| { | |
| "best_global_step": 500, | |
| "best_metric": 0.04982214793562889, | |
| "best_model_checkpoint": "C:\\Users\\rumpa\\OneDrive\\Desktop\\VedaX_AI_finetune\\VedaX_AI\\checkpoint-500", | |
| "epoch": 0.05387205387205387, | |
| "eval_steps": 500, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0026936026936026937, | |
| "grad_norm": 1.841068983078003, | |
| "learning_rate": 1.997414350355527e-05, | |
| "loss": 2.8212152099609376, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0053872053872053875, | |
| "grad_norm": 0.7459769248962402, | |
| "learning_rate": 1.9947209653092007e-05, | |
| "loss": 0.36805130004882813, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00808080808080808, | |
| "grad_norm": 0.3883790969848633, | |
| "learning_rate": 1.9920275802628747e-05, | |
| "loss": 0.08150457382202149, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.010774410774410775, | |
| "grad_norm": 0.24909840524196625, | |
| "learning_rate": 1.9893341952165484e-05, | |
| "loss": 0.06001442432403564, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.013468013468013467, | |
| "grad_norm": 0.23919348418712616, | |
| "learning_rate": 1.986640810170222e-05, | |
| "loss": 0.05564042568206787, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.01616161616161616, | |
| "grad_norm": 0.21730053424835205, | |
| "learning_rate": 1.983947425123896e-05, | |
| "loss": 0.053155436515808105, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.018855218855218854, | |
| "grad_norm": 0.345330148935318, | |
| "learning_rate": 1.98125404007757e-05, | |
| "loss": 0.05441353797912598, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.02154882154882155, | |
| "grad_norm": 0.2703924775123596, | |
| "learning_rate": 1.9785606550312436e-05, | |
| "loss": 0.05095250129699707, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.024242424242424242, | |
| "grad_norm": 0.2786615788936615, | |
| "learning_rate": 1.9758672699849173e-05, | |
| "loss": 0.050014009475708006, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.026936026936026935, | |
| "grad_norm": 0.22033053636550903, | |
| "learning_rate": 1.973173884938591e-05, | |
| "loss": 0.05086544513702393, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.02962962962962963, | |
| "grad_norm": 0.28292080760002136, | |
| "learning_rate": 1.9704804998922647e-05, | |
| "loss": 0.05024292469024658, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.03232323232323232, | |
| "grad_norm": 0.15764561295509338, | |
| "learning_rate": 1.9677871148459384e-05, | |
| "loss": 0.04976308822631836, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.035016835016835016, | |
| "grad_norm": 0.26158377528190613, | |
| "learning_rate": 1.965093729799612e-05, | |
| "loss": 0.050297212600708005, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.03771043771043771, | |
| "grad_norm": 0.32958391308784485, | |
| "learning_rate": 1.962400344753286e-05, | |
| "loss": 0.049454569816589355, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.04040404040404041, | |
| "grad_norm": 0.18668946623802185, | |
| "learning_rate": 1.95970695970696e-05, | |
| "loss": 0.05047787666320801, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.0430976430976431, | |
| "grad_norm": 0.2564663887023926, | |
| "learning_rate": 1.9570135746606336e-05, | |
| "loss": 0.0484027624130249, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.04579124579124579, | |
| "grad_norm": 0.1699737310409546, | |
| "learning_rate": 1.9543201896143073e-05, | |
| "loss": 0.048322863578796386, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.048484848484848485, | |
| "grad_norm": 0.19934280216693878, | |
| "learning_rate": 1.951626804567981e-05, | |
| "loss": 0.04795527935028076, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.05117845117845118, | |
| "grad_norm": 0.18609412014484406, | |
| "learning_rate": 1.948933419521655e-05, | |
| "loss": 0.049452505111694335, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.05387205387205387, | |
| "grad_norm": 0.15728649497032166, | |
| "learning_rate": 1.9462400344753287e-05, | |
| "loss": 0.048011641502380374, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.05387205387205387, | |
| "eval_loss": 0.04982214793562889, | |
| "eval_runtime": 144.2281, | |
| "eval_samples_per_second": 10.4, | |
| "eval_steps_per_second": 10.4, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 18564, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 392321487886848.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |