| { | |
| "best_metric": 0.9738476872444153, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.8771929824561404, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.056140350877192984, | |
| "grad_norm": 40.988529205322266, | |
| "learning_rate": 5e-05, | |
| "loss": 9.9807, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.056140350877192984, | |
| "eval_loss": 10.257285118103027, | |
| "eval_runtime": 1.7596, | |
| "eval_samples_per_second": 68.198, | |
| "eval_steps_per_second": 8.525, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11228070175438597, | |
| "grad_norm": 42.96883010864258, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3023, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": 37.69118881225586, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 8.9005, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.22456140350877193, | |
| "grad_norm": 36.252384185791016, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.791, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 30.784360885620117, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.559, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 24.132333755493164, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.6449, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3929824561403509, | |
| "grad_norm": 27.09242820739746, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.0326, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.44912280701754387, | |
| "grad_norm": 13.805081367492676, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.5471, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "grad_norm": 36.310142517089844, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.351, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 15.280241966247559, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.1087, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6175438596491228, | |
| "grad_norm": 8.321746826171875, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.0499, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": 11.641770362854004, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.0376, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7298245614035088, | |
| "grad_norm": 15.036391258239746, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.1732, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7859649122807018, | |
| "grad_norm": 10.391888618469238, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.0371, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 2.5320839881896973, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.9961, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8982456140350877, | |
| "grad_norm": 2.271365165710449, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.9803, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9543859649122807, | |
| "grad_norm": 3.9986636638641357, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.9929, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0456140350877192, | |
| "grad_norm": 12.490577697753906, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.1306, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1017543859649124, | |
| "grad_norm": 4.3462982177734375, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.9834, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1578947368421053, | |
| "grad_norm": 3.1821000576019287, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.975, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2140350877192982, | |
| "grad_norm": 2.209925413131714, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.9703, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2701754385964912, | |
| "grad_norm": 5.219216823577881, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.0513, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3263157894736843, | |
| "grad_norm": 4.299022674560547, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.9855, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3824561403508773, | |
| "grad_norm": 2.6355159282684326, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.9949, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4385964912280702, | |
| "grad_norm": 2.5065155029296875, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.9883, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4385964912280702, | |
| "eval_loss": 0.9844273924827576, | |
| "eval_runtime": 1.7474, | |
| "eval_samples_per_second": 68.672, | |
| "eval_steps_per_second": 8.584, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4947368421052631, | |
| "grad_norm": 2.8815419673919678, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9999, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.550877192982456, | |
| "grad_norm": 1.6184970140457153, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.9744, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.6070175438596492, | |
| "grad_norm": 1.700230598449707, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.9848, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.663157894736842, | |
| "grad_norm": 1.7157793045043945, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.9861, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.719298245614035, | |
| "grad_norm": 1.1912931203842163, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.9686, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.775438596491228, | |
| "grad_norm": 1.9062882661819458, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.0133, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.831578947368421, | |
| "grad_norm": 1.5787826776504517, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.9736, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.8877192982456141, | |
| "grad_norm": 3.0003042221069336, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.9805, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.943859649122807, | |
| "grad_norm": 1.2490260601043701, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.9748, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0350877192982457, | |
| "grad_norm": 5.135227203369141, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.8213, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.0912280701754384, | |
| "grad_norm": 1.504193663597107, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.9428, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.1473684210526316, | |
| "grad_norm": 1.865723729133606, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.9708, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.2035087719298247, | |
| "grad_norm": 1.2437411546707153, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9747, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.2596491228070175, | |
| "grad_norm": 3.998439073562622, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.0126, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.3157894736842106, | |
| "grad_norm": 1.3937028646469116, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.9638, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.3719298245614033, | |
| "grad_norm": 2.2477951049804688, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.9713, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.4280701754385965, | |
| "grad_norm": 1.3327833414077759, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.9563, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.4842105263157896, | |
| "grad_norm": 1.937410593032837, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.9716, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.5403508771929824, | |
| "grad_norm": 2.531614065170288, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.9813, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.5964912280701755, | |
| "grad_norm": 1.3599098920822144, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.9793, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.6526315789473687, | |
| "grad_norm": 1.3307596445083618, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.9686, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.7087719298245614, | |
| "grad_norm": 1.9670759439468384, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.955, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.7649122807017545, | |
| "grad_norm": 3.397104024887085, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.0066, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.8210526315789473, | |
| "grad_norm": 1.5758522748947144, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.9656, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.8771929824561404, | |
| "grad_norm": 1.1156949996948242, | |
| "learning_rate": 0.0, | |
| "loss": 0.9643, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.8771929824561404, | |
| "eval_loss": 0.9738476872444153, | |
| "eval_runtime": 1.7164, | |
| "eval_samples_per_second": 69.914, | |
| "eval_steps_per_second": 8.739, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 2.95300912644096e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |