030200958252, | |
| "learning_rate": 4.450050454086781e-05, | |
| "loss": 6.2789, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 15.95298068849706, | |
| "grad_norm": 1.54939866065979, | |
| "learning_rate": 4.349142280524723e-05, | |
| "loss": 6.2667, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 16.162888329135182, | |
| "grad_norm": 1.4795902967453003, | |
| "learning_rate": 4.248234106962664e-05, | |
| "loss": 6.2533, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 16.3727959697733, | |
| "grad_norm": 1.5724152326583862, | |
| "learning_rate": 4.147325933400605e-05, | |
| "loss": 6.2378, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 16.582703610411418, | |
| "grad_norm": 1.4811497926712036, | |
| "learning_rate": 4.046417759838547e-05, | |
| "loss": 6.2314, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 16.79261125104954, | |
| "grad_norm": 1.504073143005371, | |
| "learning_rate": 3.9455095862764884e-05, | |
| "loss": 6.2188, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 16.79261125104954, | |
| "eval_accuracy": 0.5560446338454638, | |
| "eval_loss": 6.114731311798096, | |
| "eval_runtime": 1.3082, | |
| "eval_samples_per_second": 366.164, | |
| "eval_steps_per_second": 3.822, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 17.002518891687657, | |
| "grad_norm": 1.5252083539962769, | |
| "learning_rate": 3.84460141271443e-05, | |
| "loss": 6.2162, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 17.212426532325775, | |
| "grad_norm": 1.5362071990966797, | |
| "learning_rate": 3.7436932391523715e-05, | |
| "loss": 6.1971, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 17.422334172963897, | |
| "grad_norm": 1.5475701093673706, | |
| "learning_rate": 3.642785065590313e-05, | |
| "loss": 6.1894, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 17.632241813602015, | |
| "grad_norm": 1.538744568824768, | |
| "learning_rate": 3.541876892028255e-05, | |
| "loss": 6.1871, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 17.842149454240133, | |
| "grad_norm": 1.5387678146362305, | |
| "learning_rate": 3.440968718466196e-05, | |
| "loss": 6.1786, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 18.052057094878254, | |
| "grad_norm": 1.5035161972045898, | |
| "learning_rate": 3.340060544904137e-05, | |
| "loss": 6.1657, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 18.261964735516372, | |
| "grad_norm": 1.527760624885559, | |
| "learning_rate": 3.239152371342079e-05, | |
| "loss": 6.1543, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 18.471872376154494, | |
| "grad_norm": 1.5932992696762085, | |
| "learning_rate": 3.13824419778002e-05, | |
| "loss": 6.1505, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 18.68178001679261, | |
| "grad_norm": 1.5544663667678833, | |
| "learning_rate": 3.0373360242179615e-05, | |
| "loss": 6.145, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 18.89168765743073, | |
| "grad_norm": 1.5456353425979614, | |
| "learning_rate": 2.9364278506559034e-05, | |
| "loss": 6.1444, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 19.10159529806885, | |
| "grad_norm": 1.5305620431900024, | |
| "learning_rate": 2.8355196770938446e-05, | |
| "loss": 6.1284, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 19.31150293870697, | |
| "grad_norm": 1.5744434595108032, | |
| "learning_rate": 2.734611503531786e-05, | |
| "loss": 6.1148, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 19.521410579345087, | |
| "grad_norm": 1.5717190504074097, | |
| "learning_rate": 2.6337033299697278e-05, | |
| "loss": 6.1111, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 19.73131821998321, | |
| "grad_norm": 1.538878321647644, | |
| "learning_rate": 2.532795156407669e-05, | |
| "loss": 6.1089, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 19.941225860621326, | |
| "grad_norm": 1.5654772520065308, | |
| "learning_rate": 2.4318869828456106e-05, | |
| "loss": 6.1033, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 20.151133501259444, | |
| "grad_norm": 1.5559521913528442, | |
| "learning_rate": 2.330978809283552e-05, | |
| "loss": 6.0921, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 20.361041141897566, | |
| "grad_norm": 1.5543068647384644, | |
| "learning_rate": 2.2300706357214934e-05, | |
| "loss": 6.0905, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 20.570948782535684, | |
| "grad_norm": 1.5312341451644897, | |
| "learning_rate": 2.129162462159435e-05, | |
| "loss": 6.0826, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 20.7808564231738, | |
| "grad_norm": 1.5084370374679565, | |
| "learning_rate": 2.0282542885973765e-05, | |
| "loss": 6.0766, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 20.990764063811923, | |
| "grad_norm": 1.5072517395019531, | |
| "learning_rate": 1.927346115035318e-05, | |
| "loss": 6.0786, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 20.990764063811923, | |
| "eval_accuracy": 0.5686208540107102, | |
| "eval_loss": 6.002164840698242, | |
| "eval_runtime": 1.2915, | |
| "eval_samples_per_second": 370.872, | |
| "eval_steps_per_second": 3.871, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 21.20067170445004, | |
| "grad_norm": 1.5406224727630615, | |
| "learning_rate": 1.8264379414732593e-05, | |
| "loss": 6.0617, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 21.410579345088163, | |
| "grad_norm": 1.5687764883041382, | |
| "learning_rate": 1.725529767911201e-05, | |
| "loss": 6.0671, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 21.62048698572628, | |
| "grad_norm": 1.5694684982299805, | |
| "learning_rate": 1.6246215943491424e-05, | |
| "loss": 6.0588, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 21.8303946263644, | |
| "grad_norm": 1.5545083284378052, | |
| "learning_rate": 1.5237134207870837e-05, | |
| "loss": 6.0546, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 22.04030226700252, | |
| "grad_norm": 1.5770336389541626, | |
| "learning_rate": 1.4228052472250252e-05, | |
| "loss": 6.0516, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 22.250209907640638, | |
| "grad_norm": 1.5537070035934448, | |
| "learning_rate": 1.3218970736629668e-05, | |
| "loss": 6.0418, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 22.460117548278756, | |
| "grad_norm": 1.5324172973632812, | |
| "learning_rate": 1.2209889001009082e-05, | |
| "loss": 6.0395, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 22.670025188916878, | |
| "grad_norm": 1.5391899347305298, | |
| "learning_rate": 1.1200807265388496e-05, | |
| "loss": 6.0396, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 22.879932829554996, | |
| "grad_norm": 1.53764808177948, | |
| "learning_rate": 1.0191725529767912e-05, | |
| "loss": 6.0349, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 23.089840470193113, | |
| "grad_norm": 1.5666145086288452, | |
| "learning_rate": 9.182643794147326e-06, | |
| "loss": 6.0295, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 23.299748110831235, | |
| "grad_norm": 1.5440330505371094, | |
| "learning_rate": 8.173562058526741e-06, | |
| "loss": 6.0249, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 23.509655751469353, | |
| "grad_norm": 1.5554158687591553, | |
| "learning_rate": 7.164480322906156e-06, | |
| "loss": 6.0222, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 23.719563392107474, | |
| "grad_norm": 1.5160704851150513, | |
| "learning_rate": 6.155398587285571e-06, | |
| "loss": 6.018, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 23.929471032745592, | |
| "grad_norm": 1.5344035625457764, | |
| "learning_rate": 5.146316851664986e-06, | |
| "loss": 6.0203, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 24.13937867338371, | |
| "grad_norm": 1.535138726234436, | |
| "learning_rate": 4.1372351160444e-06, | |
| "loss": 6.0158, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 24.349286314021832, | |
| "grad_norm": 1.5589773654937744, | |
| "learning_rate": 3.1281533804238145e-06, | |
| "loss": 6.0167, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 24.55919395465995, | |
| "grad_norm": 1.5176498889923096, | |
| "learning_rate": 2.1190716448032293e-06, | |
| "loss": 6.0094, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 24.769101595298068, | |
| "grad_norm": 1.5294731855392456, | |
| "learning_rate": 1.109989909182644e-06, | |
| "loss": 6.0103, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 24.97900923593619, | |
| "grad_norm": 1.5368298292160034, | |
| "learning_rate": 1.0090817356205853e-07, | |
| "loss": 6.0145, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "step": 59550, | |
| "total_flos": 7.69437063436032e+17, | |
| "train_loss": 7.661456682668025, | |
| "train_runtime": 32775.0534, | |
| "train_samples_per_second": 174.4, | |
| "train_steps_per_second": 1.817 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 59550, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 25, | |
| "save_steps": 10000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.69437063436032e+17, | |
| "train_batch_size": 96, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |