| { | |
| "best_metric": 0.08817896246910095, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.08226644043395548, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016453288086791095, | |
| "grad_norm": 2.793445110321045, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9811, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016453288086791095, | |
| "eval_loss": 0.5447852611541748, | |
| "eval_runtime": 8.2761, | |
| "eval_samples_per_second": 6.042, | |
| "eval_steps_per_second": 1.571, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003290657617358219, | |
| "grad_norm": 2.6458334922790527, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0801, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0049359864260373285, | |
| "grad_norm": 2.936859607696533, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.2201, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006581315234716438, | |
| "grad_norm": 3.042598247528076, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.2969, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008226644043395548, | |
| "grad_norm": 3.2381012439727783, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.4043, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009871972852074657, | |
| "grad_norm": 3.0219368934631348, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.3638, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011517301660753767, | |
| "grad_norm": 3.116426706314087, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 3.552, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013162630469432876, | |
| "grad_norm": 4.521168231964111, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.4548, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014807959278111986, | |
| "grad_norm": 8.887880325317383, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 7.7552, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016453288086791095, | |
| "grad_norm": 26.588666915893555, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 13.0843, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018098616895470203, | |
| "grad_norm": 46.92542266845703, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 21.6149, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.019743945704149314, | |
| "grad_norm": 52.9136962890625, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 25.4803, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.021389274512828422, | |
| "grad_norm": 32.47271728515625, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 16.6797, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023034603321507533, | |
| "grad_norm": 6.577832221984863, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.6593, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02467993213018664, | |
| "grad_norm": 4.443449020385742, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.4591, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026325260938865752, | |
| "grad_norm": 3.296760082244873, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.2535, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02797058974754486, | |
| "grad_norm": 2.96169114112854, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.1945, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02961591855622397, | |
| "grad_norm": 1.770756483078003, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2564, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03126124736490308, | |
| "grad_norm": 2.2403883934020996, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.3102, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03290657617358219, | |
| "grad_norm": 1.929724097251892, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.7945, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0345519049822613, | |
| "grad_norm": 2.2845964431762695, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.2824, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.036197233790940406, | |
| "grad_norm": 4.612369537353516, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.2931, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03784256259961952, | |
| "grad_norm": 11.82192611694336, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 8.9274, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03948789140829863, | |
| "grad_norm": 27.90416717529297, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 14.4093, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04113322021697774, | |
| "grad_norm": 35.26096725463867, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 16.8036, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04113322021697774, | |
| "eval_loss": 0.1036110669374466, | |
| "eval_runtime": 8.3599, | |
| "eval_samples_per_second": 5.981, | |
| "eval_steps_per_second": 1.555, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.042778549025656844, | |
| "grad_norm": 0.7192914485931396, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.5559, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.044423877834335955, | |
| "grad_norm": 0.7658919095993042, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.6265, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.046069206643015066, | |
| "grad_norm": 0.6952080726623535, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.6117, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04771453545169418, | |
| "grad_norm": 0.5986710786819458, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.6545, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04935986426037328, | |
| "grad_norm": 0.6377705335617065, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.8012, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05100519306905239, | |
| "grad_norm": 0.7861823439598083, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.9109, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.052650521877731504, | |
| "grad_norm": 0.9364539980888367, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.1027, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.054295850686410616, | |
| "grad_norm": 1.606742024421692, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.5875, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05594117949508972, | |
| "grad_norm": 2.1167681217193604, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.5575, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05758650830376883, | |
| "grad_norm": 8.326395988464355, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 5.9666, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05923183711244794, | |
| "grad_norm": 10.054471015930176, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 10.1117, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.060877165921127054, | |
| "grad_norm": 11.48097038269043, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.9451, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06252249472980616, | |
| "grad_norm": 14.909457206726074, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 8.4022, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06416782353848527, | |
| "grad_norm": 0.8173323273658752, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4723, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06581315234716438, | |
| "grad_norm": 0.884682834148407, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.5099, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06745848115584349, | |
| "grad_norm": 0.9192363619804382, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.5514, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0691038099645226, | |
| "grad_norm": 0.8022204041481018, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.7, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0707491387732017, | |
| "grad_norm": 0.6816873550415039, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.7884, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07239446758188081, | |
| "grad_norm": 1.0044586658477783, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.9553, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07403979639055992, | |
| "grad_norm": 1.6737107038497925, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.3098, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07568512519923903, | |
| "grad_norm": 1.7273823022842407, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.6871, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07733045400791815, | |
| "grad_norm": 2.9524919986724854, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.5467, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07897578281659726, | |
| "grad_norm": 6.543963432312012, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 8.2054, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08062111162527637, | |
| "grad_norm": 9.975615501403809, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.5187, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08226644043395548, | |
| "grad_norm": 18.941373825073242, | |
| "learning_rate": 1e-05, | |
| "loss": 13.8286, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08226644043395548, | |
| "eval_loss": 0.08817896246910095, | |
| "eval_runtime": 8.3777, | |
| "eval_samples_per_second": 5.968, | |
| "eval_steps_per_second": 1.552, | |
| "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": 6.570658412877578e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |