| { | |
| "best_metric": 0.8122261844116149, | |
| "best_model_checkpoint": "/home/user/emrecan/models/dbmdz_convbert-base-turkish-mc4-cased_allnli_tr/checkpoint-80000", | |
| "epoch": 3.0, | |
| "global_step": 88320, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 1.9773550724637682e-05, | |
| "loss": 0.7338, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_accuracy": 0.723586347427407, | |
| "eval_loss": 0.6721901297569275, | |
| "eval_runtime": 44.7079, | |
| "eval_samples_per_second": 219.536, | |
| "eval_steps_per_second": 6.867, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 1.9547101449275363e-05, | |
| "loss": 0.603, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_accuracy": 0.7398879266428935, | |
| "eval_loss": 0.6465004682540894, | |
| "eval_runtime": 44.7809, | |
| "eval_samples_per_second": 219.178, | |
| "eval_steps_per_second": 6.856, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 1.9320652173913047e-05, | |
| "loss": 0.5605, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_accuracy": 0.7727967396841569, | |
| "eval_loss": 0.5801343321800232, | |
| "eval_runtime": 44.4418, | |
| "eval_samples_per_second": 220.851, | |
| "eval_steps_per_second": 6.908, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 1.9094202898550727e-05, | |
| "loss": 0.55, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "eval_accuracy": 0.7626082526744778, | |
| "eval_loss": 0.5994369983673096, | |
| "eval_runtime": 44.603, | |
| "eval_samples_per_second": 220.052, | |
| "eval_steps_per_second": 6.883, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 1.8867753623188408e-05, | |
| "loss": 0.529, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_accuracy": 0.7697401935812532, | |
| "eval_loss": 0.5720144510269165, | |
| "eval_runtime": 44.7705, | |
| "eval_samples_per_second": 219.229, | |
| "eval_steps_per_second": 6.857, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 1.864130434782609e-05, | |
| "loss": 0.5196, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_accuracy": 0.7768721344880285, | |
| "eval_loss": 0.5691649317741394, | |
| "eval_runtime": 44.7386, | |
| "eval_samples_per_second": 219.385, | |
| "eval_steps_per_second": 6.862, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 1.841485507246377e-05, | |
| "loss": 0.5117, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "eval_accuracy": 0.7785022924095771, | |
| "eval_loss": 0.5724737644195557, | |
| "eval_runtime": 44.7709, | |
| "eval_samples_per_second": 219.227, | |
| "eval_steps_per_second": 6.857, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 1.818840579710145e-05, | |
| "loss": 0.5044, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_accuracy": 0.7787060621497708, | |
| "eval_loss": 0.5532070398330688, | |
| "eval_runtime": 44.6683, | |
| "eval_samples_per_second": 219.731, | |
| "eval_steps_per_second": 6.873, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 1.7961956521739134e-05, | |
| "loss": 0.5016, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "eval_accuracy": 0.7811512990320937, | |
| "eval_loss": 0.5546181797981262, | |
| "eval_runtime": 44.6036, | |
| "eval_samples_per_second": 220.049, | |
| "eval_steps_per_second": 6.883, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 1.7735507246376815e-05, | |
| "loss": 0.5031, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "eval_accuracy": 0.7869587366276108, | |
| "eval_loss": 0.5461075901985168, | |
| "eval_runtime": 44.6087, | |
| "eval_samples_per_second": 220.024, | |
| "eval_steps_per_second": 6.882, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 1.7509057971014495e-05, | |
| "loss": 0.4949, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_accuracy": 0.7825776872134488, | |
| "eval_loss": 0.5724930763244629, | |
| "eval_runtime": 44.6365, | |
| "eval_samples_per_second": 219.888, | |
| "eval_steps_per_second": 6.878, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 1.7282608695652176e-05, | |
| "loss": 0.4894, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "eval_accuracy": 0.7932755985736119, | |
| "eval_loss": 0.5418519377708435, | |
| "eval_runtime": 44.7444, | |
| "eval_samples_per_second": 219.357, | |
| "eval_steps_per_second": 6.861, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 1.7056159420289856e-05, | |
| "loss": 0.4796, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "eval_accuracy": 0.7914416709118696, | |
| "eval_loss": 0.5278186798095703, | |
| "eval_runtime": 44.5917, | |
| "eval_samples_per_second": 220.108, | |
| "eval_steps_per_second": 6.885, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 1.6829710144927537e-05, | |
| "loss": 0.4795, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "eval_accuracy": 0.7953132959755477, | |
| "eval_loss": 0.5193336606025696, | |
| "eval_runtime": 44.673, | |
| "eval_samples_per_second": 219.708, | |
| "eval_steps_per_second": 6.872, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 1.6603260869565218e-05, | |
| "loss": 0.4713, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_accuracy": 0.7770759042282221, | |
| "eval_loss": 0.5534396171569824, | |
| "eval_runtime": 44.688, | |
| "eval_samples_per_second": 219.634, | |
| "eval_steps_per_second": 6.87, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 1.6376811594202898e-05, | |
| "loss": 0.4738, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "eval_accuracy": 0.803871625063678, | |
| "eval_loss": 0.5097627639770508, | |
| "eval_runtime": 44.7421, | |
| "eval_samples_per_second": 219.368, | |
| "eval_steps_per_second": 6.862, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 1.615036231884058e-05, | |
| "loss": 0.481, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "eval_accuracy": 0.7958227203260316, | |
| "eval_loss": 0.5244179368019104, | |
| "eval_runtime": 44.7909, | |
| "eval_samples_per_second": 219.129, | |
| "eval_steps_per_second": 6.854, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "learning_rate": 1.5923913043478263e-05, | |
| "loss": 0.4634, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "eval_accuracy": 0.7972491085073866, | |
| "eval_loss": 0.5214974880218506, | |
| "eval_runtime": 44.5586, | |
| "eval_samples_per_second": 220.272, | |
| "eval_steps_per_second": 6.89, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 1.5697463768115943e-05, | |
| "loss": 0.465, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "eval_accuracy": 0.7984717269485482, | |
| "eval_loss": 0.5128703117370605, | |
| "eval_runtime": 44.7294, | |
| "eval_samples_per_second": 219.431, | |
| "eval_steps_per_second": 6.863, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 1.5471014492753624e-05, | |
| "loss": 0.4624, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "eval_accuracy": 0.8046867040244524, | |
| "eval_loss": 0.5061507821083069, | |
| "eval_runtime": 44.7949, | |
| "eval_samples_per_second": 219.11, | |
| "eval_steps_per_second": 6.853, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 1.5244565217391305e-05, | |
| "loss": 0.4597, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "eval_accuracy": 0.8028527763627101, | |
| "eval_loss": 0.5114405751228333, | |
| "eval_runtime": 47.1654, | |
| "eval_samples_per_second": 208.098, | |
| "eval_steps_per_second": 6.509, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "learning_rate": 1.5018115942028985e-05, | |
| "loss": 0.4571, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_accuracy": 0.807335710646969, | |
| "eval_loss": 0.5069620609283447, | |
| "eval_runtime": 45.7859, | |
| "eval_samples_per_second": 214.368, | |
| "eval_steps_per_second": 6.705, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "learning_rate": 1.479166666666667e-05, | |
| "loss": 0.4602, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "eval_accuracy": 0.7992868059093224, | |
| "eval_loss": 0.5114511847496033, | |
| "eval_runtime": 45.8642, | |
| "eval_samples_per_second": 214.001, | |
| "eval_steps_per_second": 6.694, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "learning_rate": 1.456521739130435e-05, | |
| "loss": 0.4552, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "eval_accuracy": 0.8051961283749364, | |
| "eval_loss": 0.5085225105285645, | |
| "eval_runtime": 46.055, | |
| "eval_samples_per_second": 213.115, | |
| "eval_steps_per_second": 6.666, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "learning_rate": 1.433876811594203e-05, | |
| "loss": 0.4538, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "eval_accuracy": 0.7973509933774835, | |
| "eval_loss": 0.5118097066879272, | |
| "eval_runtime": 45.9419, | |
| "eval_samples_per_second": 213.639, | |
| "eval_steps_per_second": 6.682, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 1.4112318840579711e-05, | |
| "loss": 0.4517, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "eval_accuracy": 0.804381049414162, | |
| "eval_loss": 0.5036212205886841, | |
| "eval_runtime": 45.8528, | |
| "eval_samples_per_second": 214.055, | |
| "eval_steps_per_second": 6.695, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "learning_rate": 1.3885869565217392e-05, | |
| "loss": 0.4517, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "eval_accuracy": 0.8062149770759043, | |
| "eval_loss": 0.4929669201374054, | |
| "eval_runtime": 45.8655, | |
| "eval_samples_per_second": 213.995, | |
| "eval_steps_per_second": 6.693, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 1.3659420289855074e-05, | |
| "loss": 0.4413, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "eval_accuracy": 0.7964340295466124, | |
| "eval_loss": 0.5306665897369385, | |
| "eval_runtime": 45.9438, | |
| "eval_samples_per_second": 213.631, | |
| "eval_steps_per_second": 6.682, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "learning_rate": 1.3432971014492755e-05, | |
| "loss": 0.4483, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "eval_accuracy": 0.7937850229240958, | |
| "eval_loss": 0.5194875001907349, | |
| "eval_runtime": 45.8704, | |
| "eval_samples_per_second": 213.972, | |
| "eval_steps_per_second": 6.693, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "learning_rate": 1.3206521739130435e-05, | |
| "loss": 0.4036, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.02, | |
| "eval_accuracy": 0.8028527763627101, | |
| "eval_loss": 0.5238322615623474, | |
| "eval_runtime": 45.9862, | |
| "eval_samples_per_second": 213.434, | |
| "eval_steps_per_second": 6.676, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 1.2980072463768116e-05, | |
| "loss": 0.3724, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "eval_accuracy": 0.8081507896077432, | |
| "eval_loss": 0.5124598741531372, | |
| "eval_runtime": 47.042, | |
| "eval_samples_per_second": 208.643, | |
| "eval_steps_per_second": 6.526, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "learning_rate": 1.2753623188405797e-05, | |
| "loss": 0.3777, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.09, | |
| "eval_accuracy": 0.8075394803871625, | |
| "eval_loss": 0.509867787361145, | |
| "eval_runtime": 46.0494, | |
| "eval_samples_per_second": 213.141, | |
| "eval_steps_per_second": 6.667, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 1.252717391304348e-05, | |
| "loss": 0.3753, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "eval_accuracy": 0.8052980132450331, | |
| "eval_loss": 0.5171676278114319, | |
| "eval_runtime": 45.8652, | |
| "eval_samples_per_second": 213.997, | |
| "eval_steps_per_second": 6.694, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 1.2300724637681161e-05, | |
| "loss": 0.367, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "eval_accuracy": 0.8052980132450331, | |
| "eval_loss": 0.5187755823135376, | |
| "eval_runtime": 45.7807, | |
| "eval_samples_per_second": 214.391, | |
| "eval_steps_per_second": 6.706, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 1.2074275362318842e-05, | |
| "loss": 0.3819, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "eval_accuracy": 0.8045848191543555, | |
| "eval_loss": 0.5218426585197449, | |
| "eval_runtime": 46.9682, | |
| "eval_samples_per_second": 208.971, | |
| "eval_steps_per_second": 6.536, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 1.1847826086956522e-05, | |
| "loss": 0.363, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "eval_accuracy": 0.7992868059093224, | |
| "eval_loss": 0.5201919078826904, | |
| "eval_runtime": 46.028, | |
| "eval_samples_per_second": 213.24, | |
| "eval_steps_per_second": 6.67, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 1.1621376811594205e-05, | |
| "loss": 0.3794, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "eval_accuracy": 0.8047885888945492, | |
| "eval_loss": 0.5240486860275269, | |
| "eval_runtime": 46.0171, | |
| "eval_samples_per_second": 213.29, | |
| "eval_steps_per_second": 6.671, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 1.1394927536231885e-05, | |
| "loss": 0.3749, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "eval_accuracy": 0.8053998981151299, | |
| "eval_loss": 0.5025837421417236, | |
| "eval_runtime": 45.9936, | |
| "eval_samples_per_second": 213.399, | |
| "eval_steps_per_second": 6.675, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 1.1168478260869566e-05, | |
| "loss": 0.367, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "eval_accuracy": 0.8075394803871625, | |
| "eval_loss": 0.5197691917419434, | |
| "eval_runtime": 46.0223, | |
| "eval_samples_per_second": 213.266, | |
| "eval_steps_per_second": 6.671, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 1.0942028985507247e-05, | |
| "loss": 0.3759, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "eval_accuracy": 0.7992868059093224, | |
| "eval_loss": 0.5298164486885071, | |
| "eval_runtime": 46.0659, | |
| "eval_samples_per_second": 213.064, | |
| "eval_steps_per_second": 6.664, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 1.0715579710144927e-05, | |
| "loss": 0.3701, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "eval_accuracy": 0.8090677534386144, | |
| "eval_loss": 0.5072407722473145, | |
| "eval_runtime": 47.2083, | |
| "eval_samples_per_second": 207.908, | |
| "eval_steps_per_second": 6.503, | |
| "step": 41000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 1.0489130434782611e-05, | |
| "loss": 0.3742, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_accuracy": 0.8097809475292919, | |
| "eval_loss": 0.507131814956665, | |
| "eval_runtime": 46.0803, | |
| "eval_samples_per_second": 212.998, | |
| "eval_steps_per_second": 6.662, | |
| "step": 42000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "learning_rate": 1.0262681159420292e-05, | |
| "loss": 0.3706, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.46, | |
| "eval_accuracy": 0.8036678553234845, | |
| "eval_loss": 0.5317161083221436, | |
| "eval_runtime": 46.1098, | |
| "eval_samples_per_second": 212.861, | |
| "eval_steps_per_second": 6.658, | |
| "step": 43000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "learning_rate": 1.0036231884057972e-05, | |
| "loss": 0.3716, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.49, | |
| "eval_accuracy": 0.8051961283749364, | |
| "eval_loss": 0.5034372210502625, | |
| "eval_runtime": 46.0657, | |
| "eval_samples_per_second": 213.065, | |
| "eval_steps_per_second": 6.664, | |
| "step": 44000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 9.809782608695653e-06, | |
| "loss": 0.3717, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_accuracy": 0.8012226184411615, | |
| "eval_loss": 0.525775671005249, | |
| "eval_runtime": 45.917, | |
| "eval_samples_per_second": 213.755, | |
| "eval_steps_per_second": 6.686, | |
| "step": 45000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "learning_rate": 9.583333333333335e-06, | |
| "loss": 0.3714, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 1.56, | |
| "eval_accuracy": 0.8049923586347427, | |
| "eval_loss": 0.5195213556289673, | |
| "eval_runtime": 46.0299, | |
| "eval_samples_per_second": 213.231, | |
| "eval_steps_per_second": 6.67, | |
| "step": 46000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 9.356884057971016e-06, | |
| "loss": 0.3781, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_accuracy": 0.8103922567498727, | |
| "eval_loss": 0.5003909468650818, | |
| "eval_runtime": 46.0896, | |
| "eval_samples_per_second": 212.955, | |
| "eval_steps_per_second": 6.661, | |
| "step": 47000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 9.130434782608697e-06, | |
| "loss": 0.3725, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_accuracy": 0.8113092205807437, | |
| "eval_loss": 0.5124202966690063, | |
| "eval_runtime": 46.0326, | |
| "eval_samples_per_second": 213.218, | |
| "eval_steps_per_second": 6.669, | |
| "step": 48000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "learning_rate": 8.903985507246377e-06, | |
| "loss": 0.3624, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 1.66, | |
| "eval_accuracy": 0.8093734080489048, | |
| "eval_loss": 0.5039945840835571, | |
| "eval_runtime": 46.0265, | |
| "eval_samples_per_second": 213.247, | |
| "eval_steps_per_second": 6.67, | |
| "step": 49000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 8.677536231884058e-06, | |
| "loss": 0.3657, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_accuracy": 0.8111054508405502, | |
| "eval_loss": 0.49794963002204895, | |
| "eval_runtime": 46.0671, | |
| "eval_samples_per_second": 213.059, | |
| "eval_steps_per_second": 6.664, | |
| "step": 50000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 8.45108695652174e-06, | |
| "loss": 0.3669, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_accuracy": 0.8099847172694855, | |
| "eval_loss": 0.4967914819717407, | |
| "eval_runtime": 47.5013, | |
| "eval_samples_per_second": 206.626, | |
| "eval_steps_per_second": 6.463, | |
| "step": 51000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 8.22463768115942e-06, | |
| "loss": 0.3636, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_accuracy": 0.8079470198675497, | |
| "eval_loss": 0.5075203776359558, | |
| "eval_runtime": 45.998, | |
| "eval_samples_per_second": 213.379, | |
| "eval_steps_per_second": 6.674, | |
| "step": 52000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 7.998188405797103e-06, | |
| "loss": 0.36, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_accuracy": 0.8110035659704534, | |
| "eval_loss": 0.498517245054245, | |
| "eval_runtime": 46.2214, | |
| "eval_samples_per_second": 212.347, | |
| "eval_steps_per_second": 6.642, | |
| "step": 53000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 7.771739130434784e-06, | |
| "loss": 0.3624, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_accuracy": 0.8070300560366785, | |
| "eval_loss": 0.5125023722648621, | |
| "eval_runtime": 46.2947, | |
| "eval_samples_per_second": 212.011, | |
| "eval_steps_per_second": 6.631, | |
| "step": 54000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 7.545289855072464e-06, | |
| "loss": 0.366, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_accuracy": 0.8117167600611309, | |
| "eval_loss": 0.4918198585510254, | |
| "eval_runtime": 46.0126, | |
| "eval_samples_per_second": 213.311, | |
| "eval_steps_per_second": 6.672, | |
| "step": 55000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 7.318840579710146e-06, | |
| "loss": 0.3655, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_accuracy": 0.8109016811003565, | |
| "eval_loss": 0.505085289478302, | |
| "eval_runtime": 46.0789, | |
| "eval_samples_per_second": 213.004, | |
| "eval_steps_per_second": 6.662, | |
| "step": 56000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "learning_rate": 7.092391304347826e-06, | |
| "loss": 0.3609, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.94, | |
| "eval_accuracy": 0.8104941416199695, | |
| "eval_loss": 0.5082952976226807, | |
| "eval_runtime": 46.1283, | |
| "eval_samples_per_second": 212.776, | |
| "eval_steps_per_second": 6.655, | |
| "step": 57000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 6.865942028985509e-06, | |
| "loss": 0.3672, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_accuracy": 0.8084564442180336, | |
| "eval_loss": 0.5128825902938843, | |
| "eval_runtime": 46.1412, | |
| "eval_samples_per_second": 212.717, | |
| "eval_steps_per_second": 6.653, | |
| "step": 58000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 6.639492753623189e-06, | |
| "loss": 0.3545, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.8109016811003565, | |
| "eval_loss": 0.5467332601547241, | |
| "eval_runtime": 46.0619, | |
| "eval_samples_per_second": 213.083, | |
| "eval_steps_per_second": 6.665, | |
| "step": 59000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "learning_rate": 6.41304347826087e-06, | |
| "loss": 0.2938, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 2.04, | |
| "eval_accuracy": 0.804890473764646, | |
| "eval_loss": 0.5634797811508179, | |
| "eval_runtime": 46.0511, | |
| "eval_samples_per_second": 213.133, | |
| "eval_steps_per_second": 6.667, | |
| "step": 60000 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "learning_rate": 6.186594202898551e-06, | |
| "loss": 0.29, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 2.07, | |
| "eval_accuracy": 0.8040753948038716, | |
| "eval_loss": 0.5781472325325012, | |
| "eval_runtime": 47.2218, | |
| "eval_samples_per_second": 207.849, | |
| "eval_steps_per_second": 6.501, | |
| "step": 61000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "learning_rate": 5.960144927536232e-06, | |
| "loss": 0.2992, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 2.11, | |
| "eval_accuracy": 0.807743250127356, | |
| "eval_loss": 0.5470119714736938, | |
| "eval_runtime": 46.0932, | |
| "eval_samples_per_second": 212.938, | |
| "eval_steps_per_second": 6.66, | |
| "step": 62000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "learning_rate": 5.733695652173914e-06, | |
| "loss": 0.2957, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 2.14, | |
| "eval_accuracy": 0.807335710646969, | |
| "eval_loss": 0.5764774084091187, | |
| "eval_runtime": 45.9878, | |
| "eval_samples_per_second": 213.426, | |
| "eval_steps_per_second": 6.676, | |
| "step": 63000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "learning_rate": 5.507246376811595e-06, | |
| "loss": 0.292, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 2.17, | |
| "eval_accuracy": 0.8105960264900662, | |
| "eval_loss": 0.547173798084259, | |
| "eval_runtime": 45.972, | |
| "eval_samples_per_second": 213.5, | |
| "eval_steps_per_second": 6.678, | |
| "step": 64000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "learning_rate": 5.2807971014492755e-06, | |
| "loss": 0.2893, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 2.21, | |
| "eval_accuracy": 0.8084564442180336, | |
| "eval_loss": 0.5590358376502991, | |
| "eval_runtime": 45.9212, | |
| "eval_samples_per_second": 213.736, | |
| "eval_steps_per_second": 6.685, | |
| "step": 65000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "learning_rate": 5.054347826086957e-06, | |
| "loss": 0.2883, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 2.24, | |
| "eval_accuracy": 0.8064187468160978, | |
| "eval_loss": 0.5534654855728149, | |
| "eval_runtime": 45.9485, | |
| "eval_samples_per_second": 213.609, | |
| "eval_steps_per_second": 6.681, | |
| "step": 66000 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "learning_rate": 4.8278985507246375e-06, | |
| "loss": 0.2923, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 2.28, | |
| "eval_accuracy": 0.8094752929190016, | |
| "eval_loss": 0.5508309602737427, | |
| "eval_runtime": 45.9406, | |
| "eval_samples_per_second": 213.645, | |
| "eval_steps_per_second": 6.683, | |
| "step": 67000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "learning_rate": 4.601449275362319e-06, | |
| "loss": 0.2868, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 2.31, | |
| "eval_accuracy": 0.8097809475292919, | |
| "eval_loss": 0.5678631067276001, | |
| "eval_runtime": 45.9005, | |
| "eval_samples_per_second": 213.832, | |
| "eval_steps_per_second": 6.688, | |
| "step": 68000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "learning_rate": 4.3750000000000005e-06, | |
| "loss": 0.2892, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 2.34, | |
| "eval_accuracy": 0.8057055527254203, | |
| "eval_loss": 0.5659688115119934, | |
| "eval_runtime": 46.0172, | |
| "eval_samples_per_second": 213.29, | |
| "eval_steps_per_second": 6.671, | |
| "step": 69000 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "learning_rate": 4.148550724637682e-06, | |
| "loss": 0.292, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 2.38, | |
| "eval_accuracy": 0.808762098828324, | |
| "eval_loss": 0.54941326379776, | |
| "eval_runtime": 46.0397, | |
| "eval_samples_per_second": 213.186, | |
| "eval_steps_per_second": 6.668, | |
| "step": 70000 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "learning_rate": 3.9221014492753625e-06, | |
| "loss": 0.286, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 2.41, | |
| "eval_accuracy": 0.8084564442180336, | |
| "eval_loss": 0.5653256177902222, | |
| "eval_runtime": 47.1102, | |
| "eval_samples_per_second": 208.341, | |
| "eval_steps_per_second": 6.517, | |
| "step": 71000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "learning_rate": 3.6956521739130436e-06, | |
| "loss": 0.2939, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 2.45, | |
| "eval_accuracy": 0.8070300560366785, | |
| "eval_loss": 0.5673069953918457, | |
| "eval_runtime": 46.0492, | |
| "eval_samples_per_second": 213.142, | |
| "eval_steps_per_second": 6.667, | |
| "step": 72000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "learning_rate": 3.4692028985507246e-06, | |
| "loss": 0.286, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 2.48, | |
| "eval_accuracy": 0.8091696383087111, | |
| "eval_loss": 0.56004798412323, | |
| "eval_runtime": 45.9369, | |
| "eval_samples_per_second": 213.663, | |
| "eval_steps_per_second": 6.683, | |
| "step": 73000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "learning_rate": 3.242753623188406e-06, | |
| "loss": 0.2844, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 2.51, | |
| "eval_accuracy": 0.8094752929190016, | |
| "eval_loss": 0.5507674217224121, | |
| "eval_runtime": 45.8631, | |
| "eval_samples_per_second": 214.006, | |
| "eval_steps_per_second": 6.694, | |
| "step": 74000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "learning_rate": 3.016304347826087e-06, | |
| "loss": 0.2913, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 2.55, | |
| "eval_accuracy": 0.808762098828324, | |
| "eval_loss": 0.5644803047180176, | |
| "eval_runtime": 45.9087, | |
| "eval_samples_per_second": 213.794, | |
| "eval_steps_per_second": 6.687, | |
| "step": 75000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "learning_rate": 2.7898550724637686e-06, | |
| "loss": 0.2859, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 2.58, | |
| "eval_accuracy": 0.8094752929190016, | |
| "eval_loss": 0.5677375197410583, | |
| "eval_runtime": 46.1274, | |
| "eval_samples_per_second": 212.78, | |
| "eval_steps_per_second": 6.655, | |
| "step": 76000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "learning_rate": 2.563405797101449e-06, | |
| "loss": 0.2892, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 2.62, | |
| "eval_accuracy": 0.8113092205807437, | |
| "eval_loss": 0.5597835183143616, | |
| "eval_runtime": 46.0994, | |
| "eval_samples_per_second": 212.909, | |
| "eval_steps_per_second": 6.66, | |
| "step": 77000 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "learning_rate": 2.3369565217391307e-06, | |
| "loss": 0.2898, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 2.65, | |
| "eval_accuracy": 0.8095771777890983, | |
| "eval_loss": 0.5617640018463135, | |
| "eval_runtime": 45.9468, | |
| "eval_samples_per_second": 213.617, | |
| "eval_steps_per_second": 6.682, | |
| "step": 78000 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "learning_rate": 2.1105072463768117e-06, | |
| "loss": 0.2814, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 2.68, | |
| "eval_accuracy": 0.8102903718797758, | |
| "eval_loss": 0.5664277672767639, | |
| "eval_runtime": 46.0837, | |
| "eval_samples_per_second": 212.982, | |
| "eval_steps_per_second": 6.662, | |
| "step": 79000 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "learning_rate": 1.884057971014493e-06, | |
| "loss": 0.2917, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 2.72, | |
| "eval_accuracy": 0.8122261844116149, | |
| "eval_loss": 0.5484075546264648, | |
| "eval_runtime": 46.0805, | |
| "eval_samples_per_second": 212.997, | |
| "eval_steps_per_second": 6.662, | |
| "step": 80000 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "learning_rate": 1.657608695652174e-06, | |
| "loss": 0.2907, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 2.75, | |
| "eval_accuracy": 0.8116148751910341, | |
| "eval_loss": 0.5522238612174988, | |
| "eval_runtime": 47.1215, | |
| "eval_samples_per_second": 208.291, | |
| "eval_steps_per_second": 6.515, | |
| "step": 81000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "learning_rate": 1.4311594202898552e-06, | |
| "loss": 0.2896, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 2.79, | |
| "eval_accuracy": 0.8092715231788079, | |
| "eval_loss": 0.5539634823799133, | |
| "eval_runtime": 46.0412, | |
| "eval_samples_per_second": 213.179, | |
| "eval_steps_per_second": 6.668, | |
| "step": 82000 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "learning_rate": 1.2047101449275363e-06, | |
| "loss": 0.2907, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 2.82, | |
| "eval_accuracy": 0.8103922567498727, | |
| "eval_loss": 0.5468757152557373, | |
| "eval_runtime": 46.1268, | |
| "eval_samples_per_second": 212.783, | |
| "eval_steps_per_second": 6.656, | |
| "step": 83000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "learning_rate": 9.782608695652175e-07, | |
| "loss": 0.2882, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 2.85, | |
| "eval_accuracy": 0.8122261844116149, | |
| "eval_loss": 0.5470659732818604, | |
| "eval_runtime": 46.0408, | |
| "eval_samples_per_second": 213.18, | |
| "eval_steps_per_second": 6.668, | |
| "step": 84000 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "learning_rate": 7.518115942028987e-07, | |
| "loss": 0.2878, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 2.89, | |
| "eval_accuracy": 0.8107997962302598, | |
| "eval_loss": 0.5532234907150269, | |
| "eval_runtime": 46.1642, | |
| "eval_samples_per_second": 212.61, | |
| "eval_steps_per_second": 6.65, | |
| "step": 85000 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "learning_rate": 5.253623188405797e-07, | |
| "loss": 0.2858, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 2.92, | |
| "eval_accuracy": 0.8115129903209374, | |
| "eval_loss": 0.5510849952697754, | |
| "eval_runtime": 46.0337, | |
| "eval_samples_per_second": 213.214, | |
| "eval_steps_per_second": 6.669, | |
| "step": 86000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "learning_rate": 2.989130434782609e-07, | |
| "loss": 0.288, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "eval_accuracy": 0.8111054508405502, | |
| "eval_loss": 0.5491093397140503, | |
| "eval_runtime": 45.9486, | |
| "eval_samples_per_second": 213.608, | |
| "eval_steps_per_second": 6.681, | |
| "step": 87000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "learning_rate": 7.246376811594204e-08, | |
| "loss": 0.2834, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 2.99, | |
| "eval_accuracy": 0.8111054508405502, | |
| "eval_loss": 0.5540585517883301, | |
| "eval_runtime": 45.8903, | |
| "eval_samples_per_second": 213.879, | |
| "eval_steps_per_second": 6.69, | |
| "step": 88000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 88320, | |
| "total_flos": 9.711893491230248e+16, | |
| "train_loss": 0.3844692539477694, | |
| "train_runtime": 45994.9721, | |
| "train_samples_per_second": 61.446, | |
| "train_steps_per_second": 1.92 | |
| } | |
| ], | |
| "max_steps": 88320, | |
| "num_train_epochs": 3, | |
| "total_flos": 9.711893491230248e+16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |