| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 57, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017543859649122806, | |
| "grad_norm": 2.410881066137832, | |
| "learning_rate": 0.0, | |
| "loss": 0.8483, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03508771929824561, | |
| "grad_norm": 2.665228254124179, | |
| "learning_rate": 3.3333333333333333e-06, | |
| "loss": 0.8763, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 2.3728587057049992, | |
| "learning_rate": 6.666666666666667e-06, | |
| "loss": 1.019, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07017543859649122, | |
| "grad_norm": 1.9987528382054482, | |
| "learning_rate": 1e-05, | |
| "loss": 1.0451, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.08771929824561403, | |
| "grad_norm": 1.2387448314677751, | |
| "learning_rate": 1.3333333333333333e-05, | |
| "loss": 0.8298, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 1.4006709843865188, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.9668, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12280701754385964, | |
| "grad_norm": 2.1941304727738995, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9639, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14035087719298245, | |
| "grad_norm": 2.0965952504080145, | |
| "learning_rate": 2.3333333333333336e-05, | |
| "loss": 0.906, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 2.0779003780741325, | |
| "learning_rate": 2.6666666666666667e-05, | |
| "loss": 0.9331, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.17543859649122806, | |
| "grad_norm": 1.914852860029578, | |
| "learning_rate": 3e-05, | |
| "loss": 0.9615, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19298245614035087, | |
| "grad_norm": 1.5453059456697873, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.9976, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 1.2149278389301041, | |
| "learning_rate": 3.6666666666666666e-05, | |
| "loss": 0.8731, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.22807017543859648, | |
| "grad_norm": 9.574453131193065, | |
| "learning_rate": 4e-05, | |
| "loss": 0.9048, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.24561403508771928, | |
| "grad_norm": 1.7542365583306754, | |
| "learning_rate": 4.3333333333333334e-05, | |
| "loss": 0.9045, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 1.5687648722942888, | |
| "learning_rate": 4.666666666666667e-05, | |
| "loss": 0.9642, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 1.1629052446813282, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9157, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.2982456140350877, | |
| "grad_norm": 1.0662859779498828, | |
| "learning_rate": 4.999830770009406e-05, | |
| "loss": 1.0076, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 1.1540729762939772, | |
| "learning_rate": 4.9993231029486544e-05, | |
| "loss": 0.8898, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 2.284686909029557, | |
| "learning_rate": 4.99847706754774e-05, | |
| "loss": 0.9111, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3508771929824561, | |
| "grad_norm": 0.9299877447474001, | |
| "learning_rate": 4.997292778346312e-05, | |
| "loss": 0.9567, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 0.7891834706045853, | |
| "learning_rate": 4.995770395678171e-05, | |
| "loss": 0.8907, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.38596491228070173, | |
| "grad_norm": 0.7738739475483105, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 0.7582, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.40350877192982454, | |
| "grad_norm": 0.7564543923604894, | |
| "learning_rate": 4.9917122201112656e-05, | |
| "loss": 0.893, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.7725302637179225, | |
| "learning_rate": 4.989176976624511e-05, | |
| "loss": 0.794, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.43859649122807015, | |
| "grad_norm": 0.7154589746662706, | |
| "learning_rate": 4.9863047384206835e-05, | |
| "loss": 0.927, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.45614035087719296, | |
| "grad_norm": 0.748200539385192, | |
| "learning_rate": 4.983095894354858e-05, | |
| "loss": 0.8946, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 0.6877177188589038, | |
| "learning_rate": 4.979550878853154e-05, | |
| "loss": 0.8108, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.49122807017543857, | |
| "grad_norm": 0.6905557124467382, | |
| "learning_rate": 4.975670171853926e-05, | |
| "loss": 0.8808, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.5087719298245614, | |
| "grad_norm": 0.6261501879052016, | |
| "learning_rate": 4.971454298742779e-05, | |
| "loss": 0.902, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 0.6935833833701227, | |
| "learning_rate": 4.966903830281449e-05, | |
| "loss": 0.7902, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.543859649122807, | |
| "grad_norm": 0.7380295796572786, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 0.8427, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 0.6686373976763716, | |
| "learning_rate": 4.9568016167660334e-05, | |
| "loss": 0.7824, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5789473684210527, | |
| "grad_norm": 0.7284830674570405, | |
| "learning_rate": 4.951251239389948e-05, | |
| "loss": 0.8758, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5964912280701754, | |
| "grad_norm": 0.7667345279664498, | |
| "learning_rate": 4.9453690018345144e-05, | |
| "loss": 0.9769, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.6140350877192983, | |
| "grad_norm": 0.7186885267427574, | |
| "learning_rate": 4.939155700460536e-05, | |
| "loss": 0.8222, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 0.7129526253734785, | |
| "learning_rate": 4.9326121764495596e-05, | |
| "loss": 0.8398, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.6491228070175439, | |
| "grad_norm": 0.6763307332151739, | |
| "learning_rate": 4.925739315689991e-05, | |
| "loss": 0.881, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.7596612492978558, | |
| "learning_rate": 4.9185380486571595e-05, | |
| "loss": 0.8883, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6842105263157895, | |
| "grad_norm": 0.574360173449421, | |
| "learning_rate": 4.9110093502873476e-05, | |
| "loss": 0.9078, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.7017543859649122, | |
| "grad_norm": 0.5045882171460956, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 0.8722, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7192982456140351, | |
| "grad_norm": 0.6267476132219085, | |
| "learning_rate": 4.894973780788722e-05, | |
| "loss": 0.883, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 0.6021189923969766, | |
| "learning_rate": 4.88646908061933e-05, | |
| "loss": 0.8144, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.7543859649122807, | |
| "grad_norm": 0.6014066609170303, | |
| "learning_rate": 4.877641290737884e-05, | |
| "loss": 0.8496, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.7719298245614035, | |
| "grad_norm": 0.6014121657776419, | |
| "learning_rate": 4.868491606285823e-05, | |
| "loss": 0.768, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 0.5324268865416073, | |
| "learning_rate": 4.859021265983959e-05, | |
| "loss": 0.8825, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.8070175438596491, | |
| "grad_norm": 0.6348338184686191, | |
| "learning_rate": 4.849231551964771e-05, | |
| "loss": 0.8587, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.8245614035087719, | |
| "grad_norm": 0.6361465840640576, | |
| "learning_rate": 4.839123789598829e-05, | |
| "loss": 0.868, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.5806423652725062, | |
| "learning_rate": 4.828699347315356e-05, | |
| "loss": 0.8445, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.8596491228070176, | |
| "grad_norm": 0.6650303211642944, | |
| "learning_rate": 4.817959636416969e-05, | |
| "loss": 0.9439, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.8771929824561403, | |
| "grad_norm": 0.49618932027271617, | |
| "learning_rate": 4.806906110888606e-05, | |
| "loss": 0.676, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8947368421052632, | |
| "grad_norm": 0.7201128419875511, | |
| "learning_rate": 4.7955402672006854e-05, | |
| "loss": 0.9129, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.9122807017543859, | |
| "grad_norm": 0.7979009332190922, | |
| "learning_rate": 4.783863644106502e-05, | |
| "loss": 0.8844, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.9298245614035088, | |
| "grad_norm": 0.5780879587849941, | |
| "learning_rate": 4.771877822433911e-05, | |
| "loss": 0.835, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 0.5125413888902927, | |
| "learning_rate": 4.759584424871302e-05, | |
| "loss": 0.7854, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.9649122807017544, | |
| "grad_norm": 0.6493310136858548, | |
| "learning_rate": 4.7469851157479177e-05, | |
| "loss": 0.8246, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.9824561403508771, | |
| "grad_norm": 0.5420670379906682, | |
| "learning_rate": 4.734081600808531e-05, | |
| "loss": 0.8357, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.8014271486806656, | |
| "learning_rate": 4.7208756269825104e-05, | |
| "loss": 0.7012, | |
| "step": 57 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 285, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 5, | |
| "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": 13124895178752.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |