| { | |
| "best_metric": 1.3463674783706665, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.4711425206124853, | |
| "eval_steps": 50, | |
| "global_step": 75, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006281900274833137, | |
| "grad_norm": 1.037642478942871, | |
| "learning_rate": 5e-06, | |
| "loss": 2.2468, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006281900274833137, | |
| "eval_loss": 2.3963544368743896, | |
| "eval_runtime": 32.6808, | |
| "eval_samples_per_second": 16.432, | |
| "eval_steps_per_second": 4.131, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012563800549666274, | |
| "grad_norm": 1.0863330364227295, | |
| "learning_rate": 1e-05, | |
| "loss": 2.3981, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01884570082449941, | |
| "grad_norm": 1.1037417650222778, | |
| "learning_rate": 1.5e-05, | |
| "loss": 2.3267, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02512760109933255, | |
| "grad_norm": 1.0553061962127686, | |
| "learning_rate": 2e-05, | |
| "loss": 2.2436, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.031409501374165684, | |
| "grad_norm": 1.052477478981018, | |
| "learning_rate": 2.5e-05, | |
| "loss": 2.367, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03769140164899882, | |
| "grad_norm": 1.0440304279327393, | |
| "learning_rate": 3e-05, | |
| "loss": 2.3552, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04397330192383196, | |
| "grad_norm": 1.0473334789276123, | |
| "learning_rate": 3.5e-05, | |
| "loss": 2.1681, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0502552021986651, | |
| "grad_norm": 1.0033868551254272, | |
| "learning_rate": 4e-05, | |
| "loss": 2.2929, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05653710247349823, | |
| "grad_norm": 1.0094962120056152, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.9839, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06281900274833137, | |
| "grad_norm": 0.9697522521018982, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0231, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0691009030231645, | |
| "grad_norm": 0.8718522787094116, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.9849, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07538280329799764, | |
| "grad_norm": 0.8731445670127869, | |
| "learning_rate": 6e-05, | |
| "loss": 1.7192, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08166470357283079, | |
| "grad_norm": 0.9176603555679321, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 1.909, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08794660384766392, | |
| "grad_norm": 0.8371685147285461, | |
| "learning_rate": 7e-05, | |
| "loss": 1.7724, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09422850412249706, | |
| "grad_norm": 0.8415525555610657, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.7574, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1005104043973302, | |
| "grad_norm": 0.9621779918670654, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7758, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.10679230467216333, | |
| "grad_norm": 0.7966982126235962, | |
| "learning_rate": 8.5e-05, | |
| "loss": 1.5015, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.11307420494699646, | |
| "grad_norm": 0.8985989689826965, | |
| "learning_rate": 9e-05, | |
| "loss": 1.5494, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1193561052218296, | |
| "grad_norm": 1.0344613790512085, | |
| "learning_rate": 9.5e-05, | |
| "loss": 1.588, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12563800549666274, | |
| "grad_norm": 1.0213881731033325, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4406, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.13191990577149587, | |
| "grad_norm": 0.8588016629219055, | |
| "learning_rate": 9.991845519630678e-05, | |
| "loss": 1.5676, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.138201806046329, | |
| "grad_norm": 0.7644623517990112, | |
| "learning_rate": 9.967408676742751e-05, | |
| "loss": 1.4261, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.14448370632116214, | |
| "grad_norm": 0.7431595921516418, | |
| "learning_rate": 9.926769179238466e-05, | |
| "loss": 1.4965, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.15076560659599528, | |
| "grad_norm": 0.7623801231384277, | |
| "learning_rate": 9.870059584711668e-05, | |
| "loss": 1.6151, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1570475068708284, | |
| "grad_norm": 0.7178940176963806, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 1.4764, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.16332940714566158, | |
| "grad_norm": 0.7043237686157227, | |
| "learning_rate": 9.709221818197624e-05, | |
| "loss": 1.5826, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1696113074204947, | |
| "grad_norm": 0.6355712413787842, | |
| "learning_rate": 9.60561826557425e-05, | |
| "loss": 1.4794, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.17589320769532785, | |
| "grad_norm": 0.6077854037284851, | |
| "learning_rate": 9.486992143456792e-05, | |
| "loss": 1.3568, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.18217510797016098, | |
| "grad_norm": 0.5768811106681824, | |
| "learning_rate": 9.353730385598887e-05, | |
| "loss": 1.3681, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.18845700824499412, | |
| "grad_norm": 0.5613104104995728, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 1.4133, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.19473890851982725, | |
| "grad_norm": 0.5721055865287781, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.4098, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.2010208087946604, | |
| "grad_norm": 0.6311193704605103, | |
| "learning_rate": 8.870708053195413e-05, | |
| "loss": 1.4254, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.20730270906949352, | |
| "grad_norm": 0.5429511666297913, | |
| "learning_rate": 8.683705689382024e-05, | |
| "loss": 1.4064, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.21358460934432666, | |
| "grad_norm": 0.5543144941329956, | |
| "learning_rate": 8.484687843276469e-05, | |
| "loss": 1.4557, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2198665096191598, | |
| "grad_norm": 0.521620512008667, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 1.3159, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.22614840989399293, | |
| "grad_norm": 0.4960021376609802, | |
| "learning_rate": 8.053239398177191e-05, | |
| "loss": 1.2849, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.23243031016882607, | |
| "grad_norm": 0.5216634273529053, | |
| "learning_rate": 7.822216094333847e-05, | |
| "loss": 1.3142, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2387122104436592, | |
| "grad_norm": 0.5064031481742859, | |
| "learning_rate": 7.58198730819481e-05, | |
| "loss": 1.2846, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.24499411071849234, | |
| "grad_norm": 0.5212217569351196, | |
| "learning_rate": 7.333336616128369e-05, | |
| "loss": 1.4381, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.25127601099332547, | |
| "grad_norm": 0.5218945145606995, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 1.3367, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.25755791126815863, | |
| "grad_norm": 0.5242222547531128, | |
| "learning_rate": 6.814038526753205e-05, | |
| "loss": 1.3794, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.26383981154299174, | |
| "grad_norm": 0.486794650554657, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 1.2687, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2701217118178249, | |
| "grad_norm": 0.5205053687095642, | |
| "learning_rate": 6.271091670967436e-05, | |
| "loss": 1.3569, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.276403612092658, | |
| "grad_norm": 0.544700026512146, | |
| "learning_rate": 5.992952333228728e-05, | |
| "loss": 1.2452, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2826855123674912, | |
| "grad_norm": 0.5707914233207703, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 1.3934, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2889674126423243, | |
| "grad_norm": 0.5490149259567261, | |
| "learning_rate": 5.427875042394199e-05, | |
| "loss": 1.3167, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.29524931291715745, | |
| "grad_norm": 0.5302465558052063, | |
| "learning_rate": 5.142780253968481e-05, | |
| "loss": 1.3685, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.30153121319199055, | |
| "grad_norm": 0.5523501634597778, | |
| "learning_rate": 4.85721974603152e-05, | |
| "loss": 1.4518, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3078131134668237, | |
| "grad_norm": 0.5642591714859009, | |
| "learning_rate": 4.5721249576058027e-05, | |
| "loss": 1.4912, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3140950137416568, | |
| "grad_norm": 0.5464029312133789, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 1.3089, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3140950137416568, | |
| "eval_loss": 1.3463674783706665, | |
| "eval_runtime": 32.641, | |
| "eval_samples_per_second": 16.452, | |
| "eval_steps_per_second": 4.136, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.32037691401649, | |
| "grad_norm": 0.5381672382354736, | |
| "learning_rate": 4.007047666771274e-05, | |
| "loss": 1.3637, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.32665881429132315, | |
| "grad_norm": 0.5182757377624512, | |
| "learning_rate": 3.728908329032567e-05, | |
| "loss": 1.2958, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.33294071456615626, | |
| "grad_norm": 0.5560421347618103, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.362, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.3392226148409894, | |
| "grad_norm": 0.5303387641906738, | |
| "learning_rate": 3.1859614732467954e-05, | |
| "loss": 1.3819, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.34550451511582253, | |
| "grad_norm": 0.5558652877807617, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 1.4103, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3517864153906557, | |
| "grad_norm": 0.5830622315406799, | |
| "learning_rate": 2.6666633838716314e-05, | |
| "loss": 1.3872, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.3580683156654888, | |
| "grad_norm": 0.534251868724823, | |
| "learning_rate": 2.418012691805191e-05, | |
| "loss": 1.2987, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.36435021594032196, | |
| "grad_norm": 0.5476053357124329, | |
| "learning_rate": 2.1777839056661554e-05, | |
| "loss": 1.5308, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.37063211621515507, | |
| "grad_norm": 0.5888764262199402, | |
| "learning_rate": 1.946760601822809e-05, | |
| "loss": 1.3414, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.37691401648998824, | |
| "grad_norm": 0.5604611039161682, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 1.3186, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.38319591676482134, | |
| "grad_norm": 0.569729208946228, | |
| "learning_rate": 1.5153121567235335e-05, | |
| "loss": 1.2864, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.3894778170396545, | |
| "grad_norm": 0.5799680948257446, | |
| "learning_rate": 1.3162943106179749e-05, | |
| "loss": 1.3188, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.3957597173144876, | |
| "grad_norm": 0.5320284962654114, | |
| "learning_rate": 1.1292919468045877e-05, | |
| "loss": 1.3297, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4020416175893208, | |
| "grad_norm": 0.6015669703483582, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 1.3177, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.4083235178641539, | |
| "grad_norm": 0.5521041750907898, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 1.3842, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.41460541813898705, | |
| "grad_norm": 0.5729659199714661, | |
| "learning_rate": 6.462696144011149e-06, | |
| "loss": 1.4533, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.42088731841382016, | |
| "grad_norm": 0.5563532710075378, | |
| "learning_rate": 5.13007856543209e-06, | |
| "loss": 1.3325, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.4271692186886533, | |
| "grad_norm": 0.5714989304542542, | |
| "learning_rate": 3.9438173442575e-06, | |
| "loss": 1.2834, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.4334511189634865, | |
| "grad_norm": 0.5417236685752869, | |
| "learning_rate": 2.9077818180237693e-06, | |
| "loss": 1.2234, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.4397330192383196, | |
| "grad_norm": 0.5344116687774658, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 1.3796, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.44601491951315275, | |
| "grad_norm": 0.5636404156684875, | |
| "learning_rate": 1.2994041528833266e-06, | |
| "loss": 1.2578, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.45229681978798586, | |
| "grad_norm": 0.5255051255226135, | |
| "learning_rate": 7.323082076153509e-07, | |
| "loss": 1.2997, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.458578720062819, | |
| "grad_norm": 0.5886712074279785, | |
| "learning_rate": 3.2591323257248893e-07, | |
| "loss": 1.2594, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.46486062033765213, | |
| "grad_norm": 0.5472262501716614, | |
| "learning_rate": 8.15448036932176e-08, | |
| "loss": 1.3018, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.4711425206124853, | |
| "grad_norm": 0.5682985782623291, | |
| "learning_rate": 0.0, | |
| "loss": 1.3637, | |
| "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": 8.09427046194217e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |