| { | |
| "best_metric": 0.01188002061098814, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2700877785280216, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0054017555705604325, | |
| "grad_norm": 653.7743530273438, | |
| "learning_rate": 5e-05, | |
| "loss": 4.0694, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0054017555705604325, | |
| "eval_loss": 4.726553916931152, | |
| "eval_runtime": 80.4724, | |
| "eval_samples_per_second": 15.508, | |
| "eval_steps_per_second": 1.939, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010803511141120865, | |
| "grad_norm": 593.2535400390625, | |
| "learning_rate": 0.0001, | |
| "loss": 3.8202, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.016205266711681297, | |
| "grad_norm": 299.866455078125, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.6744, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02160702228224173, | |
| "grad_norm": 218.7953338623047, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.5998, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02700877785280216, | |
| "grad_norm": 129.4618682861328, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.0572, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03241053342336259, | |
| "grad_norm": 178.23435974121094, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.5582, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03781228899392303, | |
| "grad_norm": 240.6701202392578, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.5021, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04321404456448346, | |
| "grad_norm": 141.92623901367188, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3307, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.048615800135043886, | |
| "grad_norm": 76.09772491455078, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.1747, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05401755570560432, | |
| "grad_norm": 75.17802429199219, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.1691, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05941931127616475, | |
| "grad_norm": 106.91887664794922, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.2135, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06482106684672519, | |
| "grad_norm": 92.54069519042969, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.2522, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07022282241728561, | |
| "grad_norm": 101.89862823486328, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.4088, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07562457798784605, | |
| "grad_norm": 52.51350784301758, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1662, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08102633355840648, | |
| "grad_norm": 21.883590698242188, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0707, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.08642808912896692, | |
| "grad_norm": 18.014198303222656, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.0596, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09182984469952735, | |
| "grad_norm": 26.78334617614746, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0584, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.09723160027008777, | |
| "grad_norm": 11.612924575805664, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0334, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10263335584064821, | |
| "grad_norm": 9.027280807495117, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0207, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.10803511141120864, | |
| "grad_norm": 8.190865516662598, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.0211, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11343686698176908, | |
| "grad_norm": 12.227516174316406, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.0242, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1188386225523295, | |
| "grad_norm": 12.942814826965332, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.0298, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.12424037812288993, | |
| "grad_norm": 13.685553550720215, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.0202, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.12964213369345037, | |
| "grad_norm": 11.94351863861084, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.032, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1350438892640108, | |
| "grad_norm": 22.69659996032715, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.0494, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1350438892640108, | |
| "eval_loss": 0.04991535469889641, | |
| "eval_runtime": 80.4344, | |
| "eval_samples_per_second": 15.516, | |
| "eval_steps_per_second": 1.939, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14044564483457123, | |
| "grad_norm": 223.9273223876953, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2406, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.14584740040513167, | |
| "grad_norm": 78.22892761230469, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0674, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1512491559756921, | |
| "grad_norm": 17.89198875427246, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0211, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.15665091154625252, | |
| "grad_norm": 15.929986953735352, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0188, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.16205266711681296, | |
| "grad_norm": 19.84815788269043, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.0162, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1674544226873734, | |
| "grad_norm": 4.899456977844238, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.0031, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.17285617825793384, | |
| "grad_norm": 9.715526580810547, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.0146, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.17825793382849425, | |
| "grad_norm": 9.339546203613281, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.0049, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.1836596893990547, | |
| "grad_norm": 8.212912559509277, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0109, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.18906144496961513, | |
| "grad_norm": 5.0012640953063965, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.0204, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.19446320054017555, | |
| "grad_norm": 33.13603973388672, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.0668, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.199864956110736, | |
| "grad_norm": 15.623924255371094, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.0206, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.20526671168129643, | |
| "grad_norm": 35.061485290527344, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.0868, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.21066846725185687, | |
| "grad_norm": 5.114437580108643, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0084, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.21607022282241728, | |
| "grad_norm": 4.4656476974487305, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.003, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.22147197839297772, | |
| "grad_norm": 1.4544063806533813, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0029, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.22687373396353816, | |
| "grad_norm": 1.5238828659057617, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0007, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.23227548953409857, | |
| "grad_norm": 2.0525293350219727, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.001, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.237677245104659, | |
| "grad_norm": 3.363405227661133, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.0064, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.24307900067521945, | |
| "grad_norm": 2.430947780609131, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.005, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.24848075624577987, | |
| "grad_norm": 4.940511703491211, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.0045, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2538825118163403, | |
| "grad_norm": 6.3675947189331055, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.013, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.25928426738690075, | |
| "grad_norm": 4.924294471740723, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.0069, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2646860229574612, | |
| "grad_norm": 11.682531356811523, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.0093, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2700877785280216, | |
| "grad_norm": 14.576727867126465, | |
| "learning_rate": 0.0, | |
| "loss": 0.0438, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2700877785280216, | |
| "eval_loss": 0.01188002061098814, | |
| "eval_runtime": 80.4597, | |
| "eval_samples_per_second": 15.511, | |
| "eval_steps_per_second": 1.939, | |
| "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": 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": 5.658021338284032e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |