| { | |
| "best_metric": 1.1147706508636475, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4022121669180493, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008044243338360985, | |
| "grad_norm": 275.3593444824219, | |
| "learning_rate": 5e-05, | |
| "loss": 58.2961, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008044243338360985, | |
| "eval_loss": 3.8809421062469482, | |
| "eval_runtime": 4.66, | |
| "eval_samples_per_second": 10.73, | |
| "eval_steps_per_second": 2.79, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01608848667672197, | |
| "grad_norm": 337.9678039550781, | |
| "learning_rate": 0.0001, | |
| "loss": 58.381, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024132730015082957, | |
| "grad_norm": 164.15354919433594, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 41.8318, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.03217697335344394, | |
| "grad_norm": 128.73129272460938, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 31.1845, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04022121669180493, | |
| "grad_norm": 99.6097183227539, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 27.1833, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.048265460030165915, | |
| "grad_norm": 66.08391571044922, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 27.4291, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0563097033685269, | |
| "grad_norm": 131.6636962890625, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 23.2627, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.06435394670688788, | |
| "grad_norm": 57.811683654785156, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 22.856, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.07239819004524888, | |
| "grad_norm": 55.452491760253906, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 21.3941, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08044243338360986, | |
| "grad_norm": 53.64926528930664, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 19.9555, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.08848667672197084, | |
| "grad_norm": 76.63052368164062, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 19.6019, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.09653092006033183, | |
| "grad_norm": 60.09281921386719, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 20.6787, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.10457516339869281, | |
| "grad_norm": 57.21773910522461, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 21.3044, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.1126194067370538, | |
| "grad_norm": 75.1263427734375, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 21.6446, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12066365007541478, | |
| "grad_norm": 55.88449478149414, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 21.9079, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.12870789341377575, | |
| "grad_norm": 67.62132263183594, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 21.7622, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 97.81370544433594, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 22.9791, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.14479638009049775, | |
| "grad_norm": 47.42399597167969, | |
| "learning_rate": 7.75e-05, | |
| "loss": 20.2514, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.15284062342885874, | |
| "grad_norm": 79.00409698486328, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 20.8471, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.16088486676721972, | |
| "grad_norm": 92.79839324951172, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 20.0545, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1689291101055807, | |
| "grad_norm": 72.07453155517578, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 19.2175, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1769733534439417, | |
| "grad_norm": 92.92733001708984, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 18.2838, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.18501759678230267, | |
| "grad_norm": 58.30161666870117, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 20.3448, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.19306184012066366, | |
| "grad_norm": 49.9283332824707, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 19.8985, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.20110608345902464, | |
| "grad_norm": 60.23078155517578, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 17.6821, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20110608345902464, | |
| "eval_loss": 1.2222079038619995, | |
| "eval_runtime": 4.7285, | |
| "eval_samples_per_second": 10.574, | |
| "eval_steps_per_second": 2.749, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.20915032679738563, | |
| "grad_norm": 59.51567459106445, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 20.4203, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.2171945701357466, | |
| "grad_norm": 94.031005859375, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 20.0566, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.2252388134741076, | |
| "grad_norm": 63.98728942871094, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 18.5908, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.23328305681246858, | |
| "grad_norm": 70.50849151611328, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 18.3789, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.24132730015082957, | |
| "grad_norm": 94.6316909790039, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 20.5791, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24937154348919055, | |
| "grad_norm": 49.107112884521484, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 20.0751, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2574157868275515, | |
| "grad_norm": 59.386619567871094, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 19.4646, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.2654600301659125, | |
| "grad_norm": 54.569854736328125, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 18.6054, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 58.54420471191406, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 19.026, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2815485168426345, | |
| "grad_norm": 44.54639434814453, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 17.7273, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2895927601809955, | |
| "grad_norm": 59.34305191040039, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 19.4993, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.29763700351935646, | |
| "grad_norm": 43.02519989013672, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 18.8984, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.30568124685771747, | |
| "grad_norm": 51.63078689575195, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 18.2151, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.3137254901960784, | |
| "grad_norm": 126.79589080810547, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 19.9692, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.32176973353443944, | |
| "grad_norm": 82.25690460205078, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 18.3356, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.3298139768728004, | |
| "grad_norm": 67.15270233154297, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 18.1798, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.3378582202111614, | |
| "grad_norm": 52.148597717285156, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 19.694, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.34590246354952237, | |
| "grad_norm": 52.65068054199219, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 18.6712, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3539467068878834, | |
| "grad_norm": 63.50575637817383, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 19.3908, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.36199095022624433, | |
| "grad_norm": 45.28229522705078, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 18.7951, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.37003519356460535, | |
| "grad_norm": 43.16271209716797, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 19.3532, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.3780794369029663, | |
| "grad_norm": 57.86573028564453, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 17.9573, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3861236802413273, | |
| "grad_norm": 32.22254180908203, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 17.9235, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3941679235796883, | |
| "grad_norm": 36.30216598510742, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 18.8893, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4022121669180493, | |
| "grad_norm": 45.27206802368164, | |
| "learning_rate": 1e-05, | |
| "loss": 17.6392, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4022121669180493, | |
| "eval_loss": 1.1147706508636475, | |
| "eval_runtime": 4.7535, | |
| "eval_samples_per_second": 10.519, | |
| "eval_steps_per_second": 2.735, | |
| "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": 5.658021338284032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |