| { | |
| "best_metric": 5.141561985015869, | |
| "best_model_checkpoint": "./qlora-out/v1.2/checkpoint-256", | |
| "epoch": 1.0, | |
| "eval_steps": 64, | |
| "global_step": 256, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "grad_norm": 0.009024755097925663, | |
| "learning_rate": 1e-05, | |
| "loss": 13.4775, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0, | |
| "eval_loss": 13.432984352111816, | |
| "eval_runtime": 117.1907, | |
| "eval_samples_per_second": 14.464, | |
| "eval_steps_per_second": 2.074, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.008986919187009335, | |
| "learning_rate": 2e-05, | |
| "loss": 13.4709, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 0.008954666554927826, | |
| "learning_rate": 3e-05, | |
| "loss": 13.4803, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.009628714993596077, | |
| "learning_rate": 4e-05, | |
| "loss": 13.4636, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.010959964245557785, | |
| "learning_rate": 5e-05, | |
| "loss": 13.435, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.01327170804142952, | |
| "learning_rate": 6e-05, | |
| "loss": 13.4603, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.016410112380981445, | |
| "learning_rate": 7e-05, | |
| "loss": 13.459, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.020337102934718132, | |
| "learning_rate": 8e-05, | |
| "loss": 13.4504, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.025200409814715385, | |
| "learning_rate": 9e-05, | |
| "loss": 13.4827, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.03093448095023632, | |
| "learning_rate": 0.0001, | |
| "loss": 13.441, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.03790152817964554, | |
| "learning_rate": 0.00011000000000000002, | |
| "loss": 13.4603, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.04524616152048111, | |
| "learning_rate": 0.00012, | |
| "loss": 13.4387, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.054408054798841476, | |
| "learning_rate": 0.00013000000000000002, | |
| "loss": 13.4697, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.06374166905879974, | |
| "learning_rate": 0.00014, | |
| "loss": 13.4468, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.07343802601099014, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 13.3862, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.08400653302669525, | |
| "learning_rate": 0.00016, | |
| "loss": 13.3262, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.09511911123991013, | |
| "learning_rate": 0.00017, | |
| "loss": 13.2573, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.10723020881414413, | |
| "learning_rate": 0.00018, | |
| "loss": 13.2185, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.12024787068367004, | |
| "learning_rate": 0.00019, | |
| "loss": 13.1834, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.13525475561618805, | |
| "learning_rate": 0.0002, | |
| "loss": 13.1029, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.14704181253910065, | |
| "learning_rate": 0.0001999979613716069, | |
| "loss": 13.0303, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.16100184619426727, | |
| "learning_rate": 0.00019999184556954776, | |
| "loss": 12.9015, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.17425554990768433, | |
| "learning_rate": 0.00019998165284317945, | |
| "loss": 12.8389, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.18788361549377441, | |
| "learning_rate": 0.00019996738360808565, | |
| "loss": 12.7146, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.20275714993476868, | |
| "learning_rate": 0.00019994903844605972, | |
| "loss": 12.5686, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.21356578171253204, | |
| "learning_rate": 0.000199926618105081, | |
| "loss": 12.4685, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.2230716049671173, | |
| "learning_rate": 0.0001999001234992844, | |
| "loss": 12.33, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.2376524955034256, | |
| "learning_rate": 0.000199869555708923, | |
| "loss": 12.1648, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.2519569396972656, | |
| "learning_rate": 0.0001998349159803241, | |
| "loss": 12.0116, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.257049024105072, | |
| "learning_rate": 0.00019979620572583846, | |
| "loss": 11.8535, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.27328285574913025, | |
| "learning_rate": 0.00019975342652378246, | |
| "loss": 11.6906, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.2857399880886078, | |
| "learning_rate": 0.00019970658011837404, | |
| "loss": 11.4716, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.2988531291484833, | |
| "learning_rate": 0.0001996556684196615, | |
| "loss": 11.3095, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "grad_norm": 0.316837877035141, | |
| "learning_rate": 0.00019960069350344548, | |
| "loss": 11.0641, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.3310101628303528, | |
| "learning_rate": 0.0001995416576111945, | |
| "loss": 10.8383, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.3369371294975281, | |
| "learning_rate": 0.00019947856314995349, | |
| "loss": 10.6568, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "grad_norm": 0.3535173535346985, | |
| "learning_rate": 0.00019941141269224564, | |
| "loss": 10.3978, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.3756394684314728, | |
| "learning_rate": 0.0001993402089759675, | |
| "loss": 10.1159, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "grad_norm": 0.38187795877456665, | |
| "learning_rate": 0.00019926495490427753, | |
| "loss": 9.879, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.39641591906547546, | |
| "learning_rate": 0.0001991856535454774, | |
| "loss": 9.5833, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.40500307083129883, | |
| "learning_rate": 0.00019910230813288712, | |
| "loss": 9.3309, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.42996540665626526, | |
| "learning_rate": 0.00019901492206471325, | |
| "loss": 8.8893, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.41511279344558716, | |
| "learning_rate": 0.00019892349890391015, | |
| "loss": 8.597, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "grad_norm": 0.35860675573349, | |
| "learning_rate": 0.00019882804237803488, | |
| "loss": 8.4768, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.3302132785320282, | |
| "learning_rate": 0.00019872855637909504, | |
| "loss": 8.3176, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.43532317876815796, | |
| "learning_rate": 0.00019862504496339037, | |
| "loss": 8.1118, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "grad_norm": 0.6842054724693298, | |
| "learning_rate": 0.000198517512351347, | |
| "loss": 8.1977, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.8128633499145508, | |
| "learning_rate": 0.0001984059629273457, | |
| "loss": 8.1527, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "grad_norm": 0.8130613565444946, | |
| "learning_rate": 0.00019829040123954297, | |
| "loss": 8.0821, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.7518128752708435, | |
| "learning_rate": 0.00019817083199968552, | |
| "loss": 7.8393, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.5997517108917236, | |
| "learning_rate": 0.00019804726008291828, | |
| "loss": 7.557, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.42999598383903503, | |
| "learning_rate": 0.00019791969052758562, | |
| "loss": 7.5165, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.3002629578113556, | |
| "learning_rate": 0.00019778812853502592, | |
| "loss": 7.3037, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.24435582756996155, | |
| "learning_rate": 0.00019765257946935944, | |
| "loss": 7.3316, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "grad_norm": 0.2515851855278015, | |
| "learning_rate": 0.00019751304885726967, | |
| "loss": 7.1767, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.2763000726699829, | |
| "learning_rate": 0.00019736954238777792, | |
| "loss": 7.0993, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "grad_norm": 0.2830991744995117, | |
| "learning_rate": 0.00019722206591201146, | |
| "loss": 7.1805, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.30122554302215576, | |
| "learning_rate": 0.00019707062544296498, | |
| "loss": 7.0762, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.3070628046989441, | |
| "learning_rate": 0.0001969152271552552, | |
| "loss": 7.1017, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "grad_norm": 0.30436331033706665, | |
| "learning_rate": 0.00019675587738486936, | |
| "loss": 7.3221, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.2854003608226776, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 6.9803, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.27880895137786865, | |
| "learning_rate": 0.0001964253495453141, | |
| "loss": 6.7288, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.2640041410923004, | |
| "learning_rate": 0.00019625418495261343, | |
| "loss": 6.8195, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.2415798306465149, | |
| "learning_rate": 0.00019607909582962477, | |
| "loss": 6.9219, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 6.202152252197266, | |
| "eval_runtime": 118.0179, | |
| "eval_samples_per_second": 14.362, | |
| "eval_steps_per_second": 2.059, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.18691398203372955, | |
| "learning_rate": 0.0001959000893151813, | |
| "loss": 6.6136, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.15952067077159882, | |
| "learning_rate": 0.00019571717270783828, | |
| "loss": 6.4341, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "grad_norm": 0.14711293578147888, | |
| "learning_rate": 0.00019553035346557543, | |
| "loss": 6.414, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.1670265942811966, | |
| "learning_rate": 0.00019533963920549306, | |
| "loss": 6.4894, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.2034294307231903, | |
| "learning_rate": 0.00019514503770350127, | |
| "loss": 6.3448, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "grad_norm": 0.22955259680747986, | |
| "learning_rate": 0.00019494655689400293, | |
| "loss": 6.3133, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.2635420262813568, | |
| "learning_rate": 0.00019474420486957042, | |
| "loss": 6.3256, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.26006290316581726, | |
| "learning_rate": 0.00019453798988061535, | |
| "loss": 6.4601, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.22863267362117767, | |
| "learning_rate": 0.0001943279203350523, | |
| "loss": 6.1397, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.18543188273906708, | |
| "learning_rate": 0.00019411400479795617, | |
| "loss": 6.5625, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "grad_norm": 0.14754259586334229, | |
| "learning_rate": 0.00019389625199121263, | |
| "loss": 6.2912, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.12668511271476746, | |
| "learning_rate": 0.00019367467079316279, | |
| "loss": 6.2679, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.1176210567355156, | |
| "learning_rate": 0.0001934492702382411, | |
| "loss": 6.2426, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.12420424073934555, | |
| "learning_rate": 0.00019322005951660697, | |
| "loss": 6.3293, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.1415456086397171, | |
| "learning_rate": 0.00019298704797377013, | |
| "loss": 6.0938, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "grad_norm": 0.1544170081615448, | |
| "learning_rate": 0.0001927502451102095, | |
| "loss": 6.1926, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.14980632066726685, | |
| "learning_rate": 0.00019250966058098588, | |
| "loss": 6.1425, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.13148672878742218, | |
| "learning_rate": 0.00019226530419534833, | |
| "loss": 6.0866, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.14052827656269073, | |
| "learning_rate": 0.00019201718591633417, | |
| "loss": 6.1682, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.1245439425110817, | |
| "learning_rate": 0.0001917653158603628, | |
| "loss": 6.0281, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "grad_norm": 0.1110084131360054, | |
| "learning_rate": 0.00019150970429682314, | |
| "loss": 6.0577, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.08920083940029144, | |
| "learning_rate": 0.000191250361647655, | |
| "loss": 6.0772, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.09026093780994415, | |
| "learning_rate": 0.0001909872984869242, | |
| "loss": 6.2326, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "grad_norm": 0.11133856326341629, | |
| "learning_rate": 0.00019072052554039122, | |
| "loss": 5.8261, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.11304065585136414, | |
| "learning_rate": 0.00019045005368507418, | |
| "loss": 6.3169, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "grad_norm": 0.10704243183135986, | |
| "learning_rate": 0.00019017589394880515, | |
| "loss": 5.9967, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.1576884537935257, | |
| "learning_rate": 0.0001898980575097806, | |
| "loss": 5.7186, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.12191645801067352, | |
| "learning_rate": 0.00018961655569610557, | |
| "loss": 5.8001, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.1100529134273529, | |
| "learning_rate": 0.00018933139998533188, | |
| "loss": 5.9882, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.10520044714212418, | |
| "learning_rate": 0.00018904260200399006, | |
| "loss": 5.8127, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "grad_norm": 0.08245933800935745, | |
| "learning_rate": 0.00018875017352711545, | |
| "loss": 6.0165, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.07817509770393372, | |
| "learning_rate": 0.00018845412647776794, | |
| "loss": 5.9087, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.07296270877122879, | |
| "learning_rate": 0.00018815447292654596, | |
| "loss": 5.8837, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "grad_norm": 0.077950619161129, | |
| "learning_rate": 0.00018785122509109426, | |
| "loss": 5.9915, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.09345076233148575, | |
| "learning_rate": 0.00018754439533560574, | |
| "loss": 5.9908, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.10249783098697662, | |
| "learning_rate": 0.00018723399617031751, | |
| "loss": 6.0887, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "grad_norm": 0.11731438338756561, | |
| "learning_rate": 0.00018692004025100054, | |
| "loss": 6.0414, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.06663200259208679, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 5.881, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.07221497595310211, | |
| "learning_rate": 0.00018628150949793261, | |
| "loss": 5.6574, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.061096612364053726, | |
| "learning_rate": 0.00018595696069872013, | |
| "loss": 5.8519, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.06478705257177353, | |
| "learning_rate": 0.00018562890721349434, | |
| "loss": 5.7816, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "grad_norm": 0.06368556618690491, | |
| "learning_rate": 0.00018529736241783824, | |
| "loss": 5.872, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.07194569706916809, | |
| "learning_rate": 0.00018496233982968457, | |
| "loss": 5.9662, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "grad_norm": 0.07953158766031265, | |
| "learning_rate": 0.00018462385310876443, | |
| "loss": 5.783, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.06713347882032394, | |
| "learning_rate": 0.00018428191605605068, | |
| "loss": 5.8917, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.06519600003957748, | |
| "learning_rate": 0.000183936542613195, | |
| "loss": 5.797, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "grad_norm": 0.0615142360329628, | |
| "learning_rate": 0.00018358774686195954, | |
| "loss": 5.8417, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.07100021839141846, | |
| "learning_rate": 0.00018323554302364272, | |
| "loss": 5.6852, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.08909253031015396, | |
| "learning_rate": 0.00018287994545849946, | |
| "loss": 5.7358, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.052479445934295654, | |
| "learning_rate": 0.00018252096866515558, | |
| "loss": 5.7226, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.05653544142842293, | |
| "learning_rate": 0.00018215862728001677, | |
| "loss": 5.6749, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "grad_norm": 0.07588440924882889, | |
| "learning_rate": 0.00018179293607667178, | |
| "loss": 5.7824, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.05357549712061882, | |
| "learning_rate": 0.00018142390996528994, | |
| "loss": 5.6497, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.07835177332162857, | |
| "learning_rate": 0.0001810515639920135, | |
| "loss": 5.823, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "grad_norm": 0.05335072800517082, | |
| "learning_rate": 0.00018067591333834383, | |
| "loss": 5.6614, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.0556107759475708, | |
| "learning_rate": 0.00018029697332052277, | |
| "loss": 5.735, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "grad_norm": 0.05811074376106262, | |
| "learning_rate": 0.0001799147593889079, | |
| "loss": 5.5866, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.06357719749212265, | |
| "learning_rate": 0.00017952928712734268, | |
| "loss": 5.6589, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.07032563537359238, | |
| "learning_rate": 0.000179140572252521, | |
| "loss": 5.5309, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.06277754157781601, | |
| "learning_rate": 0.00017874863061334657, | |
| "loss": 5.6021, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.0650109127163887, | |
| "learning_rate": 0.00017835347819028643, | |
| "loss": 5.7339, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "grad_norm": 0.07425089180469513, | |
| "learning_rate": 0.00017795513109471954, | |
| "loss": 5.5569, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.05482316017150879, | |
| "learning_rate": 0.0001775536055682799, | |
| "loss": 5.7093, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.04600892961025238, | |
| "learning_rate": 0.0001771489179821943, | |
| "loss": 5.5416, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 5.278008937835693, | |
| "eval_runtime": 118.0858, | |
| "eval_samples_per_second": 14.354, | |
| "eval_steps_per_second": 2.058, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.046527788043022156, | |
| "learning_rate": 0.0001767410848366148, | |
| "loss": 5.61, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.050605978816747665, | |
| "learning_rate": 0.000176330122759946, | |
| "loss": 5.4324, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "grad_norm": 0.04772460088133812, | |
| "learning_rate": 0.00017591604850816705, | |
| "loss": 5.5366, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.06192879006266594, | |
| "learning_rate": 0.00017549887896414851, | |
| "loss": 5.6139, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.1338934600353241, | |
| "learning_rate": 0.0001750786311369639, | |
| "loss": 5.7635, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "grad_norm": 0.07604615390300751, | |
| "learning_rate": 0.00017465532216119625, | |
| "loss": 5.8955, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.050154052674770355, | |
| "learning_rate": 0.00017422896929623959, | |
| "loss": 5.5455, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "grad_norm": 0.057466309517621994, | |
| "learning_rate": 0.00017379958992559493, | |
| "loss": 5.7089, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.055996015667915344, | |
| "learning_rate": 0.00017336720155616185, | |
| "loss": 5.6818, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.07138606905937195, | |
| "learning_rate": 0.0001729318218175245, | |
| "loss": 5.6629, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "grad_norm": 0.07406231015920639, | |
| "learning_rate": 0.0001724934684612328, | |
| "loss": 5.5892, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.06853732466697693, | |
| "learning_rate": 0.0001720521593600787, | |
| "loss": 5.4891, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.04835648089647293, | |
| "learning_rate": 0.00017160791250736752, | |
| "loss": 5.5121, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "grad_norm": 0.05019184201955795, | |
| "learning_rate": 0.00017116074601618417, | |
| "loss": 5.7229, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.04837877303361893, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 5.7613, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.56, | |
| "grad_norm": 0.04546854645013809, | |
| "learning_rate": 0.00017025772716520323, | |
| "loss": 5.5808, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.053208645433187485, | |
| "learning_rate": 0.000169801911623803, | |
| "loss": 5.5359, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.04370814561843872, | |
| "learning_rate": 0.00016934325007922417, | |
| "loss": 5.6874, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "grad_norm": 0.03918847441673279, | |
| "learning_rate": 0.00016888176123227577, | |
| "loss": 5.4949, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.07932115346193314, | |
| "learning_rate": 0.00016841746389904304, | |
| "loss": 5.8311, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "grad_norm": 0.049384649842977524, | |
| "learning_rate": 0.00016795037701012057, | |
| "loss": 5.763, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.04727654159069061, | |
| "learning_rate": 0.00016748051960984022, | |
| "loss": 5.7183, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.04280374199151993, | |
| "learning_rate": 0.00016700791085549473, | |
| "loss": 5.4721, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "grad_norm": 0.08193852752447128, | |
| "learning_rate": 0.00016653257001655652, | |
| "loss": 5.4723, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.058386653661727905, | |
| "learning_rate": 0.00016605451647389236, | |
| "loss": 5.5226, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.05409287288784981, | |
| "learning_rate": 0.00016557376971897266, | |
| "loss": 5.7237, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.03722846135497093, | |
| "learning_rate": 0.00016509034935307715, | |
| "loss": 5.6341, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.07390096038579941, | |
| "learning_rate": 0.00016460427508649546, | |
| "loss": 5.7795, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.61, | |
| "grad_norm": 0.038613855838775635, | |
| "learning_rate": 0.00016411556673772364, | |
| "loss": 5.4934, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.052825428545475006, | |
| "learning_rate": 0.00016362424423265598, | |
| "loss": 5.3813, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.035356536507606506, | |
| "learning_rate": 0.00016313032760377271, | |
| "loss": 5.5633, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "grad_norm": 0.038892149925231934, | |
| "learning_rate": 0.00016263383698932306, | |
| "loss": 5.4557, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.043012477457523346, | |
| "learning_rate": 0.00016213479263250434, | |
| "loss": 5.4882, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "grad_norm": 0.03944695368409157, | |
| "learning_rate": 0.00016163321488063637, | |
| "loss": 5.5918, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.06338631361722946, | |
| "learning_rate": 0.00016112912418433218, | |
| "loss": 5.5623, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.047581642866134644, | |
| "learning_rate": 0.0001606225410966638, | |
| "loss": 5.6071, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.035596996545791626, | |
| "learning_rate": 0.00016011348627232463, | |
| "loss": 5.4562, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.041574880480766296, | |
| "learning_rate": 0.000159601980466787, | |
| "loss": 5.5685, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "grad_norm": 0.07232942432165146, | |
| "learning_rate": 0.00015908804453545607, | |
| "loss": 5.6704, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.04852332919836044, | |
| "learning_rate": 0.00015857169943281948, | |
| "loss": 5.3836, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.04303191974759102, | |
| "learning_rate": 0.000158052966211593, | |
| "loss": 5.5911, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.66, | |
| "grad_norm": 0.04516925662755966, | |
| "learning_rate": 0.00015753186602186209, | |
| "loss": 5.532, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.05235312879085541, | |
| "learning_rate": 0.00015700842011021955, | |
| "loss": 5.6902, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "grad_norm": 0.04326900467276573, | |
| "learning_rate": 0.00015648264981889934, | |
| "loss": 5.6425, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.04079822823405266, | |
| "learning_rate": 0.00015595457658490643, | |
| "loss": 5.619, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.0557156540453434, | |
| "learning_rate": 0.0001554242219391425, | |
| "loss": 5.352, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "grad_norm": 0.06979982554912567, | |
| "learning_rate": 0.00015489160750552832, | |
| "loss": 5.7106, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.05179354175925255, | |
| "learning_rate": 0.00015435675500012212, | |
| "loss": 5.7409, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "grad_norm": 0.04983863607048988, | |
| "learning_rate": 0.0001538196862302339, | |
| "loss": 5.6446, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.040575865656137466, | |
| "learning_rate": 0.00015328042309353657, | |
| "loss": 5.6534, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.0419522225856781, | |
| "learning_rate": 0.00015273898757717293, | |
| "loss": 5.7551, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.0641922652721405, | |
| "learning_rate": 0.00015219540175685938, | |
| "loss": 5.6773, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.07758746296167374, | |
| "learning_rate": 0.00015164968779598557, | |
| "loss": 5.3518, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.036839358508586884, | |
| "learning_rate": 0.00015110186794471103, | |
| "loss": 5.6357, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "grad_norm": 0.03718819469213486, | |
| "learning_rate": 0.00015055196453905788, | |
| "loss": 5.5973, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.04714547097682953, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 5.5771, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "grad_norm": 0.04743782430887222, | |
| "learning_rate": 0.00014944599683254902, | |
| "loss": 5.5583, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.03646031394600868, | |
| "learning_rate": 0.0001488899776248367, | |
| "loss": 5.5805, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.03820512071251869, | |
| "learning_rate": 0.00014833196504719388, | |
| "loss": 5.6603, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "grad_norm": 0.0345190055668354, | |
| "learning_rate": 0.0001477719818512263, | |
| "loss": 5.5955, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.04769587889313698, | |
| "learning_rate": 0.00014721005086888676, | |
| "loss": 5.6999, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "grad_norm": 0.0692368894815445, | |
| "learning_rate": 0.00014664619501154443, | |
| "loss": 5.4506, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.03599226102232933, | |
| "learning_rate": 0.0001460804372690505, | |
| "loss": 5.4122, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.03820048272609711, | |
| "learning_rate": 0.0001455128007088009, | |
| "loss": 5.4282, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 5.192940711975098, | |
| "eval_runtime": 118.1006, | |
| "eval_samples_per_second": 14.352, | |
| "eval_steps_per_second": 2.058, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.03974439203739166, | |
| "learning_rate": 0.0001449433084747958, | |
| "loss": 5.4563, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.034280966967344284, | |
| "learning_rate": 0.00014437198378669598, | |
| "loss": 5.4544, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "grad_norm": 0.048673514276742935, | |
| "learning_rate": 0.00014379884993887606, | |
| "loss": 5.5972, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.0692707970738411, | |
| "learning_rate": 0.00014322393029947468, | |
| "loss": 5.6211, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.04898356273770332, | |
| "learning_rate": 0.000142647248309442, | |
| "loss": 5.3995, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "grad_norm": 0.058041736483573914, | |
| "learning_rate": 0.0001420688274815834, | |
| "loss": 5.4633, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.036273758858442307, | |
| "learning_rate": 0.0001414886913996015, | |
| "loss": 5.5174, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.78, | |
| "grad_norm": 0.08915985375642776, | |
| "learning_rate": 0.00014090686371713402, | |
| "loss": 5.7644, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.03881510719656944, | |
| "learning_rate": 0.00014032336815678956, | |
| "loss": 5.3306, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.03407745435833931, | |
| "learning_rate": 0.00013973822850918055, | |
| "loss": 5.3793, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "grad_norm": 0.04425397515296936, | |
| "learning_rate": 0.00013915146863195291, | |
| "loss": 5.5079, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.03599456697702408, | |
| "learning_rate": 0.0001385631124488136, | |
| "loss": 5.6079, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.06741538643836975, | |
| "learning_rate": 0.00013797318394855496, | |
| "loss": 5.4523, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.04686039686203003, | |
| "learning_rate": 0.00013738170718407687, | |
| "loss": 5.3534, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.03939492255449295, | |
| "learning_rate": 0.00013678870627140585, | |
| "loss": 5.39, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "grad_norm": 0.03362642973661423, | |
| "learning_rate": 0.00013619420538871178, | |
| "loss": 5.4704, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.04307378828525543, | |
| "learning_rate": 0.00013559822877532232, | |
| "loss": 5.3642, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.05713765695691109, | |
| "learning_rate": 0.00013500080073073435, | |
| "loss": 5.6962, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.82, | |
| "grad_norm": 0.0568612739443779, | |
| "learning_rate": 0.0001344019456136234, | |
| "loss": 5.6521, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.03639932721853256, | |
| "learning_rate": 0.00013380168784085027, | |
| "loss": 5.4487, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "grad_norm": 0.03534509986639023, | |
| "learning_rate": 0.00013320005188646587, | |
| "loss": 5.4749, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.03920762613415718, | |
| "learning_rate": 0.00013259706228071285, | |
| "loss": 5.5691, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.0338614359498024, | |
| "learning_rate": 0.00013199274360902588, | |
| "loss": 5.4251, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "grad_norm": 0.04901224374771118, | |
| "learning_rate": 0.0001313871205110291, | |
| "loss": 5.6354, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.042758435010910034, | |
| "learning_rate": 0.00013078021767953124, | |
| "loss": 5.5125, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.85, | |
| "grad_norm": 0.035222314298152924, | |
| "learning_rate": 0.00013017205985951926, | |
| "loss": 5.4903, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.06844358146190643, | |
| "learning_rate": 0.0001295626718471491, | |
| "loss": 5.6841, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.033597927540540695, | |
| "learning_rate": 0.00012895207848873487, | |
| "loss": 5.3933, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "grad_norm": 0.05063093453645706, | |
| "learning_rate": 0.0001283403046797357, | |
| "loss": 5.4618, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.03585563227534294, | |
| "learning_rate": 0.0001277273753637408, | |
| "loss": 5.4886, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "grad_norm": 0.04604891687631607, | |
| "learning_rate": 0.00012711331553145222, | |
| "loss": 5.67, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.034121155738830566, | |
| "learning_rate": 0.0001264981502196662, | |
| "loss": 5.4705, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.04434522986412048, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 5.4958, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "grad_norm": 0.030158868059515953, | |
| "learning_rate": 0.00012526460352912995, | |
| "loss": 5.5153, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.0346997007727623, | |
| "learning_rate": 0.00012464627244524593, | |
| "loss": 5.5369, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.08054299652576447, | |
| "learning_rate": 0.00012402693646954607, | |
| "loss": 5.8509, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "grad_norm": 0.05208098143339157, | |
| "learning_rate": 0.0001234066208539485, | |
| "loss": 5.3976, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.062221452593803406, | |
| "learning_rate": 0.00012278535089031378, | |
| "loss": 5.2981, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.040150679647922516, | |
| "learning_rate": 0.0001221631519094136, | |
| "loss": 5.6089, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.05412865802645683, | |
| "learning_rate": 0.00012154004927989815, | |
| "loss": 5.4375, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.038796316832304, | |
| "learning_rate": 0.00012091606840726169, | |
| "loss": 5.5065, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "grad_norm": 0.0440991073846817, | |
| "learning_rate": 0.00012029123473280668, | |
| "loss": 5.522, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.054540976881980896, | |
| "learning_rate": 0.00011966557373260654, | |
| "loss": 5.3513, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.92, | |
| "grad_norm": 0.04210669547319412, | |
| "learning_rate": 0.00011903911091646684, | |
| "loss": 5.5149, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.05175742134451866, | |
| "learning_rate": 0.00011841187182688526, | |
| "loss": 5.4831, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.04814860597252846, | |
| "learning_rate": 0.00011778388203801018, | |
| "loss": 5.441, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "grad_norm": 0.03201444074511528, | |
| "learning_rate": 0.00011715516715459785, | |
| "loss": 5.3987, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.036201510578393936, | |
| "learning_rate": 0.0001165257528109685, | |
| "loss": 5.4906, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.94, | |
| "grad_norm": 0.062432534992694855, | |
| "learning_rate": 0.00011589566466996123, | |
| "loss": 5.5572, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.03997960314154625, | |
| "learning_rate": 0.00011526492842188745, | |
| "loss": 5.3745, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.06984079629182816, | |
| "learning_rate": 0.00011463356978348371, | |
| "loss": 5.4129, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "grad_norm": 0.07232825458049774, | |
| "learning_rate": 0.00011400161449686293, | |
| "loss": 5.518, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.06185632199048996, | |
| "learning_rate": 0.00011336908832846484, | |
| "loss": 5.6377, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.033329036086797714, | |
| "learning_rate": 0.0001127360170680057, | |
| "loss": 5.4242, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.03494875878095627, | |
| "learning_rate": 0.00011210242652742631, | |
| "loss": 5.3739, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.03172081336379051, | |
| "learning_rate": 0.00011146834253984006, | |
| "loss": 5.4698, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "grad_norm": 0.04552210494875908, | |
| "learning_rate": 0.00011083379095847932, | |
| "loss": 5.5625, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.051661595702171326, | |
| "learning_rate": 0.00011019879765564153, | |
| "loss": 5.3063, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.04173550382256508, | |
| "learning_rate": 0.00010956338852163424, | |
| "loss": 5.4449, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "grad_norm": 0.036143746227025986, | |
| "learning_rate": 0.00010892758946371944, | |
| "loss": 5.4327, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.054287999868392944, | |
| "learning_rate": 0.00010829142640505738, | |
| "loss": 5.6596, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.99, | |
| "grad_norm": 0.0568251796066761, | |
| "learning_rate": 0.0001076549252836496, | |
| "loss": 5.3534, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.05703786015510559, | |
| "learning_rate": 0.00010701811205128113, | |
| "loss": 5.2521, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.03435615077614784, | |
| "learning_rate": 0.00010638101267246283, | |
| "loss": 5.4864, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 5.141561985015869, | |
| "eval_runtime": 117.9745, | |
| "eval_samples_per_second": 14.368, | |
| "eval_steps_per_second": 2.06, | |
| "step": 256 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 512, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 256, | |
| "total_flos": 1.8895499024347955e+18, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |