| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 90, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011111111111111112, | |
| "grad_norm": 0.1605497077049183, | |
| "learning_rate": 5.555555555555556e-06, | |
| "loss": 0.0722, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022222222222222223, | |
| "grad_norm": 0.15033421124192128, | |
| "learning_rate": 1.1111111111111112e-05, | |
| "loss": 0.054, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03333333333333333, | |
| "grad_norm": 0.08211350214292958, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 0.0334, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.044444444444444446, | |
| "grad_norm": 0.06523840335431949, | |
| "learning_rate": 2.2222222222222223e-05, | |
| "loss": 0.0246, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05555555555555555, | |
| "grad_norm": 0.18637955543633108, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.1101, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06666666666666667, | |
| "grad_norm": 0.13582296490853762, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.1417, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07777777777777778, | |
| "grad_norm": 0.057209465108812384, | |
| "learning_rate": 3.888888888888889e-05, | |
| "loss": 0.0104, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 0.1289372880709745, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 0.0588, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.12550793516696718, | |
| "learning_rate": 5e-05, | |
| "loss": 0.079, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.1111111111111111, | |
| "grad_norm": 0.12588386550696973, | |
| "learning_rate": 4.998119881260576e-05, | |
| "loss": 0.0544, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12222222222222222, | |
| "grad_norm": 0.05757870661729721, | |
| "learning_rate": 4.99248235291948e-05, | |
| "loss": 0.0105, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.13333333333333333, | |
| "grad_norm": 0.1018237088287416, | |
| "learning_rate": 4.983095894354858e-05, | |
| "loss": 0.0458, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.14444444444444443, | |
| "grad_norm": 0.07858785876232853, | |
| "learning_rate": 4.969974623692023e-05, | |
| "loss": 0.0101, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15555555555555556, | |
| "grad_norm": 0.13270235656692694, | |
| "learning_rate": 4.953138276568462e-05, | |
| "loss": 0.0451, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16666666666666666, | |
| "grad_norm": 0.22122914935061136, | |
| "learning_rate": 4.9326121764495596e-05, | |
| "loss": 0.0998, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 0.10426108875384622, | |
| "learning_rate": 4.9084271965397014e-05, | |
| "loss": 0.0357, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18888888888888888, | |
| "grad_norm": 0.29133753268223417, | |
| "learning_rate": 4.880619713346039e-05, | |
| "loss": 0.0787, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.16115499865436106, | |
| "learning_rate": 4.849231551964771e-05, | |
| "loss": 0.0488, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.2111111111111111, | |
| "grad_norm": 0.07393967355530186, | |
| "learning_rate": 4.814309923172227e-05, | |
| "loss": 0.0258, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.15700374728260783, | |
| "learning_rate": 4.775907352415367e-05, | |
| "loss": 0.0858, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23333333333333334, | |
| "grad_norm": 0.1492108431114542, | |
| "learning_rate": 4.734081600808531e-05, | |
| "loss": 0.0431, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24444444444444444, | |
| "grad_norm": 0.04622905558925918, | |
| "learning_rate": 4.6888955782552274e-05, | |
| "loss": 0.0111, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.25555555555555554, | |
| "grad_norm": 0.012134880102923188, | |
| "learning_rate": 4.640417248825667e-05, | |
| "loss": 0.0017, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 0.055554727516441096, | |
| "learning_rate": 4.588719528532342e-05, | |
| "loss": 0.0117, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2777777777777778, | |
| "grad_norm": 0.08925730443294172, | |
| "learning_rate": 4.533880175657419e-05, | |
| "loss": 0.0231, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.28888888888888886, | |
| "grad_norm": 0.11415762338400708, | |
| "learning_rate": 4.475981673796899e-05, | |
| "loss": 0.017, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "grad_norm": 0.1179351187059848, | |
| "learning_rate": 4.415111107797445e-05, | |
| "loss": 0.0205, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.3111111111111111, | |
| "grad_norm": 0.024178581822596096, | |
| "learning_rate": 4.351360032772512e-05, | |
| "loss": 0.004, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.32222222222222224, | |
| "grad_norm": 0.12535152202967623, | |
| "learning_rate": 4.2848243363947484e-05, | |
| "loss": 0.0271, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.3333333333333333, | |
| "grad_norm": 0.062018881983428004, | |
| "learning_rate": 4.215604094671835e-05, | |
| "loss": 0.007, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34444444444444444, | |
| "grad_norm": 0.037816804000945864, | |
| "learning_rate": 4.14380342142266e-05, | |
| "loss": 0.0047, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 0.017699161139270052, | |
| "learning_rate": 4.069530311680247e-05, | |
| "loss": 0.0019, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.36666666666666664, | |
| "grad_norm": 0.3316047300359818, | |
| "learning_rate": 3.9928964792569655e-05, | |
| "loss": 0.0521, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.37777777777777777, | |
| "grad_norm": 0.00812341155697814, | |
| "learning_rate": 3.914017188716347e-05, | |
| "loss": 0.0007, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3888888888888889, | |
| "grad_norm": 0.059422215619002315, | |
| "learning_rate": 3.8330110820042285e-05, | |
| "loss": 0.004, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.029258673095478593, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.0029, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4111111111111111, | |
| "grad_norm": 0.15233004165166694, | |
| "learning_rate": 3.665108799256348e-05, | |
| "loss": 0.0659, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4222222222222222, | |
| "grad_norm": 0.39789872295877243, | |
| "learning_rate": 3.578465164203134e-05, | |
| "loss": 0.0435, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.43333333333333335, | |
| "grad_norm": 0.011189075250554171, | |
| "learning_rate": 3.490199415097892e-05, | |
| "loss": 0.0011, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 0.1824572126769632, | |
| "learning_rate": 3.400444312011776e-05, | |
| "loss": 0.0102, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.45555555555555555, | |
| "grad_norm": 0.2180474815061088, | |
| "learning_rate": 3.309334855145803e-05, | |
| "loss": 0.0166, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.4666666666666667, | |
| "grad_norm": 0.07314406054970872, | |
| "learning_rate": 3.217008081777726e-05, | |
| "loss": 0.0053, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.4777777777777778, | |
| "grad_norm": 0.0036346591128551286, | |
| "learning_rate": 3.1236028601449534e-05, | |
| "loss": 0.0003, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.4888888888888889, | |
| "grad_norm": 0.019911172081366117, | |
| "learning_rate": 3.0292596805735274e-05, | |
| "loss": 0.0018, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.017294422932046204, | |
| "learning_rate": 2.9341204441673266e-05, | |
| "loss": 0.0014, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5111111111111111, | |
| "grad_norm": 0.017456356245774136, | |
| "learning_rate": 2.8383282493753283e-05, | |
| "loss": 0.0011, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5222222222222223, | |
| "grad_norm": 0.03586534397518869, | |
| "learning_rate": 2.742027176757948e-05, | |
| "loss": 0.0022, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.005245662030561694, | |
| "learning_rate": 2.6453620722761896e-05, | |
| "loss": 0.0007, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.5444444444444444, | |
| "grad_norm": 0.016600830265163877, | |
| "learning_rate": 2.548478329429561e-05, | |
| "loss": 0.0013, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5555555555555556, | |
| "grad_norm": 0.010620295787117045, | |
| "learning_rate": 2.4515216705704395e-05, | |
| "loss": 0.0007, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5666666666666667, | |
| "grad_norm": 0.26798972483702493, | |
| "learning_rate": 2.3546379277238107e-05, | |
| "loss": 0.0141, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.5777777777777777, | |
| "grad_norm": 0.14668317357033495, | |
| "learning_rate": 2.2579728232420525e-05, | |
| "loss": 0.0052, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.5888888888888889, | |
| "grad_norm": 0.03852832980880582, | |
| "learning_rate": 2.161671750624673e-05, | |
| "loss": 0.0024, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "grad_norm": 0.054562459369850276, | |
| "learning_rate": 2.0658795558326743e-05, | |
| "loss": 0.0037, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.6111111111111112, | |
| "grad_norm": 0.04609165413416543, | |
| "learning_rate": 1.970740319426474e-05, | |
| "loss": 0.0042, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 0.00990897990406697, | |
| "learning_rate": 1.876397139855047e-05, | |
| "loss": 0.0008, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.6333333333333333, | |
| "grad_norm": 0.034931839860100185, | |
| "learning_rate": 1.7829919182222752e-05, | |
| "loss": 0.0025, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.6444444444444445, | |
| "grad_norm": 0.009679755047760722, | |
| "learning_rate": 1.690665144854198e-05, | |
| "loss": 0.0008, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.6555555555555556, | |
| "grad_norm": 0.02141987361270307, | |
| "learning_rate": 1.5995556879882246e-05, | |
| "loss": 0.0011, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.6666666666666666, | |
| "grad_norm": 0.35778010686834366, | |
| "learning_rate": 1.509800584902108e-05, | |
| "loss": 0.0265, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6777777777777778, | |
| "grad_norm": 0.2964385330962491, | |
| "learning_rate": 1.4215348357968669e-05, | |
| "loss": 0.019, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.6888888888888889, | |
| "grad_norm": 0.003274748089771646, | |
| "learning_rate": 1.3348912007436537e-05, | |
| "loss": 0.0004, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "grad_norm": 0.09924320805951631, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 0.0095, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 0.005477355766403404, | |
| "learning_rate": 1.1669889179957725e-05, | |
| "loss": 0.0003, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.7222222222222222, | |
| "grad_norm": 0.01603763418676323, | |
| "learning_rate": 1.085982811283654e-05, | |
| "loss": 0.001, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.7333333333333333, | |
| "grad_norm": 0.022911147348485164, | |
| "learning_rate": 1.0071035207430352e-05, | |
| "loss": 0.0018, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.7444444444444445, | |
| "grad_norm": 0.008504267429334945, | |
| "learning_rate": 9.304696883197542e-06, | |
| "loss": 0.0008, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.7555555555555555, | |
| "grad_norm": 0.08777043552994244, | |
| "learning_rate": 8.561965785773413e-06, | |
| "loss": 0.0083, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.7666666666666667, | |
| "grad_norm": 0.03522101448287721, | |
| "learning_rate": 7.843959053281663e-06, | |
| "loss": 0.0017, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.7777777777777778, | |
| "grad_norm": 0.030350816175983727, | |
| "learning_rate": 7.1517566360525284e-06, | |
| "loss": 0.0025, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7888888888888889, | |
| "grad_norm": 0.0568152824957456, | |
| "learning_rate": 6.48639967227489e-06, | |
| "loss": 0.0019, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.039638875919711845, | |
| "learning_rate": 5.848888922025553e-06, | |
| "loss": 0.0024, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.8111111111111111, | |
| "grad_norm": 0.01243906370573467, | |
| "learning_rate": 5.240183262031021e-06, | |
| "loss": 0.0013, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.8222222222222222, | |
| "grad_norm": 0.012615409248578522, | |
| "learning_rate": 4.661198243425813e-06, | |
| "loss": 0.0007, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.8333333333333334, | |
| "grad_norm": 0.0012548105546647107, | |
| "learning_rate": 4.112804714676594e-06, | |
| "loss": 0.0001, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.8444444444444444, | |
| "grad_norm": 0.008842733600410168, | |
| "learning_rate": 3.595827511743341e-06, | |
| "loss": 0.0007, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.8555555555555555, | |
| "grad_norm": 0.01882589483242362, | |
| "learning_rate": 3.111044217447731e-06, | |
| "loss": 0.001, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.8666666666666667, | |
| "grad_norm": 0.004662510579663767, | |
| "learning_rate": 2.659183991914696e-06, | |
| "loss": 0.0003, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.8777777777777778, | |
| "grad_norm": 0.11369035883063458, | |
| "learning_rate": 2.2409264758463363e-06, | |
| "loss": 0.0034, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.1482671342863526, | |
| "learning_rate": 1.8569007682777417e-06, | |
| "loss": 0.0088, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "grad_norm": 0.048933647765371784, | |
| "learning_rate": 1.5076844803522922e-06, | |
| "loss": 0.0044, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.9111111111111111, | |
| "grad_norm": 0.21058010107250458, | |
| "learning_rate": 1.1938028665396173e-06, | |
| "loss": 0.0079, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.9222222222222223, | |
| "grad_norm": 0.011776152105882409, | |
| "learning_rate": 9.157280346029918e-07, | |
| "loss": 0.0006, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.9333333333333333, | |
| "grad_norm": 0.08719366671571024, | |
| "learning_rate": 6.738782355044049e-07, | |
| "loss": 0.0039, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.9444444444444444, | |
| "grad_norm": 0.05182409255535593, | |
| "learning_rate": 4.6861723431538276e-07, | |
| "loss": 0.0031, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.9555555555555556, | |
| "grad_norm": 0.00899017223628164, | |
| "learning_rate": 3.002537630797747e-07, | |
| "loss": 0.0005, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.9666666666666667, | |
| "grad_norm": 0.0036680528157307947, | |
| "learning_rate": 1.6904105645142444e-07, | |
| "loss": 0.0003, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 0.00472889066022784, | |
| "learning_rate": 7.51764708051994e-08, | |
| "loss": 0.0003, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.9888888888888889, | |
| "grad_norm": 0.02901154365250862, | |
| "learning_rate": 1.8801187394248965e-08, | |
| "loss": 0.0022, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.20690210466074088, | |
| "learning_rate": 0.0, | |
| "loss": 0.0144, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.03874664753675461, | |
| "eval_runtime": 0.4514, | |
| "eval_samples_per_second": 2.215, | |
| "eval_steps_per_second": 2.215, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 90, | |
| "total_flos": 286353899520.0, | |
| "train_loss": 0.0, | |
| "train_runtime": 1.2646, | |
| "train_samples_per_second": 71.17, | |
| "train_steps_per_second": 71.17 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 90, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 286353899520.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |