| { | |
| "best_metric": 0.48388004302978516, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.7850834151128557, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.015701668302257114, | |
| "grad_norm": 174.0449981689453, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8636, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.015701668302257114, | |
| "eval_loss": 2.6159276962280273, | |
| "eval_runtime": 36.7437, | |
| "eval_samples_per_second": 11.703, | |
| "eval_steps_per_second": 1.47, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03140333660451423, | |
| "grad_norm": 532.1987915039062, | |
| "learning_rate": 0.0001, | |
| "loss": 4.8384, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.047105004906771344, | |
| "grad_norm": 331.0499267578125, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.6012, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.06280667320902845, | |
| "grad_norm": 2862.966552734375, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 7.5431, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.07850834151128558, | |
| "grad_norm": 347.0616760253906, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.8474, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09421000981354269, | |
| "grad_norm": 279.2650146484375, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.6665, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1099116781157998, | |
| "grad_norm": 175.72076416015625, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.3088, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1256133464180569, | |
| "grad_norm": 103.9676284790039, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9821, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.14131501472031405, | |
| "grad_norm": 86.11383056640625, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.784, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.15701668302257116, | |
| "grad_norm": 75.49951171875, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.755, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17271835132482827, | |
| "grad_norm": 90.43276977539062, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.7398, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.18842001962708538, | |
| "grad_norm": 99.68488311767578, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.8248, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2041216879293425, | |
| "grad_norm": 62.287628173828125, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.8065, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2198233562315996, | |
| "grad_norm": 79.25579833984375, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.2336, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.23552502453385674, | |
| "grad_norm": 166.92649841308594, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.0317, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.2512266928361138, | |
| "grad_norm": 49.47351837158203, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5492, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.26692836113837093, | |
| "grad_norm": 106.59893035888672, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.5018, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2826300294406281, | |
| "grad_norm": 61.971343994140625, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5298, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2983316977428852, | |
| "grad_norm": 35.90945053100586, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4862, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.3140333660451423, | |
| "grad_norm": 37.26945495605469, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4935, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3297350343473994, | |
| "grad_norm": 46.713462829589844, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.5518, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.34543670264965654, | |
| "grad_norm": 32.227813720703125, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.599, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.36113837095191365, | |
| "grad_norm": 27.146421432495117, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4932, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.37684003925417076, | |
| "grad_norm": 34.5018424987793, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5336, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.39254170755642787, | |
| "grad_norm": 27.01970100402832, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5115, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.39254170755642787, | |
| "eval_loss": 0.5895436406135559, | |
| "eval_runtime": 37.3927, | |
| "eval_samples_per_second": 11.5, | |
| "eval_steps_per_second": 1.444, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.408243375858685, | |
| "grad_norm": 40.40184020996094, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8247, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.4239450441609421, | |
| "grad_norm": 101.7075424194336, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.3856, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.4396467124631992, | |
| "grad_norm": 111.83171081542969, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.4514, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.4553483807654563, | |
| "grad_norm": 39.55173110961914, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4639, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.47105004906771347, | |
| "grad_norm": 39.32386016845703, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5265, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.4867517173699706, | |
| "grad_norm": 31.605382919311523, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.4166, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.5024533856722276, | |
| "grad_norm": 28.2354679107666, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4493, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.5181550539744848, | |
| "grad_norm": 28.89419937133789, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4812, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.5338567222767419, | |
| "grad_norm": 26.995038986206055, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.4926, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.549558390578999, | |
| "grad_norm": 23.987627029418945, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4807, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.5652600588812562, | |
| "grad_norm": 26.026025772094727, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.5032, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.5809617271835132, | |
| "grad_norm": 26.77385902404785, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.5171, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.5966633954857704, | |
| "grad_norm": 21.197858810424805, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.6065, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.6123650637880275, | |
| "grad_norm": 52.91826629638672, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.6893, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.6280667320902846, | |
| "grad_norm": 115.2632064819336, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.0878, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6437684003925417, | |
| "grad_norm": 30.022024154663086, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.4786, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.6594700686947988, | |
| "grad_norm": 31.854766845703125, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4419, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.6751717369970559, | |
| "grad_norm": 33.38142013549805, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4767, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.6908734052993131, | |
| "grad_norm": 28.41339683532715, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4209, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.7065750736015701, | |
| "grad_norm": 28.06477928161621, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4269, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7222767419038273, | |
| "grad_norm": 39.25811767578125, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.525, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.7379784102060843, | |
| "grad_norm": 29.17804718017578, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4483, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.7536800785083415, | |
| "grad_norm": 37.1457633972168, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5176, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.7693817468105987, | |
| "grad_norm": 31.742942810058594, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4955, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.7850834151128557, | |
| "grad_norm": 21.142356872558594, | |
| "learning_rate": 0.0, | |
| "loss": 0.4903, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.7850834151128557, | |
| "eval_loss": 0.48388004302978516, | |
| "eval_runtime": 36.7238, | |
| "eval_samples_per_second": 11.709, | |
| "eval_steps_per_second": 1.47, | |
| "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": 6.715371720246559e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |