| { | |
| "best_metric": 0.8063623309135437, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-100", | |
| "epoch": 0.0890670229347584, | |
| "eval_steps": 25, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008906702293475841, | |
| "grad_norm": 44.20709228515625, | |
| "learning_rate": 2e-05, | |
| "loss": 5.189, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008906702293475841, | |
| "eval_loss": 6.094831943511963, | |
| "eval_runtime": 696.421, | |
| "eval_samples_per_second": 21.722, | |
| "eval_steps_per_second": 1.358, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017813404586951682, | |
| "grad_norm": 42.66680908203125, | |
| "learning_rate": 4e-05, | |
| "loss": 5.1525, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0026720106880427524, | |
| "grad_norm": 44.50114822387695, | |
| "learning_rate": 6e-05, | |
| "loss": 5.4087, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0035626809173903364, | |
| "grad_norm": 52.41817855834961, | |
| "learning_rate": 8e-05, | |
| "loss": 5.7687, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00445335114673792, | |
| "grad_norm": 57.67063522338867, | |
| "learning_rate": 0.0001, | |
| "loss": 5.3536, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005344021376085505, | |
| "grad_norm": 75.5921630859375, | |
| "learning_rate": 9.997266286704631e-05, | |
| "loss": 5.0831, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006234691605433089, | |
| "grad_norm": 85.153564453125, | |
| "learning_rate": 9.989068136093873e-05, | |
| "loss": 4.4786, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.007125361834780673, | |
| "grad_norm": 85.10086822509766, | |
| "learning_rate": 9.975414512725057e-05, | |
| "loss": 4.1905, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.008016032064128256, | |
| "grad_norm": 64.82942199707031, | |
| "learning_rate": 9.956320346634876e-05, | |
| "loss": 3.545, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00890670229347584, | |
| "grad_norm": 52.32982635498047, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 3.1496, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009797372522823424, | |
| "grad_norm": 43.146053314208984, | |
| "learning_rate": 9.901899829374047e-05, | |
| "loss": 2.8887, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.01068804275217101, | |
| "grad_norm": 43.445045471191406, | |
| "learning_rate": 9.86663298624003e-05, | |
| "loss": 2.698, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.011578712981518594, | |
| "grad_norm": 39.32986068725586, | |
| "learning_rate": 9.826044551386744e-05, | |
| "loss": 2.4633, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.012469383210866177, | |
| "grad_norm": 38.07303237915039, | |
| "learning_rate": 9.780178907671789e-05, | |
| "loss": 2.0654, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.013360053440213761, | |
| "grad_norm": 40.31012725830078, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 1.9334, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.014250723669561345, | |
| "grad_norm": 39.19505310058594, | |
| "learning_rate": 9.672822322997305e-05, | |
| "loss": 1.7227, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.01514139389890893, | |
| "grad_norm": 38.306434631347656, | |
| "learning_rate": 9.611448774886924e-05, | |
| "loss": 1.69, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01603206412825651, | |
| "grad_norm": 36.1546630859375, | |
| "learning_rate": 9.545032675245813e-05, | |
| "loss": 1.6214, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.016922734357604097, | |
| "grad_norm": 30.53850746154785, | |
| "learning_rate": 9.473646649103818e-05, | |
| "loss": 1.3828, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.01781340458695168, | |
| "grad_norm": 37.423255920410156, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 1.4083, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.018704074816299265, | |
| "grad_norm": 26.23516273498535, | |
| "learning_rate": 9.316282404787871e-05, | |
| "loss": 1.4254, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.019594745045646848, | |
| "grad_norm": 26.786113739013672, | |
| "learning_rate": 9.230476262104677e-05, | |
| "loss": 1.3075, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.020485415274994433, | |
| "grad_norm": 30.260276794433594, | |
| "learning_rate": 9.140044155740101e-05, | |
| "loss": 1.2865, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.02137608550434202, | |
| "grad_norm": 25.184106826782227, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 1.1895, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0222667557336896, | |
| "grad_norm": 23.548507690429688, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 1.2839, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0222667557336896, | |
| "eval_loss": 1.263924479484558, | |
| "eval_runtime": 701.2081, | |
| "eval_samples_per_second": 21.574, | |
| "eval_steps_per_second": 1.349, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.023157425963037187, | |
| "grad_norm": 26.05804443359375, | |
| "learning_rate": 8.842005554284296e-05, | |
| "loss": 1.4077, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02404809619238477, | |
| "grad_norm": 25.391490936279297, | |
| "learning_rate": 8.73410738492077e-05, | |
| "loss": 1.4483, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.024938766421732355, | |
| "grad_norm": 26.64982795715332, | |
| "learning_rate": 8.622126023955446e-05, | |
| "loss": 1.2018, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.025829436651079937, | |
| "grad_norm": 19.658527374267578, | |
| "learning_rate": 8.506183921362443e-05, | |
| "loss": 1.1818, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.026720106880427523, | |
| "grad_norm": 23.18828582763672, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 1.1465, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.027610777109775105, | |
| "grad_norm": 21.72152328491211, | |
| "learning_rate": 8.262928807620843e-05, | |
| "loss": 1.1506, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02850144733912269, | |
| "grad_norm": 29.772584915161133, | |
| "learning_rate": 8.135881792367686e-05, | |
| "loss": 1.0751, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.029392117568470273, | |
| "grad_norm": 21.76646614074707, | |
| "learning_rate": 8.005405736415126e-05, | |
| "loss": 0.99, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.03028278779781786, | |
| "grad_norm": 20.992374420166016, | |
| "learning_rate": 7.871643313414718e-05, | |
| "loss": 1.0642, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.03117345802716544, | |
| "grad_norm": 20.871078491210938, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 1.0183, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03206412825651302, | |
| "grad_norm": 19.493539810180664, | |
| "learning_rate": 7.594847868906076e-05, | |
| "loss": 0.9964, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03295479848586061, | |
| "grad_norm": 19.52667808532715, | |
| "learning_rate": 7.452117519152542e-05, | |
| "loss": 0.9652, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.033845468715208195, | |
| "grad_norm": 21.08563995361328, | |
| "learning_rate": 7.30670581489344e-05, | |
| "loss": 1.1014, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03473613894455578, | |
| "grad_norm": 17.96194839477539, | |
| "learning_rate": 7.158771761692464e-05, | |
| "loss": 1.241, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03562680917390336, | |
| "grad_norm": 24.256383895874023, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 1.0074, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.036517479403250945, | |
| "grad_norm": 16.780834197998047, | |
| "learning_rate": 6.855986244591104e-05, | |
| "loss": 0.9271, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03740814963259853, | |
| "grad_norm": 18.25143051147461, | |
| "learning_rate": 6.701465872208216e-05, | |
| "loss": 0.9469, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.038298819861946116, | |
| "grad_norm": 16.487092971801758, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.8354, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.039189490091293695, | |
| "grad_norm": 17.375408172607422, | |
| "learning_rate": 6.387014543809223e-05, | |
| "loss": 0.8368, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.04008016032064128, | |
| "grad_norm": 19.860628128051758, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.8107, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04097083054998887, | |
| "grad_norm": 17.61992835998535, | |
| "learning_rate": 6.066498153718735e-05, | |
| "loss": 0.9159, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.04186150077933645, | |
| "grad_norm": 21.857112884521484, | |
| "learning_rate": 5.90440267166055e-05, | |
| "loss": 0.8706, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.04275217100868404, | |
| "grad_norm": 22.603778839111328, | |
| "learning_rate": 5.74131823855921e-05, | |
| "loss": 0.968, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04364284123803162, | |
| "grad_norm": 26.721364974975586, | |
| "learning_rate": 5.577423184847932e-05, | |
| "loss": 1.1293, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0445335114673792, | |
| "grad_norm": 125.70867156982422, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.871, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0445335114673792, | |
| "eval_loss": 0.9120805859565735, | |
| "eval_runtime": 698.0211, | |
| "eval_samples_per_second": 21.673, | |
| "eval_steps_per_second": 1.355, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04542418169672679, | |
| "grad_norm": 19.553665161132812, | |
| "learning_rate": 5.247918773366112e-05, | |
| "loss": 1.1356, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.046314851926074374, | |
| "grad_norm": 17.038597106933594, | |
| "learning_rate": 5.0826697238317935e-05, | |
| "loss": 0.9157, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.04720552215542195, | |
| "grad_norm": 16.456735610961914, | |
| "learning_rate": 4.917330276168208e-05, | |
| "loss": 0.8641, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.04809619238476954, | |
| "grad_norm": 21.303831100463867, | |
| "learning_rate": 4.7520812266338885e-05, | |
| "loss": 0.979, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.048986862614117124, | |
| "grad_norm": 18.442556381225586, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.8377, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.04987753284346471, | |
| "grad_norm": 17.49199104309082, | |
| "learning_rate": 4.4225768151520694e-05, | |
| "loss": 0.9227, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.05076820307281229, | |
| "grad_norm": 16.545700073242188, | |
| "learning_rate": 4.2586817614407895e-05, | |
| "loss": 0.7409, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.051658873302159874, | |
| "grad_norm": 18.476268768310547, | |
| "learning_rate": 4.095597328339452e-05, | |
| "loss": 0.7327, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.05254954353150746, | |
| "grad_norm": 17.85874366760254, | |
| "learning_rate": 3.933501846281267e-05, | |
| "loss": 0.8013, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.053440213760855046, | |
| "grad_norm": 17.47732925415039, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.8019, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.054330883990202625, | |
| "grad_norm": 21.973190307617188, | |
| "learning_rate": 3.612985456190778e-05, | |
| "loss": 0.8761, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.05522155421955021, | |
| "grad_norm": 22.474699020385742, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 1.045, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.056112224448897796, | |
| "grad_norm": 25.610048294067383, | |
| "learning_rate": 3.298534127791785e-05, | |
| "loss": 1.1543, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.05700289467824538, | |
| "grad_norm": 28.102262496948242, | |
| "learning_rate": 3.144013755408895e-05, | |
| "loss": 0.9572, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.05789356490759296, | |
| "grad_norm": 16.78169059753418, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.8053, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.058784235136940546, | |
| "grad_norm": 26.701210021972656, | |
| "learning_rate": 2.8412282383075363e-05, | |
| "loss": 0.8915, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.05967490536628813, | |
| "grad_norm": 20.651735305786133, | |
| "learning_rate": 2.693294185106562e-05, | |
| "loss": 0.7907, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.06056557559563572, | |
| "grad_norm": 19.679340362548828, | |
| "learning_rate": 2.547882480847461e-05, | |
| "loss": 0.7364, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0614562458249833, | |
| "grad_norm": 17.274389266967773, | |
| "learning_rate": 2.405152131093926e-05, | |
| "loss": 0.7114, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.06234691605433088, | |
| "grad_norm": 17.92892074584961, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 0.8729, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.06323758628367847, | |
| "grad_norm": 18.015047073364258, | |
| "learning_rate": 2.128356686585282e-05, | |
| "loss": 0.7113, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.06412825651302605, | |
| "grad_norm": 24.12103843688965, | |
| "learning_rate": 1.9945942635848748e-05, | |
| "loss": 0.7442, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.06501892674237364, | |
| "grad_norm": 19.176523208618164, | |
| "learning_rate": 1.8641182076323148e-05, | |
| "loss": 0.7511, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.06590959697172122, | |
| "grad_norm": 22.23782730102539, | |
| "learning_rate": 1.7370711923791567e-05, | |
| "loss": 0.7453, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.06680026720106881, | |
| "grad_norm": 24.631982803344727, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.8716, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06680026720106881, | |
| "eval_loss": 0.8243863582611084, | |
| "eval_runtime": 699.4578, | |
| "eval_samples_per_second": 21.628, | |
| "eval_steps_per_second": 1.352, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.06769093743041639, | |
| "grad_norm": 17.87114143371582, | |
| "learning_rate": 1.4938160786375572e-05, | |
| "loss": 1.0139, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.06858160765976397, | |
| "grad_norm": 15.511335372924805, | |
| "learning_rate": 1.3778739760445552e-05, | |
| "loss": 0.8656, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.06947227788911156, | |
| "grad_norm": 20.296796798706055, | |
| "learning_rate": 1.2658926150792322e-05, | |
| "loss": 0.8372, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.07036294811845914, | |
| "grad_norm": 18.298046112060547, | |
| "learning_rate": 1.157994445715706e-05, | |
| "loss": 0.8844, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.07125361834780672, | |
| "grad_norm": 17.071407318115234, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.8669, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.07214428857715431, | |
| "grad_norm": 16.053665161132812, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.7517, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.07303495880650189, | |
| "grad_norm": 19.35648536682129, | |
| "learning_rate": 8.599558442598998e-06, | |
| "loss": 0.7972, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.07392562903584948, | |
| "grad_norm": 17.407955169677734, | |
| "learning_rate": 7.695237378953223e-06, | |
| "loss": 0.7013, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.07481629926519706, | |
| "grad_norm": 18.117521286010742, | |
| "learning_rate": 6.837175952121306e-06, | |
| "loss": 0.641, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.07570696949454464, | |
| "grad_norm": 18.53291893005371, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.7497, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.07659763972389223, | |
| "grad_norm": 21.79059410095215, | |
| "learning_rate": 5.263533508961827e-06, | |
| "loss": 0.829, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.07748830995323981, | |
| "grad_norm": 19.699893951416016, | |
| "learning_rate": 4.549673247541875e-06, | |
| "loss": 0.8702, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.07837898018258739, | |
| "grad_norm": 18.76403045654297, | |
| "learning_rate": 3.885512251130763e-06, | |
| "loss": 1.07, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.07926965041193498, | |
| "grad_norm": 17.980998992919922, | |
| "learning_rate": 3.271776770026963e-06, | |
| "loss": 1.0136, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.08016032064128256, | |
| "grad_norm": 17.479143142700195, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.7321, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.08105099087063015, | |
| "grad_norm": 16.1824951171875, | |
| "learning_rate": 2.1982109232821178e-06, | |
| "loss": 0.7568, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.08194166109997773, | |
| "grad_norm": 17.499082565307617, | |
| "learning_rate": 1.7395544861325718e-06, | |
| "loss": 0.8011, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.08283233132932531, | |
| "grad_norm": 17.437572479248047, | |
| "learning_rate": 1.333670137599713e-06, | |
| "loss": 0.7144, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.0837230015586729, | |
| "grad_norm": 19.064252853393555, | |
| "learning_rate": 9.810017062595322e-07, | |
| "loss": 0.7502, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.08461367178802048, | |
| "grad_norm": 18.436866760253906, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.7259, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.08550434201736808, | |
| "grad_norm": 16.668874740600586, | |
| "learning_rate": 4.367965336512403e-07, | |
| "loss": 0.764, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.08639501224671566, | |
| "grad_norm": 18.206295013427734, | |
| "learning_rate": 2.458548727494292e-07, | |
| "loss": 0.7036, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.08728568247606323, | |
| "grad_norm": 20.8583927154541, | |
| "learning_rate": 1.0931863906127327e-07, | |
| "loss": 0.6996, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.08817635270541083, | |
| "grad_norm": 17.43104362487793, | |
| "learning_rate": 2.7337132953697554e-08, | |
| "loss": 0.8025, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.0890670229347584, | |
| "grad_norm": 22.67059898376465, | |
| "learning_rate": 0.0, | |
| "loss": 0.8697, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0890670229347584, | |
| "eval_loss": 0.8063623309135437, | |
| "eval_runtime": 698.2614, | |
| "eval_samples_per_second": 21.665, | |
| "eval_steps_per_second": 1.355, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": 4.3811002881409024e+18, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |