| { | |
| "best_metric": 0.8620172142982483, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.39254170755642787, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.007850834151128557, | |
| "grad_norm": 1.135539174079895, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3562, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.007850834151128557, | |
| "eval_loss": 1.7769310474395752, | |
| "eval_runtime": 4.7057, | |
| "eval_samples_per_second": 10.625, | |
| "eval_steps_per_second": 2.763, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015701668302257114, | |
| "grad_norm": 1.5373108386993408, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5224, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.023552502453385672, | |
| "grad_norm": 0.7789191603660583, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.8343, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03140333660451423, | |
| "grad_norm": 0.6695387959480286, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.9541, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03925417075564279, | |
| "grad_norm": 0.48543453216552734, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 1.1856, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.047105004906771344, | |
| "grad_norm": 0.5540667176246643, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 1.1796, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0549558390578999, | |
| "grad_norm": 0.4394397735595703, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 1.206, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06280667320902845, | |
| "grad_norm": 0.4523168206214905, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.313, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07065750736015702, | |
| "grad_norm": 0.4538557827472687, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.4054, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07850834151128558, | |
| "grad_norm": 0.4173380434513092, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.541, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08635917566241413, | |
| "grad_norm": 0.6061396598815918, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.8941, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09421000981354269, | |
| "grad_norm": 4.069518566131592, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.9792, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10206084396467124, | |
| "grad_norm": 1.9096570014953613, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.5941, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1099116781157998, | |
| "grad_norm": 1.5357744693756104, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.0376, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.11776251226692837, | |
| "grad_norm": 0.7086212635040283, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.7146, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1256133464180569, | |
| "grad_norm": 0.535244345664978, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.6778, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.13346418056918546, | |
| "grad_norm": 0.36298349499702454, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.0007, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14131501472031405, | |
| "grad_norm": 0.4271247982978821, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.0817, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1491658488714426, | |
| "grad_norm": 0.3919868469238281, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.1191, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.15701668302257116, | |
| "grad_norm": 0.3663414418697357, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.1277, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1648675171736997, | |
| "grad_norm": 0.38228505849838257, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 1.2855, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.17271835132482827, | |
| "grad_norm": 0.45715782046318054, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 1.4302, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18056918547595682, | |
| "grad_norm": 0.7664559483528137, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 1.7109, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.18842001962708538, | |
| "grad_norm": 1.2415802478790283, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.8193, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.19627085377821393, | |
| "grad_norm": 3.0496532917022705, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 2.4089, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.19627085377821393, | |
| "eval_loss": 1.04914391040802, | |
| "eval_runtime": 2.5674, | |
| "eval_samples_per_second": 19.475, | |
| "eval_steps_per_second": 5.064, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2041216879293425, | |
| "grad_norm": 0.97491055727005, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.3922, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.21197252208047104, | |
| "grad_norm": 1.1205915212631226, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.7055, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2198233562315996, | |
| "grad_norm": 0.336657851934433, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.7726, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.22767419038272815, | |
| "grad_norm": 0.3204854726791382, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.673, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.23552502453385674, | |
| "grad_norm": 0.19506654143333435, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.9861, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2433758586849853, | |
| "grad_norm": 0.18182063102722168, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 1.0981, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2512266928361138, | |
| "grad_norm": 0.19906948506832123, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 1.0542, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2590775269872424, | |
| "grad_norm": 0.2256714254617691, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.1696, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.26692836113837093, | |
| "grad_norm": 0.23073700070381165, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 1.2768, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2747791952894995, | |
| "grad_norm": 0.2971401810646057, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 1.5064, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2826300294406281, | |
| "grad_norm": 0.6672556400299072, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 1.752, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2904808635917566, | |
| "grad_norm": 1.4457920789718628, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.7178, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2983316977428852, | |
| "grad_norm": 1.220274806022644, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.752, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.30618253189401373, | |
| "grad_norm": 0.618290364742279, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.6735, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.3140333660451423, | |
| "grad_norm": 0.4673266112804413, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.7348, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.32188420019627084, | |
| "grad_norm": 0.35256361961364746, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.5991, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3297350343473994, | |
| "grad_norm": 0.1682473123073578, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.9351, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.33758586849852795, | |
| "grad_norm": 0.15965545177459717, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.9283, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.34543670264965654, | |
| "grad_norm": 0.1923704594373703, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 1.0068, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.35328753680078506, | |
| "grad_norm": 0.20349323749542236, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 1.0288, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.36113837095191365, | |
| "grad_norm": 0.22597980499267578, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 1.228, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3689892051030422, | |
| "grad_norm": 0.3004361391067505, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 1.4147, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.37684003925417076, | |
| "grad_norm": 0.4439603388309479, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 1.5545, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.38469087340529934, | |
| "grad_norm": 0.6833898425102234, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.7517, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.39254170755642787, | |
| "grad_norm": 2.600379228591919, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1795, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.39254170755642787, | |
| "eval_loss": 0.8620172142982483, | |
| "eval_runtime": 2.7207, | |
| "eval_samples_per_second": 18.378, | |
| "eval_steps_per_second": 4.778, | |
| "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": 6.086632252354068e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |