| { | |
| "best_metric": 0.6784613322610911, | |
| "best_model_checkpoint": "/tmp/test-ner1_base/checkpoint-26840", | |
| "epoch": 120.0, | |
| "global_step": 29280, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.7635791130936762, | |
| "eval_f1": 0.4809298946603705, | |
| "eval_loss": 0.8214002847671509, | |
| "eval_precision": 0.4246311738293778, | |
| "eval_recall": 0.5544388609715243, | |
| "eval_runtime": 2.9656, | |
| "eval_samples_per_second": 374.972, | |
| "eval_steps_per_second": 11.802, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8022709381932683, | |
| "eval_f1": 0.5700258397932816, | |
| "eval_loss": 0.6734200119972229, | |
| "eval_precision": 0.5305435305435305, | |
| "eval_recall": 0.615857063093244, | |
| "eval_runtime": 2.95, | |
| "eval_samples_per_second": 376.943, | |
| "eval_steps_per_second": 11.864, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 2.05, | |
| "learning_rate": 2.9487704918032787e-05, | |
| "loss": 0.9764, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.8072087975000596, | |
| "eval_f1": 0.6019592678525393, | |
| "eval_loss": 0.6425491571426392, | |
| "eval_precision": 0.5591475095785441, | |
| "eval_recall": 0.6518704634282524, | |
| "eval_runtime": 2.9986, | |
| "eval_samples_per_second": 370.843, | |
| "eval_steps_per_second": 11.672, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.8214737243863457, | |
| "eval_f1": 0.6151294808011226, | |
| "eval_loss": 0.6202793121337891, | |
| "eval_precision": 0.5663612872915198, | |
| "eval_recall": 0.6730876605248465, | |
| "eval_runtime": 2.9638, | |
| "eval_samples_per_second": 375.198, | |
| "eval_steps_per_second": 11.809, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 4.1, | |
| "learning_rate": 2.8975409836065577e-05, | |
| "loss": 0.4504, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_accuracy": 0.8170606617208559, | |
| "eval_f1": 0.6304066304066305, | |
| "eval_loss": 0.6483346223831177, | |
| "eval_precision": 0.5879227053140097, | |
| "eval_recall": 0.6795086543830262, | |
| "eval_runtime": 2.9472, | |
| "eval_samples_per_second": 377.302, | |
| "eval_steps_per_second": 11.876, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.8137687555163283, | |
| "eval_f1": 0.607830950901181, | |
| "eval_loss": 0.6827735900878906, | |
| "eval_precision": 0.5478377772798566, | |
| "eval_recall": 0.6825795644891123, | |
| "eval_runtime": 2.9631, | |
| "eval_samples_per_second": 375.283, | |
| "eval_steps_per_second": 11.812, | |
| "step": 1464 | |
| }, | |
| { | |
| "epoch": 6.15, | |
| "learning_rate": 2.846311475409836e-05, | |
| "loss": 0.2877, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_accuracy": 0.8115025882016174, | |
| "eval_f1": 0.6301228183581126, | |
| "eval_loss": 0.709669828414917, | |
| "eval_precision": 0.5868047194798941, | |
| "eval_recall": 0.6803461753210497, | |
| "eval_runtime": 2.9712, | |
| "eval_samples_per_second": 374.266, | |
| "eval_steps_per_second": 11.78, | |
| "step": 1708 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.8133393764461726, | |
| "eval_f1": 0.6333632978040324, | |
| "eval_loss": 0.7538309097290039, | |
| "eval_precision": 0.5864447086801426, | |
| "eval_recall": 0.6884422110552764, | |
| "eval_runtime": 2.99, | |
| "eval_samples_per_second": 371.902, | |
| "eval_steps_per_second": 11.706, | |
| "step": 1952 | |
| }, | |
| { | |
| "epoch": 8.2, | |
| "learning_rate": 2.795081967213115e-05, | |
| "loss": 0.1968, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "eval_accuracy": 0.812862288590444, | |
| "eval_f1": 0.6361865177295752, | |
| "eval_loss": 0.7852667570114136, | |
| "eval_precision": 0.594850619383046, | |
| "eval_recall": 0.6836962590731435, | |
| "eval_runtime": 2.9647, | |
| "eval_samples_per_second": 375.08, | |
| "eval_steps_per_second": 11.806, | |
| "step": 2196 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.8093556928508385, | |
| "eval_f1": 0.6372536222425271, | |
| "eval_loss": 0.8311049938201904, | |
| "eval_precision": 0.5984309879872518, | |
| "eval_recall": 0.681462869905081, | |
| "eval_runtime": 3.0899, | |
| "eval_samples_per_second": 359.881, | |
| "eval_steps_per_second": 11.327, | |
| "step": 2440 | |
| }, | |
| { | |
| "epoch": 10.25, | |
| "learning_rate": 2.7438524590163935e-05, | |
| "loss": 0.1443, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 11.0, | |
| "eval_accuracy": 0.8189928675365569, | |
| "eval_f1": 0.6475366876310273, | |
| "eval_loss": 0.790969967842102, | |
| "eval_precision": 0.6101234567901235, | |
| "eval_recall": 0.6898380792853155, | |
| "eval_runtime": 2.9631, | |
| "eval_samples_per_second": 375.284, | |
| "eval_steps_per_second": 11.812, | |
| "step": 2684 | |
| }, | |
| { | |
| "epoch": 12.0, | |
| "eval_accuracy": 0.8147229312277856, | |
| "eval_f1": 0.6334806342604627, | |
| "eval_loss": 0.8414269089698792, | |
| "eval_precision": 0.5926556420233463, | |
| "eval_recall": 0.6803461753210497, | |
| "eval_runtime": 2.9571, | |
| "eval_samples_per_second": 376.042, | |
| "eval_steps_per_second": 11.836, | |
| "step": 2928 | |
| }, | |
| { | |
| "epoch": 12.3, | |
| "learning_rate": 2.6926229508196725e-05, | |
| "loss": 0.1118, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 13.0, | |
| "eval_accuracy": 0.8069225447866225, | |
| "eval_f1": 0.6412532637075719, | |
| "eval_loss": 0.8946433067321777, | |
| "eval_precision": 0.6022560078469839, | |
| "eval_recall": 0.6856504745951982, | |
| "eval_runtime": 2.9859, | |
| "eval_samples_per_second": 372.42, | |
| "eval_steps_per_second": 11.722, | |
| "step": 3172 | |
| }, | |
| { | |
| "epoch": 14.0, | |
| "eval_accuracy": 0.8129815605543761, | |
| "eval_f1": 0.6424639580602883, | |
| "eval_loss": 0.9194995760917664, | |
| "eval_precision": 0.6054841897233202, | |
| "eval_recall": 0.6842546063651591, | |
| "eval_runtime": 2.9708, | |
| "eval_samples_per_second": 374.309, | |
| "eval_steps_per_second": 11.781, | |
| "step": 3416 | |
| }, | |
| { | |
| "epoch": 14.34, | |
| "learning_rate": 2.6413934426229508e-05, | |
| "loss": 0.0838, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_accuracy": 0.8192314114644211, | |
| "eval_f1": 0.6421779340888367, | |
| "eval_loss": 0.9149069786071777, | |
| "eval_precision": 0.6019536019536019, | |
| "eval_recall": 0.6881630374092685, | |
| "eval_runtime": 2.9929, | |
| "eval_samples_per_second": 371.552, | |
| "eval_steps_per_second": 11.695, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "eval_accuracy": 0.8201140239975191, | |
| "eval_f1": 0.6456589958158997, | |
| "eval_loss": 0.9356908798217773, | |
| "eval_precision": 0.6072306935563208, | |
| "eval_recall": 0.6892797319932998, | |
| "eval_runtime": 2.9882, | |
| "eval_samples_per_second": 372.132, | |
| "eval_steps_per_second": 11.713, | |
| "step": 3904 | |
| }, | |
| { | |
| "epoch": 16.39, | |
| "learning_rate": 2.5901639344262294e-05, | |
| "loss": 0.0661, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 17.0, | |
| "eval_accuracy": 0.8172514968631474, | |
| "eval_f1": 0.6432016686220832, | |
| "eval_loss": 0.9784498810768127, | |
| "eval_precision": 0.60332599657618, | |
| "eval_recall": 0.6887213847012842, | |
| "eval_runtime": 2.968, | |
| "eval_samples_per_second": 374.663, | |
| "eval_steps_per_second": 11.792, | |
| "step": 4148 | |
| }, | |
| { | |
| "epoch": 18.0, | |
| "eval_accuracy": 0.8184442165024689, | |
| "eval_f1": 0.6472832522036575, | |
| "eval_loss": 0.9842237234115601, | |
| "eval_precision": 0.6120925603383927, | |
| "eval_recall": 0.6867671691792295, | |
| "eval_runtime": 2.981, | |
| "eval_samples_per_second": 373.035, | |
| "eval_steps_per_second": 11.741, | |
| "step": 4392 | |
| }, | |
| { | |
| "epoch": 18.44, | |
| "learning_rate": 2.5389344262295083e-05, | |
| "loss": 0.0514, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 19.0, | |
| "eval_accuracy": 0.8163688843300494, | |
| "eval_f1": 0.6476140534871526, | |
| "eval_loss": 1.0097302198410034, | |
| "eval_precision": 0.6104794859120118, | |
| "eval_recall": 0.6895589056393077, | |
| "eval_runtime": 2.9667, | |
| "eval_samples_per_second": 374.823, | |
| "eval_steps_per_second": 11.797, | |
| "step": 4636 | |
| }, | |
| { | |
| "epoch": 20.0, | |
| "eval_accuracy": 0.8167028458290594, | |
| "eval_f1": 0.648761408083442, | |
| "eval_loss": 1.0300242900848389, | |
| "eval_precision": 0.6086105675146771, | |
| "eval_recall": 0.6945840312674484, | |
| "eval_runtime": 3.032, | |
| "eval_samples_per_second": 366.754, | |
| "eval_steps_per_second": 11.544, | |
| "step": 4880 | |
| }, | |
| { | |
| "epoch": 20.49, | |
| "learning_rate": 2.487704918032787e-05, | |
| "loss": 0.0416, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 21.0, | |
| "eval_accuracy": 0.8204718398893156, | |
| "eval_f1": 0.652764946548766, | |
| "eval_loss": 1.0250210762023926, | |
| "eval_precision": 0.6190237797246558, | |
| "eval_recall": 0.6903964265773311, | |
| "eval_runtime": 2.9697, | |
| "eval_samples_per_second": 374.455, | |
| "eval_steps_per_second": 11.786, | |
| "step": 5124 | |
| }, | |
| { | |
| "epoch": 22.0, | |
| "eval_accuracy": 0.8167267002218459, | |
| "eval_f1": 0.6531738730450781, | |
| "eval_loss": 1.087920069694519, | |
| "eval_precision": 0.6170846784206605, | |
| "eval_recall": 0.6937465103294249, | |
| "eval_runtime": 2.983, | |
| "eval_samples_per_second": 372.773, | |
| "eval_steps_per_second": 11.733, | |
| "step": 5368 | |
| }, | |
| { | |
| "epoch": 22.54, | |
| "learning_rate": 2.436475409836066e-05, | |
| "loss": 0.0324, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 23.0, | |
| "eval_accuracy": 0.8127191622337253, | |
| "eval_f1": 0.6434782608695652, | |
| "eval_loss": 1.134914755821228, | |
| "eval_precision": 0.6092814371257484, | |
| "eval_recall": 0.6817420435510888, | |
| "eval_runtime": 2.9583, | |
| "eval_samples_per_second": 375.891, | |
| "eval_steps_per_second": 11.831, | |
| "step": 5612 | |
| }, | |
| { | |
| "epoch": 24.0, | |
| "eval_accuracy": 0.8181102550034589, | |
| "eval_f1": 0.6542006847511194, | |
| "eval_loss": 1.0993841886520386, | |
| "eval_precision": 0.6191425722831505, | |
| "eval_recall": 0.6934673366834171, | |
| "eval_runtime": 2.985, | |
| "eval_samples_per_second": 372.527, | |
| "eval_steps_per_second": 11.725, | |
| "step": 5856 | |
| }, | |
| { | |
| "epoch": 24.59, | |
| "learning_rate": 2.3852459016393442e-05, | |
| "loss": 0.0277, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 25.0, | |
| "eval_accuracy": 0.8152715822618736, | |
| "eval_f1": 0.6543161214032323, | |
| "eval_loss": 1.1400500535964966, | |
| "eval_precision": 0.6180193596425912, | |
| "eval_recall": 0.695142378559464, | |
| "eval_runtime": 3.0938, | |
| "eval_samples_per_second": 359.431, | |
| "eval_steps_per_second": 11.313, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 26.0, | |
| "eval_accuracy": 0.808449225924954, | |
| "eval_f1": 0.6410887880751782, | |
| "eval_loss": 1.1867998838424683, | |
| "eval_precision": 0.5983547060246794, | |
| "eval_recall": 0.6903964265773311, | |
| "eval_runtime": 2.9903, | |
| "eval_samples_per_second": 371.869, | |
| "eval_steps_per_second": 11.704, | |
| "step": 6344 | |
| }, | |
| { | |
| "epoch": 26.64, | |
| "learning_rate": 2.3340163934426228e-05, | |
| "loss": 0.0223, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 27.0, | |
| "eval_accuracy": 0.8138880274802605, | |
| "eval_f1": 0.6558120912851995, | |
| "eval_loss": 1.205185890197754, | |
| "eval_precision": 0.628228074661212, | |
| "eval_recall": 0.6859296482412061, | |
| "eval_runtime": 2.9746, | |
| "eval_samples_per_second": 373.828, | |
| "eval_steps_per_second": 11.766, | |
| "step": 6588 | |
| }, | |
| { | |
| "epoch": 28.0, | |
| "eval_accuracy": 0.81529543665466, | |
| "eval_f1": 0.6529110264160862, | |
| "eval_loss": 1.1963977813720703, | |
| "eval_precision": 0.6168363546064067, | |
| "eval_recall": 0.6934673366834171, | |
| "eval_runtime": 2.9694, | |
| "eval_samples_per_second": 374.481, | |
| "eval_steps_per_second": 11.787, | |
| "step": 6832 | |
| }, | |
| { | |
| "epoch": 28.69, | |
| "learning_rate": 2.2827868852459018e-05, | |
| "loss": 0.019, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 29.0, | |
| "eval_accuracy": 0.820161732783092, | |
| "eval_f1": 0.6533368644067797, | |
| "eval_loss": 1.1897813081741333, | |
| "eval_precision": 0.6214105793450881, | |
| "eval_recall": 0.6887213847012842, | |
| "eval_runtime": 2.9761, | |
| "eval_samples_per_second": 373.647, | |
| "eval_steps_per_second": 11.76, | |
| "step": 7076 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_accuracy": 0.8134586484101047, | |
| "eval_f1": 0.6515647505565013, | |
| "eval_loss": 1.2819464206695557, | |
| "eval_precision": 0.6135635018495684, | |
| "eval_recall": 0.6945840312674484, | |
| "eval_runtime": 2.9771, | |
| "eval_samples_per_second": 373.523, | |
| "eval_steps_per_second": 11.757, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 30.74, | |
| "learning_rate": 2.2315573770491804e-05, | |
| "loss": 0.0159, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 31.0, | |
| "eval_accuracy": 0.8127907254120846, | |
| "eval_f1": 0.6476589066178393, | |
| "eval_loss": 1.2686526775360107, | |
| "eval_precision": 0.609251968503937, | |
| "eval_recall": 0.6912339475153545, | |
| "eval_runtime": 3.0513, | |
| "eval_samples_per_second": 364.436, | |
| "eval_steps_per_second": 11.471, | |
| "step": 7564 | |
| }, | |
| { | |
| "epoch": 32.0, | |
| "eval_accuracy": 0.8158917964743208, | |
| "eval_f1": 0.6522136607026251, | |
| "eval_loss": 1.2997089624404907, | |
| "eval_precision": 0.612760736196319, | |
| "eval_recall": 0.6970965940815187, | |
| "eval_runtime": 3.0022, | |
| "eval_samples_per_second": 370.396, | |
| "eval_steps_per_second": 11.658, | |
| "step": 7808 | |
| }, | |
| { | |
| "epoch": 32.79, | |
| "learning_rate": 2.180327868852459e-05, | |
| "loss": 0.0141, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 33.0, | |
| "eval_accuracy": 0.8157248157248157, | |
| "eval_f1": 0.6490136369654441, | |
| "eval_loss": 1.2799758911132812, | |
| "eval_precision": 0.6172248803827751, | |
| "eval_recall": 0.6842546063651591, | |
| "eval_runtime": 2.9595, | |
| "eval_samples_per_second": 375.745, | |
| "eval_steps_per_second": 11.827, | |
| "step": 8052 | |
| }, | |
| { | |
| "epoch": 34.0, | |
| "eval_accuracy": 0.8141265714081248, | |
| "eval_f1": 0.6543144520910535, | |
| "eval_loss": 1.3110435009002686, | |
| "eval_precision": 0.6220432813286362, | |
| "eval_recall": 0.6901172529313233, | |
| "eval_runtime": 2.9482, | |
| "eval_samples_per_second": 377.185, | |
| "eval_steps_per_second": 11.872, | |
| "step": 8296 | |
| }, | |
| { | |
| "epoch": 34.84, | |
| "learning_rate": 2.1290983606557376e-05, | |
| "loss": 0.0107, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 35.0, | |
| "eval_accuracy": 0.8159633596526801, | |
| "eval_f1": 0.6468897020386828, | |
| "eval_loss": 1.3342597484588623, | |
| "eval_precision": 0.6081081081081081, | |
| "eval_recall": 0.6909547738693468, | |
| "eval_runtime": 2.9541, | |
| "eval_samples_per_second": 376.43, | |
| "eval_steps_per_second": 11.848, | |
| "step": 8540 | |
| }, | |
| { | |
| "epoch": 36.0, | |
| "eval_accuracy": 0.8130292693399489, | |
| "eval_f1": 0.6493064642763675, | |
| "eval_loss": 1.3406134843826294, | |
| "eval_precision": 0.6110837438423645, | |
| "eval_recall": 0.6926298157453936, | |
| "eval_runtime": 2.9685, | |
| "eval_samples_per_second": 374.606, | |
| "eval_steps_per_second": 11.791, | |
| "step": 8784 | |
| }, | |
| { | |
| "epoch": 36.89, | |
| "learning_rate": 2.0778688524590166e-05, | |
| "loss": 0.0106, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 37.0, | |
| "eval_accuracy": 0.8127430166265118, | |
| "eval_f1": 0.6453556923883139, | |
| "eval_loss": 1.3921236991882324, | |
| "eval_precision": 0.6079980251789682, | |
| "eval_recall": 0.6876046901172529, | |
| "eval_runtime": 2.9551, | |
| "eval_samples_per_second": 376.302, | |
| "eval_steps_per_second": 11.844, | |
| "step": 9028 | |
| }, | |
| { | |
| "epoch": 38.0, | |
| "eval_accuracy": 0.8099997614560721, | |
| "eval_f1": 0.6453305351521511, | |
| "eval_loss": 1.4060559272766113, | |
| "eval_precision": 0.6086095992083127, | |
| "eval_recall": 0.6867671691792295, | |
| "eval_runtime": 2.9714, | |
| "eval_samples_per_second": 374.231, | |
| "eval_steps_per_second": 11.779, | |
| "step": 9272 | |
| }, | |
| { | |
| "epoch": 38.93, | |
| "learning_rate": 2.0266393442622952e-05, | |
| "loss": 0.0088, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 39.0, | |
| "eval_accuracy": 0.8165835738651273, | |
| "eval_f1": 0.6592208482914507, | |
| "eval_loss": 1.382816195487976, | |
| "eval_precision": 0.6293475501396294, | |
| "eval_recall": 0.692071468453378, | |
| "eval_runtime": 2.9744, | |
| "eval_samples_per_second": 373.857, | |
| "eval_steps_per_second": 11.767, | |
| "step": 9516 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "eval_accuracy": 0.8129577061615897, | |
| "eval_f1": 0.6572372769332453, | |
| "eval_loss": 1.42629873752594, | |
| "eval_precision": 0.6241526487572182, | |
| "eval_recall": 0.6940256839754327, | |
| "eval_runtime": 3.0851, | |
| "eval_samples_per_second": 360.448, | |
| "eval_steps_per_second": 11.345, | |
| "step": 9760 | |
| }, | |
| { | |
| "epoch": 40.98, | |
| "learning_rate": 1.975409836065574e-05, | |
| "loss": 0.0086, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 41.0, | |
| "eval_accuracy": 0.8185157796808282, | |
| "eval_f1": 0.6573940427765386, | |
| "eval_loss": 1.3521106243133545, | |
| "eval_precision": 0.620203020549641, | |
| "eval_recall": 0.6993299832495813, | |
| "eval_runtime": 2.9673, | |
| "eval_samples_per_second": 374.747, | |
| "eval_steps_per_second": 11.795, | |
| "step": 10004 | |
| }, | |
| { | |
| "epoch": 42.0, | |
| "eval_accuracy": 0.8196369361417906, | |
| "eval_f1": 0.6713979646491698, | |
| "eval_loss": 1.372209072113037, | |
| "eval_precision": 0.6451363870303655, | |
| "eval_recall": 0.6998883305415968, | |
| "eval_runtime": 2.9625, | |
| "eval_samples_per_second": 375.361, | |
| "eval_steps_per_second": 11.814, | |
| "step": 10248 | |
| }, | |
| { | |
| "epoch": 43.0, | |
| "eval_accuracy": 0.822594880847308, | |
| "eval_f1": 0.6647074539139727, | |
| "eval_loss": 1.3783916234970093, | |
| "eval_precision": 0.6372950819672131, | |
| "eval_recall": 0.6945840312674484, | |
| "eval_runtime": 2.9632, | |
| "eval_samples_per_second": 375.273, | |
| "eval_steps_per_second": 11.812, | |
| "step": 10492 | |
| }, | |
| { | |
| "epoch": 43.03, | |
| "learning_rate": 1.9241803278688525e-05, | |
| "loss": 0.0075, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 44.0, | |
| "eval_accuracy": 0.8140072994441927, | |
| "eval_f1": 0.6623151725056613, | |
| "eval_loss": 1.433977484703064, | |
| "eval_precision": 0.6333757961783439, | |
| "eval_recall": 0.6940256839754327, | |
| "eval_runtime": 2.9882, | |
| "eval_samples_per_second": 372.133, | |
| "eval_steps_per_second": 11.713, | |
| "step": 10736 | |
| }, | |
| { | |
| "epoch": 45.0, | |
| "eval_accuracy": 0.816130340402185, | |
| "eval_f1": 0.6643708609271523, | |
| "eval_loss": 1.390194058418274, | |
| "eval_precision": 0.6320564516129032, | |
| "eval_recall": 0.7001675041876047, | |
| "eval_runtime": 2.9941, | |
| "eval_samples_per_second": 371.401, | |
| "eval_steps_per_second": 11.69, | |
| "step": 10980 | |
| }, | |
| { | |
| "epoch": 45.08, | |
| "learning_rate": 1.872950819672131e-05, | |
| "loss": 0.0066, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 46.0, | |
| "eval_accuracy": 0.8162496123661173, | |
| "eval_f1": 0.6585943669386681, | |
| "eval_loss": 1.401918888092041, | |
| "eval_precision": 0.62300796812749, | |
| "eval_recall": 0.6984924623115578, | |
| "eval_runtime": 2.9812, | |
| "eval_samples_per_second": 373.006, | |
| "eval_steps_per_second": 11.74, | |
| "step": 11224 | |
| }, | |
| { | |
| "epoch": 47.0, | |
| "eval_accuracy": 0.816130340402185, | |
| "eval_f1": 0.6548463356973996, | |
| "eval_loss": 1.431990623474121, | |
| "eval_precision": 0.6183035714285714, | |
| "eval_recall": 0.6959798994974874, | |
| "eval_runtime": 2.9274, | |
| "eval_samples_per_second": 379.864, | |
| "eval_steps_per_second": 11.956, | |
| "step": 11468 | |
| }, | |
| { | |
| "epoch": 47.13, | |
| "learning_rate": 1.82172131147541e-05, | |
| "loss": 0.0067, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 48.0, | |
| "eval_accuracy": 0.8200424608191599, | |
| "eval_f1": 0.6645460569913849, | |
| "eval_loss": 1.4461051225662231, | |
| "eval_precision": 0.6326015644713601, | |
| "eval_recall": 0.6998883305415968, | |
| "eval_runtime": 3.0764, | |
| "eval_samples_per_second": 361.458, | |
| "eval_steps_per_second": 11.377, | |
| "step": 11712 | |
| }, | |
| { | |
| "epoch": 49.0, | |
| "eval_accuracy": 0.8202332959614513, | |
| "eval_f1": 0.6595464135021096, | |
| "eval_loss": 1.432677984237671, | |
| "eval_precision": 0.6249375312343828, | |
| "eval_recall": 0.69821328866555, | |
| "eval_runtime": 3.0963, | |
| "eval_samples_per_second": 359.141, | |
| "eval_steps_per_second": 11.304, | |
| "step": 11956 | |
| }, | |
| { | |
| "epoch": 49.18, | |
| "learning_rate": 1.7704918032786887e-05, | |
| "loss": 0.0054, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 50.0, | |
| "eval_accuracy": 0.8176331671477303, | |
| "eval_f1": 0.6632, | |
| "eval_loss": 1.4615715742111206, | |
| "eval_precision": 0.6347626339969372, | |
| "eval_recall": 0.6943048576214406, | |
| "eval_runtime": 3.0477, | |
| "eval_samples_per_second": 364.866, | |
| "eval_steps_per_second": 11.484, | |
| "step": 12200 | |
| }, | |
| { | |
| "epoch": 51.0, | |
| "eval_accuracy": 0.8177047303260896, | |
| "eval_f1": 0.6543322475570033, | |
| "eval_loss": 1.4536991119384766, | |
| "eval_precision": 0.6134864402638651, | |
| "eval_recall": 0.7010050251256281, | |
| "eval_runtime": 2.9579, | |
| "eval_samples_per_second": 375.937, | |
| "eval_steps_per_second": 11.833, | |
| "step": 12444 | |
| }, | |
| { | |
| "epoch": 51.23, | |
| "learning_rate": 1.7192622950819673e-05, | |
| "loss": 0.0052, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 52.0, | |
| "eval_accuracy": 0.8095703823859164, | |
| "eval_f1": 0.6560255387071029, | |
| "eval_loss": 1.5621511936187744, | |
| "eval_precision": 0.6265243902439024, | |
| "eval_recall": 0.6884422110552764, | |
| "eval_runtime": 3.0041, | |
| "eval_samples_per_second": 370.165, | |
| "eval_steps_per_second": 11.651, | |
| "step": 12688 | |
| }, | |
| { | |
| "epoch": 53.0, | |
| "eval_accuracy": 0.8235967653443381, | |
| "eval_f1": 0.6670200079501789, | |
| "eval_loss": 1.4217201471328735, | |
| "eval_precision": 0.6348045397225726, | |
| "eval_recall": 0.7026800670016751, | |
| "eval_runtime": 3.0478, | |
| "eval_samples_per_second": 364.848, | |
| "eval_steps_per_second": 11.484, | |
| "step": 12932 | |
| }, | |
| { | |
| "epoch": 53.28, | |
| "learning_rate": 1.668032786885246e-05, | |
| "loss": 0.0051, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 54.0, | |
| "eval_accuracy": 0.8217361227069965, | |
| "eval_f1": 0.6597038603913273, | |
| "eval_loss": 1.4624608755111694, | |
| "eval_precision": 0.6265695630336514, | |
| "eval_recall": 0.696538246789503, | |
| "eval_runtime": 3.0888, | |
| "eval_samples_per_second": 360.016, | |
| "eval_steps_per_second": 11.331, | |
| "step": 13176 | |
| }, | |
| { | |
| "epoch": 55.0, | |
| "eval_accuracy": 0.8257198063023306, | |
| "eval_f1": 0.6645213193885761, | |
| "eval_loss": 1.4358925819396973, | |
| "eval_precision": 0.6393188854489165, | |
| "eval_recall": 0.6917922948073701, | |
| "eval_runtime": 3.0221, | |
| "eval_samples_per_second": 367.953, | |
| "eval_steps_per_second": 11.581, | |
| "step": 13420 | |
| }, | |
| { | |
| "epoch": 55.33, | |
| "learning_rate": 1.6168032786885245e-05, | |
| "loss": 0.0049, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 56.0, | |
| "eval_accuracy": 0.8230719687030367, | |
| "eval_f1": 0.6701528559935639, | |
| "eval_loss": 1.4616944789886475, | |
| "eval_precision": 0.6447368421052632, | |
| "eval_recall": 0.6976549413735343, | |
| "eval_runtime": 3.0092, | |
| "eval_samples_per_second": 369.528, | |
| "eval_steps_per_second": 11.631, | |
| "step": 13664 | |
| }, | |
| { | |
| "epoch": 57.0, | |
| "eval_accuracy": 0.8181102550034589, | |
| "eval_f1": 0.6630275595792837, | |
| "eval_loss": 1.5170940160751343, | |
| "eval_precision": 0.6337490455586663, | |
| "eval_recall": 0.695142378559464, | |
| "eval_runtime": 2.9576, | |
| "eval_samples_per_second": 375.979, | |
| "eval_steps_per_second": 11.834, | |
| "step": 13908 | |
| }, | |
| { | |
| "epoch": 57.38, | |
| "learning_rate": 1.5655737704918035e-05, | |
| "loss": 0.0037, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 58.0, | |
| "eval_accuracy": 0.8205672574604613, | |
| "eval_f1": 0.6667548967707781, | |
| "eval_loss": 1.4998589754104614, | |
| "eval_precision": 0.6338701560140916, | |
| "eval_recall": 0.7032384142936907, | |
| "eval_runtime": 2.9519, | |
| "eval_samples_per_second": 376.709, | |
| "eval_steps_per_second": 11.857, | |
| "step": 14152 | |
| }, | |
| { | |
| "epoch": 59.0, | |
| "eval_accuracy": 0.8208296557811121, | |
| "eval_f1": 0.6617453203269179, | |
| "eval_loss": 1.484113335609436, | |
| "eval_precision": 0.6268731268731269, | |
| "eval_recall": 0.7007258514796203, | |
| "eval_runtime": 2.9535, | |
| "eval_samples_per_second": 376.498, | |
| "eval_steps_per_second": 11.85, | |
| "step": 14396 | |
| }, | |
| { | |
| "epoch": 59.43, | |
| "learning_rate": 1.514344262295082e-05, | |
| "loss": 0.004, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 60.0, | |
| "eval_accuracy": 0.8244316690918633, | |
| "eval_f1": 0.6695859872611465, | |
| "eval_loss": 1.436055302619934, | |
| "eval_precision": 0.6380880121396054, | |
| "eval_recall": 0.7043551088777219, | |
| "eval_runtime": 2.9713, | |
| "eval_samples_per_second": 374.253, | |
| "eval_steps_per_second": 11.78, | |
| "step": 14640 | |
| }, | |
| { | |
| "epoch": 61.0, | |
| "eval_accuracy": 0.8235252021659789, | |
| "eval_f1": 0.6716417910447762, | |
| "eval_loss": 1.4800474643707275, | |
| "eval_precision": 0.6425293217746048, | |
| "eval_recall": 0.7035175879396985, | |
| "eval_runtime": 2.9663, | |
| "eval_samples_per_second": 374.881, | |
| "eval_steps_per_second": 11.799, | |
| "step": 14884 | |
| }, | |
| { | |
| "epoch": 61.48, | |
| "learning_rate": 1.4631147540983607e-05, | |
| "loss": 0.004, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 62.0, | |
| "eval_accuracy": 0.8240977075928533, | |
| "eval_f1": 0.664367206155479, | |
| "eval_loss": 1.4699968099594116, | |
| "eval_precision": 0.6329625884732053, | |
| "eval_recall": 0.6990508096035735, | |
| "eval_runtime": 2.9625, | |
| "eval_samples_per_second": 375.361, | |
| "eval_steps_per_second": 11.814, | |
| "step": 15128 | |
| }, | |
| { | |
| "epoch": 63.0, | |
| "eval_accuracy": 0.821211326065695, | |
| "eval_f1": 0.6643754130865829, | |
| "eval_loss": 1.5107179880142212, | |
| "eval_precision": 0.6309314586994728, | |
| "eval_recall": 0.7015633724176438, | |
| "eval_runtime": 2.9695, | |
| "eval_samples_per_second": 374.47, | |
| "eval_steps_per_second": 11.786, | |
| "step": 15372 | |
| }, | |
| { | |
| "epoch": 63.52, | |
| "learning_rate": 1.4118852459016394e-05, | |
| "loss": 0.0037, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 64.0, | |
| "eval_accuracy": 0.8227141528112402, | |
| "eval_f1": 0.6691489361702128, | |
| "eval_loss": 1.5131914615631104, | |
| "eval_precision": 0.6389029964448959, | |
| "eval_recall": 0.7024008933556672, | |
| "eval_runtime": 2.9514, | |
| "eval_samples_per_second": 376.769, | |
| "eval_steps_per_second": 11.859, | |
| "step": 15616 | |
| }, | |
| { | |
| "epoch": 65.0, | |
| "eval_accuracy": 0.8239307268433482, | |
| "eval_f1": 0.6631481725821349, | |
| "eval_loss": 1.5229130983352661, | |
| "eval_precision": 0.6287215411558669, | |
| "eval_recall": 0.7015633724176438, | |
| "eval_runtime": 3.0184, | |
| "eval_samples_per_second": 368.409, | |
| "eval_steps_per_second": 11.596, | |
| "step": 15860 | |
| }, | |
| { | |
| "epoch": 65.57, | |
| "learning_rate": 1.3606557377049181e-05, | |
| "loss": 0.0033, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 66.0, | |
| "eval_accuracy": 0.8242408339495718, | |
| "eval_f1": 0.6695929768555469, | |
| "eval_loss": 1.5573978424072266, | |
| "eval_precision": 0.6394817073170732, | |
| "eval_recall": 0.7026800670016751, | |
| "eval_runtime": 2.9796, | |
| "eval_samples_per_second": 373.204, | |
| "eval_steps_per_second": 11.747, | |
| "step": 16104 | |
| }, | |
| { | |
| "epoch": 67.0, | |
| "eval_accuracy": 0.8195892273562176, | |
| "eval_f1": 0.6637761135199055, | |
| "eval_loss": 1.5216217041015625, | |
| "eval_precision": 0.6269545793000745, | |
| "eval_recall": 0.7051926298157454, | |
| "eval_runtime": 2.9602, | |
| "eval_samples_per_second": 375.655, | |
| "eval_steps_per_second": 11.824, | |
| "step": 16348 | |
| }, | |
| { | |
| "epoch": 67.62, | |
| "learning_rate": 1.3094262295081968e-05, | |
| "loss": 0.0033, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 68.0, | |
| "eval_accuracy": 0.8242169795567854, | |
| "eval_f1": 0.6635576282478347, | |
| "eval_loss": 1.4876649379730225, | |
| "eval_precision": 0.6347183278103492, | |
| "eval_recall": 0.695142378559464, | |
| "eval_runtime": 2.9571, | |
| "eval_samples_per_second": 376.04, | |
| "eval_steps_per_second": 11.836, | |
| "step": 16592 | |
| }, | |
| { | |
| "epoch": 69.0, | |
| "eval_accuracy": 0.8194699553922855, | |
| "eval_f1": 0.6630635380964935, | |
| "eval_loss": 1.5372997522354126, | |
| "eval_precision": 0.6281218781218781, | |
| "eval_recall": 0.7021217197096594, | |
| "eval_runtime": 3.0929, | |
| "eval_samples_per_second": 359.536, | |
| "eval_steps_per_second": 11.316, | |
| "step": 16836 | |
| }, | |
| { | |
| "epoch": 69.67, | |
| "learning_rate": 1.2581967213114756e-05, | |
| "loss": 0.0026, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 70.0, | |
| "eval_accuracy": 0.8200663152119463, | |
| "eval_f1": 0.6651637713831056, | |
| "eval_loss": 1.5521858930587769, | |
| "eval_precision": 0.6334933063905026, | |
| "eval_recall": 0.7001675041876047, | |
| "eval_runtime": 3.0082, | |
| "eval_samples_per_second": 369.652, | |
| "eval_steps_per_second": 11.635, | |
| "step": 17080 | |
| }, | |
| { | |
| "epoch": 71.0, | |
| "eval_accuracy": 0.8226902984184538, | |
| "eval_f1": 0.6691449814126393, | |
| "eval_loss": 1.5180128812789917, | |
| "eval_precision": 0.6379746835443038, | |
| "eval_recall": 0.7035175879396985, | |
| "eval_runtime": 2.9978, | |
| "eval_samples_per_second": 370.939, | |
| "eval_steps_per_second": 11.675, | |
| "step": 17324 | |
| }, | |
| { | |
| "epoch": 71.72, | |
| "learning_rate": 1.206967213114754e-05, | |
| "loss": 0.0024, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 72.0, | |
| "eval_accuracy": 0.8218076858853558, | |
| "eval_f1": 0.67304324397144, | |
| "eval_loss": 1.5517120361328125, | |
| "eval_precision": 0.6503514709711012, | |
| "eval_recall": 0.6973757677275265, | |
| "eval_runtime": 2.9567, | |
| "eval_samples_per_second": 376.089, | |
| "eval_steps_per_second": 11.837, | |
| "step": 17568 | |
| }, | |
| { | |
| "epoch": 73.0, | |
| "eval_accuracy": 0.8206388206388207, | |
| "eval_f1": 0.6658723854911305, | |
| "eval_loss": 1.539225697517395, | |
| "eval_precision": 0.6331822759315207, | |
| "eval_recall": 0.7021217197096594, | |
| "eval_runtime": 2.9669, | |
| "eval_samples_per_second": 374.796, | |
| "eval_steps_per_second": 11.797, | |
| "step": 17812 | |
| }, | |
| { | |
| "epoch": 73.77, | |
| "learning_rate": 1.1557377049180328e-05, | |
| "loss": 0.0026, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 74.0, | |
| "eval_accuracy": 0.8245986498413683, | |
| "eval_f1": 0.669957310565635, | |
| "eval_loss": 1.5395687818527222, | |
| "eval_precision": 0.641543178334185, | |
| "eval_recall": 0.7010050251256281, | |
| "eval_runtime": 2.9773, | |
| "eval_samples_per_second": 373.49, | |
| "eval_steps_per_second": 11.756, | |
| "step": 18056 | |
| }, | |
| { | |
| "epoch": 75.0, | |
| "eval_accuracy": 0.8233343670236875, | |
| "eval_f1": 0.6740153246404087, | |
| "eval_loss": 1.5637731552124023, | |
| "eval_precision": 0.6499870365569095, | |
| "eval_recall": 0.6998883305415968, | |
| "eval_runtime": 2.9662, | |
| "eval_samples_per_second": 374.894, | |
| "eval_steps_per_second": 11.8, | |
| "step": 18300 | |
| }, | |
| { | |
| "epoch": 75.82, | |
| "learning_rate": 1.1045081967213114e-05, | |
| "loss": 0.0019, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 76.0, | |
| "eval_accuracy": 0.8201855871758784, | |
| "eval_f1": 0.6666666666666666, | |
| "eval_loss": 1.5789735317230225, | |
| "eval_precision": 0.6437857514300572, | |
| "eval_recall": 0.6912339475153545, | |
| "eval_runtime": 2.9784, | |
| "eval_samples_per_second": 373.357, | |
| "eval_steps_per_second": 11.751, | |
| "step": 18544 | |
| }, | |
| { | |
| "epoch": 77.0, | |
| "eval_accuracy": 0.8216168507430643, | |
| "eval_f1": 0.676486341724692, | |
| "eval_loss": 1.5545753240585327, | |
| "eval_precision": 0.6500257334019557, | |
| "eval_recall": 0.7051926298157454, | |
| "eval_runtime": 2.9887, | |
| "eval_samples_per_second": 372.065, | |
| "eval_steps_per_second": 11.711, | |
| "step": 18788 | |
| }, | |
| { | |
| "epoch": 77.87, | |
| "learning_rate": 1.0532786885245902e-05, | |
| "loss": 0.0029, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 78.0, | |
| "eval_accuracy": 0.8236206197371246, | |
| "eval_f1": 0.6684357171288311, | |
| "eval_loss": 1.5374187231063843, | |
| "eval_precision": 0.6369152970922882, | |
| "eval_recall": 0.7032384142936907, | |
| "eval_runtime": 2.9659, | |
| "eval_samples_per_second": 374.933, | |
| "eval_steps_per_second": 11.801, | |
| "step": 19032 | |
| }, | |
| { | |
| "epoch": 79.0, | |
| "eval_accuracy": 0.8180148374323132, | |
| "eval_f1": 0.6651595744680852, | |
| "eval_loss": 1.5923025608062744, | |
| "eval_precision": 0.6350939563230066, | |
| "eval_recall": 0.69821328866555, | |
| "eval_runtime": 2.9684, | |
| "eval_samples_per_second": 374.615, | |
| "eval_steps_per_second": 11.791, | |
| "step": 19276 | |
| }, | |
| { | |
| "epoch": 79.92, | |
| "learning_rate": 1.0020491803278688e-05, | |
| "loss": 0.0015, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 80.0, | |
| "eval_accuracy": 0.8245986498413683, | |
| "eval_f1": 0.6673737239825004, | |
| "eval_loss": 1.5727756023406982, | |
| "eval_precision": 0.6354455945468316, | |
| "eval_recall": 0.7026800670016751, | |
| "eval_runtime": 2.9791, | |
| "eval_samples_per_second": 373.261, | |
| "eval_steps_per_second": 11.748, | |
| "step": 19520 | |
| }, | |
| { | |
| "epoch": 81.0, | |
| "eval_accuracy": 0.8228811335607452, | |
| "eval_f1": 0.6686279753944906, | |
| "eval_loss": 1.564627766609192, | |
| "eval_precision": 0.6416837782340863, | |
| "eval_recall": 0.6979341150195422, | |
| "eval_runtime": 2.9678, | |
| "eval_samples_per_second": 374.693, | |
| "eval_steps_per_second": 11.793, | |
| "step": 19764 | |
| }, | |
| { | |
| "epoch": 81.97, | |
| "learning_rate": 9.508196721311476e-06, | |
| "loss": 0.0019, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 82.0, | |
| "eval_accuracy": 0.8210920541017629, | |
| "eval_f1": 0.6615000656771313, | |
| "eval_loss": 1.5844708681106567, | |
| "eval_precision": 0.6246588935747953, | |
| "eval_recall": 0.7029592406476829, | |
| "eval_runtime": 2.9641, | |
| "eval_samples_per_second": 375.15, | |
| "eval_steps_per_second": 11.808, | |
| "step": 20008 | |
| }, | |
| { | |
| "epoch": 83.0, | |
| "eval_accuracy": 0.819279120249994, | |
| "eval_f1": 0.666935159081756, | |
| "eval_loss": 1.589419960975647, | |
| "eval_precision": 0.6423584173778123, | |
| "eval_recall": 0.6934673366834171, | |
| "eval_runtime": 2.9637, | |
| "eval_samples_per_second": 375.21, | |
| "eval_steps_per_second": 11.81, | |
| "step": 20252 | |
| }, | |
| { | |
| "epoch": 84.0, | |
| "eval_accuracy": 0.8169175353641374, | |
| "eval_f1": 0.665859238325932, | |
| "eval_loss": 1.6702436208724976, | |
| "eval_precision": 0.6427643543777605, | |
| "eval_recall": 0.690675600223339, | |
| "eval_runtime": 2.99, | |
| "eval_samples_per_second": 371.906, | |
| "eval_steps_per_second": 11.706, | |
| "step": 20496 | |
| }, | |
| { | |
| "epoch": 84.02, | |
| "learning_rate": 8.995901639344264e-06, | |
| "loss": 0.0012, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 85.0, | |
| "eval_accuracy": 0.8188974499654111, | |
| "eval_f1": 0.6666666666666667, | |
| "eval_loss": 1.6313210725784302, | |
| "eval_precision": 0.6341647770219199, | |
| "eval_recall": 0.7026800670016751, | |
| "eval_runtime": 3.0786, | |
| "eval_samples_per_second": 361.198, | |
| "eval_steps_per_second": 11.369, | |
| "step": 20740 | |
| }, | |
| { | |
| "epoch": 86.0, | |
| "eval_accuracy": 0.8231912406669688, | |
| "eval_f1": 0.6679915209326974, | |
| "eval_loss": 1.5829322338104248, | |
| "eval_precision": 0.6356530509329299, | |
| "eval_recall": 0.7037967615857063, | |
| "eval_runtime": 2.9543, | |
| "eval_samples_per_second": 376.397, | |
| "eval_steps_per_second": 11.847, | |
| "step": 20984 | |
| }, | |
| { | |
| "epoch": 86.07, | |
| "learning_rate": 8.483606557377049e-06, | |
| "loss": 0.0015, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 87.0, | |
| "eval_accuracy": 0.8209966365306172, | |
| "eval_f1": 0.672317880794702, | |
| "eval_loss": 1.605576753616333, | |
| "eval_precision": 0.639616935483871, | |
| "eval_recall": 0.7085427135678392, | |
| "eval_runtime": 2.9894, | |
| "eval_samples_per_second": 371.983, | |
| "eval_steps_per_second": 11.708, | |
| "step": 21228 | |
| }, | |
| { | |
| "epoch": 88.0, | |
| "eval_accuracy": 0.8224994632761623, | |
| "eval_f1": 0.6773120425815037, | |
| "eval_loss": 1.5823140144348145, | |
| "eval_precision": 0.6470887363335875, | |
| "eval_recall": 0.7104969290898939, | |
| "eval_runtime": 2.973, | |
| "eval_samples_per_second": 374.028, | |
| "eval_steps_per_second": 11.772, | |
| "step": 21472 | |
| }, | |
| { | |
| "epoch": 88.11, | |
| "learning_rate": 7.971311475409837e-06, | |
| "loss": 0.0015, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 89.0, | |
| "eval_accuracy": 0.8249326113403783, | |
| "eval_f1": 0.6675521317572054, | |
| "eval_loss": 1.573556661605835, | |
| "eval_precision": 0.6366860907017988, | |
| "eval_recall": 0.7015633724176438, | |
| "eval_runtime": 2.9619, | |
| "eval_samples_per_second": 375.438, | |
| "eval_steps_per_second": 11.817, | |
| "step": 21716 | |
| }, | |
| { | |
| "epoch": 90.0, | |
| "eval_accuracy": 0.823644474129911, | |
| "eval_f1": 0.6724645437516724, | |
| "eval_loss": 1.5920721292495728, | |
| "eval_precision": 0.64568345323741, | |
| "eval_recall": 0.7015633724176438, | |
| "eval_runtime": 2.9692, | |
| "eval_samples_per_second": 374.506, | |
| "eval_steps_per_second": 11.788, | |
| "step": 21960 | |
| }, | |
| { | |
| "epoch": 90.16, | |
| "learning_rate": 7.459016393442623e-06, | |
| "loss": 0.0012, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 91.0, | |
| "eval_accuracy": 0.8230958230958231, | |
| "eval_f1": 0.6684364215556146, | |
| "eval_loss": 1.6113594770431519, | |
| "eval_precision": 0.6371457489878543, | |
| "eval_recall": 0.7029592406476829, | |
| "eval_runtime": 2.9681, | |
| "eval_samples_per_second": 374.651, | |
| "eval_steps_per_second": 11.792, | |
| "step": 22204 | |
| }, | |
| { | |
| "epoch": 92.0, | |
| "eval_accuracy": 0.824527086663009, | |
| "eval_f1": 0.6708355508249069, | |
| "eval_loss": 1.5752336978912354, | |
| "eval_precision": 0.6408235892221658, | |
| "eval_recall": 0.7037967615857063, | |
| "eval_runtime": 2.9615, | |
| "eval_samples_per_second": 375.482, | |
| "eval_steps_per_second": 11.818, | |
| "step": 22448 | |
| }, | |
| { | |
| "epoch": 92.21, | |
| "learning_rate": 6.946721311475411e-06, | |
| "loss": 0.0014, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 93.0, | |
| "eval_accuracy": 0.8216884139214237, | |
| "eval_f1": 0.6672859986728599, | |
| "eval_loss": 1.6123404502868652, | |
| "eval_precision": 0.6359726789779914, | |
| "eval_recall": 0.7018425460636516, | |
| "eval_runtime": 3.0214, | |
| "eval_samples_per_second": 368.046, | |
| "eval_steps_per_second": 11.584, | |
| "step": 22692 | |
| }, | |
| { | |
| "epoch": 94.0, | |
| "eval_accuracy": 0.8221177929915794, | |
| "eval_f1": 0.6681721572794899, | |
| "eval_loss": 1.618289589881897, | |
| "eval_precision": 0.6373542828180436, | |
| "eval_recall": 0.7021217197096594, | |
| "eval_runtime": 2.9574, | |
| "eval_samples_per_second": 376.01, | |
| "eval_steps_per_second": 11.835, | |
| "step": 22936 | |
| }, | |
| { | |
| "epoch": 94.26, | |
| "learning_rate": 6.434426229508197e-06, | |
| "loss": 0.0009, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 95.0, | |
| "eval_accuracy": 0.8274611769757401, | |
| "eval_f1": 0.6721267454350162, | |
| "eval_loss": 1.6077880859375, | |
| "eval_precision": 0.6474392136575272, | |
| "eval_recall": 0.6987716359575656, | |
| "eval_runtime": 2.9598, | |
| "eval_samples_per_second": 375.703, | |
| "eval_steps_per_second": 11.825, | |
| "step": 23180 | |
| }, | |
| { | |
| "epoch": 96.0, | |
| "eval_accuracy": 0.8245747954485818, | |
| "eval_f1": 0.6682679476914866, | |
| "eval_loss": 1.6201205253601074, | |
| "eval_precision": 0.6400817995910021, | |
| "eval_recall": 0.6990508096035735, | |
| "eval_runtime": 2.9623, | |
| "eval_samples_per_second": 375.385, | |
| "eval_steps_per_second": 11.815, | |
| "step": 23424 | |
| }, | |
| { | |
| "epoch": 96.31, | |
| "learning_rate": 5.922131147540984e-06, | |
| "loss": 0.0008, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 97.0, | |
| "eval_accuracy": 0.8238114548794161, | |
| "eval_f1": 0.6687067589143161, | |
| "eval_loss": 1.6216107606887817, | |
| "eval_precision": 0.6387900355871886, | |
| "eval_recall": 0.7015633724176438, | |
| "eval_runtime": 2.9859, | |
| "eval_samples_per_second": 372.411, | |
| "eval_steps_per_second": 11.722, | |
| "step": 23668 | |
| }, | |
| { | |
| "epoch": 98.0, | |
| "eval_accuracy": 0.8243839603062904, | |
| "eval_f1": 0.6703077128013853, | |
| "eval_loss": 1.6113009452819824, | |
| "eval_precision": 0.6410191082802548, | |
| "eval_recall": 0.7024008933556672, | |
| "eval_runtime": 2.9619, | |
| "eval_samples_per_second": 375.438, | |
| "eval_steps_per_second": 11.817, | |
| "step": 23912 | |
| }, | |
| { | |
| "epoch": 98.36, | |
| "learning_rate": 5.409836065573771e-06, | |
| "loss": 0.0011, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 99.0, | |
| "eval_accuracy": 0.824527086663009, | |
| "eval_f1": 0.6751609442060086, | |
| "eval_loss": 1.5995452404022217, | |
| "eval_precision": 0.6497160557563242, | |
| "eval_recall": 0.7026800670016751, | |
| "eval_runtime": 3.0743, | |
| "eval_samples_per_second": 361.705, | |
| "eval_steps_per_second": 11.385, | |
| "step": 24156 | |
| }, | |
| { | |
| "epoch": 100.0, | |
| "eval_accuracy": 0.8258629326590492, | |
| "eval_f1": 0.6711105185975204, | |
| "eval_loss": 1.5953351259231567, | |
| "eval_precision": 0.642255677468742, | |
| "eval_recall": 0.7026800670016751, | |
| "eval_runtime": 2.974, | |
| "eval_samples_per_second": 373.912, | |
| "eval_steps_per_second": 11.769, | |
| "step": 24400 | |
| }, | |
| { | |
| "epoch": 100.41, | |
| "learning_rate": 4.897540983606557e-06, | |
| "loss": 0.0009, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 101.0, | |
| "eval_accuracy": 0.8247894849836598, | |
| "eval_f1": 0.6724552497996259, | |
| "eval_loss": 1.6178245544433594, | |
| "eval_precision": 0.6447233606557377, | |
| "eval_recall": 0.7026800670016751, | |
| "eval_runtime": 3.0886, | |
| "eval_samples_per_second": 360.031, | |
| "eval_steps_per_second": 11.332, | |
| "step": 24644 | |
| }, | |
| { | |
| "epoch": 102.0, | |
| "eval_accuracy": 0.8256720975167577, | |
| "eval_f1": 0.67206585236325, | |
| "eval_loss": 1.6170806884765625, | |
| "eval_precision": 0.640759493670886, | |
| "eval_recall": 0.7065884980457845, | |
| "eval_runtime": 2.967, | |
| "eval_samples_per_second": 374.794, | |
| "eval_steps_per_second": 11.797, | |
| "step": 24888 | |
| }, | |
| { | |
| "epoch": 102.46, | |
| "learning_rate": 4.385245901639344e-06, | |
| "loss": 0.0006, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 103.0, | |
| "eval_accuracy": 0.8270795066911572, | |
| "eval_f1": 0.6780794436271232, | |
| "eval_loss": 1.6054375171661377, | |
| "eval_precision": 0.6508344030808729, | |
| "eval_recall": 0.7077051926298158, | |
| "eval_runtime": 2.9599, | |
| "eval_samples_per_second": 375.683, | |
| "eval_steps_per_second": 11.825, | |
| "step": 25132 | |
| }, | |
| { | |
| "epoch": 104.0, | |
| "eval_accuracy": 0.8251234464826698, | |
| "eval_f1": 0.6701319472211115, | |
| "eval_loss": 1.621781826019287, | |
| "eval_precision": 0.6411629686304514, | |
| "eval_recall": 0.7018425460636516, | |
| "eval_runtime": 3.0743, | |
| "eval_samples_per_second": 361.711, | |
| "eval_steps_per_second": 11.385, | |
| "step": 25376 | |
| }, | |
| { | |
| "epoch": 104.51, | |
| "learning_rate": 3.872950819672131e-06, | |
| "loss": 0.0008, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 105.0, | |
| "eval_accuracy": 0.8244555234846497, | |
| "eval_f1": 0.6738082485270488, | |
| "eval_loss": 1.6307542324066162, | |
| "eval_precision": 0.6474523932063819, | |
| "eval_recall": 0.7024008933556672, | |
| "eval_runtime": 2.9786, | |
| "eval_samples_per_second": 373.327, | |
| "eval_steps_per_second": 11.75, | |
| "step": 25620 | |
| }, | |
| { | |
| "epoch": 106.0, | |
| "eval_accuracy": 0.8267216907993608, | |
| "eval_f1": 0.6755638596022955, | |
| "eval_loss": 1.6341726779937744, | |
| "eval_precision": 0.6471490667348504, | |
| "eval_recall": 0.7065884980457845, | |
| "eval_runtime": 2.9836, | |
| "eval_samples_per_second": 372.709, | |
| "eval_steps_per_second": 11.731, | |
| "step": 25864 | |
| }, | |
| { | |
| "epoch": 106.56, | |
| "learning_rate": 3.3606557377049183e-06, | |
| "loss": 0.0004, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 107.0, | |
| "eval_accuracy": 0.8253619904105342, | |
| "eval_f1": 0.673863787818206, | |
| "eval_loss": 1.634595274925232, | |
| "eval_precision": 0.6447334863555215, | |
| "eval_recall": 0.705750977107761, | |
| "eval_runtime": 2.9821, | |
| "eval_samples_per_second": 372.893, | |
| "eval_steps_per_second": 11.737, | |
| "step": 26108 | |
| }, | |
| { | |
| "epoch": 108.0, | |
| "eval_accuracy": 0.825743660695117, | |
| "eval_f1": 0.6736758051636944, | |
| "eval_loss": 1.6328423023223877, | |
| "eval_precision": 0.6436927772126144, | |
| "eval_recall": 0.7065884980457845, | |
| "eval_runtime": 2.998, | |
| "eval_samples_per_second": 370.912, | |
| "eval_steps_per_second": 11.674, | |
| "step": 26352 | |
| }, | |
| { | |
| "epoch": 108.61, | |
| "learning_rate": 2.848360655737705e-06, | |
| "loss": 0.0008, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 109.0, | |
| "eval_accuracy": 0.8256720975167577, | |
| "eval_f1": 0.674515050167224, | |
| "eval_loss": 1.6220307350158691, | |
| "eval_precision": 0.6475725661443616, | |
| "eval_recall": 0.7037967615857063, | |
| "eval_runtime": 2.9865, | |
| "eval_samples_per_second": 372.341, | |
| "eval_steps_per_second": 11.719, | |
| "step": 26596 | |
| }, | |
| { | |
| "epoch": 110.0, | |
| "eval_accuracy": 0.8276281577252451, | |
| "eval_f1": 0.6784613322610911, | |
| "eval_loss": 1.6160385608673096, | |
| "eval_precision": 0.6524877545759217, | |
| "eval_recall": 0.7065884980457845, | |
| "eval_runtime": 2.9726, | |
| "eval_samples_per_second": 374.081, | |
| "eval_steps_per_second": 11.774, | |
| "step": 26840 | |
| }, | |
| { | |
| "epoch": 110.66, | |
| "learning_rate": 2.336065573770492e-06, | |
| "loss": 0.0006, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 111.0, | |
| "eval_accuracy": 0.8270079435127978, | |
| "eval_f1": 0.6741363211951447, | |
| "eval_loss": 1.609981656074524, | |
| "eval_precision": 0.6454661558109834, | |
| "eval_recall": 0.7054718034617532, | |
| "eval_runtime": 2.9645, | |
| "eval_samples_per_second": 375.104, | |
| "eval_steps_per_second": 11.806, | |
| "step": 27084 | |
| }, | |
| { | |
| "epoch": 112.0, | |
| "eval_accuracy": 0.8246702130197275, | |
| "eval_f1": 0.6708255906556942, | |
| "eval_loss": 1.6269794702529907, | |
| "eval_precision": 0.6394230769230769, | |
| "eval_recall": 0.7054718034617532, | |
| "eval_runtime": 2.9668, | |
| "eval_samples_per_second": 374.813, | |
| "eval_steps_per_second": 11.797, | |
| "step": 27328 | |
| }, | |
| { | |
| "epoch": 112.7, | |
| "learning_rate": 1.8237704918032786e-06, | |
| "loss": 0.0005, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 113.0, | |
| "eval_accuracy": 0.8273180506190215, | |
| "eval_f1": 0.6754362416107383, | |
| "eval_loss": 1.6233818531036377, | |
| "eval_precision": 0.6504653567735263, | |
| "eval_recall": 0.7024008933556672, | |
| "eval_runtime": 2.9684, | |
| "eval_samples_per_second": 374.612, | |
| "eval_steps_per_second": 11.791, | |
| "step": 27572 | |
| }, | |
| { | |
| "epoch": 114.0, | |
| "eval_accuracy": 0.8252188640538155, | |
| "eval_f1": 0.6711945665201757, | |
| "eval_loss": 1.632752537727356, | |
| "eval_precision": 0.6417112299465241, | |
| "eval_recall": 0.7035175879396985, | |
| "eval_runtime": 2.9514, | |
| "eval_samples_per_second": 376.771, | |
| "eval_steps_per_second": 11.859, | |
| "step": 27816 | |
| }, | |
| { | |
| "epoch": 114.75, | |
| "learning_rate": 1.3114754098360657e-06, | |
| "loss": 0.0004, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 115.0, | |
| "eval_accuracy": 0.8251473008754562, | |
| "eval_f1": 0.6710262912051248, | |
| "eval_loss": 1.635224461555481, | |
| "eval_precision": 0.6428023523395551, | |
| "eval_recall": 0.7018425460636516, | |
| "eval_runtime": 2.9586, | |
| "eval_samples_per_second": 375.859, | |
| "eval_steps_per_second": 11.83, | |
| "step": 28060 | |
| }, | |
| { | |
| "epoch": 116.0, | |
| "eval_accuracy": 0.8265308556570693, | |
| "eval_f1": 0.6743162108072048, | |
| "eval_loss": 1.6268539428710938, | |
| "eval_precision": 0.6457960644007156, | |
| "eval_recall": 0.7054718034617532, | |
| "eval_runtime": 3.1118, | |
| "eval_samples_per_second": 357.346, | |
| "eval_steps_per_second": 11.247, | |
| "step": 28304 | |
| }, | |
| { | |
| "epoch": 116.8, | |
| "learning_rate": 7.991803278688524e-07, | |
| "loss": 0.0005, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 117.0, | |
| "eval_accuracy": 0.8253381360177476, | |
| "eval_f1": 0.6728024543150594, | |
| "eval_loss": 1.6376687288284302, | |
| "eval_precision": 0.6441890166028097, | |
| "eval_recall": 0.7040759352317141, | |
| "eval_runtime": 2.9567, | |
| "eval_samples_per_second": 376.091, | |
| "eval_steps_per_second": 11.837, | |
| "step": 28548 | |
| }, | |
| { | |
| "epoch": 118.0, | |
| "eval_accuracy": 0.8256959519095441, | |
| "eval_f1": 0.6736027744431106, | |
| "eval_loss": 1.6352702379226685, | |
| "eval_precision": 0.644955300127714, | |
| "eval_recall": 0.7049134561697376, | |
| "eval_runtime": 2.977, | |
| "eval_samples_per_second": 373.528, | |
| "eval_steps_per_second": 11.757, | |
| "step": 28792 | |
| }, | |
| { | |
| "epoch": 118.85, | |
| "learning_rate": 2.8688524590163937e-07, | |
| "loss": 0.0004, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 119.0, | |
| "eval_accuracy": 0.825743660695117, | |
| "eval_f1": 0.6747793527681197, | |
| "eval_loss": 1.6394999027252197, | |
| "eval_precision": 0.6475872689938398, | |
| "eval_recall": 0.7043551088777219, | |
| "eval_runtime": 2.9575, | |
| "eval_samples_per_second": 375.995, | |
| "eval_steps_per_second": 11.834, | |
| "step": 29036 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "eval_accuracy": 0.8256005343383984, | |
| "eval_f1": 0.6740641711229947, | |
| "eval_loss": 1.6384611129760742, | |
| "eval_precision": 0.6467419189327861, | |
| "eval_recall": 0.7037967615857063, | |
| "eval_runtime": 2.9942, | |
| "eval_samples_per_second": 371.386, | |
| "eval_steps_per_second": 11.689, | |
| "step": 29280 | |
| }, | |
| { | |
| "epoch": 120.0, | |
| "step": 29280, | |
| "total_flos": 1.220726808511488e+17, | |
| "train_loss": 0.045685164459416124, | |
| "train_runtime": 6878.0479, | |
| "train_samples_per_second": 135.823, | |
| "train_steps_per_second": 4.257 | |
| } | |
| ], | |
| "max_steps": 29280, | |
| "num_train_epochs": 120, | |
| "total_flos": 1.220726808511488e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |