| { | |
| "best_metric": 0.8066132068634033, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.014646649578908825, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002929329915781765, | |
| "grad_norm": 0.39543473720550537, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6275, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002929329915781765, | |
| "eval_loss": 1.0773006677627563, | |
| "eval_runtime": 5.2078, | |
| "eval_samples_per_second": 9.601, | |
| "eval_steps_per_second": 2.496, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000585865983156353, | |
| "grad_norm": 0.44357961416244507, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7537, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008787989747345295, | |
| "grad_norm": 0.4342201352119446, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.7862, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.001171731966312706, | |
| "grad_norm": 0.3189747631549835, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.8274, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0014646649578908824, | |
| "grad_norm": 0.40255191922187805, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.8206, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.001757597949469059, | |
| "grad_norm": 0.3787446618080139, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.8321, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0020505309410472354, | |
| "grad_norm": 0.3350811004638672, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.8573, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002343463932625412, | |
| "grad_norm": 0.35608580708503723, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.0498, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0026363969242035883, | |
| "grad_norm": 0.4504380524158478, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.1057, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0029293299157817647, | |
| "grad_norm": 0.5150558948516846, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.0003, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0032222629073599416, | |
| "grad_norm": 0.5009474158287048, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.9379, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.003515195898938118, | |
| "grad_norm": 0.5560330748558044, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.9863, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0038081288905162944, | |
| "grad_norm": 0.612939178943634, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.579, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.004101061882094471, | |
| "grad_norm": 0.6755250692367554, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.6675, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004393994873672647, | |
| "grad_norm": 0.5051892399787903, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.7374, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004686927865250824, | |
| "grad_norm": 0.3121183216571808, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.681, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004979860856829, | |
| "grad_norm": 0.2881810963153839, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.7763, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0052727938484071766, | |
| "grad_norm": 0.2979393005371094, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.7754, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005565726839985353, | |
| "grad_norm": 0.31740421056747437, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.8575, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005858659831563529, | |
| "grad_norm": 0.3379293978214264, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.8978, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006151592823141707, | |
| "grad_norm": 0.38314786553382874, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.9831, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006444525814719883, | |
| "grad_norm": 0.4961355924606323, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.9615, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0067374588062980596, | |
| "grad_norm": 0.6407526135444641, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.9681, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.007030391797876236, | |
| "grad_norm": 0.6046722531318665, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.8766, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.007323324789454412, | |
| "grad_norm": 0.7880678772926331, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.7987, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007323324789454412, | |
| "eval_loss": 0.809256911277771, | |
| "eval_runtime": 4.05, | |
| "eval_samples_per_second": 12.346, | |
| "eval_steps_per_second": 3.21, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007616257781032589, | |
| "grad_norm": 0.18660973012447357, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.5492, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007909190772610765, | |
| "grad_norm": 0.21695637702941895, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.6171, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.008202123764188942, | |
| "grad_norm": 0.2558394968509674, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.6352, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008495056755767118, | |
| "grad_norm": 0.30923590064048767, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.7514, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008787989747345295, | |
| "grad_norm": 0.29804402589797974, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.7326, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009080922738923471, | |
| "grad_norm": 0.3356321454048157, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.7845, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.009373855730501647, | |
| "grad_norm": 0.3836168348789215, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.8783, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009666788722079824, | |
| "grad_norm": 0.4422508776187897, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.0204, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009959721713658, | |
| "grad_norm": 0.6576272249221802, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.0405, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.010252654705236177, | |
| "grad_norm": 0.8195415139198303, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.0154, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.010545587696814353, | |
| "grad_norm": 0.7149752974510193, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.9485, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.01083852068839253, | |
| "grad_norm": 0.5546535849571228, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.8952, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.011131453679970706, | |
| "grad_norm": 0.22018006443977356, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.5962, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.011424386671548882, | |
| "grad_norm": 0.17659281194210052, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.5691, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011717319663127059, | |
| "grad_norm": 0.20161019265651703, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.6794, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.012010252654705237, | |
| "grad_norm": 0.2220175713300705, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.7288, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.012303185646283413, | |
| "grad_norm": 0.22722084820270538, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.7078, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01259611863786159, | |
| "grad_norm": 0.2322564572095871, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.7349, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.012889051629439766, | |
| "grad_norm": 0.2695636451244354, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.789, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.013181984621017943, | |
| "grad_norm": 0.2991158664226532, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.9157, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.013474917612596119, | |
| "grad_norm": 0.28474679589271545, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.016, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.013767850604174296, | |
| "grad_norm": 0.33788153529167175, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.9079, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.014060783595752472, | |
| "grad_norm": 0.38621529936790466, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.9021, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.014353716587330648, | |
| "grad_norm": 0.4887455105781555, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.8839, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.014646649578908825, | |
| "grad_norm": 0.754707932472229, | |
| "learning_rate": 1e-05, | |
| "loss": 0.9356, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.014646649578908825, | |
| "eval_loss": 0.8066132068634033, | |
| "eval_runtime": 4.0311, | |
| "eval_samples_per_second": 12.404, | |
| "eval_steps_per_second": 3.225, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 6.027764453490033e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |