| { | |
| "best_metric": 4.043777942657471, | |
| "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": 2.2364661693573, | |
| "learning_rate": 5e-05, | |
| "loss": 4.171, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.056838365896980464, | |
| "eval_loss": 5.347789287567139, | |
| "eval_runtime": 0.6382, | |
| "eval_samples_per_second": 78.342, | |
| "eval_steps_per_second": 20.369, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11367673179396093, | |
| "grad_norm": 1.7895739078521729, | |
| "learning_rate": 0.0001, | |
| "loss": 4.8151, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1705150976909414, | |
| "grad_norm": 2.7331533432006836, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 5.1544, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.22735346358792186, | |
| "grad_norm": 1.7573771476745605, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 5.347, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2841918294849023, | |
| "grad_norm": 1.0575058460235596, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 4.1473, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3410301953818828, | |
| "grad_norm": 0.7738857269287109, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 4.4641, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3978685612788632, | |
| "grad_norm": 2.7124485969543457, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.7569, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.4547069271758437, | |
| "grad_norm": 1.5827847719192505, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 5.0478, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5115452930728241, | |
| "grad_norm": 0.872265636920929, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 3.977, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5683836589698046, | |
| "grad_norm": 0.7036884427070618, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.2225, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6252220248667851, | |
| "grad_norm": 0.9477807879447937, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 4.5216, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6820603907637656, | |
| "grad_norm": 1.073500156402588, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.6968, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.738898756660746, | |
| "grad_norm": 0.6695452332496643, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 3.9704, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7957371225577264, | |
| "grad_norm": 0.652845025062561, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 4.1003, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8525754884547069, | |
| "grad_norm": 0.7173386812210083, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 4.2267, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9094138543516874, | |
| "grad_norm": 0.9569276571273804, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 4.4941, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9662522202486679, | |
| "grad_norm": 1.4495911598205566, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 4.9847, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0373001776198933, | |
| "grad_norm": 1.1459908485412598, | |
| "learning_rate": 7.75e-05, | |
| "loss": 6.802, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0941385435168738, | |
| "grad_norm": 1.0883979797363281, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.8296, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1509769094138544, | |
| "grad_norm": 0.8071144223213196, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 4.2843, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2078152753108349, | |
| "grad_norm": 1.0637041330337524, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 4.4735, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2646536412078153, | |
| "grad_norm": 1.1672452688217163, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.841, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3214920071047958, | |
| "grad_norm": 0.76850825548172, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.951, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3783303730017762, | |
| "grad_norm": 0.9217700362205505, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 4.1167, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4351687388987566, | |
| "grad_norm": 0.8780374526977539, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 4.2914, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4351687388987566, | |
| "eval_loss": 4.218059539794922, | |
| "eval_runtime": 0.6531, | |
| "eval_samples_per_second": 76.553, | |
| "eval_steps_per_second": 19.904, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.492007104795737, | |
| "grad_norm": 0.6616500020027161, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.0374, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5488454706927177, | |
| "grad_norm": 0.9311549067497253, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 4.6396, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.605683836589698, | |
| "grad_norm": 0.7478369474411011, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 3.8456, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.6625222024866786, | |
| "grad_norm": 0.6867173910140991, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 4.1692, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7193605683836588, | |
| "grad_norm": 0.5758339166641235, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.2151, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7761989342806395, | |
| "grad_norm": 1.5432807207107544, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 5.6372, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.83303730017762, | |
| "grad_norm": 0.5938176512718201, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.8315, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.8898756660746003, | |
| "grad_norm": 0.652653157711029, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 4.0855, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.9467140319715808, | |
| "grad_norm": 1.2059962749481201, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 4.448, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0177619893428065, | |
| "grad_norm": 0.9915326833724976, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 6.6656, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.0746003552397867, | |
| "grad_norm": 0.5259771943092346, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 3.3707, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.1314387211367674, | |
| "grad_norm": 0.7280540466308594, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 3.8562, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.1882770870337476, | |
| "grad_norm": 0.7593219876289368, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 4.1603, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.2451154529307282, | |
| "grad_norm": 0.7831996083259583, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 3.4129, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.301953818827709, | |
| "grad_norm": 0.9821178317070007, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 4.3152, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.358792184724689, | |
| "grad_norm": 0.5698879957199097, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.8146, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.4156305506216698, | |
| "grad_norm": 0.6594037413597107, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 4.0656, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.47246891651865, | |
| "grad_norm": 0.6938492059707642, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.8914, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.5293072824156306, | |
| "grad_norm": 1.052404761314392, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 4.7826, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.586145648312611, | |
| "grad_norm": 0.5612595677375793, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 3.7658, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.6429840142095915, | |
| "grad_norm": 0.7995758056640625, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 4.0587, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.699822380106572, | |
| "grad_norm": 0.6661505699157715, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.0607, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.7566607460035524, | |
| "grad_norm": 0.7999106645584106, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 4.5456, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.8134991119005326, | |
| "grad_norm": 0.5701779127120972, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 3.6241, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.8703374777975132, | |
| "grad_norm": 0.5628406405448914, | |
| "learning_rate": 1e-05, | |
| "loss": 3.9367, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.8703374777975132, | |
| "eval_loss": 4.043777942657471, | |
| "eval_runtime": 0.661, | |
| "eval_samples_per_second": 75.642, | |
| "eval_steps_per_second": 19.667, | |
| "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": 1.13737243557888e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |