| { | |
| "best_metric": 1.4909886121749878, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.13828867761452032, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002765773552290406, | |
| "grad_norm": 7.74644660949707, | |
| "learning_rate": 5e-05, | |
| "loss": 3.7525, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002765773552290406, | |
| "eval_loss": 6.271673202514648, | |
| "eval_runtime": 167.7197, | |
| "eval_samples_per_second": 14.524, | |
| "eval_steps_per_second": 1.819, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005531547104580812, | |
| "grad_norm": 8.671770095825195, | |
| "learning_rate": 0.0001, | |
| "loss": 3.9867, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00829732065687122, | |
| "grad_norm": 7.7077717781066895, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 3.9001, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.011063094209161625, | |
| "grad_norm": 4.913783073425293, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.2398, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.013828867761452032, | |
| "grad_norm": 7.3940653800964355, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.8743, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01659464131374244, | |
| "grad_norm": 5.659930229187012, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.719, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.019360414866032842, | |
| "grad_norm": 6.561766147613525, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.712, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02212618841832325, | |
| "grad_norm": 6.276236057281494, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.7624, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.024891961970613656, | |
| "grad_norm": 4.224053859710693, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.3442, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.027657735522904063, | |
| "grad_norm": 5.290657043457031, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.1353, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03042350907519447, | |
| "grad_norm": 5.441473007202148, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.0582, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03318928262748488, | |
| "grad_norm": 5.823805332183838, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.8597, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.035955056179775284, | |
| "grad_norm": 5.8297438621521, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.9792, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.038720829732065684, | |
| "grad_norm": 3.249824285507202, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8443, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04148660328435609, | |
| "grad_norm": 2.8901705741882324, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.7674, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0442523768366465, | |
| "grad_norm": 3.005765438079834, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.8365, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.047018150388936905, | |
| "grad_norm": 2.9200236797332764, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.8778, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.04978392394122731, | |
| "grad_norm": 2.5125443935394287, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.8721, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.05254969749351772, | |
| "grad_norm": 3.8412601947784424, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.8064, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.055315471045808126, | |
| "grad_norm": 3.584010124206543, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6176, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05808124459809853, | |
| "grad_norm": 3.3721632957458496, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.6571, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06084701815038894, | |
| "grad_norm": 3.820169448852539, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.8113, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.06361279170267935, | |
| "grad_norm": 4.488033294677734, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5862, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06637856525496975, | |
| "grad_norm": 4.486863613128662, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.6111, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.06914433880726016, | |
| "grad_norm": 6.375380516052246, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.6642, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.06914433880726016, | |
| "eval_loss": 1.6207541227340698, | |
| "eval_runtime": 168.5461, | |
| "eval_samples_per_second": 14.453, | |
| "eval_steps_per_second": 1.81, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07191011235955057, | |
| "grad_norm": 2.3166110515594482, | |
| "learning_rate": 5e-05, | |
| "loss": 1.6658, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.07467588591184096, | |
| "grad_norm": 2.2079741954803467, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.5891, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07744165946413137, | |
| "grad_norm": 2.1089913845062256, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.611, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.08020743301642178, | |
| "grad_norm": 2.063892126083374, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.6323, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.08297320656871218, | |
| "grad_norm": 2.1836607456207275, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.5434, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08573898012100259, | |
| "grad_norm": 2.6283938884735107, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.6996, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.088504753673293, | |
| "grad_norm": 2.6632418632507324, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.7309, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0912705272255834, | |
| "grad_norm": 2.8932669162750244, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.6558, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.09403630077787381, | |
| "grad_norm": 3.0536949634552, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.6094, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.09680207433016422, | |
| "grad_norm": 3.8116891384124756, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.6626, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09956784788245462, | |
| "grad_norm": 4.177957057952881, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.2707, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.10233362143474503, | |
| "grad_norm": 5.071949005126953, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.4014, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.10509939498703544, | |
| "grad_norm": 2.227691888809204, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.526, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.10786516853932585, | |
| "grad_norm": 1.9869389533996582, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.5391, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.11063094209161625, | |
| "grad_norm": 1.6682724952697754, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.4795, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11339671564390666, | |
| "grad_norm": 1.789174199104309, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.5158, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.11616248919619707, | |
| "grad_norm": 1.8229426145553589, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.545, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.11892826274848747, | |
| "grad_norm": 2.1133134365081787, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.4575, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.12169403630077788, | |
| "grad_norm": 2.527867317199707, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.6157, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.12445980985306827, | |
| "grad_norm": 2.451172113418579, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.655, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1272255834053587, | |
| "grad_norm": 2.618565082550049, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.4986, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1299913569576491, | |
| "grad_norm": 2.9134609699249268, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.4604, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.1327571305099395, | |
| "grad_norm": 3.504913568496704, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.4817, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.13552290406222992, | |
| "grad_norm": 4.311337471008301, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.1932, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.13828867761452032, | |
| "grad_norm": 4.128970623016357, | |
| "learning_rate": 0.0, | |
| "loss": 1.1704, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13828867761452032, | |
| "eval_loss": 1.4909886121749878, | |
| "eval_runtime": 168.4634, | |
| "eval_samples_per_second": 14.46, | |
| "eval_steps_per_second": 1.81, | |
| "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": 6.174479344467968e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |