| { | |
| "best_metric": 0.9842267397484589, | |
| "best_model_checkpoint": "/home/alexanders/Workspaces/malexandersalazar/xlm-roberta-large-cls-toxicity/data/models/xlm-roberta-large-cls-toxicity/config_5/checkpoint-28610", | |
| "epoch": 9.999737922599808, | |
| "eval_steps": 500, | |
| "global_step": 28610, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.1747182667947934, | |
| "grad_norm": 12.17603588104248, | |
| "learning_rate": 6.934153502027121e-07, | |
| "loss": 0.7119, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3494365335895868, | |
| "grad_norm": 13.519432067871094, | |
| "learning_rate": 1.3910247448622957e-06, | |
| "loss": 0.3407, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5241548003843802, | |
| "grad_norm": 11.993674278259277, | |
| "learning_rate": 2.090032154340836e-06, | |
| "loss": 0.1725, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.6988730671791736, | |
| "grad_norm": 13.306364059448242, | |
| "learning_rate": 2.789039563819377e-06, | |
| "loss": 0.1498, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.8735913339739669, | |
| "grad_norm": 13.724279403686523, | |
| "learning_rate": 3.488046973297917e-06, | |
| "loss": 0.1368, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.9997379225998078, | |
| "eval_accuracy": 0.9578529000698812, | |
| "eval_f1": 0.9580195344026164, | |
| "eval_loss": 0.14260601997375488, | |
| "eval_precision": 0.9585943807196626, | |
| "eval_recall": 0.9578529000698812, | |
| "eval_runtime": 68.6764, | |
| "eval_samples_per_second": 333.389, | |
| "eval_steps_per_second": 20.837, | |
| "step": 2861 | |
| }, | |
| { | |
| "epoch": 1.0485716781689525, | |
| "grad_norm": 15.129600524902344, | |
| "learning_rate": 4.187054382776457e-06, | |
| "loss": 0.1225, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.223289944963746, | |
| "grad_norm": 18.516948699951172, | |
| "learning_rate": 4.884663777436041e-06, | |
| "loss": 0.111, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.3980082117585393, | |
| "grad_norm": 3.170327663421631, | |
| "learning_rate": 5.583671186914582e-06, | |
| "loss": 0.109, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.5727264785533328, | |
| "grad_norm": 9.642043113708496, | |
| "learning_rate": 6.281280581574165e-06, | |
| "loss": 0.1045, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.747444745348126, | |
| "grad_norm": 12.047298431396484, | |
| "learning_rate": 6.980287991052706e-06, | |
| "loss": 0.0981, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.9221630121429194, | |
| "grad_norm": 11.591704368591309, | |
| "learning_rate": 7.679295400531246e-06, | |
| "loss": 0.0983, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.9997379225998078, | |
| "eval_accuracy": 0.9699074074074074, | |
| "eval_f1": 0.9698689694737291, | |
| "eval_loss": 0.09155124425888062, | |
| "eval_precision": 0.9698681669937823, | |
| "eval_recall": 0.9699074074074074, | |
| "eval_runtime": 68.6299, | |
| "eval_samples_per_second": 333.616, | |
| "eval_steps_per_second": 20.851, | |
| "step": 5722 | |
| }, | |
| { | |
| "epoch": 2.097143356337905, | |
| "grad_norm": 7.699872970581055, | |
| "learning_rate": 8.378302810009785e-06, | |
| "loss": 0.0818, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 2.2718616231326987, | |
| "grad_norm": 2.9679672718048096, | |
| "learning_rate": 9.077310219488328e-06, | |
| "loss": 0.078, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 2.446579889927492, | |
| "grad_norm": 5.794170379638672, | |
| "learning_rate": 9.776317628966868e-06, | |
| "loss": 0.0769, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 2.6212981567222853, | |
| "grad_norm": 7.152242183685303, | |
| "learning_rate": 9.842009600596542e-06, | |
| "loss": 0.0719, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 2.7960164235170786, | |
| "grad_norm": 3.8340728282928467, | |
| "learning_rate": 9.608985412685837e-06, | |
| "loss": 0.0708, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 2.970734690311872, | |
| "grad_norm": 13.128349304199219, | |
| "learning_rate": 9.375961224775132e-06, | |
| "loss": 0.0748, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 2.9997379225998078, | |
| "eval_accuracy": 0.9731394129979035, | |
| "eval_f1": 0.9731494346588756, | |
| "eval_loss": 0.09937231242656708, | |
| "eval_precision": 0.9731628120366744, | |
| "eval_recall": 0.9731394129979035, | |
| "eval_runtime": 68.6513, | |
| "eval_samples_per_second": 333.512, | |
| "eval_steps_per_second": 20.844, | |
| "step": 8583 | |
| }, | |
| { | |
| "epoch": 3.145715034506858, | |
| "grad_norm": 20.52392578125, | |
| "learning_rate": 9.142937036864427e-06, | |
| "loss": 0.0504, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 3.320433301301651, | |
| "grad_norm": 33.67174530029297, | |
| "learning_rate": 8.909912848953722e-06, | |
| "loss": 0.049, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 3.4951515680964444, | |
| "grad_norm": 0.8490325212478638, | |
| "learning_rate": 8.676888661043017e-06, | |
| "loss": 0.0464, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 3.6698698348912377, | |
| "grad_norm": 13.017010688781738, | |
| "learning_rate": 8.443864473132312e-06, | |
| "loss": 0.0463, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 3.844588101686031, | |
| "grad_norm": 0.6549157500267029, | |
| "learning_rate": 8.210840285221606e-06, | |
| "loss": 0.049, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 3.9997379225998078, | |
| "eval_accuracy": 0.9785552061495457, | |
| "eval_f1": 0.9785386610066998, | |
| "eval_loss": 0.0886269360780716, | |
| "eval_precision": 0.9785361579407956, | |
| "eval_recall": 0.9785552061495457, | |
| "eval_runtime": 68.6459, | |
| "eval_samples_per_second": 333.538, | |
| "eval_steps_per_second": 20.846, | |
| "step": 11444 | |
| }, | |
| { | |
| "epoch": 4.019568445881017, | |
| "grad_norm": 40.50947952270508, | |
| "learning_rate": 7.977816097310901e-06, | |
| "loss": 0.0454, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 4.19428671267581, | |
| "grad_norm": 1.1528542041778564, | |
| "learning_rate": 7.744791909400196e-06, | |
| "loss": 0.029, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 4.369004979470604, | |
| "grad_norm": 42.926326751708984, | |
| "learning_rate": 7.512233769865313e-06, | |
| "loss": 0.0313, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 4.543723246265397, | |
| "grad_norm": 13.328317642211914, | |
| "learning_rate": 7.2792095819546074e-06, | |
| "loss": 0.0326, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 4.71844151306019, | |
| "grad_norm": 0.08160242438316345, | |
| "learning_rate": 7.0461853940439014e-06, | |
| "loss": 0.0293, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 4.893159779854984, | |
| "grad_norm": 21.219942092895508, | |
| "learning_rate": 6.813161206133197e-06, | |
| "loss": 0.0281, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 4.999737922599808, | |
| "eval_accuracy": 0.9791229909154437, | |
| "eval_f1": 0.9791175700337718, | |
| "eval_loss": 0.12131603062152863, | |
| "eval_precision": 0.9791137606071209, | |
| "eval_recall": 0.9791229909154437, | |
| "eval_runtime": 68.6286, | |
| "eval_samples_per_second": 333.622, | |
| "eval_steps_per_second": 20.851, | |
| "step": 14305 | |
| }, | |
| { | |
| "epoch": 5.068140124049969, | |
| "grad_norm": 8.010854721069336, | |
| "learning_rate": 6.580137018222492e-06, | |
| "loss": 0.0292, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 5.242858390844763, | |
| "grad_norm": 4.4188337326049805, | |
| "learning_rate": 6.347112830311787e-06, | |
| "loss": 0.0215, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 5.4175766576395565, | |
| "grad_norm": 65.55230712890625, | |
| "learning_rate": 6.1145546907769025e-06, | |
| "loss": 0.021, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 5.592294924434349, | |
| "grad_norm": 0.20221485197544098, | |
| "learning_rate": 5.881530502866198e-06, | |
| "loss": 0.0225, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 5.767013191229143, | |
| "grad_norm": 65.68180084228516, | |
| "learning_rate": 5.648506314955493e-06, | |
| "loss": 0.0199, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 5.941731458023936, | |
| "grad_norm": 0.33296695351600647, | |
| "learning_rate": 5.415482127044788e-06, | |
| "loss": 0.0211, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 5.999737922599808, | |
| "eval_accuracy": 0.9804769392033543, | |
| "eval_f1": 0.98049806714974, | |
| "eval_loss": 0.10157082974910736, | |
| "eval_precision": 0.9805481970936862, | |
| "eval_recall": 0.9804769392033543, | |
| "eval_runtime": 68.666, | |
| "eval_samples_per_second": 333.44, | |
| "eval_steps_per_second": 20.84, | |
| "step": 17166 | |
| }, | |
| { | |
| "epoch": 6.116711802218922, | |
| "grad_norm": 0.5054177045822144, | |
| "learning_rate": 5.182457939134083e-06, | |
| "loss": 0.0149, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 6.291430069013716, | |
| "grad_norm": 0.08331651240587234, | |
| "learning_rate": 4.9494337512233775e-06, | |
| "loss": 0.0141, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 6.466148335808509, | |
| "grad_norm": 0.04097016155719757, | |
| "learning_rate": 4.716409563312672e-06, | |
| "loss": 0.0107, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 6.640866602603302, | |
| "grad_norm": 0.009394422173500061, | |
| "learning_rate": 4.483385375401967e-06, | |
| "loss": 0.0142, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 6.815584869398096, | |
| "grad_norm": 55.671607971191406, | |
| "learning_rate": 4.250361187491262e-06, | |
| "loss": 0.0112, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 6.990303136192889, | |
| "grad_norm": 37.646053314208984, | |
| "learning_rate": 4.018269096332199e-06, | |
| "loss": 0.0143, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 6.999737922599808, | |
| "eval_accuracy": 0.9821366177498253, | |
| "eval_f1": 0.9821391542473246, | |
| "eval_loss": 0.12774688005447388, | |
| "eval_precision": 0.9821421791956497, | |
| "eval_recall": 0.9821366177498253, | |
| "eval_runtime": 68.6239, | |
| "eval_samples_per_second": 333.645, | |
| "eval_steps_per_second": 20.853, | |
| "step": 20027 | |
| }, | |
| { | |
| "epoch": 7.165283480387875, | |
| "grad_norm": 4.926445007324219, | |
| "learning_rate": 3.7852449084214942e-06, | |
| "loss": 0.0079, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 7.340001747182668, | |
| "grad_norm": 8.786434173583984, | |
| "learning_rate": 3.5522207205107895e-06, | |
| "loss": 0.0089, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 7.5147200139774615, | |
| "grad_norm": 0.1356939673423767, | |
| "learning_rate": 3.319196532600084e-06, | |
| "loss": 0.0074, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 7.689438280772254, | |
| "grad_norm": 16.782020568847656, | |
| "learning_rate": 3.0861723446893788e-06, | |
| "loss": 0.0096, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 7.864156547567048, | |
| "grad_norm": 0.0004071469884365797, | |
| "learning_rate": 2.853148156778674e-06, | |
| "loss": 0.007, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 7.999737922599808, | |
| "eval_accuracy": 0.9819619147449337, | |
| "eval_f1": 0.9819917414068494, | |
| "eval_loss": 0.14060455560684204, | |
| "eval_precision": 0.9820904217450387, | |
| "eval_recall": 0.9819619147449337, | |
| "eval_runtime": 68.6348, | |
| "eval_samples_per_second": 333.592, | |
| "eval_steps_per_second": 20.849, | |
| "step": 22888 | |
| }, | |
| { | |
| "epoch": 8.039136891762034, | |
| "grad_norm": 0.003943814896047115, | |
| "learning_rate": 2.6201239688679685e-06, | |
| "loss": 0.008, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 8.213855158556827, | |
| "grad_norm": 12.356912612915039, | |
| "learning_rate": 2.3870997809572637e-06, | |
| "loss": 0.0051, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 8.38857342535162, | |
| "grad_norm": 0.018336663022637367, | |
| "learning_rate": 2.1540755930465586e-06, | |
| "loss": 0.0053, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 8.563291692146414, | |
| "grad_norm": 0.031037895008921623, | |
| "learning_rate": 1.9210514051358534e-06, | |
| "loss": 0.0048, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 8.738009958941207, | |
| "grad_norm": 0.0018096828134730458, | |
| "learning_rate": 1.6884932656009695e-06, | |
| "loss": 0.0041, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 8.912728225736, | |
| "grad_norm": 0.006106176879256964, | |
| "learning_rate": 1.455935126066086e-06, | |
| "loss": 0.0043, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 8.999737922599808, | |
| "eval_accuracy": 0.9835779175401816, | |
| "eval_f1": 0.9835697887213877, | |
| "eval_loss": 0.15101368725299835, | |
| "eval_precision": 0.9835675135482098, | |
| "eval_recall": 0.9835779175401816, | |
| "eval_runtime": 68.619, | |
| "eval_samples_per_second": 333.668, | |
| "eval_steps_per_second": 20.854, | |
| "step": 25749 | |
| }, | |
| { | |
| "epoch": 9.087708569930987, | |
| "grad_norm": 0.00021469616331160069, | |
| "learning_rate": 1.2229109381553806e-06, | |
| "loss": 0.0036, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 9.26242683672578, | |
| "grad_norm": 0.008365228772163391, | |
| "learning_rate": 9.898867502446755e-07, | |
| "loss": 0.0027, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 9.437145103520573, | |
| "grad_norm": 0.0006792581407353282, | |
| "learning_rate": 7.568625623339704e-07, | |
| "loss": 0.0028, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 9.611863370315366, | |
| "grad_norm": 0.004307614639401436, | |
| "learning_rate": 5.238383744232652e-07, | |
| "loss": 0.0021, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 9.78658163711016, | |
| "grad_norm": 0.0005787264672107995, | |
| "learning_rate": 2.9081418651256006e-07, | |
| "loss": 0.0031, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 9.961299903904953, | |
| "grad_norm": 0.008150073699653149, | |
| "learning_rate": 5.7789998601854876e-08, | |
| "loss": 0.0019, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 9.999737922599808, | |
| "eval_accuracy": 0.9842330538085255, | |
| "eval_f1": 0.9842291652151357, | |
| "eval_loss": 0.14871150255203247, | |
| "eval_precision": 0.9842267397484589, | |
| "eval_recall": 0.9842330538085255, | |
| "eval_runtime": 68.5176, | |
| "eval_samples_per_second": 334.162, | |
| "eval_steps_per_second": 20.885, | |
| "step": 28610 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 28610, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.001 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7066719997407396e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |