| { | |
| "best_metric": 0.5159067511558533, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1142061281337048, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022284122562674095, | |
| "grad_norm": 30.866960525512695, | |
| "learning_rate": 5e-05, | |
| "loss": 9.0769, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022284122562674095, | |
| "eval_loss": 8.731489181518555, | |
| "eval_runtime": 4.6802, | |
| "eval_samples_per_second": 64.741, | |
| "eval_steps_per_second": 8.119, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04456824512534819, | |
| "grad_norm": 35.00822067260742, | |
| "learning_rate": 0.0001, | |
| "loss": 8.9305, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06685236768802229, | |
| "grad_norm": 29.040769577026367, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.1472, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08913649025069638, | |
| "grad_norm": 17.517667770385742, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.5425, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11142061281337047, | |
| "grad_norm": 9.844194412231445, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.0754, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13370473537604458, | |
| "grad_norm": 6.558274269104004, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.3057, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15598885793871867, | |
| "grad_norm": 4.910419940948486, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.8803, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.17827298050139276, | |
| "grad_norm": 3.809398651123047, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6958, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.20055710306406685, | |
| "grad_norm": 5.165838241577148, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6014, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.22284122562674094, | |
| "grad_norm": 9.54565715789795, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.6692, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24512534818941503, | |
| "grad_norm": 7.332498550415039, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.585, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.26740947075208915, | |
| "grad_norm": 11.09341812133789, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6227, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.28969359331476324, | |
| "grad_norm": 12.350174903869629, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6362, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.31197771587743733, | |
| "grad_norm": 3.0692760944366455, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5194, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3342618384401114, | |
| "grad_norm": 3.36543607711792, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.5659, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3565459610027855, | |
| "grad_norm": 5.607704162597656, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5629, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3788300835654596, | |
| "grad_norm": 6.10757303237915, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5898, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4011142061281337, | |
| "grad_norm": 4.869055271148682, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5669, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4233983286908078, | |
| "grad_norm": 2.869997262954712, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.5249, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4456824512534819, | |
| "grad_norm": 3.0591838359832764, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.558, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.467966573816156, | |
| "grad_norm": 2.3886196613311768, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5523, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.49025069637883006, | |
| "grad_norm": 2.7517380714416504, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5185, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5125348189415042, | |
| "grad_norm": 4.07460880279541, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5284, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5348189415041783, | |
| "grad_norm": 0.6786271929740906, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5028, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5571030640668524, | |
| "grad_norm": 2.6502835750579834, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.4916, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5571030640668524, | |
| "eval_loss": 0.5757180452346802, | |
| "eval_runtime": 4.406, | |
| "eval_samples_per_second": 68.769, | |
| "eval_steps_per_second": 8.625, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5793871866295265, | |
| "grad_norm": 5.951724529266357, | |
| "learning_rate": 5e-05, | |
| "loss": 0.563, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6016713091922006, | |
| "grad_norm": 1.962470531463623, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5493, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6239554317548747, | |
| "grad_norm": 1.5062148571014404, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5041, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6462395543175488, | |
| "grad_norm": 3.15012264251709, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5864, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6685236768802229, | |
| "grad_norm": 0.9960513114929199, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5485, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6908077994428969, | |
| "grad_norm": 2.9807181358337402, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5871, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.713091922005571, | |
| "grad_norm": 0.8017144203186035, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5185, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7353760445682451, | |
| "grad_norm": 1.2120144367218018, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4994, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7576601671309192, | |
| "grad_norm": 2.6110732555389404, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5343, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7799442896935933, | |
| "grad_norm": 3.2504384517669678, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.5009, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8022284122562674, | |
| "grad_norm": 2.49662446975708, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4935, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8245125348189415, | |
| "grad_norm": 1.3326027393341064, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.541, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8467966573816156, | |
| "grad_norm": 2.0869436264038086, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5217, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8690807799442897, | |
| "grad_norm": 1.49491548538208, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.5261, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8913649025069638, | |
| "grad_norm": 3.31276273727417, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5595, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9136490250696379, | |
| "grad_norm": 2.444161891937256, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5109, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.935933147632312, | |
| "grad_norm": 3.385462522506714, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.5329, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.958217270194986, | |
| "grad_norm": 1.8717201948165894, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.5601, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9805013927576601, | |
| "grad_norm": 2.7141246795654297, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5087, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0027855153203342, | |
| "grad_norm": 2.526226758956909, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.5976, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0250696378830084, | |
| "grad_norm": 1.1575802564620972, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.5293, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0473537604456824, | |
| "grad_norm": 0.5721626281738281, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.5247, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0696378830083566, | |
| "grad_norm": 3.1409993171691895, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.4927, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0919220055710306, | |
| "grad_norm": 0.9633862972259521, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4579, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1142061281337048, | |
| "grad_norm": 2.3224472999572754, | |
| "learning_rate": 0.0, | |
| "loss": 0.4813, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1142061281337048, | |
| "eval_loss": 0.5159067511558533, | |
| "eval_runtime": 7.2968, | |
| "eval_samples_per_second": 41.525, | |
| "eval_steps_per_second": 5.208, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.6068485461311488e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |