| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9999310202110782, | |
| "eval_steps": 500, | |
| "global_step": 453, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022073532454990687, | |
| "grad_norm": 1.5836448669433594, | |
| "learning_rate": 1.0869565217391305e-05, | |
| "loss": 1.0047, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.044147064909981375, | |
| "grad_norm": 0.4156560003757477, | |
| "learning_rate": 2.173913043478261e-05, | |
| "loss": 0.9551, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06622059736497206, | |
| "grad_norm": 0.33475786447525024, | |
| "learning_rate": 3.260869565217392e-05, | |
| "loss": 0.9291, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08829412981996275, | |
| "grad_norm": 0.721441924571991, | |
| "learning_rate": 4.347826086956522e-05, | |
| "loss": 0.914, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11036766227495344, | |
| "grad_norm": 0.2514866292476654, | |
| "learning_rate": 4.9988084660498037e-05, | |
| "loss": 0.9187, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13244119472994412, | |
| "grad_norm": 0.21546441316604614, | |
| "learning_rate": 4.985416749673074e-05, | |
| "loss": 0.9183, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1545147271849348, | |
| "grad_norm": 0.2580913007259369, | |
| "learning_rate": 4.957223915853709e-05, | |
| "loss": 0.9048, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1765882596399255, | |
| "grad_norm": 0.24421757459640503, | |
| "learning_rate": 4.9143978581429445e-05, | |
| "loss": 0.8957, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1986617920949162, | |
| "grad_norm": 0.23899255692958832, | |
| "learning_rate": 4.857193613652711e-05, | |
| "loss": 0.8952, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22073532454990688, | |
| "grad_norm": 0.25667503476142883, | |
| "learning_rate": 4.78595184426236e-05, | |
| "loss": 0.8866, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24280885700489757, | |
| "grad_norm": 0.3306167423725128, | |
| "learning_rate": 4.7010968079140294e-05, | |
| "loss": 0.8895, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.26488238945988823, | |
| "grad_norm": 0.2200348675251007, | |
| "learning_rate": 4.6031338320779534e-05, | |
| "loss": 0.8815, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.28695592191487895, | |
| "grad_norm": 0.28366169333457947, | |
| "learning_rate": 4.492646304433711e-05, | |
| "loss": 0.8808, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3090294543698696, | |
| "grad_norm": 0.22618895769119263, | |
| "learning_rate": 4.3702921986884574e-05, | |
| "loss": 0.8716, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.33110298682486033, | |
| "grad_norm": 0.27280193567276, | |
| "learning_rate": 4.236800156221536e-05, | |
| "loss": 0.8823, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.353176519279851, | |
| "grad_norm": 0.19905485212802887, | |
| "learning_rate": 4.092965146890002e-05, | |
| "loss": 0.8725, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.3752500517348417, | |
| "grad_norm": 0.3659760355949402, | |
| "learning_rate": 3.9396437348357684e-05, | |
| "loss": 0.8684, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.3973235841898324, | |
| "grad_norm": 0.2508715093135834, | |
| "learning_rate": 3.777748977487366e-05, | |
| "loss": 0.89, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.41939711664482304, | |
| "grad_norm": 0.24242979288101196, | |
| "learning_rate": 3.608244988133713e-05, | |
| "loss": 0.8706, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.44147064909981376, | |
| "grad_norm": 0.191656693816185, | |
| "learning_rate": 3.432141194450772e-05, | |
| "loss": 0.872, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.4635441815548044, | |
| "grad_norm": 0.2087477147579193, | |
| "learning_rate": 3.2504863271726286e-05, | |
| "loss": 0.8682, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.48561771400979514, | |
| "grad_norm": 0.2208724468946457, | |
| "learning_rate": 3.064362174705578e-05, | |
| "loss": 0.8794, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5076912464647858, | |
| "grad_norm": 0.19049623608589172, | |
| "learning_rate": 2.8748771408776466e-05, | |
| "loss": 0.8716, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5297647789197765, | |
| "grad_norm": 0.18646596372127533, | |
| "learning_rate": 2.683159644188339e-05, | |
| "loss": 0.8807, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5518383113747672, | |
| "grad_norm": 0.17940568923950195, | |
| "learning_rate": 2.4903513978673077e-05, | |
| "loss": 0.8701, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5739118438297579, | |
| "grad_norm": 0.17862474918365479, | |
| "learning_rate": 2.2976006107604482e-05, | |
| "loss": 0.8632, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5959853762847486, | |
| "grad_norm": 0.16970194876194, | |
| "learning_rate": 2.1060551495333818e-05, | |
| "loss": 0.8761, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6180589087397392, | |
| "grad_norm": 0.1763421595096588, | |
| "learning_rate": 1.9168557029126963e-05, | |
| "loss": 0.8611, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6401324411947299, | |
| "grad_norm": 0.16400456428527832, | |
| "learning_rate": 1.7311289886731408e-05, | |
| "loss": 0.8616, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6622059736497207, | |
| "grad_norm": 0.17227979004383087, | |
| "learning_rate": 1.549981043824425e-05, | |
| "loss": 0.8603, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6842795061047113, | |
| "grad_norm": 0.15701688826084137, | |
| "learning_rate": 1.3744906379558165e-05, | |
| "loss": 0.8608, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.706353038559702, | |
| "grad_norm": 0.15198074281215668, | |
| "learning_rate": 1.2057028489632682e-05, | |
| "loss": 0.8703, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7284265710146927, | |
| "grad_norm": 0.14645570516586304, | |
| "learning_rate": 1.0446228394168356e-05, | |
| "loss": 0.8518, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.7505001034696834, | |
| "grad_norm": 0.14851906895637512, | |
| "learning_rate": 8.922098706312548e-06, | |
| "loss": 0.8609, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7725736359246741, | |
| "grad_norm": 0.14792883396148682, | |
| "learning_rate": 7.493715900870027e-06, | |
| "loss": 0.8504, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.7946471683796648, | |
| "grad_norm": 0.14906203746795654, | |
| "learning_rate": 6.169586262213081e-06, | |
| "loss": 0.8614, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8167207008346554, | |
| "grad_norm": 0.13984321057796478, | |
| "learning_rate": 4.957595227781395e-06, | |
| "loss": 0.8574, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8387942332896461, | |
| "grad_norm": 0.13922333717346191, | |
| "learning_rate": 3.864960428840375e-06, | |
| "loss": 0.8501, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8608677657446369, | |
| "grad_norm": 0.14093540608882904, | |
| "learning_rate": 2.8981887081491576e-06, | |
| "loss": 0.85, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.8829412981996275, | |
| "grad_norm": 0.13516093790531158, | |
| "learning_rate": 2.0630373705058407e-06, | |
| "loss": 0.8599, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.9050148306546182, | |
| "grad_norm": 0.1319512128829956, | |
| "learning_rate": 1.3644798969302403e-06, | |
| "loss": 0.8627, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9270883631096088, | |
| "grad_norm": 0.13131946325302124, | |
| "learning_rate": 8.066763266625282e-07, | |
| "loss": 0.8567, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9491618955645996, | |
| "grad_norm": 0.13254371285438538, | |
| "learning_rate": 3.929484833584546e-07, | |
| "loss": 0.8484, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9712354280195903, | |
| "grad_norm": 0.1311715841293335, | |
| "learning_rate": 1.2576019301373532e-07, | |
| "loss": 0.8591, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.993308960474581, | |
| "grad_norm": 0.13352562487125397, | |
| "learning_rate": 6.702611423550775e-09, | |
| "loss": 0.8493, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.9999310202110782, | |
| "step": 453, | |
| "total_flos": 1.7598525261526073e+19, | |
| "train_loss": 0.8787032284220849, | |
| "train_runtime": 87969.9071, | |
| "train_samples_per_second": 2.637, | |
| "train_steps_per_second": 0.005 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 453, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.7598525261526073e+19, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |