|
{ |
|
"best_metric": 1.135033369064331, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-200", |
|
"epoch": 0.011536853034913402, |
|
"eval_steps": 50, |
|
"global_step": 200, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 5.768426517456701e-05, |
|
"eval_loss": 2.3238277435302734, |
|
"eval_runtime": 495.8901, |
|
"eval_samples_per_second": 58.878, |
|
"eval_steps_per_second": 14.721, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.00017305279552370101, |
|
"grad_norm": 0.45083099603652954, |
|
"learning_rate": 3e-05, |
|
"loss": 1.4648, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.00034610559104740203, |
|
"grad_norm": 0.5587688684463501, |
|
"learning_rate": 6e-05, |
|
"loss": 1.8717, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.0005191583865711031, |
|
"grad_norm": 0.5804035067558289, |
|
"learning_rate": 9e-05, |
|
"loss": 1.8528, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.0006922111820948041, |
|
"grad_norm": 0.5394102931022644, |
|
"learning_rate": 9.997266286704631e-05, |
|
"loss": 1.8216, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.0008652639776185052, |
|
"grad_norm": 0.5287687182426453, |
|
"learning_rate": 9.98292246503335e-05, |
|
"loss": 1.4867, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.0010383167731422061, |
|
"grad_norm": 0.5580219626426697, |
|
"learning_rate": 9.956320346634876e-05, |
|
"loss": 1.553, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.0012113695686659072, |
|
"grad_norm": 0.5071175694465637, |
|
"learning_rate": 9.917525374361912e-05, |
|
"loss": 1.4905, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.0013844223641896081, |
|
"grad_norm": 0.618292510509491, |
|
"learning_rate": 9.86663298624003e-05, |
|
"loss": 1.3951, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.0015574751597133092, |
|
"grad_norm": 0.46973147988319397, |
|
"learning_rate": 9.803768380684242e-05, |
|
"loss": 1.5449, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.0017305279552370103, |
|
"grad_norm": 0.49171945452690125, |
|
"learning_rate": 9.729086208503174e-05, |
|
"loss": 1.3479, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.0019035807507607112, |
|
"grad_norm": 0.48666226863861084, |
|
"learning_rate": 9.642770192448536e-05, |
|
"loss": 1.4163, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.0020766335462844123, |
|
"grad_norm": 0.5254663825035095, |
|
"learning_rate": 9.545032675245813e-05, |
|
"loss": 1.3606, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.0022496863418081134, |
|
"grad_norm": 0.4926294684410095, |
|
"learning_rate": 9.43611409721806e-05, |
|
"loss": 1.3109, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.0024227391373318145, |
|
"grad_norm": 0.5055580735206604, |
|
"learning_rate": 9.316282404787871e-05, |
|
"loss": 1.3493, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.002595791932855515, |
|
"grad_norm": 0.5364347100257874, |
|
"learning_rate": 9.185832391312644e-05, |
|
"loss": 1.4115, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.0027688447283792162, |
|
"grad_norm": 0.7558141350746155, |
|
"learning_rate": 9.045084971874738e-05, |
|
"loss": 1.4071, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.0028842132587283504, |
|
"eval_loss": 1.2356951236724854, |
|
"eval_runtime": 500.8722, |
|
"eval_samples_per_second": 58.292, |
|
"eval_steps_per_second": 14.575, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.0029418975239029173, |
|
"grad_norm": 0.4775656461715698, |
|
"learning_rate": 8.894386393810563e-05, |
|
"loss": 1.2319, |
|
"step": 51 |
|
}, |
|
{ |
|
"epoch": 0.0031149503194266184, |
|
"grad_norm": 0.5036152601242065, |
|
"learning_rate": 8.73410738492077e-05, |
|
"loss": 0.9718, |
|
"step": 54 |
|
}, |
|
{ |
|
"epoch": 0.0032880031149503195, |
|
"grad_norm": 0.39522024989128113, |
|
"learning_rate": 8.564642241456986e-05, |
|
"loss": 1.1598, |
|
"step": 57 |
|
}, |
|
{ |
|
"epoch": 0.0034610559104740206, |
|
"grad_norm": 0.35405585169792175, |
|
"learning_rate": 8.386407858128706e-05, |
|
"loss": 1.0674, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.0036341087059977213, |
|
"grad_norm": 0.4121133089065552, |
|
"learning_rate": 8.199842702516583e-05, |
|
"loss": 1.0174, |
|
"step": 63 |
|
}, |
|
{ |
|
"epoch": 0.0038071615015214224, |
|
"grad_norm": 0.32193905115127563, |
|
"learning_rate": 8.005405736415126e-05, |
|
"loss": 1.0159, |
|
"step": 66 |
|
}, |
|
{ |
|
"epoch": 0.003980214297045124, |
|
"grad_norm": 0.3453183174133301, |
|
"learning_rate": 7.803575286758364e-05, |
|
"loss": 1.0557, |
|
"step": 69 |
|
}, |
|
{ |
|
"epoch": 0.0041532670925688246, |
|
"grad_norm": 0.3785501718521118, |
|
"learning_rate": 7.594847868906076e-05, |
|
"loss": 1.2081, |
|
"step": 72 |
|
}, |
|
{ |
|
"epoch": 0.004326319888092525, |
|
"grad_norm": 0.3871416747570038, |
|
"learning_rate": 7.379736965185368e-05, |
|
"loss": 1.1649, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.004499372683616227, |
|
"grad_norm": 0.4219188988208771, |
|
"learning_rate": 7.158771761692464e-05, |
|
"loss": 1.1471, |
|
"step": 78 |
|
}, |
|
{ |
|
"epoch": 0.004672425479139927, |
|
"grad_norm": 0.40537410974502563, |
|
"learning_rate": 6.932495846462261e-05, |
|
"loss": 1.3124, |
|
"step": 81 |
|
}, |
|
{ |
|
"epoch": 0.004845478274663629, |
|
"grad_norm": 0.36390063166618347, |
|
"learning_rate": 6.701465872208216e-05, |
|
"loss": 1.2589, |
|
"step": 84 |
|
}, |
|
{ |
|
"epoch": 0.00501853107018733, |
|
"grad_norm": 0.4167007803916931, |
|
"learning_rate": 6.466250186922325e-05, |
|
"loss": 1.0981, |
|
"step": 87 |
|
}, |
|
{ |
|
"epoch": 0.00519158386571103, |
|
"grad_norm": 0.4835963845252991, |
|
"learning_rate": 6.227427435703997e-05, |
|
"loss": 1.3458, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.005364636661234732, |
|
"grad_norm": 0.46142578125, |
|
"learning_rate": 5.985585137257401e-05, |
|
"loss": 1.1397, |
|
"step": 93 |
|
}, |
|
{ |
|
"epoch": 0.0055376894567584324, |
|
"grad_norm": 0.5481660962104797, |
|
"learning_rate": 5.74131823855921e-05, |
|
"loss": 1.1947, |
|
"step": 96 |
|
}, |
|
{ |
|
"epoch": 0.005710742252282134, |
|
"grad_norm": 0.6424285173416138, |
|
"learning_rate": 5.495227651252315e-05, |
|
"loss": 1.4071, |
|
"step": 99 |
|
}, |
|
{ |
|
"epoch": 0.005768426517456701, |
|
"eval_loss": 1.1644848585128784, |
|
"eval_runtime": 495.3076, |
|
"eval_samples_per_second": 58.947, |
|
"eval_steps_per_second": 14.738, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.005883795047805835, |
|
"grad_norm": 0.46381473541259766, |
|
"learning_rate": 5.247918773366112e-05, |
|
"loss": 1.1083, |
|
"step": 102 |
|
}, |
|
{ |
|
"epoch": 0.006056847843329536, |
|
"grad_norm": 0.5000247955322266, |
|
"learning_rate": 5e-05, |
|
"loss": 1.0165, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.006229900638853237, |
|
"grad_norm": 0.38582298159599304, |
|
"learning_rate": 4.7520812266338885e-05, |
|
"loss": 1.059, |
|
"step": 108 |
|
}, |
|
{ |
|
"epoch": 0.0064029534343769375, |
|
"grad_norm": 0.40634816884994507, |
|
"learning_rate": 4.504772348747687e-05, |
|
"loss": 1.021, |
|
"step": 111 |
|
}, |
|
{ |
|
"epoch": 0.006576006229900639, |
|
"grad_norm": 0.32036200165748596, |
|
"learning_rate": 4.2586817614407895e-05, |
|
"loss": 0.9665, |
|
"step": 114 |
|
}, |
|
{ |
|
"epoch": 0.00674905902542434, |
|
"grad_norm": 0.3690759241580963, |
|
"learning_rate": 4.0144148627425993e-05, |
|
"loss": 1.1389, |
|
"step": 117 |
|
}, |
|
{ |
|
"epoch": 0.006922111820948041, |
|
"grad_norm": 0.3883983790874481, |
|
"learning_rate": 3.772572564296005e-05, |
|
"loss": 1.1566, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.007095164616471742, |
|
"grad_norm": 0.4271601438522339, |
|
"learning_rate": 3.533749813077677e-05, |
|
"loss": 1.1872, |
|
"step": 123 |
|
}, |
|
{ |
|
"epoch": 0.0072682174119954425, |
|
"grad_norm": 0.358237087726593, |
|
"learning_rate": 3.298534127791785e-05, |
|
"loss": 1.1692, |
|
"step": 126 |
|
}, |
|
{ |
|
"epoch": 0.007441270207519144, |
|
"grad_norm": 0.365348219871521, |
|
"learning_rate": 3.0675041535377405e-05, |
|
"loss": 1.1708, |
|
"step": 129 |
|
}, |
|
{ |
|
"epoch": 0.007614323003042845, |
|
"grad_norm": 0.41103696823120117, |
|
"learning_rate": 2.8412282383075363e-05, |
|
"loss": 1.2572, |
|
"step": 132 |
|
}, |
|
{ |
|
"epoch": 0.007787375798566546, |
|
"grad_norm": 0.41762009263038635, |
|
"learning_rate": 2.6202630348146324e-05, |
|
"loss": 1.1534, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.007960428594090248, |
|
"grad_norm": 0.39923688769340515, |
|
"learning_rate": 2.405152131093926e-05, |
|
"loss": 1.3375, |
|
"step": 138 |
|
}, |
|
{ |
|
"epoch": 0.008133481389613948, |
|
"grad_norm": 0.47532254457473755, |
|
"learning_rate": 2.196424713241637e-05, |
|
"loss": 1.3354, |
|
"step": 141 |
|
}, |
|
{ |
|
"epoch": 0.008306534185137649, |
|
"grad_norm": 0.3896162211894989, |
|
"learning_rate": 1.9945942635848748e-05, |
|
"loss": 1.3604, |
|
"step": 144 |
|
}, |
|
{ |
|
"epoch": 0.00847958698066135, |
|
"grad_norm": 0.4989997446537018, |
|
"learning_rate": 1.800157297483417e-05, |
|
"loss": 1.3699, |
|
"step": 147 |
|
}, |
|
{ |
|
"epoch": 0.00865263977618505, |
|
"grad_norm": 0.7773590087890625, |
|
"learning_rate": 1.6135921418712956e-05, |
|
"loss": 1.333, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.00865263977618505, |
|
"eval_loss": 1.139582872390747, |
|
"eval_runtime": 496.6517, |
|
"eval_samples_per_second": 58.788, |
|
"eval_steps_per_second": 14.698, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.008825692571708753, |
|
"grad_norm": 0.343904584646225, |
|
"learning_rate": 1.435357758543015e-05, |
|
"loss": 0.9637, |
|
"step": 153 |
|
}, |
|
{ |
|
"epoch": 0.008998745367232453, |
|
"grad_norm": 0.38003867864608765, |
|
"learning_rate": 1.2658926150792322e-05, |
|
"loss": 0.9447, |
|
"step": 156 |
|
}, |
|
{ |
|
"epoch": 0.009171798162756154, |
|
"grad_norm": 0.3449487090110779, |
|
"learning_rate": 1.1056136061894384e-05, |
|
"loss": 1.0876, |
|
"step": 159 |
|
}, |
|
{ |
|
"epoch": 0.009344850958279855, |
|
"grad_norm": 0.4446622431278229, |
|
"learning_rate": 9.549150281252633e-06, |
|
"loss": 1.1895, |
|
"step": 162 |
|
}, |
|
{ |
|
"epoch": 0.009517903753803555, |
|
"grad_norm": 0.4309278428554535, |
|
"learning_rate": 8.141676086873572e-06, |
|
"loss": 1.0161, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 0.009690956549327258, |
|
"grad_norm": 0.3661138713359833, |
|
"learning_rate": 6.837175952121306e-06, |
|
"loss": 1.1177, |
|
"step": 168 |
|
}, |
|
{ |
|
"epoch": 0.009864009344850959, |
|
"grad_norm": 0.3448355793952942, |
|
"learning_rate": 5.6388590278194096e-06, |
|
"loss": 1.0711, |
|
"step": 171 |
|
}, |
|
{ |
|
"epoch": 0.01003706214037466, |
|
"grad_norm": 0.35449743270874023, |
|
"learning_rate": 4.549673247541875e-06, |
|
"loss": 1.1541, |
|
"step": 174 |
|
}, |
|
{ |
|
"epoch": 0.01021011493589836, |
|
"grad_norm": 0.37603992223739624, |
|
"learning_rate": 3.5722980755146517e-06, |
|
"loss": 1.1487, |
|
"step": 177 |
|
}, |
|
{ |
|
"epoch": 0.01038316773142206, |
|
"grad_norm": 0.4178571105003357, |
|
"learning_rate": 2.7091379149682685e-06, |
|
"loss": 1.1862, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.010556220526945763, |
|
"grad_norm": 0.5295783281326294, |
|
"learning_rate": 1.962316193157593e-06, |
|
"loss": 1.2777, |
|
"step": 183 |
|
}, |
|
{ |
|
"epoch": 0.010729273322469464, |
|
"grad_norm": 0.5361846089363098, |
|
"learning_rate": 1.333670137599713e-06, |
|
"loss": 1.1756, |
|
"step": 186 |
|
}, |
|
{ |
|
"epoch": 0.010902326117993164, |
|
"grad_norm": 0.42806971073150635, |
|
"learning_rate": 8.247462563808817e-07, |
|
"loss": 1.2366, |
|
"step": 189 |
|
}, |
|
{ |
|
"epoch": 0.011075378913516865, |
|
"grad_norm": 0.45333951711654663, |
|
"learning_rate": 4.367965336512403e-07, |
|
"loss": 1.0958, |
|
"step": 192 |
|
}, |
|
{ |
|
"epoch": 0.011248431709040567, |
|
"grad_norm": 0.8909216523170471, |
|
"learning_rate": 1.7077534966650766e-07, |
|
"loss": 1.1446, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 0.011421484504564268, |
|
"grad_norm": 0.8104519248008728, |
|
"learning_rate": 2.7337132953697554e-08, |
|
"loss": 1.4137, |
|
"step": 198 |
|
}, |
|
{ |
|
"epoch": 0.011536853034913402, |
|
"eval_loss": 1.135033369064331, |
|
"eval_runtime": 500.4661, |
|
"eval_samples_per_second": 58.34, |
|
"eval_steps_per_second": 14.586, |
|
"step": 200 |
|
} |
|
], |
|
"logging_steps": 3, |
|
"max_steps": 200, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 50, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 5, |
|
"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": 1.3737759080448e+16, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|