| { | |
| "best_metric": 2.5790822505950928, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.6509240246406571, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03285420944558522, | |
| "grad_norm": 0.6311900019645691, | |
| "learning_rate": 5e-05, | |
| "loss": 2.2234, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03285420944558522, | |
| "eval_loss": 2.9316341876983643, | |
| "eval_runtime": 5.9386, | |
| "eval_samples_per_second": 34.52, | |
| "eval_steps_per_second": 4.378, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06570841889117043, | |
| "grad_norm": 0.9081849455833435, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5157, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.09856262833675565, | |
| "grad_norm": 0.875443160533905, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.9443, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.13141683778234087, | |
| "grad_norm": 0.681532084941864, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.8083, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.16427104722792607, | |
| "grad_norm": 0.7546427249908447, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.7923, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1971252566735113, | |
| "grad_norm": 0.7163383960723877, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.6759, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2299794661190965, | |
| "grad_norm": 0.7841737866401672, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.7357, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.26283367556468173, | |
| "grad_norm": 0.5721498131752014, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1194, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.29568788501026694, | |
| "grad_norm": 0.5235785245895386, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.3936, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.32854209445585214, | |
| "grad_norm": 0.5043471455574036, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.5788, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3613963039014374, | |
| "grad_norm": 0.49539726972579956, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.6342, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3942505133470226, | |
| "grad_norm": 0.5420206189155579, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.6928, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4271047227926078, | |
| "grad_norm": 0.5541395545005798, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.7383, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.459958932238193, | |
| "grad_norm": 0.6163436770439148, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.6837, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4928131416837782, | |
| "grad_norm": 0.9190883636474609, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.7666, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.5256673511293635, | |
| "grad_norm": 0.38201871514320374, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.1146, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5585215605749486, | |
| "grad_norm": 0.48645922541618347, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.5198, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5913757700205339, | |
| "grad_norm": 0.4911983609199524, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.5752, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.6242299794661191, | |
| "grad_norm": 0.5300045609474182, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.6961, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.6570841889117043, | |
| "grad_norm": 0.5103335380554199, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.5715, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6899383983572895, | |
| "grad_norm": 0.5545403361320496, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.5873, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.7227926078028748, | |
| "grad_norm": 0.6748920679092407, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.6207, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.75564681724846, | |
| "grad_norm": 0.3921031355857849, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.0321, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7885010266940452, | |
| "grad_norm": 0.4426540434360504, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.2132, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.8213552361396304, | |
| "grad_norm": 0.4701845347881317, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.5561, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8213552361396304, | |
| "eval_loss": 2.6144490242004395, | |
| "eval_runtime": 5.9393, | |
| "eval_samples_per_second": 34.516, | |
| "eval_steps_per_second": 4.378, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8542094455852156, | |
| "grad_norm": 0.4761195182800293, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6846, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8870636550308009, | |
| "grad_norm": 0.5094211101531982, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.7143, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.919917864476386, | |
| "grad_norm": 0.5358983874320984, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.6664, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9527720739219713, | |
| "grad_norm": 0.6261024475097656, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.6405, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.9856262833675564, | |
| "grad_norm": 0.8257274627685547, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.6263, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.0266940451745379, | |
| "grad_norm": 1.1825813055038452, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 4.2278, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.0595482546201231, | |
| "grad_norm": 0.40372803807258606, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.0355, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.0924024640657084, | |
| "grad_norm": 0.4721590280532837, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.5572, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.1252566735112937, | |
| "grad_norm": 0.475892037153244, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.3979, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.158110882956879, | |
| "grad_norm": 0.5070028901100159, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.556, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1909650924024642, | |
| "grad_norm": 0.5608769059181213, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.4592, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.2238193018480492, | |
| "grad_norm": 0.6679421663284302, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.5307, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.2566735112936345, | |
| "grad_norm": 0.42008689045906067, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.8624, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.2895277207392197, | |
| "grad_norm": 0.4553283751010895, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.1853, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.322381930184805, | |
| "grad_norm": 0.46935948729515076, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.2706, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.35523613963039, | |
| "grad_norm": 0.4959513247013092, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.4294, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3880903490759753, | |
| "grad_norm": 0.5358001589775085, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.5825, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.4209445585215605, | |
| "grad_norm": 0.5627439022064209, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.499, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.4537987679671458, | |
| "grad_norm": 0.6085307598114014, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.4359, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.486652977412731, | |
| "grad_norm": 0.8430867791175842, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.6336, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.5195071868583163, | |
| "grad_norm": 0.4500504732131958, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.1174, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.5523613963039016, | |
| "grad_norm": 0.4381200969219208, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.016, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.5852156057494866, | |
| "grad_norm": 0.515243649482727, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.5711, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.6180698151950719, | |
| "grad_norm": 0.5294801592826843, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.4628, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.6509240246406571, | |
| "grad_norm": 0.5349022746086121, | |
| "learning_rate": 0.0, | |
| "loss": 2.4572, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.6509240246406571, | |
| "eval_loss": 2.5790822505950928, | |
| "eval_runtime": 5.9316, | |
| "eval_samples_per_second": 34.561, | |
| "eval_steps_per_second": 4.383, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 5.645754911686656e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |