| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3909539275833033, | |
| "eval_steps": 500, | |
| "global_step": 19500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01002445968162316, | |
| "grad_norm": 0.21047678589820862, | |
| "learning_rate": 2.969926620955131e-05, | |
| "loss": 0.0466, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02004891936324632, | |
| "grad_norm": 0.3244280219078064, | |
| "learning_rate": 2.939853241910261e-05, | |
| "loss": 0.0426, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03007337904486948, | |
| "grad_norm": 0.3163236379623413, | |
| "learning_rate": 2.9097798628653917e-05, | |
| "loss": 0.0382, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04009783872649264, | |
| "grad_norm": 0.21580693125724792, | |
| "learning_rate": 2.879706483820522e-05, | |
| "loss": 0.036, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.0501222984081158, | |
| "grad_norm": 0.25340843200683594, | |
| "learning_rate": 2.849633104775653e-05, | |
| "loss": 0.0337, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.06014675808973896, | |
| "grad_norm": 0.23738078773021698, | |
| "learning_rate": 2.819559725730783e-05, | |
| "loss": 0.0314, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.07017121777136212, | |
| "grad_norm": 0.15767431259155273, | |
| "learning_rate": 2.7894863466859138e-05, | |
| "loss": 0.0304, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.08019567745298528, | |
| "grad_norm": 0.14462140202522278, | |
| "learning_rate": 2.7594129676410442e-05, | |
| "loss": 0.03, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.09022013713460844, | |
| "grad_norm": 0.1084773987531662, | |
| "learning_rate": 2.729339588596175e-05, | |
| "loss": 0.0292, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.1002445968162316, | |
| "grad_norm": 0.1659129112958908, | |
| "learning_rate": 2.699266209551305e-05, | |
| "loss": 0.0286, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.11026905649785476, | |
| "grad_norm": 0.13866464793682098, | |
| "learning_rate": 2.6691928305064358e-05, | |
| "loss": 0.0284, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.12029351617947792, | |
| "grad_norm": 0.18351516127586365, | |
| "learning_rate": 2.6391194514615663e-05, | |
| "loss": 0.028, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.13031797586110108, | |
| "grad_norm": 0.12797561287879944, | |
| "learning_rate": 2.609046072416697e-05, | |
| "loss": 0.0277, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.14034243554272424, | |
| "grad_norm": 0.1829468458890915, | |
| "learning_rate": 2.578972693371827e-05, | |
| "loss": 0.0275, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.1503668952243474, | |
| "grad_norm": 0.10733053088188171, | |
| "learning_rate": 2.548899314326958e-05, | |
| "loss": 0.027, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.16039135490597056, | |
| "grad_norm": 0.12314225733280182, | |
| "learning_rate": 2.5188259352820883e-05, | |
| "loss": 0.0267, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.17041581458759372, | |
| "grad_norm": 0.1012982577085495, | |
| "learning_rate": 2.488752556237219e-05, | |
| "loss": 0.0265, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.18044027426921688, | |
| "grad_norm": 0.1413574069738388, | |
| "learning_rate": 2.4586791771923492e-05, | |
| "loss": 0.0263, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.19046473395084004, | |
| "grad_norm": 0.15352074801921844, | |
| "learning_rate": 2.42860579814748e-05, | |
| "loss": 0.0264, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.2004891936324632, | |
| "grad_norm": 0.11118650436401367, | |
| "learning_rate": 2.3985324191026104e-05, | |
| "loss": 0.0263, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.21051365331408636, | |
| "grad_norm": 0.1239309310913086, | |
| "learning_rate": 2.368459040057741e-05, | |
| "loss": 0.026, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.22053811299570952, | |
| "grad_norm": 0.09220115840435028, | |
| "learning_rate": 2.3383856610128712e-05, | |
| "loss": 0.0255, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.23056257267733268, | |
| "grad_norm": 0.12439100444316864, | |
| "learning_rate": 2.308312281968002e-05, | |
| "loss": 0.0258, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.24058703235895584, | |
| "grad_norm": 0.12189625203609467, | |
| "learning_rate": 2.2782389029231324e-05, | |
| "loss": 0.0256, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.25061149204057903, | |
| "grad_norm": 0.14276236295700073, | |
| "learning_rate": 2.2481655238782632e-05, | |
| "loss": 0.0255, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.26063595172220216, | |
| "grad_norm": 0.11102870106697083, | |
| "learning_rate": 2.2180921448333933e-05, | |
| "loss": 0.0255, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.27066041140382535, | |
| "grad_norm": 0.12738683819770813, | |
| "learning_rate": 2.188018765788524e-05, | |
| "loss": 0.0251, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.2806848710854485, | |
| "grad_norm": 0.14391563832759857, | |
| "learning_rate": 2.1579453867436545e-05, | |
| "loss": 0.025, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.29070933076707167, | |
| "grad_norm": 0.12654729187488556, | |
| "learning_rate": 2.1278720076987853e-05, | |
| "loss": 0.025, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.3007337904486948, | |
| "grad_norm": 0.1650782972574234, | |
| "learning_rate": 2.0977986286539154e-05, | |
| "loss": 0.0247, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.310758250130318, | |
| "grad_norm": 0.1010371670126915, | |
| "learning_rate": 2.067725249609046e-05, | |
| "loss": 0.0248, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.3207827098119411, | |
| "grad_norm": 0.08663147687911987, | |
| "learning_rate": 2.0376518705641766e-05, | |
| "loss": 0.0245, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.3308071694935643, | |
| "grad_norm": 0.11956797540187836, | |
| "learning_rate": 2.0075784915193073e-05, | |
| "loss": 0.0245, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.34083162917518744, | |
| "grad_norm": 0.07630161195993423, | |
| "learning_rate": 1.9775051124744374e-05, | |
| "loss": 0.0243, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.35085608885681063, | |
| "grad_norm": 0.10799304395914078, | |
| "learning_rate": 1.9474317334295682e-05, | |
| "loss": 0.0245, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.36088054853843377, | |
| "grad_norm": 0.12928515672683716, | |
| "learning_rate": 1.9173583543846986e-05, | |
| "loss": 0.024, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.37090500822005695, | |
| "grad_norm": 0.13743112981319427, | |
| "learning_rate": 1.8872849753398294e-05, | |
| "loss": 0.0241, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.3809294679016801, | |
| "grad_norm": 0.1442175954580307, | |
| "learning_rate": 1.8572115962949595e-05, | |
| "loss": 0.0241, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.3909539275833033, | |
| "grad_norm": 0.09911152720451355, | |
| "learning_rate": 1.8271382172500902e-05, | |
| "loss": 0.0238, | |
| "step": 19500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 49878, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |