| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 0.11273957158962795, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002254791431792559, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002254791431792559, | |
| "eval_loss": NaN, | |
| "eval_runtime": 201.9202, | |
| "eval_samples_per_second": 14.798, | |
| "eval_steps_per_second": 1.852, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004509582863585118, | |
| "grad_norm": 0.0, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.006764374295377677, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009019165727170236, | |
| "grad_norm": 6.439255714416504, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.0658, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011273957158962795, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.013528748590755355, | |
| "grad_norm": 0.0, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.015783540022547914, | |
| "grad_norm": 13.426411628723145, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 6.6367, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.018038331454340473, | |
| "grad_norm": 14.613255500793457, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.8099, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.020293122886133032, | |
| "grad_norm": 15.032930374145508, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 9.2525, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02254791431792559, | |
| "grad_norm": 17.658451080322266, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 7.5193, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02480270574971815, | |
| "grad_norm": 16.159095764160156, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 6.0037, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.02705749718151071, | |
| "grad_norm": 13.322366714477539, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 4.3432, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.029312288613303268, | |
| "grad_norm": 11.127376556396484, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.6831, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03156708004509583, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.033821871476888386, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.036076662908680945, | |
| "grad_norm": 10.085834503173828, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.1855, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.038331454340473504, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.040586245772266064, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.04284103720405862, | |
| "grad_norm": 0.0, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.04509582863585118, | |
| "grad_norm": 25.233718872070312, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 5.9613, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04735062006764374, | |
| "grad_norm": 22.64263153076172, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 6.1834, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0496054114994363, | |
| "grad_norm": 14.661815643310547, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 4.6658, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.05186020293122886, | |
| "grad_norm": 15.324529647827148, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.5992, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.05411499436302142, | |
| "grad_norm": 13.3060884475708, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.7297, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.05636978579481398, | |
| "grad_norm": 8.085643768310547, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.9261, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05636978579481398, | |
| "eval_loss": NaN, | |
| "eval_runtime": 201.7596, | |
| "eval_samples_per_second": 14.81, | |
| "eval_steps_per_second": 1.854, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.058624577226606536, | |
| "grad_norm": 0.0, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.060879368658399095, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.06313416009019165, | |
| "grad_norm": 2.1285784244537354, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.0987, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.06538895152198422, | |
| "grad_norm": 0.0, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.06764374295377677, | |
| "grad_norm": 8.128816604614258, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.0764, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06989853438556934, | |
| "grad_norm": 8.919053077697754, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.7324, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.07215332581736189, | |
| "grad_norm": 10.01648998260498, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.172, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.07440811724915446, | |
| "grad_norm": 6.418951988220215, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.0659, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.07666290868094701, | |
| "grad_norm": 4.666852951049805, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.2771, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.07891770011273957, | |
| "grad_norm": 3.2862226963043213, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.1777, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.08117249154453213, | |
| "grad_norm": 2.7737483978271484, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.9861, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0834272829763247, | |
| "grad_norm": 3.1474602222442627, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.9087, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.08568207440811725, | |
| "grad_norm": 4.241426467895508, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.1816, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.08793686583990981, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.09019165727170236, | |
| "grad_norm": 0.0, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09244644870349493, | |
| "grad_norm": 0.0, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.09470124013528748, | |
| "grad_norm": 0.0, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.09695603156708005, | |
| "grad_norm": 4.324437618255615, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.6584, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0992108229988726, | |
| "grad_norm": 5.493435859680176, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8257, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.10146561443066517, | |
| "grad_norm": 6.390080451965332, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.1197, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.10372040586245772, | |
| "grad_norm": 3.0929791927337646, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.0103, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.10597519729425028, | |
| "grad_norm": 2.387812376022339, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.7846, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.10822998872604284, | |
| "grad_norm": 2.138292074203491, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.9271, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1104847801578354, | |
| "grad_norm": 2.3450963497161865, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.51, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.11273957158962795, | |
| "grad_norm": 2.4274940490722656, | |
| "learning_rate": 0.0, | |
| "loss": 1.7368, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11273957158962795, | |
| "eval_loss": NaN, | |
| "eval_runtime": 201.7805, | |
| "eval_samples_per_second": 14.808, | |
| "eval_steps_per_second": 1.853, | |
| "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": 1 | |
| } | |
| }, | |
| "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 | |
| } | |