| { | |
| "best_metric": 0.6680810938236681, | |
| "best_model_checkpoint": "videomae-base-finetuned-chickenbehaviour-2/checkpoint-23865", | |
| "epoch": 79.01218956303049, | |
| "eval_steps": 500, | |
| "global_step": 127240, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 34.09493637084961, | |
| "learning_rate": 6.251964790946243e-06, | |
| "loss": 2.035, | |
| "step": 1591 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "eval_accuracy": 0.5115511551155115, | |
| "eval_f1": 0.4139359299241216, | |
| "eval_loss": 1.6961450576782227, | |
| "eval_precision": 0.426389188260245, | |
| "eval_recall": 0.5115511551155115, | |
| "eval_runtime": 443.2234, | |
| "eval_samples_per_second": 9.571, | |
| "eval_steps_per_second": 1.198, | |
| "step": 1591 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "grad_norm": 25.231983184814453, | |
| "learning_rate": 1.2503929581892487e-05, | |
| "loss": 1.5431, | |
| "step": 3182 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "eval_accuracy": 0.5898161244695899, | |
| "eval_f1": 0.5166622256451852, | |
| "eval_loss": 1.439492106437683, | |
| "eval_precision": 0.5240058255527255, | |
| "eval_recall": 0.5898161244695899, | |
| "eval_runtime": 437.564, | |
| "eval_samples_per_second": 9.695, | |
| "eval_steps_per_second": 1.214, | |
| "step": 3182 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "grad_norm": 24.721105575561523, | |
| "learning_rate": 1.875589437283873e-05, | |
| "loss": 1.4118, | |
| "step": 4773 | |
| }, | |
| { | |
| "epoch": 2.01, | |
| "eval_accuracy": 0.6051390853371051, | |
| "eval_f1": 0.5535236961754626, | |
| "eval_loss": 1.363150715827942, | |
| "eval_precision": 0.5552721379615939, | |
| "eval_recall": 0.6051390853371051, | |
| "eval_runtime": 683.9412, | |
| "eval_samples_per_second": 6.202, | |
| "eval_steps_per_second": 0.776, | |
| "step": 4773 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "grad_norm": 7.513462066650391, | |
| "learning_rate": 2.5007859163784973e-05, | |
| "loss": 1.3413, | |
| "step": 6364 | |
| }, | |
| { | |
| "epoch": 3.01, | |
| "eval_accuracy": 0.6020744931636021, | |
| "eval_f1": 0.5384080508073906, | |
| "eval_loss": 1.331170678138733, | |
| "eval_precision": 0.551611875314686, | |
| "eval_recall": 0.6020744931636021, | |
| "eval_runtime": 680.73, | |
| "eval_samples_per_second": 6.232, | |
| "eval_steps_per_second": 0.78, | |
| "step": 6364 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "grad_norm": 23.583574295043945, | |
| "learning_rate": 3.125982395473121e-05, | |
| "loss": 1.2969, | |
| "step": 7955 | |
| }, | |
| { | |
| "epoch": 4.01, | |
| "eval_accuracy": 0.6211692597831212, | |
| "eval_f1": 0.5663241746963936, | |
| "eval_loss": 1.273905873298645, | |
| "eval_precision": 0.6121530259266542, | |
| "eval_recall": 0.6211692597831212, | |
| "eval_runtime": 663.3464, | |
| "eval_samples_per_second": 6.395, | |
| "eval_steps_per_second": 0.8, | |
| "step": 7955 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "grad_norm": 12.484142303466797, | |
| "learning_rate": 3.751178874567746e-05, | |
| "loss": 1.2636, | |
| "step": 9546 | |
| }, | |
| { | |
| "epoch": 5.01, | |
| "eval_accuracy": 0.6058462989156058, | |
| "eval_f1": 0.5429975108084805, | |
| "eval_loss": 1.3211930990219116, | |
| "eval_precision": 0.6186956973637323, | |
| "eval_recall": 0.6058462989156058, | |
| "eval_runtime": 661.8451, | |
| "eval_samples_per_second": 6.409, | |
| "eval_steps_per_second": 0.802, | |
| "step": 9546 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "grad_norm": 6.579521179199219, | |
| "learning_rate": 4.3763753536623704e-05, | |
| "loss": 1.2231, | |
| "step": 11137 | |
| }, | |
| { | |
| "epoch": 6.01, | |
| "eval_accuracy": 0.6242338519566243, | |
| "eval_f1": 0.5747264230461347, | |
| "eval_loss": 1.2543139457702637, | |
| "eval_precision": 0.6460983768240532, | |
| "eval_recall": 0.6242338519566243, | |
| "eval_runtime": 669.9717, | |
| "eval_samples_per_second": 6.332, | |
| "eval_steps_per_second": 0.793, | |
| "step": 11137 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "grad_norm": 12.255209922790527, | |
| "learning_rate": 4.99982535191589e-05, | |
| "loss": 1.1989, | |
| "step": 12728 | |
| }, | |
| { | |
| "epoch": 7.01, | |
| "eval_accuracy": 0.6404997642621405, | |
| "eval_f1": 0.5869125503826516, | |
| "eval_loss": 1.2377874851226807, | |
| "eval_precision": 0.6356351683189131, | |
| "eval_recall": 0.6404997642621405, | |
| "eval_runtime": 678.5987, | |
| "eval_samples_per_second": 6.251, | |
| "eval_steps_per_second": 0.782, | |
| "step": 12728 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "grad_norm": 9.07247257232666, | |
| "learning_rate": 4.9303590764609316e-05, | |
| "loss": 1.1566, | |
| "step": 14319 | |
| }, | |
| { | |
| "epoch": 8.01, | |
| "eval_accuracy": 0.6527581329561527, | |
| "eval_f1": 0.594207871765373, | |
| "eval_loss": 1.2123682498931885, | |
| "eval_precision": 0.6198764093734253, | |
| "eval_recall": 0.6527581329561527, | |
| "eval_runtime": 667.9014, | |
| "eval_samples_per_second": 6.351, | |
| "eval_steps_per_second": 0.795, | |
| "step": 14319 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "grad_norm": 13.849576950073242, | |
| "learning_rate": 4.8608928010059734e-05, | |
| "loss": 1.1145, | |
| "step": 15910 | |
| }, | |
| { | |
| "epoch": 9.01, | |
| "eval_accuracy": 0.6475719000471476, | |
| "eval_f1": 0.605227949854272, | |
| "eval_loss": 1.1802877187728882, | |
| "eval_precision": 0.6340925434803425, | |
| "eval_recall": 0.6475719000471476, | |
| "eval_runtime": 672.4937, | |
| "eval_samples_per_second": 6.308, | |
| "eval_steps_per_second": 0.79, | |
| "step": 15910 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "grad_norm": 26.01058006286621, | |
| "learning_rate": 4.791426525551015e-05, | |
| "loss": 1.0567, | |
| "step": 17501 | |
| }, | |
| { | |
| "epoch": 10.01, | |
| "eval_accuracy": 0.6265912305516266, | |
| "eval_f1": 0.5969458291906395, | |
| "eval_loss": 1.2576700448989868, | |
| "eval_precision": 0.6278990782548687, | |
| "eval_recall": 0.6265912305516266, | |
| "eval_runtime": 662.684, | |
| "eval_samples_per_second": 6.401, | |
| "eval_steps_per_second": 0.801, | |
| "step": 17501 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "grad_norm": 4.436341285705566, | |
| "learning_rate": 4.721960250096057e-05, | |
| "loss": 1.0172, | |
| "step": 19092 | |
| }, | |
| { | |
| "epoch": 11.01, | |
| "eval_accuracy": 0.657001414427157, | |
| "eval_f1": 0.6082570131553916, | |
| "eval_loss": 1.1961308717727661, | |
| "eval_precision": 0.6369039125738234, | |
| "eval_recall": 0.657001414427157, | |
| "eval_runtime": 753.1481, | |
| "eval_samples_per_second": 5.632, | |
| "eval_steps_per_second": 0.705, | |
| "step": 19092 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "grad_norm": 12.711715698242188, | |
| "learning_rate": 4.652493974641098e-05, | |
| "loss": 0.9817, | |
| "step": 20683 | |
| }, | |
| { | |
| "epoch": 12.01, | |
| "eval_accuracy": 0.6619519094766619, | |
| "eval_f1": 0.6048958777519221, | |
| "eval_loss": 1.2287497520446777, | |
| "eval_precision": 0.6498679093091749, | |
| "eval_recall": 0.6619519094766619, | |
| "eval_runtime": 765.9815, | |
| "eval_samples_per_second": 5.538, | |
| "eval_steps_per_second": 0.693, | |
| "step": 20683 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "grad_norm": 6.408486366271973, | |
| "learning_rate": 4.583027699186141e-05, | |
| "loss": 0.9279, | |
| "step": 22274 | |
| }, | |
| { | |
| "epoch": 13.01, | |
| "eval_accuracy": 0.6548797736916548, | |
| "eval_f1": 0.6213080237690763, | |
| "eval_loss": 1.2358391284942627, | |
| "eval_precision": 0.6503596413080538, | |
| "eval_recall": 0.6548797736916548, | |
| "eval_runtime": 754.2864, | |
| "eval_samples_per_second": 5.624, | |
| "eval_steps_per_second": 0.704, | |
| "step": 22274 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "grad_norm": 14.318334579467773, | |
| "learning_rate": 4.513561423731182e-05, | |
| "loss": 0.8913, | |
| "step": 23865 | |
| }, | |
| { | |
| "epoch": 14.01, | |
| "eval_accuracy": 0.6680810938236681, | |
| "eval_f1": 0.6307923814434653, | |
| "eval_loss": 1.181541919708252, | |
| "eval_precision": 0.6325361512013947, | |
| "eval_recall": 0.6680810938236681, | |
| "eval_runtime": 766.2903, | |
| "eval_samples_per_second": 5.536, | |
| "eval_steps_per_second": 0.693, | |
| "step": 23865 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "grad_norm": 14.112875938415527, | |
| "learning_rate": 4.444095148276224e-05, | |
| "loss": 0.8559, | |
| "step": 25456 | |
| }, | |
| { | |
| "epoch": 15.01, | |
| "eval_accuracy": 0.639085337105139, | |
| "eval_f1": 0.6036680470772597, | |
| "eval_loss": 1.3211859464645386, | |
| "eval_precision": 0.639173575618385, | |
| "eval_recall": 0.639085337105139, | |
| "eval_runtime": 741.2024, | |
| "eval_samples_per_second": 5.723, | |
| "eval_steps_per_second": 0.716, | |
| "step": 25456 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "grad_norm": 19.837888717651367, | |
| "learning_rate": 4.3746288728212655e-05, | |
| "loss": 0.8083, | |
| "step": 27047 | |
| }, | |
| { | |
| "epoch": 16.01, | |
| "eval_accuracy": 0.6230551626591231, | |
| "eval_f1": 0.6006019601279614, | |
| "eval_loss": 1.307276725769043, | |
| "eval_precision": 0.6250962347990193, | |
| "eval_recall": 0.6230551626591231, | |
| "eval_runtime": 755.5211, | |
| "eval_samples_per_second": 5.615, | |
| "eval_steps_per_second": 0.703, | |
| "step": 27047 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "grad_norm": 7.695098876953125, | |
| "learning_rate": 4.305162597366307e-05, | |
| "loss": 0.7662, | |
| "step": 28638 | |
| }, | |
| { | |
| "epoch": 17.01, | |
| "eval_accuracy": 0.6461574728901461, | |
| "eval_f1": 0.6214078287802024, | |
| "eval_loss": 1.2981834411621094, | |
| "eval_precision": 0.625200272023183, | |
| "eval_recall": 0.6461574728901461, | |
| "eval_runtime": 760.7104, | |
| "eval_samples_per_second": 5.576, | |
| "eval_steps_per_second": 0.698, | |
| "step": 28638 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "grad_norm": 17.791141510009766, | |
| "learning_rate": 4.2356963219113485e-05, | |
| "loss": 0.7363, | |
| "step": 30229 | |
| }, | |
| { | |
| "epoch": 18.01, | |
| "eval_accuracy": 0.6574728901461575, | |
| "eval_f1": 0.6264016299127368, | |
| "eval_loss": 1.3019486665725708, | |
| "eval_precision": 0.6427931632515602, | |
| "eval_recall": 0.6574728901461575, | |
| "eval_runtime": 732.8997, | |
| "eval_samples_per_second": 5.788, | |
| "eval_steps_per_second": 0.725, | |
| "step": 30229 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "grad_norm": 12.370431900024414, | |
| "learning_rate": 4.166230046456391e-05, | |
| "loss": 0.6787, | |
| "step": 31820 | |
| }, | |
| { | |
| "epoch": 19.01, | |
| "eval_accuracy": 0.6511079679396511, | |
| "eval_f1": 0.6229627569285623, | |
| "eval_loss": 1.3867465257644653, | |
| "eval_precision": 0.6368072307821887, | |
| "eval_recall": 0.6511079679396511, | |
| "eval_runtime": 662.5188, | |
| "eval_samples_per_second": 6.403, | |
| "eval_steps_per_second": 0.801, | |
| "step": 31820 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "grad_norm": 10.867647171020508, | |
| "learning_rate": 4.096763771001432e-05, | |
| "loss": 0.6433, | |
| "step": 33411 | |
| }, | |
| { | |
| "epoch": 20.01, | |
| "eval_accuracy": 0.6364922206506365, | |
| "eval_f1": 0.6138991311356594, | |
| "eval_loss": 1.4018532037734985, | |
| "eval_precision": 0.6374756941286471, | |
| "eval_recall": 0.6364922206506365, | |
| "eval_runtime": 667.8552, | |
| "eval_samples_per_second": 6.352, | |
| "eval_steps_per_second": 0.795, | |
| "step": 33411 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "grad_norm": 23.982513427734375, | |
| "learning_rate": 4.0272974955464746e-05, | |
| "loss": 0.5969, | |
| "step": 35002 | |
| }, | |
| { | |
| "epoch": 21.01, | |
| "eval_accuracy": 0.6341348420556341, | |
| "eval_f1": 0.6104193509325564, | |
| "eval_loss": 1.4419147968292236, | |
| "eval_precision": 0.6211641893240438, | |
| "eval_recall": 0.6341348420556341, | |
| "eval_runtime": 657.2327, | |
| "eval_samples_per_second": 6.454, | |
| "eval_steps_per_second": 0.808, | |
| "step": 35002 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "grad_norm": 4.0233635902404785, | |
| "learning_rate": 3.957831220091516e-05, | |
| "loss": 0.563, | |
| "step": 36593 | |
| }, | |
| { | |
| "epoch": 22.01, | |
| "eval_accuracy": 0.6508722300801508, | |
| "eval_f1": 0.6170283959147944, | |
| "eval_loss": 1.4777988195419312, | |
| "eval_precision": 0.6292668904937919, | |
| "eval_recall": 0.6508722300801508, | |
| "eval_runtime": 657.9566, | |
| "eval_samples_per_second": 6.447, | |
| "eval_steps_per_second": 0.807, | |
| "step": 36593 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "grad_norm": 23.503877639770508, | |
| "learning_rate": 3.8883649446365576e-05, | |
| "loss": 0.5252, | |
| "step": 38184 | |
| }, | |
| { | |
| "epoch": 23.01, | |
| "eval_accuracy": 0.6433286185761433, | |
| "eval_f1": 0.6213976507987007, | |
| "eval_loss": 1.486406683921814, | |
| "eval_precision": 0.6316274985409115, | |
| "eval_recall": 0.6433286185761433, | |
| "eval_runtime": 652.8988, | |
| "eval_samples_per_second": 6.497, | |
| "eval_steps_per_second": 0.813, | |
| "step": 38184 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "grad_norm": 29.642290115356445, | |
| "learning_rate": 3.8188986691815994e-05, | |
| "loss": 0.5, | |
| "step": 39775 | |
| }, | |
| { | |
| "epoch": 24.01, | |
| "eval_accuracy": 0.6232909005186232, | |
| "eval_f1": 0.6023496407577721, | |
| "eval_loss": 1.6704081296920776, | |
| "eval_precision": 0.6273005697774543, | |
| "eval_recall": 0.6232909005186232, | |
| "eval_runtime": 651.691, | |
| "eval_samples_per_second": 6.509, | |
| "eval_steps_per_second": 0.815, | |
| "step": 39775 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "grad_norm": 0.25407856702804565, | |
| "learning_rate": 3.749432393726641e-05, | |
| "loss": 0.4622, | |
| "step": 41366 | |
| }, | |
| { | |
| "epoch": 25.01, | |
| "eval_accuracy": 0.6487505893446488, | |
| "eval_f1": 0.6119499708020253, | |
| "eval_loss": 1.665787935256958, | |
| "eval_precision": 0.6259817520615986, | |
| "eval_recall": 0.6487505893446488, | |
| "eval_runtime": 664.0356, | |
| "eval_samples_per_second": 6.388, | |
| "eval_steps_per_second": 0.8, | |
| "step": 41366 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "grad_norm": 12.53039836883545, | |
| "learning_rate": 3.6799661182716824e-05, | |
| "loss": 0.4292, | |
| "step": 42957 | |
| }, | |
| { | |
| "epoch": 26.01, | |
| "eval_accuracy": 0.6494578029231495, | |
| "eval_f1": 0.6242771027666587, | |
| "eval_loss": 1.6428192853927612, | |
| "eval_precision": 0.6286829818492489, | |
| "eval_recall": 0.6494578029231495, | |
| "eval_runtime": 673.3255, | |
| "eval_samples_per_second": 6.3, | |
| "eval_steps_per_second": 0.789, | |
| "step": 42957 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "grad_norm": 2.96919846534729, | |
| "learning_rate": 3.610499842816725e-05, | |
| "loss": 0.4044, | |
| "step": 44548 | |
| }, | |
| { | |
| "epoch": 27.01, | |
| "eval_accuracy": 0.6586515794436586, | |
| "eval_f1": 0.6387100670675616, | |
| "eval_loss": 1.6702899932861328, | |
| "eval_precision": 0.6310773161399348, | |
| "eval_recall": 0.6586515794436586, | |
| "eval_runtime": 657.3579, | |
| "eval_samples_per_second": 6.453, | |
| "eval_steps_per_second": 0.808, | |
| "step": 44548 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "grad_norm": 2.961900472640991, | |
| "learning_rate": 3.541033567361766e-05, | |
| "loss": 0.3952, | |
| "step": 46139 | |
| }, | |
| { | |
| "epoch": 28.01, | |
| "eval_accuracy": 0.632956152758133, | |
| "eval_f1": 0.6123356581191824, | |
| "eval_loss": 1.7576137781143188, | |
| "eval_precision": 0.6170827944289541, | |
| "eval_recall": 0.632956152758133, | |
| "eval_runtime": 659.0162, | |
| "eval_samples_per_second": 6.437, | |
| "eval_steps_per_second": 0.806, | |
| "step": 46139 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "grad_norm": 17.30776596069336, | |
| "learning_rate": 3.471567291906808e-05, | |
| "loss": 0.3681, | |
| "step": 47730 | |
| }, | |
| { | |
| "epoch": 29.01, | |
| "eval_accuracy": 0.6553512494106554, | |
| "eval_f1": 0.6231268362993411, | |
| "eval_loss": 1.9031915664672852, | |
| "eval_precision": 0.6349163976683712, | |
| "eval_recall": 0.6553512494106554, | |
| "eval_runtime": 657.4951, | |
| "eval_samples_per_second": 6.452, | |
| "eval_steps_per_second": 0.808, | |
| "step": 47730 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "grad_norm": 15.424605369567871, | |
| "learning_rate": 3.40210101645185e-05, | |
| "loss": 0.3541, | |
| "step": 49321 | |
| }, | |
| { | |
| "epoch": 30.01, | |
| "eval_accuracy": 0.6445073078736445, | |
| "eval_f1": 0.6207211544517277, | |
| "eval_loss": 1.9507993459701538, | |
| "eval_precision": 0.632026480012122, | |
| "eval_recall": 0.6445073078736445, | |
| "eval_runtime": 655.6116, | |
| "eval_samples_per_second": 6.47, | |
| "eval_steps_per_second": 0.81, | |
| "step": 49321 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "grad_norm": 0.31878066062927246, | |
| "learning_rate": 3.3326347409968915e-05, | |
| "loss": 0.322, | |
| "step": 50912 | |
| }, | |
| { | |
| "epoch": 31.01, | |
| "eval_accuracy": 0.6225836869401226, | |
| "eval_f1": 0.6098707323593034, | |
| "eval_loss": 2.1316964626312256, | |
| "eval_precision": 0.6276797078299916, | |
| "eval_recall": 0.6225836869401226, | |
| "eval_runtime": 655.8263, | |
| "eval_samples_per_second": 6.468, | |
| "eval_steps_per_second": 0.81, | |
| "step": 50912 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "grad_norm": 1.1452162265777588, | |
| "learning_rate": 3.263168465541933e-05, | |
| "loss": 0.3239, | |
| "step": 52503 | |
| }, | |
| { | |
| "epoch": 32.01, | |
| "eval_accuracy": 0.6508722300801508, | |
| "eval_f1": 0.6327759879930807, | |
| "eval_loss": 1.9785257577896118, | |
| "eval_precision": 0.6320825441180629, | |
| "eval_recall": 0.6508722300801508, | |
| "eval_runtime": 656.8912, | |
| "eval_samples_per_second": 6.458, | |
| "eval_steps_per_second": 0.808, | |
| "step": 52503 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "grad_norm": 18.911890029907227, | |
| "learning_rate": 3.193702190086975e-05, | |
| "loss": 0.301, | |
| "step": 54094 | |
| }, | |
| { | |
| "epoch": 33.01, | |
| "eval_accuracy": 0.6435643564356436, | |
| "eval_f1": 0.6097216315179437, | |
| "eval_loss": 2.2050163745880127, | |
| "eval_precision": 0.6258806132730886, | |
| "eval_recall": 0.6435643564356436, | |
| "eval_runtime": 659.2017, | |
| "eval_samples_per_second": 6.435, | |
| "eval_steps_per_second": 0.806, | |
| "step": 54094 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "grad_norm": 0.37402623891830444, | |
| "learning_rate": 3.124235914632016e-05, | |
| "loss": 0.28, | |
| "step": 55685 | |
| }, | |
| { | |
| "epoch": 34.01, | |
| "eval_accuracy": 0.6320132013201321, | |
| "eval_f1": 0.6173670056289928, | |
| "eval_loss": 2.2267725467681885, | |
| "eval_precision": 0.6318691154473476, | |
| "eval_recall": 0.6320132013201321, | |
| "eval_runtime": 655.5706, | |
| "eval_samples_per_second": 6.471, | |
| "eval_steps_per_second": 0.81, | |
| "step": 55685 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "grad_norm": 0.24996362626552582, | |
| "learning_rate": 3.054769639177059e-05, | |
| "loss": 0.2742, | |
| "step": 57276 | |
| }, | |
| { | |
| "epoch": 35.01, | |
| "eval_accuracy": 0.641914191419142, | |
| "eval_f1": 0.6158490856542709, | |
| "eval_loss": 2.3538448810577393, | |
| "eval_precision": 0.6239469548156946, | |
| "eval_recall": 0.641914191419142, | |
| "eval_runtime": 658.9065, | |
| "eval_samples_per_second": 6.438, | |
| "eval_steps_per_second": 0.806, | |
| "step": 57276 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "grad_norm": 40.534271240234375, | |
| "learning_rate": 2.9853033637221e-05, | |
| "loss": 0.2433, | |
| "step": 58867 | |
| }, | |
| { | |
| "epoch": 36.01, | |
| "eval_accuracy": 0.6478076379066479, | |
| "eval_f1": 0.6184054664095173, | |
| "eval_loss": 2.3947157859802246, | |
| "eval_precision": 0.6237019229335129, | |
| "eval_recall": 0.6478076379066479, | |
| "eval_runtime": 658.8157, | |
| "eval_samples_per_second": 6.439, | |
| "eval_steps_per_second": 0.806, | |
| "step": 58867 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "grad_norm": 0.18938298523426056, | |
| "learning_rate": 2.915837088267142e-05, | |
| "loss": 0.2677, | |
| "step": 60458 | |
| }, | |
| { | |
| "epoch": 37.01, | |
| "eval_accuracy": 0.6454502593116455, | |
| "eval_f1": 0.6234092398599342, | |
| "eval_loss": 2.400697708129883, | |
| "eval_precision": 0.6284538940001326, | |
| "eval_recall": 0.6454502593116455, | |
| "eval_runtime": 672.9538, | |
| "eval_samples_per_second": 6.304, | |
| "eval_steps_per_second": 0.789, | |
| "step": 60458 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "grad_norm": 0.05054619163274765, | |
| "learning_rate": 2.8463708128121836e-05, | |
| "loss": 0.2316, | |
| "step": 62049 | |
| }, | |
| { | |
| "epoch": 38.01, | |
| "eval_accuracy": 0.6296558227251297, | |
| "eval_f1": 0.6119646490374726, | |
| "eval_loss": 2.5197205543518066, | |
| "eval_precision": 0.6245868321675843, | |
| "eval_recall": 0.6296558227251297, | |
| "eval_runtime": 677.5713, | |
| "eval_samples_per_second": 6.261, | |
| "eval_steps_per_second": 0.784, | |
| "step": 62049 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "grad_norm": 0.9518815875053406, | |
| "learning_rate": 2.7769045373572254e-05, | |
| "loss": 0.2229, | |
| "step": 63640 | |
| }, | |
| { | |
| "epoch": 39.01, | |
| "eval_accuracy": 0.6506364922206507, | |
| "eval_f1": 0.6235476374240025, | |
| "eval_loss": 2.547842264175415, | |
| "eval_precision": 0.6321911444043747, | |
| "eval_recall": 0.6506364922206507, | |
| "eval_runtime": 680.5865, | |
| "eval_samples_per_second": 6.233, | |
| "eval_steps_per_second": 0.78, | |
| "step": 63640 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "grad_norm": 0.030849022790789604, | |
| "learning_rate": 2.707438261902267e-05, | |
| "loss": 0.215, | |
| "step": 65231 | |
| }, | |
| { | |
| "epoch": 40.01, | |
| "eval_accuracy": 0.6445073078736445, | |
| "eval_f1": 0.6209448574869749, | |
| "eval_loss": 2.516798734664917, | |
| "eval_precision": 0.6454990917874304, | |
| "eval_recall": 0.6445073078736445, | |
| "eval_runtime": 663.9051, | |
| "eval_samples_per_second": 6.389, | |
| "eval_steps_per_second": 0.8, | |
| "step": 65231 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "grad_norm": 0.38587260246276855, | |
| "learning_rate": 2.637971986447309e-05, | |
| "loss": 0.2032, | |
| "step": 66822 | |
| }, | |
| { | |
| "epoch": 41.01, | |
| "eval_accuracy": 0.6442715700141443, | |
| "eval_f1": 0.6161042310233847, | |
| "eval_loss": 2.6606993675231934, | |
| "eval_precision": 0.6304245945338769, | |
| "eval_recall": 0.6442715700141443, | |
| "eval_runtime": 670.0548, | |
| "eval_samples_per_second": 6.331, | |
| "eval_steps_per_second": 0.792, | |
| "step": 66822 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "grad_norm": 52.90748977661133, | |
| "learning_rate": 2.5685057109923506e-05, | |
| "loss": 0.1957, | |
| "step": 68413 | |
| }, | |
| { | |
| "epoch": 42.01, | |
| "eval_accuracy": 0.6218764733616219, | |
| "eval_f1": 0.6058915424282973, | |
| "eval_loss": 2.6433801651000977, | |
| "eval_precision": 0.6206059185377255, | |
| "eval_recall": 0.6218764733616219, | |
| "eval_runtime": 666.3612, | |
| "eval_samples_per_second": 6.366, | |
| "eval_steps_per_second": 0.797, | |
| "step": 68413 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "grad_norm": 0.5584044456481934, | |
| "learning_rate": 2.499039435537392e-05, | |
| "loss": 0.1839, | |
| "step": 70004 | |
| }, | |
| { | |
| "epoch": 43.01, | |
| "eval_accuracy": 0.648043375766148, | |
| "eval_f1": 0.6202014579788635, | |
| "eval_loss": 2.637795925140381, | |
| "eval_precision": 0.6181521426299653, | |
| "eval_recall": 0.648043375766148, | |
| "eval_runtime": 669.3865, | |
| "eval_samples_per_second": 6.337, | |
| "eval_steps_per_second": 0.793, | |
| "step": 70004 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "grad_norm": 0.02387963980436325, | |
| "learning_rate": 2.429573160082434e-05, | |
| "loss": 0.1672, | |
| "step": 71595 | |
| }, | |
| { | |
| "epoch": 44.01, | |
| "eval_accuracy": 0.632956152758133, | |
| "eval_f1": 0.6095258779451574, | |
| "eval_loss": 2.8354904651641846, | |
| "eval_precision": 0.6175432549732301, | |
| "eval_recall": 0.632956152758133, | |
| "eval_runtime": 658.5104, | |
| "eval_samples_per_second": 6.442, | |
| "eval_steps_per_second": 0.806, | |
| "step": 71595 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "grad_norm": 0.04022861644625664, | |
| "learning_rate": 2.3601068846274757e-05, | |
| "loss": 0.1554, | |
| "step": 73186 | |
| }, | |
| { | |
| "epoch": 45.01, | |
| "eval_accuracy": 0.6296558227251297, | |
| "eval_f1": 0.609015505263741, | |
| "eval_loss": 2.8833281993865967, | |
| "eval_precision": 0.6179849508221367, | |
| "eval_recall": 0.6296558227251297, | |
| "eval_runtime": 666.4351, | |
| "eval_samples_per_second": 6.365, | |
| "eval_steps_per_second": 0.797, | |
| "step": 73186 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "grad_norm": 3.8721201419830322, | |
| "learning_rate": 2.2906406091725175e-05, | |
| "loss": 0.1525, | |
| "step": 74777 | |
| }, | |
| { | |
| "epoch": 46.01, | |
| "eval_accuracy": 0.6499292786421499, | |
| "eval_f1": 0.6246638391623945, | |
| "eval_loss": 2.8732240200042725, | |
| "eval_precision": 0.6212359780695843, | |
| "eval_recall": 0.6499292786421499, | |
| "eval_runtime": 672.5613, | |
| "eval_samples_per_second": 6.307, | |
| "eval_steps_per_second": 0.79, | |
| "step": 74777 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "grad_norm": 0.009451803751289845, | |
| "learning_rate": 2.221174333717559e-05, | |
| "loss": 0.1443, | |
| "step": 76368 | |
| }, | |
| { | |
| "epoch": 47.01, | |
| "eval_accuracy": 0.6513437057991514, | |
| "eval_f1": 0.6297491645477588, | |
| "eval_loss": 2.7935521602630615, | |
| "eval_precision": 0.6239725322581114, | |
| "eval_recall": 0.6513437057991514, | |
| "eval_runtime": 673.447, | |
| "eval_samples_per_second": 6.299, | |
| "eval_steps_per_second": 0.788, | |
| "step": 76368 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "grad_norm": 0.0011284707579761744, | |
| "learning_rate": 2.151708058262601e-05, | |
| "loss": 0.1361, | |
| "step": 77959 | |
| }, | |
| { | |
| "epoch": 48.01, | |
| "eval_accuracy": 0.6442715700141443, | |
| "eval_f1": 0.6229754386330917, | |
| "eval_loss": 2.8814539909362793, | |
| "eval_precision": 0.6187358231984663, | |
| "eval_recall": 0.6442715700141443, | |
| "eval_runtime": 674.3209, | |
| "eval_samples_per_second": 6.291, | |
| "eval_steps_per_second": 0.787, | |
| "step": 77959 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "grad_norm": 102.50770568847656, | |
| "learning_rate": 2.0822417828076427e-05, | |
| "loss": 0.1351, | |
| "step": 79550 | |
| }, | |
| { | |
| "epoch": 49.01, | |
| "eval_accuracy": 0.6428571428571429, | |
| "eval_f1": 0.6174587269654099, | |
| "eval_loss": 3.070270299911499, | |
| "eval_precision": 0.6243702935522684, | |
| "eval_recall": 0.6428571428571429, | |
| "eval_runtime": 669.5589, | |
| "eval_samples_per_second": 6.336, | |
| "eval_steps_per_second": 0.793, | |
| "step": 79550 | |
| }, | |
| { | |
| "epoch": 50.01, | |
| "grad_norm": 8.653002738952637, | |
| "learning_rate": 2.0127755073526845e-05, | |
| "loss": 0.1196, | |
| "step": 81141 | |
| }, | |
| { | |
| "epoch": 50.01, | |
| "eval_accuracy": 0.6423856671381424, | |
| "eval_f1": 0.6190424793456692, | |
| "eval_loss": 3.027528762817383, | |
| "eval_precision": 0.625005878732158, | |
| "eval_recall": 0.6423856671381424, | |
| "eval_runtime": 677.2082, | |
| "eval_samples_per_second": 6.264, | |
| "eval_steps_per_second": 0.784, | |
| "step": 81141 | |
| }, | |
| { | |
| "epoch": 51.01, | |
| "grad_norm": 62.25484848022461, | |
| "learning_rate": 1.943309231897726e-05, | |
| "loss": 0.111, | |
| "step": 82732 | |
| }, | |
| { | |
| "epoch": 51.01, | |
| "eval_accuracy": 0.641914191419142, | |
| "eval_f1": 0.618920231303522, | |
| "eval_loss": 3.1254563331604004, | |
| "eval_precision": 0.6280670220001587, | |
| "eval_recall": 0.641914191419142, | |
| "eval_runtime": 651.0502, | |
| "eval_samples_per_second": 6.516, | |
| "eval_steps_per_second": 0.816, | |
| "step": 82732 | |
| }, | |
| { | |
| "epoch": 52.01, | |
| "grad_norm": 18.133270263671875, | |
| "learning_rate": 1.8738429564427678e-05, | |
| "loss": 0.1119, | |
| "step": 84323 | |
| }, | |
| { | |
| "epoch": 52.01, | |
| "eval_accuracy": 0.6471004243281471, | |
| "eval_f1": 0.6214547873156199, | |
| "eval_loss": 3.1854350566864014, | |
| "eval_precision": 0.629875200916356, | |
| "eval_recall": 0.6471004243281471, | |
| "eval_runtime": 653.5, | |
| "eval_samples_per_second": 6.491, | |
| "eval_steps_per_second": 0.813, | |
| "step": 84323 | |
| }, | |
| { | |
| "epoch": 53.01, | |
| "grad_norm": 19.144214630126953, | |
| "learning_rate": 1.8043766809878096e-05, | |
| "loss": 0.1069, | |
| "step": 85914 | |
| }, | |
| { | |
| "epoch": 53.01, | |
| "eval_accuracy": 0.6383781235266384, | |
| "eval_f1": 0.6195011414926834, | |
| "eval_loss": 3.2136049270629883, | |
| "eval_precision": 0.6251413165179668, | |
| "eval_recall": 0.6383781235266384, | |
| "eval_runtime": 653.7257, | |
| "eval_samples_per_second": 6.489, | |
| "eval_steps_per_second": 0.812, | |
| "step": 85914 | |
| }, | |
| { | |
| "epoch": 54.01, | |
| "grad_norm": 0.010962074622511864, | |
| "learning_rate": 1.7349104055328515e-05, | |
| "loss": 0.093, | |
| "step": 87505 | |
| }, | |
| { | |
| "epoch": 54.01, | |
| "eval_accuracy": 0.6506364922206507, | |
| "eval_f1": 0.6154588049677499, | |
| "eval_loss": 3.3124778270721436, | |
| "eval_precision": 0.614483037031078, | |
| "eval_recall": 0.6506364922206507, | |
| "eval_runtime": 653.1839, | |
| "eval_samples_per_second": 6.494, | |
| "eval_steps_per_second": 0.813, | |
| "step": 87505 | |
| }, | |
| { | |
| "epoch": 55.01, | |
| "grad_norm": 4.032207489013672, | |
| "learning_rate": 1.665444130077893e-05, | |
| "loss": 0.0901, | |
| "step": 89096 | |
| }, | |
| { | |
| "epoch": 55.01, | |
| "eval_accuracy": 0.6383781235266384, | |
| "eval_f1": 0.6217233442126047, | |
| "eval_loss": 3.3028151988983154, | |
| "eval_precision": 0.6277366002975752, | |
| "eval_recall": 0.6383781235266384, | |
| "eval_runtime": 651.3473, | |
| "eval_samples_per_second": 6.513, | |
| "eval_steps_per_second": 0.815, | |
| "step": 89096 | |
| }, | |
| { | |
| "epoch": 56.01, | |
| "grad_norm": 0.039573218673467636, | |
| "learning_rate": 1.5959778546229348e-05, | |
| "loss": 0.0776, | |
| "step": 90687 | |
| }, | |
| { | |
| "epoch": 56.01, | |
| "eval_accuracy": 0.6487505893446488, | |
| "eval_f1": 0.6297653212708532, | |
| "eval_loss": 3.3314833641052246, | |
| "eval_precision": 0.6272429266150353, | |
| "eval_recall": 0.6487505893446488, | |
| "eval_runtime": 649.3376, | |
| "eval_samples_per_second": 6.533, | |
| "eval_steps_per_second": 0.818, | |
| "step": 90687 | |
| }, | |
| { | |
| "epoch": 57.01, | |
| "grad_norm": 0.0005812808522023261, | |
| "learning_rate": 1.5265115791679766e-05, | |
| "loss": 0.0837, | |
| "step": 92278 | |
| }, | |
| { | |
| "epoch": 57.01, | |
| "eval_accuracy": 0.6558227251296558, | |
| "eval_f1": 0.6242411319775614, | |
| "eval_loss": 3.438481092453003, | |
| "eval_precision": 0.6374388645077231, | |
| "eval_recall": 0.6558227251296558, | |
| "eval_runtime": 658.6971, | |
| "eval_samples_per_second": 6.44, | |
| "eval_steps_per_second": 0.806, | |
| "step": 92278 | |
| }, | |
| { | |
| "epoch": 58.01, | |
| "grad_norm": 0.04262514412403107, | |
| "learning_rate": 1.4570453037130182e-05, | |
| "loss": 0.0701, | |
| "step": 93869 | |
| }, | |
| { | |
| "epoch": 58.01, | |
| "eval_accuracy": 0.644035832154644, | |
| "eval_f1": 0.6285778416417378, | |
| "eval_loss": 3.3799736499786377, | |
| "eval_precision": 0.6320916006510833, | |
| "eval_recall": 0.644035832154644, | |
| "eval_runtime": 669.2439, | |
| "eval_samples_per_second": 6.338, | |
| "eval_steps_per_second": 0.793, | |
| "step": 93869 | |
| }, | |
| { | |
| "epoch": 59.01, | |
| "grad_norm": 0.001757206628099084, | |
| "learning_rate": 1.38757902825806e-05, | |
| "loss": 0.0682, | |
| "step": 95460 | |
| }, | |
| { | |
| "epoch": 59.01, | |
| "eval_accuracy": 0.6541725601131542, | |
| "eval_f1": 0.6262011153983429, | |
| "eval_loss": 3.4473154544830322, | |
| "eval_precision": 0.6343707774148433, | |
| "eval_recall": 0.6541725601131542, | |
| "eval_runtime": 660.2778, | |
| "eval_samples_per_second": 6.425, | |
| "eval_steps_per_second": 0.804, | |
| "step": 95460 | |
| }, | |
| { | |
| "epoch": 60.01, | |
| "grad_norm": 0.08907134085893631, | |
| "learning_rate": 1.3181127528031017e-05, | |
| "loss": 0.0763, | |
| "step": 97051 | |
| }, | |
| { | |
| "epoch": 60.01, | |
| "eval_accuracy": 0.6315417256011315, | |
| "eval_f1": 0.6148352414634933, | |
| "eval_loss": 3.450514316558838, | |
| "eval_precision": 0.6148635373339948, | |
| "eval_recall": 0.6315417256011315, | |
| "eval_runtime": 666.8615, | |
| "eval_samples_per_second": 6.361, | |
| "eval_steps_per_second": 0.796, | |
| "step": 97051 | |
| }, | |
| { | |
| "epoch": 61.01, | |
| "grad_norm": 0.0005003924597986042, | |
| "learning_rate": 1.2486464773481436e-05, | |
| "loss": 0.0629, | |
| "step": 98642 | |
| }, | |
| { | |
| "epoch": 61.01, | |
| "eval_accuracy": 0.6504007543611504, | |
| "eval_f1": 0.6253235814801552, | |
| "eval_loss": 3.440239906311035, | |
| "eval_precision": 0.6233462363989224, | |
| "eval_recall": 0.6504007543611504, | |
| "eval_runtime": 653.614, | |
| "eval_samples_per_second": 6.49, | |
| "eval_steps_per_second": 0.812, | |
| "step": 98642 | |
| }, | |
| { | |
| "epoch": 62.01, | |
| "grad_norm": 0.06604283303022385, | |
| "learning_rate": 1.1791802018931852e-05, | |
| "loss": 0.0552, | |
| "step": 100233 | |
| }, | |
| { | |
| "epoch": 62.01, | |
| "eval_accuracy": 0.6537010843941538, | |
| "eval_f1": 0.6314537569564033, | |
| "eval_loss": 3.4401602745056152, | |
| "eval_precision": 0.6324239134320033, | |
| "eval_recall": 0.6537010843941538, | |
| "eval_runtime": 663.5087, | |
| "eval_samples_per_second": 6.393, | |
| "eval_steps_per_second": 0.8, | |
| "step": 100233 | |
| }, | |
| { | |
| "epoch": 63.01, | |
| "grad_norm": 0.00693962536752224, | |
| "learning_rate": 1.109713926438227e-05, | |
| "loss": 0.0463, | |
| "step": 101824 | |
| }, | |
| { | |
| "epoch": 63.01, | |
| "eval_accuracy": 0.6466289486091467, | |
| "eval_f1": 0.6216674773439607, | |
| "eval_loss": 3.529994010925293, | |
| "eval_precision": 0.6217012879573426, | |
| "eval_recall": 0.6466289486091467, | |
| "eval_runtime": 686.7487, | |
| "eval_samples_per_second": 6.177, | |
| "eval_steps_per_second": 0.773, | |
| "step": 101824 | |
| }, | |
| { | |
| "epoch": 64.01, | |
| "grad_norm": 0.0005720761837437749, | |
| "learning_rate": 1.0402476509832687e-05, | |
| "loss": 0.0471, | |
| "step": 103415 | |
| }, | |
| { | |
| "epoch": 64.01, | |
| "eval_accuracy": 0.6511079679396511, | |
| "eval_f1": 0.6222590555700158, | |
| "eval_loss": 3.6793229579925537, | |
| "eval_precision": 0.6346230225230813, | |
| "eval_recall": 0.6511079679396511, | |
| "eval_runtime": 669.336, | |
| "eval_samples_per_second": 6.338, | |
| "eval_steps_per_second": 0.793, | |
| "step": 103415 | |
| }, | |
| { | |
| "epoch": 65.01, | |
| "grad_norm": 0.0010839367751032114, | |
| "learning_rate": 9.707813755283105e-06, | |
| "loss": 0.0448, | |
| "step": 105006 | |
| }, | |
| { | |
| "epoch": 65.01, | |
| "eval_accuracy": 0.6449787835926449, | |
| "eval_f1": 0.6169893577308092, | |
| "eval_loss": 3.685042142868042, | |
| "eval_precision": 0.6265011843748146, | |
| "eval_recall": 0.6449787835926449, | |
| "eval_runtime": 670.2367, | |
| "eval_samples_per_second": 6.329, | |
| "eval_steps_per_second": 0.792, | |
| "step": 105006 | |
| }, | |
| { | |
| "epoch": 66.01, | |
| "grad_norm": 0.03215405344963074, | |
| "learning_rate": 9.013151000733522e-06, | |
| "loss": 0.0362, | |
| "step": 106597 | |
| }, | |
| { | |
| "epoch": 66.01, | |
| "eval_accuracy": 0.6482791136256483, | |
| "eval_f1": 0.624213528202086, | |
| "eval_loss": 3.658543348312378, | |
| "eval_precision": 0.6265115566919579, | |
| "eval_recall": 0.6482791136256483, | |
| "eval_runtime": 655.7488, | |
| "eval_samples_per_second": 6.469, | |
| "eval_steps_per_second": 0.81, | |
| "step": 106597 | |
| }, | |
| { | |
| "epoch": 67.01, | |
| "grad_norm": 0.00014659887528978288, | |
| "learning_rate": 8.31848824618394e-06, | |
| "loss": 0.0419, | |
| "step": 108188 | |
| }, | |
| { | |
| "epoch": 67.01, | |
| "eval_accuracy": 0.6343705799151343, | |
| "eval_f1": 0.6168968855551049, | |
| "eval_loss": 3.6284878253936768, | |
| "eval_precision": 0.6192216504465796, | |
| "eval_recall": 0.6343705799151343, | |
| "eval_runtime": 667.7711, | |
| "eval_samples_per_second": 6.352, | |
| "eval_steps_per_second": 0.795, | |
| "step": 108188 | |
| }, | |
| { | |
| "epoch": 68.01, | |
| "grad_norm": 0.0006045685149729252, | |
| "learning_rate": 7.6238254916343565e-06, | |
| "loss": 0.0309, | |
| "step": 109779 | |
| }, | |
| { | |
| "epoch": 68.01, | |
| "eval_accuracy": 0.648986327204149, | |
| "eval_f1": 0.6269316812634602, | |
| "eval_loss": 3.665743112564087, | |
| "eval_precision": 0.6264133629902356, | |
| "eval_recall": 0.648986327204149, | |
| "eval_runtime": 670.5591, | |
| "eval_samples_per_second": 6.326, | |
| "eval_steps_per_second": 0.792, | |
| "step": 109779 | |
| }, | |
| { | |
| "epoch": 69.01, | |
| "grad_norm": 0.0056765577755868435, | |
| "learning_rate": 6.929162737084774e-06, | |
| "loss": 0.0312, | |
| "step": 111370 | |
| }, | |
| { | |
| "epoch": 69.01, | |
| "eval_accuracy": 0.6416784535596417, | |
| "eval_f1": 0.6205254067422245, | |
| "eval_loss": 3.7122817039489746, | |
| "eval_precision": 0.6239256088005212, | |
| "eval_recall": 0.6416784535596417, | |
| "eval_runtime": 661.8739, | |
| "eval_samples_per_second": 6.409, | |
| "eval_steps_per_second": 0.802, | |
| "step": 111370 | |
| }, | |
| { | |
| "epoch": 70.01, | |
| "grad_norm": 0.0024060504510998726, | |
| "learning_rate": 6.234499982535192e-06, | |
| "loss": 0.0315, | |
| "step": 112961 | |
| }, | |
| { | |
| "epoch": 70.01, | |
| "eval_accuracy": 0.648986327204149, | |
| "eval_f1": 0.6189187635444573, | |
| "eval_loss": 3.753802537918091, | |
| "eval_precision": 0.6224224422132874, | |
| "eval_recall": 0.648986327204149, | |
| "eval_runtime": 664.7996, | |
| "eval_samples_per_second": 6.381, | |
| "eval_steps_per_second": 0.799, | |
| "step": 112961 | |
| }, | |
| { | |
| "epoch": 71.01, | |
| "grad_norm": 0.047281160950660706, | |
| "learning_rate": 5.53983722798561e-06, | |
| "loss": 0.0294, | |
| "step": 114552 | |
| }, | |
| { | |
| "epoch": 71.01, | |
| "eval_accuracy": 0.6482791136256483, | |
| "eval_f1": 0.6236630466746416, | |
| "eval_loss": 3.706387519836426, | |
| "eval_precision": 0.6234001348683471, | |
| "eval_recall": 0.6482791136256483, | |
| "eval_runtime": 677.1081, | |
| "eval_samples_per_second": 6.265, | |
| "eval_steps_per_second": 0.784, | |
| "step": 114552 | |
| }, | |
| { | |
| "epoch": 72.01, | |
| "grad_norm": 0.00014872274186927825, | |
| "learning_rate": 4.845174473436027e-06, | |
| "loss": 0.0282, | |
| "step": 116143 | |
| }, | |
| { | |
| "epoch": 72.01, | |
| "eval_accuracy": 0.6428571428571429, | |
| "eval_f1": 0.6192426747671007, | |
| "eval_loss": 3.7945356369018555, | |
| "eval_precision": 0.624713412639683, | |
| "eval_recall": 0.6428571428571429, | |
| "eval_runtime": 677.029, | |
| "eval_samples_per_second": 6.266, | |
| "eval_steps_per_second": 0.784, | |
| "step": 116143 | |
| }, | |
| { | |
| "epoch": 73.01, | |
| "grad_norm": 0.0006783913122490048, | |
| "learning_rate": 4.150511718886444e-06, | |
| "loss": 0.0275, | |
| "step": 117734 | |
| }, | |
| { | |
| "epoch": 73.01, | |
| "eval_accuracy": 0.6527581329561527, | |
| "eval_f1": 0.6271859964586763, | |
| "eval_loss": 3.7549855709075928, | |
| "eval_precision": 0.6297463780952456, | |
| "eval_recall": 0.6527581329561527, | |
| "eval_runtime": 694.5725, | |
| "eval_samples_per_second": 6.107, | |
| "eval_steps_per_second": 0.764, | |
| "step": 117734 | |
| }, | |
| { | |
| "epoch": 74.01, | |
| "grad_norm": 0.10241026431322098, | |
| "learning_rate": 3.4558489643368614e-06, | |
| "loss": 0.0319, | |
| "step": 119325 | |
| }, | |
| { | |
| "epoch": 74.01, | |
| "eval_accuracy": 0.6508722300801508, | |
| "eval_f1": 0.6233733427088337, | |
| "eval_loss": 3.740715980529785, | |
| "eval_precision": 0.628877991091339, | |
| "eval_recall": 0.6508722300801508, | |
| "eval_runtime": 654.6009, | |
| "eval_samples_per_second": 6.48, | |
| "eval_steps_per_second": 0.811, | |
| "step": 119325 | |
| }, | |
| { | |
| "epoch": 75.01, | |
| "grad_norm": 0.00016077565669547766, | |
| "learning_rate": 2.7611862097872788e-06, | |
| "loss": 0.021, | |
| "step": 120916 | |
| }, | |
| { | |
| "epoch": 75.01, | |
| "eval_accuracy": 0.6532296086751532, | |
| "eval_f1": 0.6269729664014984, | |
| "eval_loss": 3.75272536277771, | |
| "eval_precision": 0.6290218177795819, | |
| "eval_recall": 0.6532296086751532, | |
| "eval_runtime": 658.8706, | |
| "eval_samples_per_second": 6.438, | |
| "eval_steps_per_second": 0.806, | |
| "step": 120916 | |
| }, | |
| { | |
| "epoch": 76.01, | |
| "grad_norm": 0.0008236940484493971, | |
| "learning_rate": 2.066523455237696e-06, | |
| "loss": 0.0159, | |
| "step": 122507 | |
| }, | |
| { | |
| "epoch": 76.01, | |
| "eval_accuracy": 0.6515794436586516, | |
| "eval_f1": 0.6242553810002985, | |
| "eval_loss": 3.7779977321624756, | |
| "eval_precision": 0.6240515257248215, | |
| "eval_recall": 0.6515794436586516, | |
| "eval_runtime": 660.4492, | |
| "eval_samples_per_second": 6.423, | |
| "eval_steps_per_second": 0.804, | |
| "step": 122507 | |
| }, | |
| { | |
| "epoch": 77.01, | |
| "grad_norm": 0.004408856853842735, | |
| "learning_rate": 1.3718607006881136e-06, | |
| "loss": 0.0133, | |
| "step": 124098 | |
| }, | |
| { | |
| "epoch": 77.01, | |
| "eval_accuracy": 0.6499292786421499, | |
| "eval_f1": 0.624040880732074, | |
| "eval_loss": 3.7923333644866943, | |
| "eval_precision": 0.6271592552161068, | |
| "eval_recall": 0.6499292786421499, | |
| "eval_runtime": 666.8007, | |
| "eval_samples_per_second": 6.362, | |
| "eval_steps_per_second": 0.796, | |
| "step": 124098 | |
| }, | |
| { | |
| "epoch": 78.01, | |
| "grad_norm": 0.0014601564034819603, | |
| "learning_rate": 6.771979461385309e-07, | |
| "loss": 0.0125, | |
| "step": 125689 | |
| }, | |
| { | |
| "epoch": 78.01, | |
| "eval_accuracy": 0.6504007543611504, | |
| "eval_f1": 0.6216504935099332, | |
| "eval_loss": 3.8070006370544434, | |
| "eval_precision": 0.6262856082095383, | |
| "eval_recall": 0.6504007543611504, | |
| "eval_runtime": 667.8654, | |
| "eval_samples_per_second": 6.352, | |
| "eval_steps_per_second": 0.795, | |
| "step": 125689 | |
| }, | |
| { | |
| "epoch": 79.01, | |
| "grad_norm": 0.0005495115183293819, | |
| "learning_rate": 0.0, | |
| "loss": 0.0132, | |
| "step": 127240 | |
| }, | |
| { | |
| "epoch": 79.01, | |
| "eval_accuracy": 0.6506364922206507, | |
| "eval_f1": 0.6225468142229464, | |
| "eval_loss": 3.796358108520508, | |
| "eval_precision": 0.6264178866401664, | |
| "eval_recall": 0.6506364922206507, | |
| "eval_runtime": 698.0179, | |
| "eval_samples_per_second": 6.077, | |
| "eval_steps_per_second": 0.761, | |
| "step": 127240 | |
| }, | |
| { | |
| "epoch": 79.01, | |
| "step": 127240, | |
| "total_flos": 1.2682038581932563e+21, | |
| "train_loss": 0.41676221998635044, | |
| "train_runtime": 266875.9954, | |
| "train_samples_per_second": 3.814, | |
| "train_steps_per_second": 0.477 | |
| }, | |
| { | |
| "epoch": 79.01, | |
| "eval_accuracy": 0.6697312588401697, | |
| "eval_f1": 0.635434606603408, | |
| "eval_loss": 1.1357100009918213, | |
| "eval_precision": 0.642912037609069, | |
| "eval_recall": 0.6697312588401697, | |
| "eval_runtime": 859.5426, | |
| "eval_samples_per_second": 4.935, | |
| "eval_steps_per_second": 0.618, | |
| "step": 127240 | |
| }, | |
| { | |
| "epoch": 79.01, | |
| "eval_accuracy": 0.6697312588401697, | |
| "eval_f1": 0.635434606603408, | |
| "eval_loss": 1.1357100009918213, | |
| "eval_precision": 0.642912037609069, | |
| "eval_recall": 0.6697312588401697, | |
| "eval_runtime": 860.1584, | |
| "eval_samples_per_second": 4.932, | |
| "eval_steps_per_second": 0.617, | |
| "step": 127240 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 127240, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 9223372036854775807, | |
| "save_steps": 500, | |
| "total_flos": 1.2682038581932563e+21, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |