| { | |
| "best_metric": 2.542440414428711, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.5429122468659595, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03085824493731919, | |
| "grad_norm": 3.645392656326294, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0123, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03085824493731919, | |
| "eval_loss": 3.7543375492095947, | |
| "eval_runtime": 1.0331, | |
| "eval_samples_per_second": 48.4, | |
| "eval_steps_per_second": 12.584, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06171648987463838, | |
| "grad_norm": 5.241004467010498, | |
| "learning_rate": 0.0001, | |
| "loss": 3.1782, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09257473481195758, | |
| "grad_norm": 1.4361050128936768, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.241, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.12343297974927676, | |
| "grad_norm": 1.6955221891403198, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.3964, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.15429122468659595, | |
| "grad_norm": 1.686437726020813, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.4925, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.18514946962391515, | |
| "grad_norm": 1.9754894971847534, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.4824, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.21600771456123433, | |
| "grad_norm": 2.0430104732513428, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 3.7856, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.24686595949855353, | |
| "grad_norm": 3.8526413440704346, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.5574, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2777242044358727, | |
| "grad_norm": 1.4491136074066162, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 2.7759, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.3085824493731919, | |
| "grad_norm": 1.1960725784301758, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 2.9386, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3394406943105111, | |
| "grad_norm": 0.9575656652450562, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 2.9346, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3702989392478303, | |
| "grad_norm": 0.935650110244751, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.8546, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.40115718418514945, | |
| "grad_norm": 0.9993137121200562, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.9409, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.43201542912246865, | |
| "grad_norm": 1.0999501943588257, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 3.0825, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.46287367405978785, | |
| "grad_norm": 2.216306209564209, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 3.3732, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.49373191899710706, | |
| "grad_norm": 3.9499778747558594, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 3.8786, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5245901639344263, | |
| "grad_norm": 0.9244690537452698, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 2.6767, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5554484088717454, | |
| "grad_norm": 0.9053135514259338, | |
| "learning_rate": 7.75e-05, | |
| "loss": 2.6557, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5863066538090647, | |
| "grad_norm": 0.9432013034820557, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 2.7071, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6171648987463838, | |
| "grad_norm": 0.8254294991493225, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 2.7248, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.648023143683703, | |
| "grad_norm": 0.9236817955970764, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.7812, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6788813886210222, | |
| "grad_norm": 1.1492239236831665, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 2.8238, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7097396335583414, | |
| "grad_norm": 1.7809970378875732, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 2.9972, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7405978784956606, | |
| "grad_norm": 5.237351417541504, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 3.336, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7714561234329798, | |
| "grad_norm": 0.719531238079071, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.5666, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7714561234329798, | |
| "eval_loss": 2.6764278411865234, | |
| "eval_runtime": 1.0189, | |
| "eval_samples_per_second": 49.072, | |
| "eval_steps_per_second": 12.759, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8023143683702989, | |
| "grad_norm": 0.6719350814819336, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 2.6062, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8331726133076182, | |
| "grad_norm": 0.7067621946334839, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 2.6239, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8640308582449373, | |
| "grad_norm": 0.7096052765846252, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 2.6449, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8948891031822566, | |
| "grad_norm": 0.9343886971473694, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 2.7355, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9257473481195757, | |
| "grad_norm": 0.8786309957504272, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 2.7085, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9566055930568949, | |
| "grad_norm": 1.608211636543274, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 2.8077, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9874638379942141, | |
| "grad_norm": 3.240671157836914, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.0358, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.0183220829315334, | |
| "grad_norm": 0.9655975103378296, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 4.2671, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0491803278688525, | |
| "grad_norm": 0.45573168992996216, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 2.4911, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0800385728061717, | |
| "grad_norm": 0.6124336123466492, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 2.5842, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1108968177434908, | |
| "grad_norm": 0.7188212275505066, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 2.6513, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.14175506268081, | |
| "grad_norm": 0.6598315238952637, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 2.5331, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.1726133076181293, | |
| "grad_norm": 0.8761363625526428, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 2.683, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.2034715525554485, | |
| "grad_norm": 1.1395080089569092, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 2.8706, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.2343297974927676, | |
| "grad_norm": 2.4882192611694336, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 2.8492, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2651880424300868, | |
| "grad_norm": 1.7844231128692627, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 2.3893, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.296046287367406, | |
| "grad_norm": 0.4351036250591278, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 2.4818, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.326904532304725, | |
| "grad_norm": 0.5659633874893188, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 2.5207, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.3577627772420444, | |
| "grad_norm": 0.6583766937255859, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 2.5642, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.3886210221793636, | |
| "grad_norm": 0.7262064218521118, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 2.5321, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.4194792671166827, | |
| "grad_norm": 0.8103611469268799, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 2.5716, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.4503375120540019, | |
| "grad_norm": 1.1891920566558838, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 2.8041, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.4811957569913212, | |
| "grad_norm": 2.4868645668029785, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 2.8477, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.5120540019286404, | |
| "grad_norm": 1.4715479612350464, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 2.3655, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.5429122468659595, | |
| "grad_norm": 0.4287128448486328, | |
| "learning_rate": 1e-05, | |
| "loss": 2.4207, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.5429122468659595, | |
| "eval_loss": 2.542440414428711, | |
| "eval_runtime": 1.0194, | |
| "eval_samples_per_second": 49.047, | |
| "eval_steps_per_second": 12.752, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 8.34067497043886e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |