| { | |
| "best_metric": 2.8776087760925293, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03696345238645289, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007392690477290579, | |
| "grad_norm": 0.6081264019012451, | |
| "learning_rate": 5e-05, | |
| "loss": 3.1577, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007392690477290579, | |
| "eval_loss": 4.195895195007324, | |
| "eval_runtime": 969.06, | |
| "eval_samples_per_second": 9.404, | |
| "eval_steps_per_second": 1.176, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014785380954581157, | |
| "grad_norm": 0.9309924840927124, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4383, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0022178071431871735, | |
| "grad_norm": 0.5503907203674316, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.5455, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0029570761909162315, | |
| "grad_norm": 0.7579587697982788, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.5382, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0036963452386452895, | |
| "grad_norm": 1.0003035068511963, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.6219, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004435614286374347, | |
| "grad_norm": 1.165474772453308, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.6023, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0051748833341034054, | |
| "grad_norm": 1.2234491109848022, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.6794, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005914152381832463, | |
| "grad_norm": 1.4161816835403442, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.6668, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.006653421429561521, | |
| "grad_norm": 1.5868772268295288, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 3.6169, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007392690477290579, | |
| "grad_norm": 1.3991680145263672, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 3.6064, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008131959525019637, | |
| "grad_norm": 1.551560401916504, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.844, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.008871228572748694, | |
| "grad_norm": 2.185145616531372, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.8718, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.009610497620477753, | |
| "grad_norm": 0.964591920375824, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.7685, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.010349766668206811, | |
| "grad_norm": 1.0235710144042969, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.8684, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011089035715935868, | |
| "grad_norm": 0.9440206289291382, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.8124, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.011828304763664926, | |
| "grad_norm": 0.5510419607162476, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.8748, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.012567573811393984, | |
| "grad_norm": 0.4680745005607605, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.9763, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.013306842859123043, | |
| "grad_norm": 0.6219832301139832, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.9339, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0140461119068521, | |
| "grad_norm": 1.7636165618896484, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.9163, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.014785380954581158, | |
| "grad_norm": 2.6265430450439453, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.0557, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.015524650002310215, | |
| "grad_norm": 4.389255523681641, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.1214, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.016263919050039273, | |
| "grad_norm": 4.146439075469971, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.1418, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.01700318809776833, | |
| "grad_norm": 3.0236587524414062, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.283, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.017742457145497388, | |
| "grad_norm": 4.432220935821533, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.3437, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.018481726193226446, | |
| "grad_norm": 9.338114738464355, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.4673, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.018481726193226446, | |
| "eval_loss": 2.9710018634796143, | |
| "eval_runtime": 969.1531, | |
| "eval_samples_per_second": 9.403, | |
| "eval_steps_per_second": 1.176, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.019220995240955507, | |
| "grad_norm": 0.4898509681224823, | |
| "learning_rate": 5e-05, | |
| "loss": 2.6365, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.019960264288684564, | |
| "grad_norm": 0.6298810243606567, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.6809, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.020699533336413622, | |
| "grad_norm": 0.39488282799720764, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.7452, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.02143880238414268, | |
| "grad_norm": 0.5900229811668396, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.7869, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.022178071431871737, | |
| "grad_norm": 0.4614380896091461, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.8356, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.022917340479600794, | |
| "grad_norm": 0.3697441816329956, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.8268, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.023656609527329852, | |
| "grad_norm": 0.3978196084499359, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.8809, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.02439587857505891, | |
| "grad_norm": 0.44170308113098145, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.9129, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.025135147622787967, | |
| "grad_norm": 0.563273549079895, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.0687, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.025874416670517025, | |
| "grad_norm": 0.7094810009002686, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 3.0865, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.026613685718246086, | |
| "grad_norm": 0.7585165500640869, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 3.0847, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.027352954765975143, | |
| "grad_norm": 1.6270757913589478, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 3.1534, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0280922238137042, | |
| "grad_norm": 0.6695430278778076, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.5163, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02883149286143326, | |
| "grad_norm": 0.613318145275116, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.642, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.029570761909162316, | |
| "grad_norm": 0.6652768850326538, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.6482, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.030310030956891373, | |
| "grad_norm": 0.6474655270576477, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.7102, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03104930000462043, | |
| "grad_norm": 0.7044395208358765, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.7681, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03178856905234949, | |
| "grad_norm": 0.558677077293396, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.8322, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.032527838100078546, | |
| "grad_norm": 0.5612611770629883, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.8228, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.033267107147807604, | |
| "grad_norm": 0.3718057870864868, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.9401, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03400637619553666, | |
| "grad_norm": 0.5113263726234436, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 3.0313, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03474564524326572, | |
| "grad_norm": 0.666543185710907, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.9171, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.035484914290994776, | |
| "grad_norm": 0.9058085083961487, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 3.0978, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.036224183338723834, | |
| "grad_norm": 0.7812164425849915, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 3.1293, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03696345238645289, | |
| "grad_norm": 2.9717793464660645, | |
| "learning_rate": 0.0, | |
| "loss": 3.3199, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03696345238645289, | |
| "eval_loss": 2.8776087760925293, | |
| "eval_runtime": 969.1036, | |
| "eval_samples_per_second": 9.404, | |
| "eval_steps_per_second": 1.176, | |
| "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": 1.0228361536208896e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |