| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 7.092526690391459, | |
| "eval_steps": 25, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17793594306049823, | |
| "grad_norm": 3.1571543216705322, | |
| "learning_rate": 0.0001951951951951952, | |
| "loss": 2.3406, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.35587188612099646, | |
| "grad_norm": 1.42654550075531, | |
| "learning_rate": 0.0001901901901901902, | |
| "loss": 1.3793, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5338078291814946, | |
| "grad_norm": 1.1719086170196533, | |
| "learning_rate": 0.0001851851851851852, | |
| "loss": 1.2397, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7117437722419929, | |
| "grad_norm": 1.6048916578292847, | |
| "learning_rate": 0.00018018018018018018, | |
| "loss": 1.2513, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8896797153024911, | |
| "grad_norm": 0.9349364638328552, | |
| "learning_rate": 0.0001751751751751752, | |
| "loss": 1.1693, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.0640569395017794, | |
| "grad_norm": 1.2133198976516724, | |
| "learning_rate": 0.0001701701701701702, | |
| "loss": 1.2021, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.2419928825622777, | |
| "grad_norm": 1.7000682353973389, | |
| "learning_rate": 0.00016516516516516518, | |
| "loss": 1.0343, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.4199288256227758, | |
| "grad_norm": 1.325333833694458, | |
| "learning_rate": 0.00016016016016016018, | |
| "loss": 1.105, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.5978647686832739, | |
| "grad_norm": 1.2120150327682495, | |
| "learning_rate": 0.00015515515515515516, | |
| "loss": 1.2193, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.7758007117437722, | |
| "grad_norm": 1.1473174095153809, | |
| "learning_rate": 0.00015015015015015014, | |
| "loss": 1.0786, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.9537366548042705, | |
| "grad_norm": 1.087303876876831, | |
| "learning_rate": 0.00014514514514514515, | |
| "loss": 1.0669, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 2.1281138790035588, | |
| "grad_norm": 1.2311229705810547, | |
| "learning_rate": 0.00014014014014014013, | |
| "loss": 1.1659, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.306049822064057, | |
| "grad_norm": 1.148964524269104, | |
| "learning_rate": 0.00013513513513513514, | |
| "loss": 1.1135, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 2.4839857651245554, | |
| "grad_norm": 1.0676476955413818, | |
| "learning_rate": 0.00013013013013013014, | |
| "loss": 0.9726, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 2.6619217081850532, | |
| "grad_norm": 1.005470633506775, | |
| "learning_rate": 0.00012512512512512512, | |
| "loss": 0.9146, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 2.8398576512455516, | |
| "grad_norm": 1.5128366947174072, | |
| "learning_rate": 0.00012012012012012013, | |
| "loss": 1.0593, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 3.01423487544484, | |
| "grad_norm": 0.8878112435340881, | |
| "learning_rate": 0.00011511511511511512, | |
| "loss": 1.0623, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 3.192170818505338, | |
| "grad_norm": 1.3680928945541382, | |
| "learning_rate": 0.00011011011011011012, | |
| "loss": 0.9638, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 3.3701067615658364, | |
| "grad_norm": 1.0474141836166382, | |
| "learning_rate": 0.00010510510510510511, | |
| "loss": 0.9672, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 3.5480427046263348, | |
| "grad_norm": 0.9096865057945251, | |
| "learning_rate": 0.00010010010010010012, | |
| "loss": 0.9519, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 3.7259786476868326, | |
| "grad_norm": 1.9101051092147827, | |
| "learning_rate": 9.50950950950951e-05, | |
| "loss": 0.9851, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 3.903914590747331, | |
| "grad_norm": 1.1126383543014526, | |
| "learning_rate": 9.009009009009009e-05, | |
| "loss": 0.9335, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 4.07829181494662, | |
| "grad_norm": 1.3586586713790894, | |
| "learning_rate": 8.50850850850851e-05, | |
| "loss": 0.9603, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 4.2562277580071175, | |
| "grad_norm": 1.1161298751831055, | |
| "learning_rate": 8.008008008008009e-05, | |
| "loss": 0.8657, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 4.434163701067615, | |
| "grad_norm": 1.347420573234558, | |
| "learning_rate": 7.507507507507507e-05, | |
| "loss": 0.982, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 4.612099644128114, | |
| "grad_norm": 1.450341820716858, | |
| "learning_rate": 7.007007007007007e-05, | |
| "loss": 0.8658, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 4.790035587188612, | |
| "grad_norm": 1.0948293209075928, | |
| "learning_rate": 6.506506506506507e-05, | |
| "loss": 0.9306, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 4.967971530249111, | |
| "grad_norm": 1.7064975500106812, | |
| "learning_rate": 6.0060060060060066e-05, | |
| "loss": 0.8281, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 5.142348754448399, | |
| "grad_norm": 1.314003586769104, | |
| "learning_rate": 5.505505505505506e-05, | |
| "loss": 0.7796, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 5.320284697508897, | |
| "grad_norm": 1.3033592700958252, | |
| "learning_rate": 5.005005005005006e-05, | |
| "loss": 0.8998, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 5.498220640569395, | |
| "grad_norm": 2.4211108684539795, | |
| "learning_rate": 4.5045045045045046e-05, | |
| "loss": 0.8154, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 5.6761565836298935, | |
| "grad_norm": 1.4809461832046509, | |
| "learning_rate": 4.0040040040040046e-05, | |
| "loss": 0.8276, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 5.854092526690391, | |
| "grad_norm": 1.4405505657196045, | |
| "learning_rate": 3.503503503503503e-05, | |
| "loss": 0.8643, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 6.02846975088968, | |
| "grad_norm": 1.4615403413772583, | |
| "learning_rate": 3.0030030030030033e-05, | |
| "loss": 0.8953, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 6.2064056939501775, | |
| "grad_norm": 1.3846161365509033, | |
| "learning_rate": 2.502502502502503e-05, | |
| "loss": 0.7582, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 6.384341637010676, | |
| "grad_norm": 1.0929971933364868, | |
| "learning_rate": 2.0020020020020023e-05, | |
| "loss": 0.8246, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 6.562277580071174, | |
| "grad_norm": 1.1935001611709595, | |
| "learning_rate": 1.5015015015015016e-05, | |
| "loss": 0.8572, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 6.740213523131673, | |
| "grad_norm": 1.4628770351409912, | |
| "learning_rate": 1.0010010010010011e-05, | |
| "loss": 0.8221, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 6.918149466192171, | |
| "grad_norm": 1.2371264696121216, | |
| "learning_rate": 5.005005005005006e-06, | |
| "loss": 0.7659, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 7.092526690391459, | |
| "grad_norm": 1.589613676071167, | |
| "learning_rate": 0.0, | |
| "loss": 0.7643, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 8, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.060019431812096e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |