|
{ |
|
"best_metric": 1.4570739269256592, |
|
"best_model_checkpoint": "miner_id_24/checkpoint-50", |
|
"epoch": 0.00704324552753909, |
|
"eval_steps": 50, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0001408649105507818, |
|
"grad_norm": 10.031426429748535, |
|
"learning_rate": 1e-05, |
|
"loss": 2.3655, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0001408649105507818, |
|
"eval_loss": 4.294093608856201, |
|
"eval_runtime": 240.4456, |
|
"eval_samples_per_second": 49.729, |
|
"eval_steps_per_second": 12.435, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0002817298211015636, |
|
"grad_norm": 16.766931533813477, |
|
"learning_rate": 2e-05, |
|
"loss": 3.0245, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0004225947316523454, |
|
"grad_norm": 14.750626564025879, |
|
"learning_rate": 3e-05, |
|
"loss": 3.262, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0005634596422031273, |
|
"grad_norm": 13.338021278381348, |
|
"learning_rate": 4e-05, |
|
"loss": 3.3109, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.000704324552753909, |
|
"grad_norm": 9.850285530090332, |
|
"learning_rate": 5e-05, |
|
"loss": 3.5079, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0008451894633046908, |
|
"grad_norm": 7.1621174812316895, |
|
"learning_rate": 6e-05, |
|
"loss": 2.8592, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.0009860543738554725, |
|
"grad_norm": 13.172682762145996, |
|
"learning_rate": 7e-05, |
|
"loss": 2.8717, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.0011269192844062545, |
|
"grad_norm": 5.506401538848877, |
|
"learning_rate": 8e-05, |
|
"loss": 2.6399, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.0012677841949570363, |
|
"grad_norm": 3.732410192489624, |
|
"learning_rate": 9e-05, |
|
"loss": 2.4251, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.001408649105507818, |
|
"grad_norm": 3.3708877563476562, |
|
"learning_rate": 0.0001, |
|
"loss": 2.3888, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0015495140160585999, |
|
"grad_norm": 5.507050037384033, |
|
"learning_rate": 9.999316524962345e-05, |
|
"loss": 2.2776, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.0016903789266093816, |
|
"grad_norm": 5.705183506011963, |
|
"learning_rate": 9.997266286704631e-05, |
|
"loss": 2.2514, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.0018312438371601634, |
|
"grad_norm": 8.796576499938965, |
|
"learning_rate": 9.993849845741524e-05, |
|
"loss": 2.1019, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.001972108747710945, |
|
"grad_norm": 3.9234306812286377, |
|
"learning_rate": 9.989068136093873e-05, |
|
"loss": 1.7961, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.002112973658261727, |
|
"grad_norm": 2.623748302459717, |
|
"learning_rate": 9.98292246503335e-05, |
|
"loss": 1.3583, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.002253838568812509, |
|
"grad_norm": 4.477276802062988, |
|
"learning_rate": 9.975414512725057e-05, |
|
"loss": 1.4632, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.0023947034793632906, |
|
"grad_norm": 5.722939968109131, |
|
"learning_rate": 9.966546331768191e-05, |
|
"loss": 1.4597, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.0025355683899140726, |
|
"grad_norm": 3.1406970024108887, |
|
"learning_rate": 9.956320346634876e-05, |
|
"loss": 1.1818, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.002676433300464854, |
|
"grad_norm": 3.0936570167541504, |
|
"learning_rate": 9.944739353007344e-05, |
|
"loss": 1.0524, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.002817298211015636, |
|
"grad_norm": 2.623175859451294, |
|
"learning_rate": 9.931806517013612e-05, |
|
"loss": 1.2207, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0029581631215664177, |
|
"grad_norm": 7.455384731292725, |
|
"learning_rate": 9.917525374361912e-05, |
|
"loss": 1.0805, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.0030990280321171997, |
|
"grad_norm": 2.4907939434051514, |
|
"learning_rate": 9.901899829374047e-05, |
|
"loss": 1.0991, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.0032398929426679813, |
|
"grad_norm": 2.3516669273376465, |
|
"learning_rate": 9.884934153917997e-05, |
|
"loss": 1.0731, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.0033807578532187633, |
|
"grad_norm": 1.8740895986557007, |
|
"learning_rate": 9.86663298624003e-05, |
|
"loss": 1.0548, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.003521622763769545, |
|
"grad_norm": 2.03414249420166, |
|
"learning_rate": 9.847001329696653e-05, |
|
"loss": 1.0929, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.003662487674320327, |
|
"grad_norm": 2.503605365753174, |
|
"learning_rate": 9.826044551386744e-05, |
|
"loss": 0.8563, |
|
"step": 26 |
|
}, |
|
{ |
|
"epoch": 0.0038033525848711084, |
|
"grad_norm": 2.086621046066284, |
|
"learning_rate": 9.803768380684242e-05, |
|
"loss": 0.8946, |
|
"step": 27 |
|
}, |
|
{ |
|
"epoch": 0.00394421749542189, |
|
"grad_norm": 2.400827646255493, |
|
"learning_rate": 9.780178907671789e-05, |
|
"loss": 0.8641, |
|
"step": 28 |
|
}, |
|
{ |
|
"epoch": 0.0040850824059726724, |
|
"grad_norm": 2.0889105796813965, |
|
"learning_rate": 9.755282581475769e-05, |
|
"loss": 0.7307, |
|
"step": 29 |
|
}, |
|
{ |
|
"epoch": 0.004225947316523454, |
|
"grad_norm": 1.8822883367538452, |
|
"learning_rate": 9.729086208503174e-05, |
|
"loss": 0.7232, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.004366812227074236, |
|
"grad_norm": 2.5694515705108643, |
|
"learning_rate": 9.701596950580806e-05, |
|
"loss": 0.8975, |
|
"step": 31 |
|
}, |
|
{ |
|
"epoch": 0.004507677137625018, |
|
"grad_norm": 3.4608964920043945, |
|
"learning_rate": 9.672822322997305e-05, |
|
"loss": 0.6979, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 0.0046485420481758, |
|
"grad_norm": 2.8889780044555664, |
|
"learning_rate": 9.642770192448536e-05, |
|
"loss": 0.8112, |
|
"step": 33 |
|
}, |
|
{ |
|
"epoch": 0.004789406958726581, |
|
"grad_norm": 3.957289218902588, |
|
"learning_rate": 9.611448774886924e-05, |
|
"loss": 0.6703, |
|
"step": 34 |
|
}, |
|
{ |
|
"epoch": 0.004930271869277363, |
|
"grad_norm": 1.575763463973999, |
|
"learning_rate": 9.578866633275288e-05, |
|
"loss": 0.473, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.005071136779828145, |
|
"grad_norm": 1.765645146369934, |
|
"learning_rate": 9.545032675245813e-05, |
|
"loss": 0.4878, |
|
"step": 36 |
|
}, |
|
{ |
|
"epoch": 0.005212001690378927, |
|
"grad_norm": 1.6332755088806152, |
|
"learning_rate": 9.509956150664796e-05, |
|
"loss": 0.7539, |
|
"step": 37 |
|
}, |
|
{ |
|
"epoch": 0.005352866600929708, |
|
"grad_norm": 2.3892107009887695, |
|
"learning_rate": 9.473646649103818e-05, |
|
"loss": 0.7547, |
|
"step": 38 |
|
}, |
|
{ |
|
"epoch": 0.00549373151148049, |
|
"grad_norm": 2.25726580619812, |
|
"learning_rate": 9.43611409721806e-05, |
|
"loss": 0.5751, |
|
"step": 39 |
|
}, |
|
{ |
|
"epoch": 0.005634596422031272, |
|
"grad_norm": 2.58968448638916, |
|
"learning_rate": 9.397368756032445e-05, |
|
"loss": 0.7205, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.005775461332582054, |
|
"grad_norm": 2.499601364135742, |
|
"learning_rate": 9.357421218136386e-05, |
|
"loss": 0.6855, |
|
"step": 41 |
|
}, |
|
{ |
|
"epoch": 0.0059163262431328354, |
|
"grad_norm": 6.7224273681640625, |
|
"learning_rate": 9.316282404787871e-05, |
|
"loss": 0.9355, |
|
"step": 42 |
|
}, |
|
{ |
|
"epoch": 0.006057191153683617, |
|
"grad_norm": 2.4964160919189453, |
|
"learning_rate": 9.273963562927695e-05, |
|
"loss": 0.965, |
|
"step": 43 |
|
}, |
|
{ |
|
"epoch": 0.0061980560642343994, |
|
"grad_norm": 1.7799794673919678, |
|
"learning_rate": 9.230476262104677e-05, |
|
"loss": 0.9326, |
|
"step": 44 |
|
}, |
|
{ |
|
"epoch": 0.006338920974785181, |
|
"grad_norm": 2.3146729469299316, |
|
"learning_rate": 9.185832391312644e-05, |
|
"loss": 1.3381, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.006479785885335963, |
|
"grad_norm": 3.97938871383667, |
|
"learning_rate": 9.140044155740101e-05, |
|
"loss": 1.7827, |
|
"step": 46 |
|
}, |
|
{ |
|
"epoch": 0.006620650795886745, |
|
"grad_norm": 3.983363628387451, |
|
"learning_rate": 9.093124073433463e-05, |
|
"loss": 1.7851, |
|
"step": 47 |
|
}, |
|
{ |
|
"epoch": 0.006761515706437527, |
|
"grad_norm": 5.531325340270996, |
|
"learning_rate": 9.045084971874738e-05, |
|
"loss": 2.2786, |
|
"step": 48 |
|
}, |
|
{ |
|
"epoch": 0.006902380616988308, |
|
"grad_norm": 6.642470836639404, |
|
"learning_rate": 8.995939984474624e-05, |
|
"loss": 2.0166, |
|
"step": 49 |
|
}, |
|
{ |
|
"epoch": 0.00704324552753909, |
|
"grad_norm": 7.111599445343018, |
|
"learning_rate": 8.945702546981969e-05, |
|
"loss": 2.3552, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.00704324552753909, |
|
"eval_loss": 1.4570739269256592, |
|
"eval_runtime": 240.4101, |
|
"eval_samples_per_second": 49.736, |
|
"eval_steps_per_second": 12.437, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 200, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 50, |
|
"stateful_callbacks": { |
|
"EarlyStoppingCallback": { |
|
"args": { |
|
"early_stopping_patience": 5, |
|
"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": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 1.0719067958673408e+16, |
|
"train_batch_size": 8, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|