| { | |
| "best_metric": 0.03977901116013527, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.35650623885918004, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0071301247771836, | |
| "grad_norm": 0.08278653025627136, | |
| "learning_rate": 2e-05, | |
| "loss": 0.1105, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0071301247771836, | |
| "eval_loss": 0.30820322036743164, | |
| "eval_runtime": 2.2537, | |
| "eval_samples_per_second": 105.162, | |
| "eval_steps_per_second": 13.312, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0142602495543672, | |
| "grad_norm": 0.12395651638507843, | |
| "learning_rate": 4e-05, | |
| "loss": 0.1383, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0213903743315508, | |
| "grad_norm": 0.14602020382881165, | |
| "learning_rate": 6e-05, | |
| "loss": 0.1844, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0285204991087344, | |
| "grad_norm": 0.1675848662853241, | |
| "learning_rate": 8e-05, | |
| "loss": 0.2217, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.035650623885918005, | |
| "grad_norm": 0.1843155473470688, | |
| "learning_rate": 0.0001, | |
| "loss": 0.1998, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0427807486631016, | |
| "grad_norm": 0.16934125125408173, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.1785, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.049910873440285206, | |
| "grad_norm": 0.1613176167011261, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 0.1868, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0570409982174688, | |
| "grad_norm": 0.1733686327934265, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.2031, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06417112299465241, | |
| "grad_norm": 0.14902785420417786, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.166, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07130124777183601, | |
| "grad_norm": 0.13887515664100647, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 0.1258, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0784313725490196, | |
| "grad_norm": 0.17867763340473175, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.1448, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0855614973262032, | |
| "grad_norm": 0.17290876805782318, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.1159, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.09269162210338681, | |
| "grad_norm": 0.1344744861125946, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 0.117, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09982174688057041, | |
| "grad_norm": 0.12855705618858337, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.1, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10695187165775401, | |
| "grad_norm": 0.11990569531917572, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0908, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1140819964349376, | |
| "grad_norm": 0.12420638650655746, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 0.0918, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.12121212121212122, | |
| "grad_norm": 0.10110359638929367, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.0807, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.12834224598930483, | |
| "grad_norm": 0.11858529597520828, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.081, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1354723707664884, | |
| "grad_norm": 0.12513737380504608, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 0.0827, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.14260249554367202, | |
| "grad_norm": 0.1261119544506073, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0748, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1497326203208556, | |
| "grad_norm": 0.09696108102798462, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.0701, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1568627450980392, | |
| "grad_norm": 0.10414668172597885, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 0.0723, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.16399286987522282, | |
| "grad_norm": 0.07875572890043259, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0567, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1711229946524064, | |
| "grad_norm": 0.1584327220916748, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.0823, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.17825311942959002, | |
| "grad_norm": 0.08050437271595001, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 0.064, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17825311942959002, | |
| "eval_loss": 0.05796569958329201, | |
| "eval_runtime": 2.2026, | |
| "eval_samples_per_second": 107.598, | |
| "eval_steps_per_second": 13.62, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.18538324420677363, | |
| "grad_norm": 0.07493649423122406, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.0611, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1925133689839572, | |
| "grad_norm": 0.07159044593572617, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.0583, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19964349376114082, | |
| "grad_norm": 0.09012464433908463, | |
| "learning_rate": 4.825502516487497e-05, | |
| "loss": 0.0563, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.20677361853832443, | |
| "grad_norm": 0.07136638462543488, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.059, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.21390374331550802, | |
| "grad_norm": 0.08499963581562042, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0565, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.22103386809269163, | |
| "grad_norm": 0.07798349112272263, | |
| "learning_rate": 3.790390522001662e-05, | |
| "loss": 0.0516, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2281639928698752, | |
| "grad_norm": 0.10759936273097992, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0643, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.09819392114877701, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.0548, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.24242424242424243, | |
| "grad_norm": 0.08380597084760666, | |
| "learning_rate": 2.8081442660546125e-05, | |
| "loss": 0.057, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.24955436720142601, | |
| "grad_norm": 0.14951787889003754, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0873, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.25668449197860965, | |
| "grad_norm": 0.10837426036596298, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.1191, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2638146167557932, | |
| "grad_norm": 0.08535134047269821, | |
| "learning_rate": 1.9216926233717085e-05, | |
| "loss": 0.0501, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2709447415329768, | |
| "grad_norm": 0.0877317264676094, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.0653, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.27807486631016043, | |
| "grad_norm": 0.10669784247875214, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.1165, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.28520499108734404, | |
| "grad_norm": 0.08177712559700012, | |
| "learning_rate": 1.1697777844051105e-05, | |
| "loss": 0.0484, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.29233511586452765, | |
| "grad_norm": 0.07238364964723587, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0279, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2994652406417112, | |
| "grad_norm": 0.06635749340057373, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.0218, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.3065953654188948, | |
| "grad_norm": 0.06545112282037735, | |
| "learning_rate": 5.852620357053651e-06, | |
| "loss": 0.0233, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3137254901960784, | |
| "grad_norm": 0.05112336948513985, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.0245, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.32085561497326204, | |
| "grad_norm": 0.06570974737405777, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.0308, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.32798573975044565, | |
| "grad_norm": 0.08460719138383865, | |
| "learning_rate": 1.9369152030840556e-06, | |
| "loss": 0.0231, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.33511586452762926, | |
| "grad_norm": 0.052217718213796616, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.0225, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.3422459893048128, | |
| "grad_norm": 0.05215289071202278, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.0227, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3493761140819964, | |
| "grad_norm": 0.050525881350040436, | |
| "learning_rate": 1.2179748700879012e-07, | |
| "loss": 0.0303, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.35650623885918004, | |
| "grad_norm": 0.05176819860935211, | |
| "learning_rate": 0.0, | |
| "loss": 0.0213, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.35650623885918004, | |
| "eval_loss": 0.03977901116013527, | |
| "eval_runtime": 2.2053, | |
| "eval_samples_per_second": 107.47, | |
| "eval_steps_per_second": 13.604, | |
| "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": 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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2060663862067200.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |