| { | |
| "best_metric": 4.716582775115967, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.245125348189415, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04456824512534819, | |
| "grad_norm": 3.7572438716888428, | |
| "learning_rate": 5e-05, | |
| "loss": 10.7898, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04456824512534819, | |
| "eval_loss": 11.917471885681152, | |
| "eval_runtime": 2.4732, | |
| "eval_samples_per_second": 20.217, | |
| "eval_steps_per_second": 5.256, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.08913649025069638, | |
| "grad_norm": 2.1436166763305664, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8556, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.13370473537604458, | |
| "grad_norm": 1.6581848859786987, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 11.401, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.17827298050139276, | |
| "grad_norm": 2.0293407440185547, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 11.9143, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.22284122562674094, | |
| "grad_norm": 2.4636528491973877, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 12.2427, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.26740947075208915, | |
| "grad_norm": 6.925570487976074, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 8.1847, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.31197771587743733, | |
| "grad_norm": 4.652174949645996, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 7.1735, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.3565459610027855, | |
| "grad_norm": 2.5405783653259277, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 8.5635, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.4011142061281337, | |
| "grad_norm": 3.3183186054229736, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 9.1195, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.4456824512534819, | |
| "grad_norm": 3.9773972034454346, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 9.513, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.49025069637883006, | |
| "grad_norm": 5.126943588256836, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 10.8839, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.5348189415041783, | |
| "grad_norm": 6.313504695892334, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 4.9107, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.5793871866295265, | |
| "grad_norm": 3.481841564178467, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 6.6301, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.6239554317548747, | |
| "grad_norm": 3.6504743099212646, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 7.2363, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.6685236768802229, | |
| "grad_norm": 3.431692361831665, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 6.7311, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.713091922005571, | |
| "grad_norm": 4.575716495513916, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 7.6788, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.7576601671309192, | |
| "grad_norm": 4.351408958435059, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 4.4246, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.8022284122562674, | |
| "grad_norm": 3.999706983566284, | |
| "learning_rate": 7.75e-05, | |
| "loss": 5.5048, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.8467966573816156, | |
| "grad_norm": 2.2049319744110107, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 6.6618, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.8913649025069638, | |
| "grad_norm": 2.0348222255706787, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 6.2686, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.935933147632312, | |
| "grad_norm": 2.430169105529785, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 6.3663, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.9805013927576601, | |
| "grad_norm": 4.576208114624023, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 7.0645, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.033426183844011, | |
| "grad_norm": 5.862423896789551, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 8.5183, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.0779944289693593, | |
| "grad_norm": 3.1182539463043213, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 5.0484, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.1225626740947074, | |
| "grad_norm": 2.3813588619232178, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 5.7541, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1225626740947074, | |
| "eval_loss": 5.417140483856201, | |
| "eval_runtime": 1.8352, | |
| "eval_samples_per_second": 27.245, | |
| "eval_steps_per_second": 7.084, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.1671309192200556, | |
| "grad_norm": 2.453505516052246, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 5.583, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.2116991643454038, | |
| "grad_norm": 2.5713016986846924, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 5.6186, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.2562674094707522, | |
| "grad_norm": 1.9322009086608887, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 3.9696, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.3008356545961002, | |
| "grad_norm": 2.791020631790161, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 4.4587, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.3454038997214486, | |
| "grad_norm": 2.149622917175293, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 4.8004, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.3899721448467965, | |
| "grad_norm": 2.2228457927703857, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 5.1657, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.434540389972145, | |
| "grad_norm": 2.323864221572876, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 5.0189, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.479108635097493, | |
| "grad_norm": 2.922153949737549, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 5.52, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.5236768802228413, | |
| "grad_norm": 2.770920515060425, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 4.2389, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.5682451253481893, | |
| "grad_norm": 2.918221950531006, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 4.0683, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.6128133704735377, | |
| "grad_norm": 2.5188300609588623, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 5.1571, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.6573816155988856, | |
| "grad_norm": 2.6808626651763916, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 5.0721, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.701949860724234, | |
| "grad_norm": 1.907468318939209, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 5.1194, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.7465181058495822, | |
| "grad_norm": 1.6851441860198975, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 3.4621, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.7910863509749304, | |
| "grad_norm": 2.436414957046509, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 4.29, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.8356545961002786, | |
| "grad_norm": 1.9236414432525635, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 4.988, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.8802228412256268, | |
| "grad_norm": 1.9346405267715454, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 4.5542, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.924791086350975, | |
| "grad_norm": 2.173877000808716, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 4.9275, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.9693593314763231, | |
| "grad_norm": 3.563979148864746, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 5.8462, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.022284122562674, | |
| "grad_norm": 3.204674005508423, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 7.8565, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.066852367688022, | |
| "grad_norm": 1.8876923322677612, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 3.5769, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.1114206128133706, | |
| "grad_norm": 1.8125336170196533, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 4.7022, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.1559888579387185, | |
| "grad_norm": 1.8523550033569336, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 4.4587, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.200557103064067, | |
| "grad_norm": 2.4004316329956055, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 4.7921, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.245125348189415, | |
| "grad_norm": 1.909448504447937, | |
| "learning_rate": 1e-05, | |
| "loss": 2.6394, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.245125348189415, | |
| "eval_loss": 4.716582775115967, | |
| "eval_runtime": 1.8513, | |
| "eval_samples_per_second": 27.009, | |
| "eval_steps_per_second": 7.022, | |
| "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": 5.624057810649088e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |