| { | |
| "best_metric": 1.6797080039978027, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.09363295880149813, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018726591760299626, | |
| "grad_norm": 1.7517485618591309, | |
| "learning_rate": 5e-05, | |
| "loss": 4.2167, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018726591760299626, | |
| "eval_loss": 5.32598352432251, | |
| "eval_runtime": 242.9608, | |
| "eval_samples_per_second": 14.809, | |
| "eval_steps_per_second": 1.852, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003745318352059925, | |
| "grad_norm": 2.233262777328491, | |
| "learning_rate": 0.0001, | |
| "loss": 4.7102, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0056179775280898875, | |
| "grad_norm": 2.4297382831573486, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.8826, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00749063670411985, | |
| "grad_norm": 3.3503963947296143, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.4998, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009363295880149813, | |
| "grad_norm": 3.326855421066284, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.9762, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011235955056179775, | |
| "grad_norm": 5.497750759124756, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.4664, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013108614232209739, | |
| "grad_norm": 3.591024398803711, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.8895, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0149812734082397, | |
| "grad_norm": 3.615856647491455, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.6043, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.016853932584269662, | |
| "grad_norm": 2.7465076446533203, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.3626, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018726591760299626, | |
| "grad_norm": 3.563035011291504, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.0889, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.020599250936329586, | |
| "grad_norm": 2.8092472553253174, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.9644, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02247191011235955, | |
| "grad_norm": 2.3839683532714844, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.8961, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.024344569288389514, | |
| "grad_norm": 2.2432806491851807, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.0467, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.026217228464419477, | |
| "grad_norm": 1.7278889417648315, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.9476, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.028089887640449437, | |
| "grad_norm": 1.5298266410827637, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.9927, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0299625468164794, | |
| "grad_norm": 1.4526454210281372, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.8496, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.031835205992509365, | |
| "grad_norm": 1.2890679836273193, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.7717, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.033707865168539325, | |
| "grad_norm": 1.2238835096359253, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.8753, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.035580524344569285, | |
| "grad_norm": 1.2657208442687988, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.6777, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03745318352059925, | |
| "grad_norm": 1.1719173192977905, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6835, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03932584269662921, | |
| "grad_norm": 1.0336369276046753, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.7054, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.04119850187265917, | |
| "grad_norm": 1.1664713621139526, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.6424, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.04307116104868914, | |
| "grad_norm": 1.1926559209823608, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.6149, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0449438202247191, | |
| "grad_norm": 1.1861246824264526, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.6253, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04681647940074907, | |
| "grad_norm": 1.3473325967788696, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.5603, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04681647940074907, | |
| "eval_loss": 1.7174628973007202, | |
| "eval_runtime": 242.9675, | |
| "eval_samples_per_second": 14.809, | |
| "eval_steps_per_second": 1.852, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04868913857677903, | |
| "grad_norm": 2.2478160858154297, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0625, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05056179775280899, | |
| "grad_norm": 1.5112407207489014, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.8351, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.052434456928838954, | |
| "grad_norm": 1.1244219541549683, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.7192, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.054307116104868915, | |
| "grad_norm": 1.005778431892395, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.685, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.056179775280898875, | |
| "grad_norm": 0.9678806662559509, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.6409, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05805243445692884, | |
| "grad_norm": 1.0039587020874023, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.6625, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0599250936329588, | |
| "grad_norm": 1.1212393045425415, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.5962, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06179775280898876, | |
| "grad_norm": 1.1912685632705688, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.5737, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06367041198501873, | |
| "grad_norm": 1.0543924570083618, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.6632, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06554307116104868, | |
| "grad_norm": 1.2754708528518677, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.5752, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.06741573033707865, | |
| "grad_norm": 1.1570887565612793, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.5309, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.06928838951310862, | |
| "grad_norm": 1.335957646369934, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.5368, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.07116104868913857, | |
| "grad_norm": 1.1365514993667603, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.8507, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07303370786516854, | |
| "grad_norm": 1.1642248630523682, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.7966, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0749063670411985, | |
| "grad_norm": 1.0239207744598389, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.6646, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07677902621722846, | |
| "grad_norm": 1.0390326976776123, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.7976, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.07865168539325842, | |
| "grad_norm": 0.9292603731155396, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.6664, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08052434456928839, | |
| "grad_norm": 0.9708360433578491, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.6991, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08239700374531835, | |
| "grad_norm": 0.917884349822998, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.6031, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08426966292134831, | |
| "grad_norm": 0.955154538154602, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.7643, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08614232209737828, | |
| "grad_norm": 0.9974094033241272, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.597, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.08801498127340825, | |
| "grad_norm": 0.9787687063217163, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.618, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0898876404494382, | |
| "grad_norm": 0.9520777463912964, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.6154, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.09176029962546817, | |
| "grad_norm": 1.1157002449035645, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.6452, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.09363295880149813, | |
| "grad_norm": 1.192071557044983, | |
| "learning_rate": 0.0, | |
| "loss": 1.5853, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09363295880149813, | |
| "eval_loss": 1.6797080039978027, | |
| "eval_runtime": 243.0062, | |
| "eval_samples_per_second": 14.806, | |
| "eval_steps_per_second": 1.852, | |
| "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": 5.968083617316864e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |