| { | |
| "best_metric": 0.24364762008190155, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 2.856140350877193, | |
| "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": 0.5651276707649231, | |
| "learning_rate": 5e-05, | |
| "loss": 1.4725, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.056140350877192984, | |
| "eval_loss": 1.7714346647262573, | |
| "eval_runtime": 1.3479, | |
| "eval_samples_per_second": 89.029, | |
| "eval_steps_per_second": 11.129, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11228070175438597, | |
| "grad_norm": 0.6416943669319153, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6539, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.16842105263157894, | |
| "grad_norm": 0.6658276915550232, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.7257, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.22456140350877193, | |
| "grad_norm": 0.8303353786468506, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.0857, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2807017543859649, | |
| "grad_norm": 0.5310768485069275, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.2739, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3368421052631579, | |
| "grad_norm": 0.5690150856971741, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.2439, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3929824561403509, | |
| "grad_norm": 0.6279029846191406, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.1812, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.44912280701754387, | |
| "grad_norm": 0.9386560320854187, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.304, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5052631578947369, | |
| "grad_norm": 0.7043356895446777, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.8478, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5614035087719298, | |
| "grad_norm": 1.41144597530365, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.7629, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.6175438596491228, | |
| "grad_norm": 0.870070219039917, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.6928, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6736842105263158, | |
| "grad_norm": 0.7913166284561157, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6501, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7298245614035088, | |
| "grad_norm": 0.7600938081741333, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5388, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7859649122807018, | |
| "grad_norm": 0.6539992094039917, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4374, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.864997923374176, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4098, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.8982456140350877, | |
| "grad_norm": 0.3268994987010956, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.3976, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9543859649122807, | |
| "grad_norm": 0.32331573963165283, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.3891, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.0350877192982457, | |
| "grad_norm": 0.33268672227859497, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5223, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.0912280701754387, | |
| "grad_norm": 0.17669150233268738, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.3078, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1473684210526316, | |
| "grad_norm": 0.17232191562652588, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.3084, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2035087719298245, | |
| "grad_norm": 0.19485709071159363, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.3945, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2596491228070175, | |
| "grad_norm": 0.14998270571231842, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.2605, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3157894736842106, | |
| "grad_norm": 0.14380517601966858, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.3034, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3719298245614036, | |
| "grad_norm": 0.12622232735157013, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.2755, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4280701754385965, | |
| "grad_norm": 0.15098120272159576, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.3322, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4280701754385965, | |
| "eval_loss": 0.2937827408313751, | |
| "eval_runtime": 1.3438, | |
| "eval_samples_per_second": 89.301, | |
| "eval_steps_per_second": 11.163, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4842105263157894, | |
| "grad_norm": 0.14724570512771606, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2336, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5403508771929824, | |
| "grad_norm": 0.1329941749572754, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.2956, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.5964912280701755, | |
| "grad_norm": 0.12431260943412781, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.2782, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.6526315789473685, | |
| "grad_norm": 0.14311625063419342, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.3268, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7087719298245614, | |
| "grad_norm": 0.15831390023231506, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.2467, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7649122807017545, | |
| "grad_norm": 0.13795287907123566, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.2934, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.8210526315789473, | |
| "grad_norm": 0.135288804769516, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.259, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.8771929824561404, | |
| "grad_norm": 0.1479368656873703, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.2468, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.9333333333333333, | |
| "grad_norm": 0.17140528559684753, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.3291, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0140350877192983, | |
| "grad_norm": 0.23568753898143768, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4309, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.0701754385964914, | |
| "grad_norm": 0.1325768381357193, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.2595, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.126315789473684, | |
| "grad_norm": 0.14927180111408234, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.2653, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.1824561403508773, | |
| "grad_norm": 0.1620611846446991, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.2591, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.23859649122807, | |
| "grad_norm": 0.17460227012634277, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.2285, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.294736842105263, | |
| "grad_norm": 0.1393241584300995, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.2285, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.3508771929824563, | |
| "grad_norm": 0.14091889560222626, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.2552, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.407017543859649, | |
| "grad_norm": 0.15764474868774414, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.2962, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.463157894736842, | |
| "grad_norm": 0.16738121211528778, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.2559, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.519298245614035, | |
| "grad_norm": 0.138456791639328, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.2269, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.575438596491228, | |
| "grad_norm": 0.1286228895187378, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.2557, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.6315789473684212, | |
| "grad_norm": 0.13272061944007874, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.1985, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.687719298245614, | |
| "grad_norm": 0.1482582837343216, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.2735, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.743859649122807, | |
| "grad_norm": 0.14489953219890594, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.2213, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.8, | |
| "grad_norm": 0.12907636165618896, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.2865, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.856140350877193, | |
| "grad_norm": 0.13516248762607574, | |
| "learning_rate": 0.0, | |
| "loss": 0.2261, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.856140350877193, | |
| "eval_loss": 0.24364762008190155, | |
| "eval_runtime": 1.3454, | |
| "eval_samples_per_second": 89.192, | |
| "eval_steps_per_second": 11.149, | |
| "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": 1.059536353886208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |