| { | |
| "best_metric": NaN, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.23856858846918488, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0031809145129224653, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-06, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031809145129224653, | |
| "eval_loss": NaN, | |
| "eval_runtime": 75.8185, | |
| "eval_samples_per_second": 6.99, | |
| "eval_steps_per_second": 1.754, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006361829025844931, | |
| "grad_norm": NaN, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.009542743538767396, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.012723658051689861, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.015904572564612324, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.5e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.019085487077534793, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.022266401590457258, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.5e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.025447316103379723, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.028628230616302187, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03180914512922465, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03499005964214712, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.038170974155069586, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04135188866799205, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.044532803180914515, | |
| "grad_norm": NaN, | |
| "learning_rate": 7e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.04771371769383698, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.050894632206759445, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.054075546719681906, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.057256461232604375, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.060437375745526836, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0636182902584493, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06679920477137177, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.06998011928429423, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0731610337972167, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07634194831013917, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.07952286282306163, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0827037773359841, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08588469184890656, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.08906560636182903, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09224652087475149, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09542743538767395, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09860834990059641, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.10178926441351889, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.10497017892644135, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.10815109343936381, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11133200795228629, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11451292246520875, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.11769383697813121, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12087475149105367, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12405566600397615, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1272365805168986, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13041749502982108, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13359840954274355, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.136779324055666, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.13996023856858847, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14314115308151093, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.1463220675944334, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.14950298210735585, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15268389662027834, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1558648111332008, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.15904572564612326, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.15904572564612326, | |
| "eval_loss": NaN, | |
| "eval_runtime": 76.0843, | |
| "eval_samples_per_second": 6.966, | |
| "eval_steps_per_second": 1.748, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16222664015904573, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.1654075546719682, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.16858846918489065, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.0, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.1717693836978131, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.1749502982107356, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 0.0, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.17813121272365806, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 0.0, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.18131212723658052, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.18449304174950298, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 0.0, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.18767395626242545, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 0.0, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.1908548707753479, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.19403578528827037, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 0.0, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.19721669980119283, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 0.0, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.20039761431411532, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.20357852882703778, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.0, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.20675944333996024, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 0.0, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2099403578528827, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.21312127236580516, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 0.0, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.21630218687872763, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 0.0, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.2194831013916501, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.22266401590457258, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.22584493041749504, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 0.0, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.2290258449304175, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.23220675944333996, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 0.0, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.23538767395626242, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 0.0, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.23856858846918488, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 75 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 2.147424726417408e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |