| { | |
| "best_metric": 0.3318357467651367, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.8703374777975132, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.056838365896980464, | |
| "grad_norm": 9.934815406799316, | |
| "learning_rate": 5e-05, | |
| "loss": 2.4198, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.056838365896980464, | |
| "eval_loss": 2.6544065475463867, | |
| "eval_runtime": 1.4201, | |
| "eval_samples_per_second": 35.209, | |
| "eval_steps_per_second": 9.154, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11367673179396093, | |
| "grad_norm": 10.013323783874512, | |
| "learning_rate": 0.0001, | |
| "loss": 2.4429, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1705150976909414, | |
| "grad_norm": 6.692012786865234, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 2.112, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.22735346358792186, | |
| "grad_norm": 5.411765098571777, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 1.5513, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2841918294849023, | |
| "grad_norm": 3.5160973072052, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.028, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3410301953818828, | |
| "grad_norm": 3.2901923656463623, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.8045, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3978685612788632, | |
| "grad_norm": 2.3307533264160156, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.5893, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4547069271758437, | |
| "grad_norm": 1.451710820198059, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.6319, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5115452930728241, | |
| "grad_norm": 1.1875934600830078, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.5036, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5683836589698046, | |
| "grad_norm": 1.0255441665649414, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.4298, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6252220248667851, | |
| "grad_norm": 1.1630241870880127, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.5249, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6820603907637656, | |
| "grad_norm": 0.9122489094734192, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.4253, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.738898756660746, | |
| "grad_norm": 0.9681995511054993, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.4728, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7957371225577264, | |
| "grad_norm": 0.7876354455947876, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.3958, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8525754884547069, | |
| "grad_norm": 0.800581693649292, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.4924, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9094138543516874, | |
| "grad_norm": 0.8582223057746887, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.4756, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9662522202486679, | |
| "grad_norm": 0.768711507320404, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.4044, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0373001776198933, | |
| "grad_norm": 1.4927573204040527, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.6043, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0941385435168738, | |
| "grad_norm": 0.6560688018798828, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.3224, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1509769094138544, | |
| "grad_norm": 0.7688695192337036, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.4185, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2078152753108349, | |
| "grad_norm": 0.6545513272285461, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.335, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2646536412078153, | |
| "grad_norm": 0.7087210416793823, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.326, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3214920071047958, | |
| "grad_norm": 0.697533905506134, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.3226, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3783303730017762, | |
| "grad_norm": 0.7587358951568604, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.3534, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4351687388987566, | |
| "grad_norm": 0.7912662625312805, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.3522, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4351687388987566, | |
| "eval_loss": 0.3542141020298004, | |
| "eval_runtime": 1.4703, | |
| "eval_samples_per_second": 34.007, | |
| "eval_steps_per_second": 8.842, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.492007104795737, | |
| "grad_norm": 0.7071423530578613, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.3258, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5488454706927177, | |
| "grad_norm": 0.6703159809112549, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.2989, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.605683836589698, | |
| "grad_norm": 0.7624469995498657, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.3332, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.6625222024866786, | |
| "grad_norm": 0.7111221551895142, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.2975, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7193605683836588, | |
| "grad_norm": 0.742264449596405, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.3184, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7761989342806395, | |
| "grad_norm": 0.7061470746994019, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.2985, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.83303730017762, | |
| "grad_norm": 0.6659010052680969, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.2693, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.8898756660746003, | |
| "grad_norm": 0.7084206342697144, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.2736, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.9467140319715808, | |
| "grad_norm": 0.7416772842407227, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.3343, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0177619893428065, | |
| "grad_norm": 1.3899123668670654, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.5565, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.0746003552397867, | |
| "grad_norm": 0.6840583682060242, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.2102, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.1314387211367674, | |
| "grad_norm": 0.6961442232131958, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.2701, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.1882770870337476, | |
| "grad_norm": 0.6428714394569397, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.217, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.2451154529307282, | |
| "grad_norm": 0.6439923644065857, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.2425, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.301953818827709, | |
| "grad_norm": 0.6059988141059875, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.1859, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.358792184724689, | |
| "grad_norm": 0.6674396991729736, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.2118, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.4156305506216698, | |
| "grad_norm": 0.6682599782943726, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.2391, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.47246891651865, | |
| "grad_norm": 0.7165043354034424, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.282, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.5293072824156306, | |
| "grad_norm": 0.6763691902160645, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.2266, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.586145648312611, | |
| "grad_norm": 0.6700581312179565, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.2136, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.6429840142095915, | |
| "grad_norm": 0.6825120449066162, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.2172, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.699822380106572, | |
| "grad_norm": 0.6850205659866333, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.2504, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.7566607460035524, | |
| "grad_norm": 0.8236407041549683, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.2738, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.8134991119005326, | |
| "grad_norm": 0.7022649645805359, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.2272, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.8703374777975132, | |
| "grad_norm": 0.7667473554611206, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2614, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.8703374777975132, | |
| "eval_loss": 0.3318357467651367, | |
| "eval_runtime": 1.4602, | |
| "eval_samples_per_second": 34.243, | |
| "eval_steps_per_second": 8.903, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 1.589463780163584e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |