| { | |
| "best_metric": 1.4252018928527832, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.20964360587002095, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0041928721174004195, | |
| "grad_norm": 26.132644653320312, | |
| "learning_rate": 1e-05, | |
| "loss": 11.9012, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0041928721174004195, | |
| "eval_loss": 3.0544967651367188, | |
| "eval_runtime": 44.0725, | |
| "eval_samples_per_second": 9.121, | |
| "eval_steps_per_second": 2.292, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008385744234800839, | |
| "grad_norm": 36.28742980957031, | |
| "learning_rate": 2e-05, | |
| "loss": 13.0845, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.012578616352201259, | |
| "grad_norm": 45.885284423828125, | |
| "learning_rate": 3e-05, | |
| "loss": 14.6054, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.016771488469601678, | |
| "grad_norm": 42.03292465209961, | |
| "learning_rate": 4e-05, | |
| "loss": 13.9683, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.020964360587002098, | |
| "grad_norm": 47.916175842285156, | |
| "learning_rate": 5e-05, | |
| "loss": 10.7715, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.025157232704402517, | |
| "grad_norm": 20.316499710083008, | |
| "learning_rate": 6e-05, | |
| "loss": 8.3264, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.029350104821802937, | |
| "grad_norm": 21.001514434814453, | |
| "learning_rate": 7e-05, | |
| "loss": 7.8696, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.033542976939203356, | |
| "grad_norm": 19.75449562072754, | |
| "learning_rate": 8e-05, | |
| "loss": 6.6757, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03773584905660377, | |
| "grad_norm": 22.971229553222656, | |
| "learning_rate": 9e-05, | |
| "loss": 6.8329, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.041928721174004195, | |
| "grad_norm": 21.109153747558594, | |
| "learning_rate": 0.0001, | |
| "loss": 6.7707, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04612159329140461, | |
| "grad_norm": 18.65835189819336, | |
| "learning_rate": 9.999316524962345e-05, | |
| "loss": 6.3268, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.050314465408805034, | |
| "grad_norm": 17.413570404052734, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 5.7432, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05450733752620545, | |
| "grad_norm": 17.838520050048828, | |
| "learning_rate": 9.993849845741524e-05, | |
| "loss": 5.8578, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05870020964360587, | |
| "grad_norm": 21.145803451538086, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 5.4755, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06289308176100629, | |
| "grad_norm": 15.322203636169434, | |
| "learning_rate": 9.98292246503335e-05, | |
| "loss": 5.9927, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06708595387840671, | |
| "grad_norm": 13.84201431274414, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 5.5105, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07127882599580712, | |
| "grad_norm": 13.809650421142578, | |
| "learning_rate": 9.966546331768191e-05, | |
| "loss": 5.3261, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07547169811320754, | |
| "grad_norm": 14.959165573120117, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 5.2148, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07966457023060797, | |
| "grad_norm": 15.26698112487793, | |
| "learning_rate": 9.944739353007344e-05, | |
| "loss": 5.5136, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08385744234800839, | |
| "grad_norm": 16.680856704711914, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 5.2218, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0880503144654088, | |
| "grad_norm": 14.962255477905273, | |
| "learning_rate": 9.917525374361912e-05, | |
| "loss": 4.9713, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09224318658280922, | |
| "grad_norm": 16.719751358032227, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 5.0492, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09643605870020965, | |
| "grad_norm": 13.605834007263184, | |
| "learning_rate": 9.884934153917997e-05, | |
| "loss": 5.1194, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.10062893081761007, | |
| "grad_norm": 14.808418273925781, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 4.6639, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10482180293501048, | |
| "grad_norm": 13.41181755065918, | |
| "learning_rate": 9.847001329696653e-05, | |
| "loss": 5.3685, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1090146750524109, | |
| "grad_norm": 15.861624717712402, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 4.9872, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11320754716981132, | |
| "grad_norm": 14.191696166992188, | |
| "learning_rate": 9.803768380684242e-05, | |
| "loss": 5.2217, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11740041928721175, | |
| "grad_norm": 14.087152481079102, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 4.8128, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.12159329140461216, | |
| "grad_norm": 13.271366119384766, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 4.8184, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12578616352201258, | |
| "grad_norm": 14.966277122497559, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 4.9615, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.129979035639413, | |
| "grad_norm": 12.936847686767578, | |
| "learning_rate": 9.701596950580806e-05, | |
| "loss": 4.8281, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.13417190775681342, | |
| "grad_norm": 12.324258804321289, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 4.7617, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.13836477987421383, | |
| "grad_norm": 13.070696830749512, | |
| "learning_rate": 9.642770192448536e-05, | |
| "loss": 5.0061, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.14255765199161424, | |
| "grad_norm": 14.148125648498535, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 4.9349, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.14675052410901468, | |
| "grad_norm": 12.829872131347656, | |
| "learning_rate": 9.578866633275288e-05, | |
| "loss": 5.1966, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1509433962264151, | |
| "grad_norm": 15.064430236816406, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 5.1889, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.15513626834381553, | |
| "grad_norm": 13.483580589294434, | |
| "learning_rate": 9.509956150664796e-05, | |
| "loss": 4.9406, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.15932914046121593, | |
| "grad_norm": 14.467133522033691, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 4.6874, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.16352201257861634, | |
| "grad_norm": 14.77626895904541, | |
| "learning_rate": 9.43611409721806e-05, | |
| "loss": 5.4034, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.16771488469601678, | |
| "grad_norm": 13.509198188781738, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 5.0737, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1719077568134172, | |
| "grad_norm": 14.06533432006836, | |
| "learning_rate": 9.357421218136386e-05, | |
| "loss": 4.9448, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.1761006289308176, | |
| "grad_norm": 14.199156761169434, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 5.2226, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.18029350104821804, | |
| "grad_norm": 14.681893348693848, | |
| "learning_rate": 9.273963562927695e-05, | |
| "loss": 5.2379, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.18448637316561844, | |
| "grad_norm": 15.566058158874512, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 5.2613, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.18867924528301888, | |
| "grad_norm": 13.801526069641113, | |
| "learning_rate": 9.185832391312644e-05, | |
| "loss": 5.461, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1928721174004193, | |
| "grad_norm": 18.503665924072266, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 5.5382, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1970649895178197, | |
| "grad_norm": 233.49794006347656, | |
| "learning_rate": 9.093124073433463e-05, | |
| "loss": 5.9307, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.20125786163522014, | |
| "grad_norm": 85.2809066772461, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 5.412, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.20545073375262055, | |
| "grad_norm": 18.1092529296875, | |
| "learning_rate": 8.995939984474624e-05, | |
| "loss": 5.5137, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.20964360587002095, | |
| "grad_norm": 17.491830825805664, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 5.7121, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20964360587002095, | |
| "eval_loss": 1.4252018928527832, | |
| "eval_runtime": 45.3289, | |
| "eval_samples_per_second": 8.869, | |
| "eval_steps_per_second": 2.228, | |
| "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": 7.834714099207373e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |