| { | |
| "best_metric": 0.08922764658927917, | |
| "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": 2.9340085983276367, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9811, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016453288086791095, | |
| "eval_loss": 0.5447852611541748, | |
| "eval_runtime": 8.3061, | |
| "eval_samples_per_second": 6.02, | |
| "eval_steps_per_second": 1.565, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003290657617358219, | |
| "grad_norm": 2.7483158111572266, | |
| "learning_rate": 0.0001, | |
| "loss": 3.0801, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0049359864260373285, | |
| "grad_norm": 3.0211894512176514, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.2171, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006581315234716438, | |
| "grad_norm": 3.101088523864746, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.2919, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008226644043395548, | |
| "grad_norm": 3.177380084991455, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.3945, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009871972852074657, | |
| "grad_norm": 3.1485860347747803, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.3476, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011517301660753767, | |
| "grad_norm": 3.2044968605041504, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 3.5363, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013162630469432876, | |
| "grad_norm": 4.661653518676758, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.4327, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014807959278111986, | |
| "grad_norm": 8.384300231933594, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 7.6822, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016453288086791095, | |
| "grad_norm": 15.747698783874512, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 12.8179, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018098616895470203, | |
| "grad_norm": 36.05744552612305, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 21.0175, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.019743945704149314, | |
| "grad_norm": 47.37175750732422, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 24.7845, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.021389274512828422, | |
| "grad_norm": 32.3269157409668, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 16.2157, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023034603321507533, | |
| "grad_norm": 6.595750331878662, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.6754, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02467993213018664, | |
| "grad_norm": 4.476025581359863, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.4852, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026325260938865752, | |
| "grad_norm": 3.3909082412719727, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.2812, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.02797058974754486, | |
| "grad_norm": 3.04364275932312, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.224, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02961591855622397, | |
| "grad_norm": 2.1135096549987793, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2866, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03126124736490308, | |
| "grad_norm": 1.528654932975769, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.3186, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03290657617358219, | |
| "grad_norm": 7.454995632171631, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.7653, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0345519049822613, | |
| "grad_norm": 2.611647844314575, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.2766, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.036197233790940406, | |
| "grad_norm": 5.667532444000244, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 4.3051, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03784256259961952, | |
| "grad_norm": 14.412378311157227, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 8.8846, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03948789140829863, | |
| "grad_norm": 33.06006622314453, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 14.0859, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04113322021697774, | |
| "grad_norm": 29.786027908325195, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 16.3331, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04113322021697774, | |
| "eval_loss": 0.10174055397510529, | |
| "eval_runtime": 8.2589, | |
| "eval_samples_per_second": 6.054, | |
| "eval_steps_per_second": 1.574, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.042778549025656844, | |
| "grad_norm": 0.891169011592865, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.5517, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.044423877834335955, | |
| "grad_norm": 0.7230943441390991, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.6284, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.046069206643015066, | |
| "grad_norm": 0.6296717524528503, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.6151, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.04771453545169418, | |
| "grad_norm": 0.5857284665107727, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.6614, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04935986426037328, | |
| "grad_norm": 0.654015064239502, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.809, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05100519306905239, | |
| "grad_norm": 0.729507565498352, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.9166, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.052650521877731504, | |
| "grad_norm": 0.8457760214805603, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.1044, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.054295850686410616, | |
| "grad_norm": 1.332365870475769, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.5837, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05594117949508972, | |
| "grad_norm": 2.186558961868286, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.5722, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.05758650830376883, | |
| "grad_norm": 8.118924140930176, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 6.0169, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05923183711244794, | |
| "grad_norm": 10.122238159179688, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 10.1049, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.060877165921127054, | |
| "grad_norm": 11.095065116882324, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 11.9234, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06252249472980616, | |
| "grad_norm": 15.164539337158203, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 8.3837, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06416782353848527, | |
| "grad_norm": 0.9335575103759766, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4713, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06581315234716438, | |
| "grad_norm": 0.951163649559021, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.5083, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06745848115584349, | |
| "grad_norm": 1.1648244857788086, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.5451, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0691038099645226, | |
| "grad_norm": 0.5956860780715942, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.6876, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0707491387732017, | |
| "grad_norm": 1.2150315046310425, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.8026, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.07239446758188081, | |
| "grad_norm": 1.453965663909912, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.9668, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07403979639055992, | |
| "grad_norm": 2.6636314392089844, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.3575, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07568512519923903, | |
| "grad_norm": 3.017009735107422, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.7308, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07733045400791815, | |
| "grad_norm": 4.661072254180908, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.6012, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07897578281659726, | |
| "grad_norm": 8.242691040039062, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 8.213, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08062111162527637, | |
| "grad_norm": 11.560867309570312, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 11.5814, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08226644043395548, | |
| "grad_norm": 18.662717819213867, | |
| "learning_rate": 1e-05, | |
| "loss": 13.808, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08226644043395548, | |
| "eval_loss": 0.08922764658927917, | |
| "eval_runtime": 8.2665, | |
| "eval_samples_per_second": 6.048, | |
| "eval_steps_per_second": 1.573, | |
| "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 | |
| } | |