| { | |
| "best_metric": 0.03536833077669144, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.6996699669966997, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.052805280528052806, | |
| "grad_norm": 240.3042449951172, | |
| "learning_rate": 5e-05, | |
| "loss": 61.3338, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.052805280528052806, | |
| "eval_loss": 3.5627546310424805, | |
| "eval_runtime": 4.3018, | |
| "eval_samples_per_second": 29.755, | |
| "eval_steps_per_second": 3.719, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.10561056105610561, | |
| "grad_norm": 312.2116394042969, | |
| "learning_rate": 0.0001, | |
| "loss": 55.4131, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.15841584158415842, | |
| "grad_norm": 184.56300354003906, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 35.5412, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.21122112211221122, | |
| "grad_norm": 111.88742065429688, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 19.9948, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.264026402640264, | |
| "grad_norm": 86.86764526367188, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 24.8855, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.31683168316831684, | |
| "grad_norm": 132.280029296875, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 18.4034, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3696369636963696, | |
| "grad_norm": 144.69395446777344, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 15.066, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.42244224422442245, | |
| "grad_norm": 64.07872772216797, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.6669, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4752475247524752, | |
| "grad_norm": 71.51905822753906, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 9.8098, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.528052805280528, | |
| "grad_norm": 96.21553802490234, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 19.7731, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.5808580858085809, | |
| "grad_norm": 66.71566772460938, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.8857, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6336633663366337, | |
| "grad_norm": 56.84700393676758, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.1991, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.6864686468646864, | |
| "grad_norm": 57.972469329833984, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 8.0601, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7392739273927392, | |
| "grad_norm": 61.932777404785156, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 9.777, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.7920792079207921, | |
| "grad_norm": 61.04229736328125, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 8.4654, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8448844884488449, | |
| "grad_norm": 55.51152801513672, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 5.9386, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.8976897689768977, | |
| "grad_norm": 43.309749603271484, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 3.4815, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.9504950495049505, | |
| "grad_norm": 49.29344177246094, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.9009, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.033003300330033, | |
| "grad_norm": 71.64353942871094, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 5.4645, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.0858085808580857, | |
| "grad_norm": 54.31509017944336, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.0766, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.1386138613861387, | |
| "grad_norm": 80.26276397705078, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.1301, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.1914191419141915, | |
| "grad_norm": 56.407894134521484, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.6217, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.2442244224422443, | |
| "grad_norm": 45.19135284423828, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.4165, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.297029702970297, | |
| "grad_norm": 74.26824951171875, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.6401, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.3498349834983498, | |
| "grad_norm": 48.40488052368164, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.9736, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.3498349834983498, | |
| "eval_loss": 0.08991359174251556, | |
| "eval_runtime": 4.5659, | |
| "eval_samples_per_second": 28.034, | |
| "eval_steps_per_second": 3.504, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4026402640264026, | |
| "grad_norm": 49.3033561706543, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6019, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.4554455445544554, | |
| "grad_norm": 40.293243408203125, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.6071, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.5082508250825084, | |
| "grad_norm": 52.87701416015625, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.4937, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.561056105610561, | |
| "grad_norm": 46.945491790771484, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.7908, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.613861386138614, | |
| "grad_norm": 58.49090576171875, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5764, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.6666666666666665, | |
| "grad_norm": 34.49781036376953, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.7194719471947195, | |
| "grad_norm": 45.59718704223633, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6603, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.7722772277227723, | |
| "grad_norm": 26.68146324157715, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.685, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.825082508250825, | |
| "grad_norm": 29.098257064819336, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.4208, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.8778877887788779, | |
| "grad_norm": 36.968624114990234, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.17, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.9306930693069306, | |
| "grad_norm": 20.257652282714844, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.1213, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.0132013201320134, | |
| "grad_norm": 20.416902542114258, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.3783, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.066006600660066, | |
| "grad_norm": 14.051177978515625, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1184, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.118811881188119, | |
| "grad_norm": 9.072379112243652, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.07, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.1716171617161715, | |
| "grad_norm": 14.456093788146973, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0421, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.2244224422442245, | |
| "grad_norm": 8.208637237548828, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0268, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.2772277227722775, | |
| "grad_norm": 33.25442886352539, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.2891, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.33003300330033, | |
| "grad_norm": 8.580497741699219, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.0713, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.382838283828383, | |
| "grad_norm": 5.246236801147461, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0203, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.4356435643564356, | |
| "grad_norm": 3.4388229846954346, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.0178, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.4884488448844886, | |
| "grad_norm": 18.330442428588867, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4954, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.541254125412541, | |
| "grad_norm": 10.584196090698242, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.1212, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.594059405940594, | |
| "grad_norm": 19.070772171020508, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0592, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.6468646864686467, | |
| "grad_norm": 24.324411392211914, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0942, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.6996699669966997, | |
| "grad_norm": 9.229938507080078, | |
| "learning_rate": 0.0, | |
| "loss": 0.2343, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.6996699669966997, | |
| "eval_loss": 0.03536833077669144, | |
| "eval_runtime": 4.8433, | |
| "eval_samples_per_second": 26.428, | |
| "eval_steps_per_second": 3.304, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.932088473514148e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |