| { | |
| "best_metric": 0.8608695652173913, | |
| "best_model_checkpoint": "/home/ubuntu/utah/babylm-24/src/evaluation/results/finetune/DebertaV2-Base-10M_babylm-A/sst2/checkpoint-42095", | |
| "epoch": 8.0, | |
| "eval_steps": 500, | |
| "global_step": 67352, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05938947618482005, | |
| "grad_norm": 2.9371345043182373, | |
| "learning_rate": 2.991091578572277e-05, | |
| "loss": 0.5976, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.1187789523696401, | |
| "grad_norm": 6.96113920211792, | |
| "learning_rate": 2.982183157144554e-05, | |
| "loss": 0.4885, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.17816842855446016, | |
| "grad_norm": 5.86502742767334, | |
| "learning_rate": 2.973274735716831e-05, | |
| "loss": 0.4746, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.2375579047392802, | |
| "grad_norm": 7.14243745803833, | |
| "learning_rate": 2.964366314289108e-05, | |
| "loss": 0.4426, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.2969473809241002, | |
| "grad_norm": 8.168976783752441, | |
| "learning_rate": 2.955457892861385e-05, | |
| "loss": 0.4213, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.3563368571089203, | |
| "grad_norm": 12.06148624420166, | |
| "learning_rate": 2.9465494714336618e-05, | |
| "loss": 0.3904, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.41572633329374037, | |
| "grad_norm": 5.824960708618164, | |
| "learning_rate": 2.937641050005939e-05, | |
| "loss": 0.3788, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.4751158094785604, | |
| "grad_norm": 4.579179763793945, | |
| "learning_rate": 2.9287326285782158e-05, | |
| "loss": 0.3646, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.5345052856633804, | |
| "grad_norm": 25.88724136352539, | |
| "learning_rate": 2.919824207150493e-05, | |
| "loss": 0.3727, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.5938947618482004, | |
| "grad_norm": 1.1444391012191772, | |
| "learning_rate": 2.91091578572277e-05, | |
| "loss": 0.3607, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.6532842380330206, | |
| "grad_norm": 6.4522600173950195, | |
| "learning_rate": 2.902007364295047e-05, | |
| "loss": 0.3597, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.7126737142178406, | |
| "grad_norm": 13.808451652526855, | |
| "learning_rate": 2.8930989428673242e-05, | |
| "loss": 0.3384, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.7720631904026607, | |
| "grad_norm": 16.229154586791992, | |
| "learning_rate": 2.884190521439601e-05, | |
| "loss": 0.3408, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.8314526665874807, | |
| "grad_norm": 26.570392608642578, | |
| "learning_rate": 2.8752821000118782e-05, | |
| "loss": 0.3391, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.8908421427723008, | |
| "grad_norm": 4.880529880523682, | |
| "learning_rate": 2.866373678584155e-05, | |
| "loss": 0.3436, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.9502316189571208, | |
| "grad_norm": 18.9448299407959, | |
| "learning_rate": 2.857465257156432e-05, | |
| "loss": 0.3151, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.8463302850723267, | |
| "eval_f1": 0.8466819221967964, | |
| "eval_loss": 0.40749993920326233, | |
| "eval_mcc": 0.694664779303656, | |
| "eval_runtime": 0.7142, | |
| "eval_samples_per_second": 610.484, | |
| "eval_steps_per_second": 77.011, | |
| "step": 8419 | |
| }, | |
| { | |
| "epoch": 1.0096210951419409, | |
| "grad_norm": 11.80332088470459, | |
| "learning_rate": 2.848556835728709e-05, | |
| "loss": 0.3028, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.0690105713267608, | |
| "grad_norm": 22.269908905029297, | |
| "learning_rate": 2.839648414300986e-05, | |
| "loss": 0.2843, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.128400047511581, | |
| "grad_norm": 14.310569763183594, | |
| "learning_rate": 2.830739992873263e-05, | |
| "loss": 0.2653, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.187789523696401, | |
| "grad_norm": 6.787134170532227, | |
| "learning_rate": 2.82183157144554e-05, | |
| "loss": 0.2808, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.247178999881221, | |
| "grad_norm": 1.5390983819961548, | |
| "learning_rate": 2.812923150017817e-05, | |
| "loss": 0.2651, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.3065684760660412, | |
| "grad_norm": 0.39634034037590027, | |
| "learning_rate": 2.804014728590094e-05, | |
| "loss": 0.2641, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 1.3659579522508611, | |
| "grad_norm": 0.24770836532115936, | |
| "learning_rate": 2.795106307162371e-05, | |
| "loss": 0.2448, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 1.425347428435681, | |
| "grad_norm": 16.2122859954834, | |
| "learning_rate": 2.786197885734648e-05, | |
| "loss": 0.2632, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 1.4847369046205012, | |
| "grad_norm": 4.9013285636901855, | |
| "learning_rate": 2.777289464306925e-05, | |
| "loss": 0.2547, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 1.5441263808053214, | |
| "grad_norm": 8.146185874938965, | |
| "learning_rate": 2.7683810428792017e-05, | |
| "loss": 0.2602, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 1.6035158569901413, | |
| "grad_norm": 13.071233749389648, | |
| "learning_rate": 2.759472621451479e-05, | |
| "loss": 0.2492, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 1.6629053331749613, | |
| "grad_norm": 0.20201528072357178, | |
| "learning_rate": 2.7505642000237557e-05, | |
| "loss": 0.2559, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 1.7222948093597814, | |
| "grad_norm": 3.819157123565674, | |
| "learning_rate": 2.741655778596033e-05, | |
| "loss": 0.237, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.7816842855446016, | |
| "grad_norm": 0.21059203147888184, | |
| "learning_rate": 2.7327473571683097e-05, | |
| "loss": 0.2485, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.8410737617294215, | |
| "grad_norm": 0.5426599383354187, | |
| "learning_rate": 2.7238389357405867e-05, | |
| "loss": 0.2451, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.9004632379142414, | |
| "grad_norm": 64.44636535644531, | |
| "learning_rate": 2.714930514312864e-05, | |
| "loss": 0.2523, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.9598527140990618, | |
| "grad_norm": 4.042015552520752, | |
| "learning_rate": 2.7060220928851407e-05, | |
| "loss": 0.2707, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8394495248794556, | |
| "eval_f1": 0.8379629629629629, | |
| "eval_loss": 0.6586544513702393, | |
| "eval_mcc": 0.6824127269645459, | |
| "eval_runtime": 0.6937, | |
| "eval_samples_per_second": 628.482, | |
| "eval_steps_per_second": 79.281, | |
| "step": 16838 | |
| }, | |
| { | |
| "epoch": 2.0192421902838817, | |
| "grad_norm": 0.36723724007606506, | |
| "learning_rate": 2.697113671457418e-05, | |
| "loss": 0.2145, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 2.0786316664687017, | |
| "grad_norm": 0.06311015039682388, | |
| "learning_rate": 2.6882052500296947e-05, | |
| "loss": 0.1803, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 2.1380211426535216, | |
| "grad_norm": 0.21473073959350586, | |
| "learning_rate": 2.6792968286019718e-05, | |
| "loss": 0.1914, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 2.197410618838342, | |
| "grad_norm": 12.172515869140625, | |
| "learning_rate": 2.6703884071742488e-05, | |
| "loss": 0.1957, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 2.256800095023162, | |
| "grad_norm": 0.08349990844726562, | |
| "learning_rate": 2.6614799857465258e-05, | |
| "loss": 0.2067, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 2.316189571207982, | |
| "grad_norm": 6.744356632232666, | |
| "learning_rate": 2.6525715643188028e-05, | |
| "loss": 0.1858, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 2.375579047392802, | |
| "grad_norm": 23.043901443481445, | |
| "learning_rate": 2.6436631428910798e-05, | |
| "loss": 0.1994, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 2.434968523577622, | |
| "grad_norm": 0.16990970075130463, | |
| "learning_rate": 2.6347547214633565e-05, | |
| "loss": 0.2012, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 2.494357999762442, | |
| "grad_norm": 4.681793689727783, | |
| "learning_rate": 2.6258463000356338e-05, | |
| "loss": 0.1931, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 2.553747475947262, | |
| "grad_norm": 8.904121398925781, | |
| "learning_rate": 2.6169378786079108e-05, | |
| "loss": 0.1899, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 2.6131369521320824, | |
| "grad_norm": 0.045907679945230484, | |
| "learning_rate": 2.608029457180188e-05, | |
| "loss": 0.2032, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 2.6725264283169023, | |
| "grad_norm": 0.12679323554039001, | |
| "learning_rate": 2.599121035752465e-05, | |
| "loss": 0.2189, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 2.7319159045017223, | |
| "grad_norm": 0.09417314827442169, | |
| "learning_rate": 2.5902126143247415e-05, | |
| "loss": 0.193, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 2.791305380686542, | |
| "grad_norm": 0.06781476736068726, | |
| "learning_rate": 2.581304192897019e-05, | |
| "loss": 0.2021, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 2.850694856871362, | |
| "grad_norm": 0.15305034816265106, | |
| "learning_rate": 2.5723957714692955e-05, | |
| "loss": 0.198, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 2.9100843330561825, | |
| "grad_norm": 0.7531378865242004, | |
| "learning_rate": 2.563487350041573e-05, | |
| "loss": 0.1799, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 2.9694738092410025, | |
| "grad_norm": 0.24162191152572632, | |
| "learning_rate": 2.5545789286138496e-05, | |
| "loss": 0.1858, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.85550457239151, | |
| "eval_f1": 0.8538283062645011, | |
| "eval_loss": 0.5957673788070679, | |
| "eval_mcc": 0.7149506045130871, | |
| "eval_runtime": 0.7033, | |
| "eval_samples_per_second": 619.903, | |
| "eval_steps_per_second": 78.199, | |
| "step": 25257 | |
| }, | |
| { | |
| "epoch": 3.0288632854258224, | |
| "grad_norm": 0.03327510878443718, | |
| "learning_rate": 2.5456705071861266e-05, | |
| "loss": 0.1564, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 3.0882527616106428, | |
| "grad_norm": 59.41106033325195, | |
| "learning_rate": 2.5367620857584036e-05, | |
| "loss": 0.1308, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 3.1476422377954627, | |
| "grad_norm": 0.029464269056916237, | |
| "learning_rate": 2.5278536643306806e-05, | |
| "loss": 0.1276, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 3.2070317139802826, | |
| "grad_norm": 0.1652437150478363, | |
| "learning_rate": 2.518945242902958e-05, | |
| "loss": 0.1532, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 3.2664211901651026, | |
| "grad_norm": 0.20975850522518158, | |
| "learning_rate": 2.5100368214752346e-05, | |
| "loss": 0.1558, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 3.325810666349923, | |
| "grad_norm": 0.33388465642929077, | |
| "learning_rate": 2.5011284000475116e-05, | |
| "loss": 0.1421, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 3.385200142534743, | |
| "grad_norm": 0.06191316992044449, | |
| "learning_rate": 2.4922199786197886e-05, | |
| "loss": 0.1356, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 3.444589618719563, | |
| "grad_norm": 0.03824834153056145, | |
| "learning_rate": 2.4833115571920656e-05, | |
| "loss": 0.1615, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 3.503979094904383, | |
| "grad_norm": 0.03963463753461838, | |
| "learning_rate": 2.4744031357643426e-05, | |
| "loss": 0.1515, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 3.563368571089203, | |
| "grad_norm": 0.26668134331703186, | |
| "learning_rate": 2.4654947143366197e-05, | |
| "loss": 0.1578, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 3.622758047274023, | |
| "grad_norm": 0.07644706219434738, | |
| "learning_rate": 2.4565862929088963e-05, | |
| "loss": 0.1399, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 3.682147523458843, | |
| "grad_norm": 0.02788461185991764, | |
| "learning_rate": 2.4476778714811737e-05, | |
| "loss": 0.156, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 3.741536999643663, | |
| "grad_norm": 0.2001054584980011, | |
| "learning_rate": 2.4387694500534507e-05, | |
| "loss": 0.1519, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 3.8009264758284833, | |
| "grad_norm": 9.855899810791016, | |
| "learning_rate": 2.4298610286257277e-05, | |
| "loss": 0.1498, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 3.8603159520133032, | |
| "grad_norm": 0.25349605083465576, | |
| "learning_rate": 2.4209526071980047e-05, | |
| "loss": 0.1582, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 3.919705428198123, | |
| "grad_norm": 0.10745853930711746, | |
| "learning_rate": 2.4120441857702814e-05, | |
| "loss": 0.154, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 3.9790949043829436, | |
| "grad_norm": 0.018555356189608574, | |
| "learning_rate": 2.4031357643425587e-05, | |
| "loss": 0.1567, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8463302850723267, | |
| "eval_f1": 0.8546637744034707, | |
| "eval_loss": 0.6577614545822144, | |
| "eval_mcc": 0.6923721957357695, | |
| "eval_runtime": 0.7006, | |
| "eval_samples_per_second": 622.298, | |
| "eval_steps_per_second": 78.501, | |
| "step": 33676 | |
| }, | |
| { | |
| "epoch": 4.0384843805677635, | |
| "grad_norm": 0.04052357375621796, | |
| "learning_rate": 2.3942273429148354e-05, | |
| "loss": 0.1321, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 4.097873856752583, | |
| "grad_norm": 28.136058807373047, | |
| "learning_rate": 2.3853189214871127e-05, | |
| "loss": 0.12, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 4.157263332937403, | |
| "grad_norm": 12.880512237548828, | |
| "learning_rate": 2.3764105000593894e-05, | |
| "loss": 0.1092, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 4.216652809122223, | |
| "grad_norm": 0.02295825444161892, | |
| "learning_rate": 2.3675020786316664e-05, | |
| "loss": 0.1015, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 4.276042285307043, | |
| "grad_norm": 16.506240844726562, | |
| "learning_rate": 2.3585936572039434e-05, | |
| "loss": 0.1011, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 4.335431761491864, | |
| "grad_norm": 0.05963263288140297, | |
| "learning_rate": 2.3496852357762204e-05, | |
| "loss": 0.1203, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 4.394821237676684, | |
| "grad_norm": 6.27707576751709, | |
| "learning_rate": 2.3407768143484978e-05, | |
| "loss": 0.108, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 4.454210713861504, | |
| "grad_norm": 0.04750403016805649, | |
| "learning_rate": 2.3318683929207745e-05, | |
| "loss": 0.111, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 4.513600190046324, | |
| "grad_norm": 0.11624455451965332, | |
| "learning_rate": 2.3229599714930515e-05, | |
| "loss": 0.1253, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 4.572989666231144, | |
| "grad_norm": 0.024209963157773018, | |
| "learning_rate": 2.3140515500653285e-05, | |
| "loss": 0.1087, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 4.632379142415964, | |
| "grad_norm": 0.38843753933906555, | |
| "learning_rate": 2.3051431286376055e-05, | |
| "loss": 0.134, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 4.691768618600784, | |
| "grad_norm": 0.3449760973453522, | |
| "learning_rate": 2.2962347072098825e-05, | |
| "loss": 0.1211, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 4.751158094785604, | |
| "grad_norm": 0.3117709457874298, | |
| "learning_rate": 2.2873262857821595e-05, | |
| "loss": 0.1151, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 4.810547570970424, | |
| "grad_norm": 0.09373793005943298, | |
| "learning_rate": 2.2784178643544362e-05, | |
| "loss": 0.1247, | |
| "step": 40500 | |
| }, | |
| { | |
| "epoch": 4.869937047155244, | |
| "grad_norm": 25.01434898376465, | |
| "learning_rate": 2.2695094429267135e-05, | |
| "loss": 0.131, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 4.929326523340064, | |
| "grad_norm": 0.02744464948773384, | |
| "learning_rate": 2.2606010214989902e-05, | |
| "loss": 0.1432, | |
| "step": 41500 | |
| }, | |
| { | |
| "epoch": 4.988715999524884, | |
| "grad_norm": 18.553770065307617, | |
| "learning_rate": 2.2516926000712676e-05, | |
| "loss": 0.1145, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.853210985660553, | |
| "eval_f1": 0.8608695652173913, | |
| "eval_loss": 0.7391630411148071, | |
| "eval_mcc": 0.7061073536146776, | |
| "eval_runtime": 0.728, | |
| "eval_samples_per_second": 598.936, | |
| "eval_steps_per_second": 75.554, | |
| "step": 42095 | |
| }, | |
| { | |
| "epoch": 5.048105475709704, | |
| "grad_norm": 0.027907686308026314, | |
| "learning_rate": 2.2427841786435446e-05, | |
| "loss": 0.0863, | |
| "step": 42500 | |
| }, | |
| { | |
| "epoch": 5.107494951894524, | |
| "grad_norm": 0.025640016421675682, | |
| "learning_rate": 2.2338757572158212e-05, | |
| "loss": 0.0777, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 5.166884428079344, | |
| "grad_norm": 0.02034921571612358, | |
| "learning_rate": 2.2249673357880986e-05, | |
| "loss": 0.0911, | |
| "step": 43500 | |
| }, | |
| { | |
| "epoch": 5.226273904264165, | |
| "grad_norm": 0.013952106237411499, | |
| "learning_rate": 2.2160589143603753e-05, | |
| "loss": 0.1016, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 5.285663380448985, | |
| "grad_norm": 0.0147418063133955, | |
| "learning_rate": 2.2071504929326526e-05, | |
| "loss": 0.0962, | |
| "step": 44500 | |
| }, | |
| { | |
| "epoch": 5.345052856633805, | |
| "grad_norm": 7.1807122230529785, | |
| "learning_rate": 2.1982420715049293e-05, | |
| "loss": 0.0818, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 5.404442332818625, | |
| "grad_norm": 0.024392470717430115, | |
| "learning_rate": 2.1893336500772063e-05, | |
| "loss": 0.0834, | |
| "step": 45500 | |
| }, | |
| { | |
| "epoch": 5.463831809003445, | |
| "grad_norm": 0.009795928373932838, | |
| "learning_rate": 2.1804252286494833e-05, | |
| "loss": 0.0979, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 5.5232212851882645, | |
| "grad_norm": 0.013820298947393894, | |
| "learning_rate": 2.1715168072217603e-05, | |
| "loss": 0.1039, | |
| "step": 46500 | |
| }, | |
| { | |
| "epoch": 5.582610761373084, | |
| "grad_norm": 0.01806664653122425, | |
| "learning_rate": 2.1626083857940373e-05, | |
| "loss": 0.104, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 5.642000237557904, | |
| "grad_norm": 0.020521830767393112, | |
| "learning_rate": 2.1536999643663143e-05, | |
| "loss": 0.0938, | |
| "step": 47500 | |
| }, | |
| { | |
| "epoch": 5.701389713742724, | |
| "grad_norm": 0.04232034087181091, | |
| "learning_rate": 2.1447915429385913e-05, | |
| "loss": 0.0845, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 5.760779189927545, | |
| "grad_norm": 0.41699323058128357, | |
| "learning_rate": 2.1358831215108683e-05, | |
| "loss": 0.1029, | |
| "step": 48500 | |
| }, | |
| { | |
| "epoch": 5.820168666112365, | |
| "grad_norm": 0.017835628241300583, | |
| "learning_rate": 2.1269747000831454e-05, | |
| "loss": 0.1023, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 5.879558142297185, | |
| "grad_norm": 0.027343884110450745, | |
| "learning_rate": 2.1180662786554224e-05, | |
| "loss": 0.0985, | |
| "step": 49500 | |
| }, | |
| { | |
| "epoch": 5.938947618482005, | |
| "grad_norm": 0.4489924907684326, | |
| "learning_rate": 2.1091578572276994e-05, | |
| "loss": 0.099, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 5.998337094666825, | |
| "grad_norm": 4.496362686157227, | |
| "learning_rate": 2.100249435799976e-05, | |
| "loss": 0.0995, | |
| "step": 50500 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8279816508293152, | |
| "eval_f1": 0.845360824742268, | |
| "eval_loss": 0.9949702024459839, | |
| "eval_mcc": 0.6612999229278168, | |
| "eval_runtime": 0.7516, | |
| "eval_samples_per_second": 580.102, | |
| "eval_steps_per_second": 73.178, | |
| "step": 50514 | |
| }, | |
| { | |
| "epoch": 6.057726570851645, | |
| "grad_norm": 0.04877474159002304, | |
| "learning_rate": 2.0913410143722534e-05, | |
| "loss": 0.0626, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 6.117116047036465, | |
| "grad_norm": 0.1524512767791748, | |
| "learning_rate": 2.08243259294453e-05, | |
| "loss": 0.0703, | |
| "step": 51500 | |
| }, | |
| { | |
| "epoch": 6.1765055232212855, | |
| "grad_norm": 8.834334373474121, | |
| "learning_rate": 2.0735241715168074e-05, | |
| "loss": 0.0719, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 6.2358949994061055, | |
| "grad_norm": 0.009824572131037712, | |
| "learning_rate": 2.0646157500890844e-05, | |
| "loss": 0.0573, | |
| "step": 52500 | |
| }, | |
| { | |
| "epoch": 6.295284475590925, | |
| "grad_norm": 0.8331696391105652, | |
| "learning_rate": 2.055707328661361e-05, | |
| "loss": 0.0629, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 6.354673951775745, | |
| "grad_norm": 0.0664055198431015, | |
| "learning_rate": 2.0467989072336384e-05, | |
| "loss": 0.0672, | |
| "step": 53500 | |
| }, | |
| { | |
| "epoch": 6.414063427960565, | |
| "grad_norm": 0.03841827064752579, | |
| "learning_rate": 2.037890485805915e-05, | |
| "loss": 0.0793, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 6.473452904145385, | |
| "grad_norm": 0.07754085958003998, | |
| "learning_rate": 2.0289820643781925e-05, | |
| "loss": 0.0741, | |
| "step": 54500 | |
| }, | |
| { | |
| "epoch": 6.532842380330205, | |
| "grad_norm": 694.4078979492188, | |
| "learning_rate": 2.020073642950469e-05, | |
| "loss": 0.0634, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 6.592231856515026, | |
| "grad_norm": 0.1212846115231514, | |
| "learning_rate": 2.011165221522746e-05, | |
| "loss": 0.0841, | |
| "step": 55500 | |
| }, | |
| { | |
| "epoch": 6.651621332699846, | |
| "grad_norm": 0.015646882355213165, | |
| "learning_rate": 2.002256800095023e-05, | |
| "loss": 0.0718, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 6.711010808884666, | |
| "grad_norm": 0.04938916116952896, | |
| "learning_rate": 1.9933483786673e-05, | |
| "loss": 0.0926, | |
| "step": 56500 | |
| }, | |
| { | |
| "epoch": 6.770400285069486, | |
| "grad_norm": 0.0076505206525325775, | |
| "learning_rate": 1.9844399572395772e-05, | |
| "loss": 0.0901, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 6.829789761254306, | |
| "grad_norm": 0.015326344408094883, | |
| "learning_rate": 1.9755315358118542e-05, | |
| "loss": 0.0814, | |
| "step": 57500 | |
| }, | |
| { | |
| "epoch": 6.889179237439126, | |
| "grad_norm": 0.08718911558389664, | |
| "learning_rate": 1.9666231143841312e-05, | |
| "loss": 0.0811, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 6.948568713623946, | |
| "grad_norm": 0.01760442741215229, | |
| "learning_rate": 1.9577146929564082e-05, | |
| "loss": 0.0842, | |
| "step": 58500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8440366983413696, | |
| "eval_f1": 0.8482142857142857, | |
| "eval_loss": 0.810035765171051, | |
| "eval_mcc": 0.6879791966290185, | |
| "eval_runtime": 0.6705, | |
| "eval_samples_per_second": 650.225, | |
| "eval_steps_per_second": 82.024, | |
| "step": 58933 | |
| }, | |
| { | |
| "epoch": 7.0079581898087655, | |
| "grad_norm": 0.017652327194809914, | |
| "learning_rate": 1.9488062715286852e-05, | |
| "loss": 0.0831, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 7.067347665993586, | |
| "grad_norm": 0.017668193206191063, | |
| "learning_rate": 1.9398978501009622e-05, | |
| "loss": 0.0472, | |
| "step": 59500 | |
| }, | |
| { | |
| "epoch": 7.126737142178406, | |
| "grad_norm": 0.06514804065227509, | |
| "learning_rate": 1.9309894286732392e-05, | |
| "loss": 0.0625, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 7.186126618363226, | |
| "grad_norm": 0.007870903238654137, | |
| "learning_rate": 1.922081007245516e-05, | |
| "loss": 0.0537, | |
| "step": 60500 | |
| }, | |
| { | |
| "epoch": 7.245516094548046, | |
| "grad_norm": 0.0029470089357346296, | |
| "learning_rate": 1.9131725858177933e-05, | |
| "loss": 0.0506, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 7.304905570732866, | |
| "grad_norm": 0.004455640912055969, | |
| "learning_rate": 1.90426416439007e-05, | |
| "loss": 0.0459, | |
| "step": 61500 | |
| }, | |
| { | |
| "epoch": 7.364295046917686, | |
| "grad_norm": 0.054865576326847076, | |
| "learning_rate": 1.8953557429623473e-05, | |
| "loss": 0.055, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 7.423684523102506, | |
| "grad_norm": 0.07598511129617691, | |
| "learning_rate": 1.886447321534624e-05, | |
| "loss": 0.0598, | |
| "step": 62500 | |
| }, | |
| { | |
| "epoch": 7.483073999287326, | |
| "grad_norm": 0.12898291647434235, | |
| "learning_rate": 1.877538900106901e-05, | |
| "loss": 0.0522, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 7.542463475472147, | |
| "grad_norm": 0.006004431750625372, | |
| "learning_rate": 1.8686304786791783e-05, | |
| "loss": 0.0602, | |
| "step": 63500 | |
| }, | |
| { | |
| "epoch": 7.601852951656967, | |
| "grad_norm": 0.02722933515906334, | |
| "learning_rate": 1.859722057251455e-05, | |
| "loss": 0.0604, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 7.6612424278417866, | |
| "grad_norm": 0.019477859139442444, | |
| "learning_rate": 1.8508136358237323e-05, | |
| "loss": 0.0682, | |
| "step": 64500 | |
| }, | |
| { | |
| "epoch": 7.7206319040266065, | |
| "grad_norm": 0.029639530926942825, | |
| "learning_rate": 1.841905214396009e-05, | |
| "loss": 0.0734, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 7.780021380211426, | |
| "grad_norm": 0.019286124035716057, | |
| "learning_rate": 1.832996792968286e-05, | |
| "loss": 0.0732, | |
| "step": 65500 | |
| }, | |
| { | |
| "epoch": 7.839410856396246, | |
| "grad_norm": 0.012325610034167767, | |
| "learning_rate": 1.824088371540563e-05, | |
| "loss": 0.0534, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 7.898800332581066, | |
| "grad_norm": 0.0682038888335228, | |
| "learning_rate": 1.81517995011284e-05, | |
| "loss": 0.0886, | |
| "step": 66500 | |
| }, | |
| { | |
| "epoch": 7.958189808765887, | |
| "grad_norm": 0.006911112926900387, | |
| "learning_rate": 1.806271528685117e-05, | |
| "loss": 0.0656, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8417431116104126, | |
| "eval_f1": 0.8516129032258064, | |
| "eval_loss": 0.8965951204299927, | |
| "eval_mcc": 0.6835885663714486, | |
| "eval_runtime": 0.6751, | |
| "eval_samples_per_second": 645.866, | |
| "eval_steps_per_second": 81.474, | |
| "step": 67352 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "step": 67352, | |
| "total_flos": 3.178750951973683e+16, | |
| "train_loss": 0.16765205063521402, | |
| "train_runtime": 3789.576, | |
| "train_samples_per_second": 355.443, | |
| "train_steps_per_second": 44.432 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 168380, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 20, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.001 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.178750951973683e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |