| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.24832381425378694, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00024832381425378696, | |
| "grad_norm": 10.215656280517578, | |
| "learning_rate": 0.0, | |
| "loss": 2.4774, | |
| "num_input_tokens_seen": 262144, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004966476285075739, | |
| "grad_norm": 11.095035552978516, | |
| "learning_rate": 1.0000000000000001e-07, | |
| "loss": 2.9956, | |
| "num_input_tokens_seen": 524288, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0007449714427613609, | |
| "grad_norm": 15.851714134216309, | |
| "learning_rate": 2.0000000000000002e-07, | |
| "loss": 3.5577, | |
| "num_input_tokens_seen": 786432, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009932952570151478, | |
| "grad_norm": 13.334907531738281, | |
| "learning_rate": 3.0000000000000004e-07, | |
| "loss": 3.5265, | |
| "num_input_tokens_seen": 1048576, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0012416190712689348, | |
| "grad_norm": 13.653706550598145, | |
| "learning_rate": 4.0000000000000003e-07, | |
| "loss": 3.2742, | |
| "num_input_tokens_seen": 1310720, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0014899428855227217, | |
| "grad_norm": 10.820155143737793, | |
| "learning_rate": 5.000000000000001e-07, | |
| "loss": 2.7898, | |
| "num_input_tokens_seen": 1572864, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0017382666997765085, | |
| "grad_norm": 8.97152042388916, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 2.3872, | |
| "num_input_tokens_seen": 1835008, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0019865905140302956, | |
| "grad_norm": 8.390254020690918, | |
| "learning_rate": 7.000000000000001e-07, | |
| "loss": 2.4003, | |
| "num_input_tokens_seen": 2097152, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0022349143282840824, | |
| "grad_norm": 7.845387935638428, | |
| "learning_rate": 8.000000000000001e-07, | |
| "loss": 2.3165, | |
| "num_input_tokens_seen": 2359296, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0024832381425378696, | |
| "grad_norm": 10.649581909179688, | |
| "learning_rate": 9.000000000000001e-07, | |
| "loss": 3.193, | |
| "num_input_tokens_seen": 2621440, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0027315619567916563, | |
| "grad_norm": 9.258522033691406, | |
| "learning_rate": 1.0000000000000002e-06, | |
| "loss": 3.0098, | |
| "num_input_tokens_seen": 2883584, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0029798857710454435, | |
| "grad_norm": 8.765289306640625, | |
| "learning_rate": 1.1e-06, | |
| "loss": 2.5393, | |
| "num_input_tokens_seen": 3145728, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00322820958529923, | |
| "grad_norm": 10.003978729248047, | |
| "learning_rate": 1.2000000000000002e-06, | |
| "loss": 2.9451, | |
| "num_input_tokens_seen": 3407872, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003476533399553017, | |
| "grad_norm": 8.10649585723877, | |
| "learning_rate": 1.3e-06, | |
| "loss": 2.7237, | |
| "num_input_tokens_seen": 3670016, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.003724857213806804, | |
| "grad_norm": 8.63984489440918, | |
| "learning_rate": 1.4000000000000001e-06, | |
| "loss": 2.922, | |
| "num_input_tokens_seen": 3932160, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003973181028060591, | |
| "grad_norm": 6.354504585266113, | |
| "learning_rate": 1.5e-06, | |
| "loss": 2.494, | |
| "num_input_tokens_seen": 4194304, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.004221504842314378, | |
| "grad_norm": 6.988131046295166, | |
| "learning_rate": 1.6000000000000001e-06, | |
| "loss": 3.051, | |
| "num_input_tokens_seen": 4456448, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.004469828656568165, | |
| "grad_norm": 6.21164608001709, | |
| "learning_rate": 1.7000000000000002e-06, | |
| "loss": 2.8812, | |
| "num_input_tokens_seen": 4718592, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0047181524708219515, | |
| "grad_norm": 7.339629173278809, | |
| "learning_rate": 1.8000000000000001e-06, | |
| "loss": 2.8418, | |
| "num_input_tokens_seen": 4980736, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.004966476285075739, | |
| "grad_norm": 5.495388031005859, | |
| "learning_rate": 1.9000000000000002e-06, | |
| "loss": 2.4937, | |
| "num_input_tokens_seen": 5242880, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005214800099329526, | |
| "grad_norm": 4.960653305053711, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 2.5324, | |
| "num_input_tokens_seen": 5505024, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.005463123913583313, | |
| "grad_norm": 5.600866794586182, | |
| "learning_rate": 2.1000000000000002e-06, | |
| "loss": 2.9153, | |
| "num_input_tokens_seen": 5767168, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.005711447727837099, | |
| "grad_norm": 4.116523265838623, | |
| "learning_rate": 2.2e-06, | |
| "loss": 2.4081, | |
| "num_input_tokens_seen": 6029312, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.005959771542090887, | |
| "grad_norm": 3.069936990737915, | |
| "learning_rate": 2.3000000000000004e-06, | |
| "loss": 2.059, | |
| "num_input_tokens_seen": 6291456, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006208095356344674, | |
| "grad_norm": 5.050525188446045, | |
| "learning_rate": 2.4000000000000003e-06, | |
| "loss": 2.802, | |
| "num_input_tokens_seen": 6553600, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.00645641917059846, | |
| "grad_norm": 4.871302604675293, | |
| "learning_rate": 2.5e-06, | |
| "loss": 2.5931, | |
| "num_input_tokens_seen": 6815744, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.006704742984852247, | |
| "grad_norm": 3.577676773071289, | |
| "learning_rate": 2.6e-06, | |
| "loss": 2.6076, | |
| "num_input_tokens_seen": 7077888, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.006953066799106034, | |
| "grad_norm": 4.384449481964111, | |
| "learning_rate": 2.7000000000000004e-06, | |
| "loss": 2.8547, | |
| "num_input_tokens_seen": 7340032, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0072013906133598215, | |
| "grad_norm": 2.9289448261260986, | |
| "learning_rate": 2.8000000000000003e-06, | |
| "loss": 2.1733, | |
| "num_input_tokens_seen": 7602176, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.007449714427613608, | |
| "grad_norm": 3.34555983543396, | |
| "learning_rate": 2.9e-06, | |
| "loss": 2.4006, | |
| "num_input_tokens_seen": 7864320, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.007698038241867395, | |
| "grad_norm": 2.8291356563568115, | |
| "learning_rate": 3e-06, | |
| "loss": 2.4605, | |
| "num_input_tokens_seen": 8126464, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.007946362056121183, | |
| "grad_norm": 2.9072861671447754, | |
| "learning_rate": 3.1000000000000004e-06, | |
| "loss": 2.5204, | |
| "num_input_tokens_seen": 8388608, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.008194685870374968, | |
| "grad_norm": 2.771606683731079, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 2.4139, | |
| "num_input_tokens_seen": 8650752, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.008443009684628756, | |
| "grad_norm": 2.580414295196533, | |
| "learning_rate": 3.3000000000000006e-06, | |
| "loss": 2.5677, | |
| "num_input_tokens_seen": 8912896, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.008691333498882544, | |
| "grad_norm": 2.1037166118621826, | |
| "learning_rate": 3.4000000000000005e-06, | |
| "loss": 2.1773, | |
| "num_input_tokens_seen": 9175040, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.00893965731313633, | |
| "grad_norm": 2.0104498863220215, | |
| "learning_rate": 3.5e-06, | |
| "loss": 2.1332, | |
| "num_input_tokens_seen": 9437184, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.009187981127390117, | |
| "grad_norm": 1.954823613166809, | |
| "learning_rate": 3.6000000000000003e-06, | |
| "loss": 2.3993, | |
| "num_input_tokens_seen": 9699328, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.009436304941643903, | |
| "grad_norm": 2.064880847930908, | |
| "learning_rate": 3.7e-06, | |
| "loss": 2.6064, | |
| "num_input_tokens_seen": 9961472, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.00968462875589769, | |
| "grad_norm": 1.6983036994934082, | |
| "learning_rate": 3.8000000000000005e-06, | |
| "loss": 1.9788, | |
| "num_input_tokens_seen": 10223616, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.009932952570151478, | |
| "grad_norm": 1.7680089473724365, | |
| "learning_rate": 3.900000000000001e-06, | |
| "loss": 2.3603, | |
| "num_input_tokens_seen": 10485760, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.010181276384405264, | |
| "grad_norm": 1.5656706094741821, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 2.2015, | |
| "num_input_tokens_seen": 10747904, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.010429600198659052, | |
| "grad_norm": 1.4727283716201782, | |
| "learning_rate": 4.1e-06, | |
| "loss": 2.0206, | |
| "num_input_tokens_seen": 11010048, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.010677924012912838, | |
| "grad_norm": 1.2997132539749146, | |
| "learning_rate": 4.2000000000000004e-06, | |
| "loss": 1.7953, | |
| "num_input_tokens_seen": 11272192, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.010926247827166625, | |
| "grad_norm": 1.439453363418579, | |
| "learning_rate": 4.3e-06, | |
| "loss": 2.124, | |
| "num_input_tokens_seen": 11534336, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.011174571641420413, | |
| "grad_norm": 1.43881356716156, | |
| "learning_rate": 4.4e-06, | |
| "loss": 2.4577, | |
| "num_input_tokens_seen": 11796480, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.011422895455674199, | |
| "grad_norm": 1.5415407419204712, | |
| "learning_rate": 4.5e-06, | |
| "loss": 2.3313, | |
| "num_input_tokens_seen": 12058624, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.011671219269927986, | |
| "grad_norm": 1.2109966278076172, | |
| "learning_rate": 4.600000000000001e-06, | |
| "loss": 2.0387, | |
| "num_input_tokens_seen": 12320768, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.011919543084181774, | |
| "grad_norm": 1.2937291860580444, | |
| "learning_rate": 4.7e-06, | |
| "loss": 2.3696, | |
| "num_input_tokens_seen": 12582912, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.01216786689843556, | |
| "grad_norm": 1.2319666147232056, | |
| "learning_rate": 4.800000000000001e-06, | |
| "loss": 2.3702, | |
| "num_input_tokens_seen": 12845056, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.012416190712689347, | |
| "grad_norm": 2.2272355556488037, | |
| "learning_rate": 4.9000000000000005e-06, | |
| "loss": 1.7134, | |
| "num_input_tokens_seen": 13107200, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.012664514526943133, | |
| "grad_norm": 0.9094964265823364, | |
| "learning_rate": 5e-06, | |
| "loss": 1.8803, | |
| "num_input_tokens_seen": 13369344, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.01291283834119692, | |
| "grad_norm": 1.3690983057022095, | |
| "learning_rate": 5.1e-06, | |
| "loss": 2.541, | |
| "num_input_tokens_seen": 13631488, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.013161162155450708, | |
| "grad_norm": 0.8856329917907715, | |
| "learning_rate": 5.2e-06, | |
| "loss": 2.1698, | |
| "num_input_tokens_seen": 13893632, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.013409485969704494, | |
| "grad_norm": 0.9775459170341492, | |
| "learning_rate": 5.300000000000001e-06, | |
| "loss": 2.0176, | |
| "num_input_tokens_seen": 14155776, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.013657809783958282, | |
| "grad_norm": 0.8204602599143982, | |
| "learning_rate": 5.400000000000001e-06, | |
| "loss": 1.895, | |
| "num_input_tokens_seen": 14417920, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.013906133598212068, | |
| "grad_norm": 0.9787035584449768, | |
| "learning_rate": 5.500000000000001e-06, | |
| "loss": 2.1046, | |
| "num_input_tokens_seen": 14680064, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.014154457412465855, | |
| "grad_norm": 0.7377949357032776, | |
| "learning_rate": 5.600000000000001e-06, | |
| "loss": 1.9217, | |
| "num_input_tokens_seen": 14942208, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.014402781226719643, | |
| "grad_norm": 0.8319304585456848, | |
| "learning_rate": 5.7e-06, | |
| "loss": 2.278, | |
| "num_input_tokens_seen": 15204352, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.014651105040973429, | |
| "grad_norm": 0.8811312317848206, | |
| "learning_rate": 5.8e-06, | |
| "loss": 2.4527, | |
| "num_input_tokens_seen": 15466496, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.014899428855227216, | |
| "grad_norm": 0.8537189364433289, | |
| "learning_rate": 5.9e-06, | |
| "loss": 2.0035, | |
| "num_input_tokens_seen": 15728640, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.015147752669481004, | |
| "grad_norm": 0.8903886079788208, | |
| "learning_rate": 6e-06, | |
| "loss": 2.0959, | |
| "num_input_tokens_seen": 15990784, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.01539607648373479, | |
| "grad_norm": 0.7955805659294128, | |
| "learning_rate": 6.1e-06, | |
| "loss": 1.9258, | |
| "num_input_tokens_seen": 16252928, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.015644400297988578, | |
| "grad_norm": 0.7012743353843689, | |
| "learning_rate": 6.200000000000001e-06, | |
| "loss": 1.8984, | |
| "num_input_tokens_seen": 16515072, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.015892724112242365, | |
| "grad_norm": 1.0720924139022827, | |
| "learning_rate": 6.300000000000001e-06, | |
| "loss": 2.3707, | |
| "num_input_tokens_seen": 16777216, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.01614104792649615, | |
| "grad_norm": 0.7156981229782104, | |
| "learning_rate": 6.4000000000000006e-06, | |
| "loss": 2.0082, | |
| "num_input_tokens_seen": 17039360, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.016389371740749937, | |
| "grad_norm": 1.379465103149414, | |
| "learning_rate": 6.5000000000000004e-06, | |
| "loss": 1.893, | |
| "num_input_tokens_seen": 17301504, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.016637695555003724, | |
| "grad_norm": 0.6216750144958496, | |
| "learning_rate": 6.600000000000001e-06, | |
| "loss": 1.7876, | |
| "num_input_tokens_seen": 17563648, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.016886019369257512, | |
| "grad_norm": 0.6770815253257751, | |
| "learning_rate": 6.700000000000001e-06, | |
| "loss": 1.813, | |
| "num_input_tokens_seen": 17825792, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.0171343431835113, | |
| "grad_norm": 0.8068878054618835, | |
| "learning_rate": 6.800000000000001e-06, | |
| "loss": 1.9584, | |
| "num_input_tokens_seen": 18087936, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.017382666997765087, | |
| "grad_norm": 0.642892062664032, | |
| "learning_rate": 6.9e-06, | |
| "loss": 1.5887, | |
| "num_input_tokens_seen": 18350080, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01763099081201887, | |
| "grad_norm": 0.6749325394630432, | |
| "learning_rate": 7e-06, | |
| "loss": 1.7739, | |
| "num_input_tokens_seen": 18612224, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.01787931462627266, | |
| "grad_norm": 0.6361634135246277, | |
| "learning_rate": 7.100000000000001e-06, | |
| "loss": 1.8437, | |
| "num_input_tokens_seen": 18874368, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.018127638440526447, | |
| "grad_norm": 0.8063591718673706, | |
| "learning_rate": 7.2000000000000005e-06, | |
| "loss": 1.7656, | |
| "num_input_tokens_seen": 19136512, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.018375962254780234, | |
| "grad_norm": 0.608739972114563, | |
| "learning_rate": 7.3e-06, | |
| "loss": 2.0104, | |
| "num_input_tokens_seen": 19398656, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.018624286069034022, | |
| "grad_norm": 0.6015883088111877, | |
| "learning_rate": 7.4e-06, | |
| "loss": 2.0805, | |
| "num_input_tokens_seen": 19660800, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.018872609883287806, | |
| "grad_norm": 0.5737051367759705, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.9203, | |
| "num_input_tokens_seen": 19922944, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.019120933697541594, | |
| "grad_norm": 0.5844286680221558, | |
| "learning_rate": 7.600000000000001e-06, | |
| "loss": 2.0768, | |
| "num_input_tokens_seen": 20185088, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.01936925751179538, | |
| "grad_norm": 0.5958046913146973, | |
| "learning_rate": 7.7e-06, | |
| "loss": 1.5849, | |
| "num_input_tokens_seen": 20447232, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.01961758132604917, | |
| "grad_norm": 0.7638349533081055, | |
| "learning_rate": 7.800000000000002e-06, | |
| "loss": 2.2179, | |
| "num_input_tokens_seen": 20709376, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.019865905140302956, | |
| "grad_norm": 0.5547915697097778, | |
| "learning_rate": 7.9e-06, | |
| "loss": 1.8943, | |
| "num_input_tokens_seen": 20971520, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.02011422895455674, | |
| "grad_norm": 0.45996469259262085, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 1.5404, | |
| "num_input_tokens_seen": 21233664, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.020362552768810528, | |
| "grad_norm": 0.5060412883758545, | |
| "learning_rate": 8.1e-06, | |
| "loss": 1.7184, | |
| "num_input_tokens_seen": 21495808, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.020610876583064316, | |
| "grad_norm": 0.5570970773696899, | |
| "learning_rate": 8.2e-06, | |
| "loss": 2.0638, | |
| "num_input_tokens_seen": 21757952, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.020859200397318103, | |
| "grad_norm": 0.47680890560150146, | |
| "learning_rate": 8.3e-06, | |
| "loss": 1.4177, | |
| "num_input_tokens_seen": 22020096, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.02110752421157189, | |
| "grad_norm": 0.5959429144859314, | |
| "learning_rate": 8.400000000000001e-06, | |
| "loss": 2.1659, | |
| "num_input_tokens_seen": 22282240, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.021355848025825675, | |
| "grad_norm": 0.5277214646339417, | |
| "learning_rate": 8.5e-06, | |
| "loss": 1.8083, | |
| "num_input_tokens_seen": 22544384, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.021604171840079463, | |
| "grad_norm": 0.5346829891204834, | |
| "learning_rate": 8.6e-06, | |
| "loss": 1.9323, | |
| "num_input_tokens_seen": 22806528, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.02185249565433325, | |
| "grad_norm": 0.5096192359924316, | |
| "learning_rate": 8.700000000000001e-06, | |
| "loss": 1.401, | |
| "num_input_tokens_seen": 23068672, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.022100819468587038, | |
| "grad_norm": 0.49696552753448486, | |
| "learning_rate": 8.8e-06, | |
| "loss": 1.4828, | |
| "num_input_tokens_seen": 23330816, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.022349143282840826, | |
| "grad_norm": 0.5156976580619812, | |
| "learning_rate": 8.900000000000001e-06, | |
| "loss": 1.9016, | |
| "num_input_tokens_seen": 23592960, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.02259746709709461, | |
| "grad_norm": 0.4339764714241028, | |
| "learning_rate": 9e-06, | |
| "loss": 1.3645, | |
| "num_input_tokens_seen": 23855104, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.022845790911348397, | |
| "grad_norm": 0.5163502097129822, | |
| "learning_rate": 9.100000000000001e-06, | |
| "loss": 1.9044, | |
| "num_input_tokens_seen": 24117248, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.023094114725602185, | |
| "grad_norm": 0.44321632385253906, | |
| "learning_rate": 9.200000000000002e-06, | |
| "loss": 1.7322, | |
| "num_input_tokens_seen": 24379392, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.023342438539855973, | |
| "grad_norm": 0.5554404258728027, | |
| "learning_rate": 9.3e-06, | |
| "loss": 2.0536, | |
| "num_input_tokens_seen": 24641536, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.02359076235410976, | |
| "grad_norm": 0.5148480534553528, | |
| "learning_rate": 9.4e-06, | |
| "loss": 1.9353, | |
| "num_input_tokens_seen": 24903680, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.023839086168363548, | |
| "grad_norm": 0.4365761876106262, | |
| "learning_rate": 9.5e-06, | |
| "loss": 2.1485, | |
| "num_input_tokens_seen": 25165824, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.024087409982617332, | |
| "grad_norm": 0.6153504252433777, | |
| "learning_rate": 9.600000000000001e-06, | |
| "loss": 2.3459, | |
| "num_input_tokens_seen": 25427968, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.02433573379687112, | |
| "grad_norm": 0.7189298272132874, | |
| "learning_rate": 9.7e-06, | |
| "loss": 1.5111, | |
| "num_input_tokens_seen": 25690112, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.024584057611124907, | |
| "grad_norm": 0.40012645721435547, | |
| "learning_rate": 9.800000000000001e-06, | |
| "loss": 2.0235, | |
| "num_input_tokens_seen": 25952256, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.024832381425378695, | |
| "grad_norm": 1.3065471649169922, | |
| "learning_rate": 9.9e-06, | |
| "loss": 2.1165, | |
| "num_input_tokens_seen": 26214400, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.025080705239632482, | |
| "grad_norm": 0.7975507378578186, | |
| "learning_rate": 1e-05, | |
| "loss": 1.722, | |
| "num_input_tokens_seen": 26476544, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.025329029053886266, | |
| "grad_norm": 0.5044583678245544, | |
| "learning_rate": 9.999969538288953e-06, | |
| "loss": 2.0617, | |
| "num_input_tokens_seen": 26738688, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.025577352868140054, | |
| "grad_norm": 0.6180616021156311, | |
| "learning_rate": 9.999878153526974e-06, | |
| "loss": 1.8041, | |
| "num_input_tokens_seen": 27000832, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.02582567668239384, | |
| "grad_norm": 0.3513893485069275, | |
| "learning_rate": 9.999725846827562e-06, | |
| "loss": 2.0049, | |
| "num_input_tokens_seen": 27262976, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.02607400049664763, | |
| "grad_norm": 0.5015475153923035, | |
| "learning_rate": 9.999512620046523e-06, | |
| "loss": 1.9308, | |
| "num_input_tokens_seen": 27525120, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.026322324310901417, | |
| "grad_norm": 0.35490310192108154, | |
| "learning_rate": 9.999238475781957e-06, | |
| "loss": 1.7832, | |
| "num_input_tokens_seen": 27787264, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.0265706481251552, | |
| "grad_norm": 0.4982094168663025, | |
| "learning_rate": 9.998903417374228e-06, | |
| "loss": 2.1659, | |
| "num_input_tokens_seen": 28049408, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.02681897193940899, | |
| "grad_norm": 0.3601139783859253, | |
| "learning_rate": 9.998507448905917e-06, | |
| "loss": 1.8221, | |
| "num_input_tokens_seen": 28311552, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.027067295753662776, | |
| "grad_norm": 0.47446349263191223, | |
| "learning_rate": 9.998050575201772e-06, | |
| "loss": 1.4861, | |
| "num_input_tokens_seen": 28573696, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.027315619567916564, | |
| "grad_norm": 0.4510415196418762, | |
| "learning_rate": 9.997532801828659e-06, | |
| "loss": 1.8413, | |
| "num_input_tokens_seen": 28835840, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02756394338217035, | |
| "grad_norm": 0.34447139501571655, | |
| "learning_rate": 9.99695413509548e-06, | |
| "loss": 1.9358, | |
| "num_input_tokens_seen": 29097984, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.027812267196424136, | |
| "grad_norm": 0.7382912039756775, | |
| "learning_rate": 9.996314582053106e-06, | |
| "loss": 2.0478, | |
| "num_input_tokens_seen": 29360128, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.028060591010677923, | |
| "grad_norm": 0.4270409345626831, | |
| "learning_rate": 9.995614150494293e-06, | |
| "loss": 1.4107, | |
| "num_input_tokens_seen": 29622272, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.02830891482493171, | |
| "grad_norm": 0.6236165761947632, | |
| "learning_rate": 9.994852848953574e-06, | |
| "loss": 1.9327, | |
| "num_input_tokens_seen": 29884416, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.0285572386391855, | |
| "grad_norm": 0.44820812344551086, | |
| "learning_rate": 9.994030686707171e-06, | |
| "loss": 1.6324, | |
| "num_input_tokens_seen": 30146560, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.028805562453439286, | |
| "grad_norm": 0.34471920132637024, | |
| "learning_rate": 9.993147673772869e-06, | |
| "loss": 2.0254, | |
| "num_input_tokens_seen": 30408704, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.02905388626769307, | |
| "grad_norm": 0.4757576584815979, | |
| "learning_rate": 9.992203820909906e-06, | |
| "loss": 2.1909, | |
| "num_input_tokens_seen": 30670848, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.029302210081946858, | |
| "grad_norm": 0.5577523112297058, | |
| "learning_rate": 9.991199139618828e-06, | |
| "loss": 1.7591, | |
| "num_input_tokens_seen": 30932992, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.029550533896200645, | |
| "grad_norm": 0.4104521572589874, | |
| "learning_rate": 9.990133642141359e-06, | |
| "loss": 1.8473, | |
| "num_input_tokens_seen": 31195136, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.029798857710454433, | |
| "grad_norm": 0.3846544921398163, | |
| "learning_rate": 9.989007341460251e-06, | |
| "loss": 1.786, | |
| "num_input_tokens_seen": 31457280, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.03004718152470822, | |
| "grad_norm": 0.5335818529129028, | |
| "learning_rate": 9.987820251299121e-06, | |
| "loss": 2.5372, | |
| "num_input_tokens_seen": 31719424, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.030295505338962008, | |
| "grad_norm": 0.5046745538711548, | |
| "learning_rate": 9.98657238612229e-06, | |
| "loss": 2.0604, | |
| "num_input_tokens_seen": 31981568, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.030543829153215792, | |
| "grad_norm": 0.554063618183136, | |
| "learning_rate": 9.985263761134602e-06, | |
| "loss": 2.0795, | |
| "num_input_tokens_seen": 32243712, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.03079215296746958, | |
| "grad_norm": 0.3117339611053467, | |
| "learning_rate": 9.983894392281237e-06, | |
| "loss": 1.7701, | |
| "num_input_tokens_seen": 32505856, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.031040476781723367, | |
| "grad_norm": 0.42565709352493286, | |
| "learning_rate": 9.982464296247523e-06, | |
| "loss": 1.7209, | |
| "num_input_tokens_seen": 32768000, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.031288800595977155, | |
| "grad_norm": 0.5742325782775879, | |
| "learning_rate": 9.980973490458728e-06, | |
| "loss": 1.5624, | |
| "num_input_tokens_seen": 33030144, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.03153712441023094, | |
| "grad_norm": 0.4478677213191986, | |
| "learning_rate": 9.979421993079853e-06, | |
| "loss": 2.0519, | |
| "num_input_tokens_seen": 33292288, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.03178544822448473, | |
| "grad_norm": 0.40014106035232544, | |
| "learning_rate": 9.9778098230154e-06, | |
| "loss": 1.7002, | |
| "num_input_tokens_seen": 33554432, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.032033772038738514, | |
| "grad_norm": 0.37266790866851807, | |
| "learning_rate": 9.976136999909156e-06, | |
| "loss": 1.7795, | |
| "num_input_tokens_seen": 33816576, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.0322820958529923, | |
| "grad_norm": 0.7558661103248596, | |
| "learning_rate": 9.974403544143942e-06, | |
| "loss": 1.5417, | |
| "num_input_tokens_seen": 34078720, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.03253041966724609, | |
| "grad_norm": 0.42118939757347107, | |
| "learning_rate": 9.972609476841368e-06, | |
| "loss": 1.728, | |
| "num_input_tokens_seen": 34340864, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.032778743481499874, | |
| "grad_norm": 0.45237675309181213, | |
| "learning_rate": 9.970754819861577e-06, | |
| "loss": 1.651, | |
| "num_input_tokens_seen": 34603008, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.033027067295753665, | |
| "grad_norm": 0.42204225063323975, | |
| "learning_rate": 9.968839595802982e-06, | |
| "loss": 1.6179, | |
| "num_input_tokens_seen": 34865152, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.03327539111000745, | |
| "grad_norm": 0.7443103790283203, | |
| "learning_rate": 9.966863828001982e-06, | |
| "loss": 2.0339, | |
| "num_input_tokens_seen": 35127296, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.03352371492426124, | |
| "grad_norm": 0.46790680289268494, | |
| "learning_rate": 9.964827540532685e-06, | |
| "loss": 1.7902, | |
| "num_input_tokens_seen": 35389440, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.033772038738515024, | |
| "grad_norm": 0.4609277546405792, | |
| "learning_rate": 9.962730758206612e-06, | |
| "loss": 1.7105, | |
| "num_input_tokens_seen": 35651584, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.03402036255276881, | |
| "grad_norm": 0.4367188513278961, | |
| "learning_rate": 9.960573506572391e-06, | |
| "loss": 1.5516, | |
| "num_input_tokens_seen": 35913728, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.0342686863670226, | |
| "grad_norm": 0.518988311290741, | |
| "learning_rate": 9.958355811915452e-06, | |
| "loss": 1.4072, | |
| "num_input_tokens_seen": 36175872, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.034517010181276384, | |
| "grad_norm": 0.32017022371292114, | |
| "learning_rate": 9.95607770125771e-06, | |
| "loss": 1.7326, | |
| "num_input_tokens_seen": 36438016, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.034765333995530175, | |
| "grad_norm": 0.4322156310081482, | |
| "learning_rate": 9.953739202357219e-06, | |
| "loss": 1.3485, | |
| "num_input_tokens_seen": 36700160, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.03501365780978396, | |
| "grad_norm": 0.5065650939941406, | |
| "learning_rate": 9.951340343707852e-06, | |
| "loss": 1.8844, | |
| "num_input_tokens_seen": 36962304, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.03526198162403774, | |
| "grad_norm": 0.46633732318878174, | |
| "learning_rate": 9.948881154538946e-06, | |
| "loss": 1.0832, | |
| "num_input_tokens_seen": 37224448, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.035510305438291534, | |
| "grad_norm": 0.42399951815605164, | |
| "learning_rate": 9.946361664814942e-06, | |
| "loss": 2.0688, | |
| "num_input_tokens_seen": 37486592, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.03575862925254532, | |
| "grad_norm": 0.6287701725959778, | |
| "learning_rate": 9.94378190523503e-06, | |
| "loss": 1.6954, | |
| "num_input_tokens_seen": 37748736, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.03600695306679911, | |
| "grad_norm": 0.38575854897499084, | |
| "learning_rate": 9.941141907232766e-06, | |
| "loss": 1.6803, | |
| "num_input_tokens_seen": 38010880, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.03625527688105289, | |
| "grad_norm": 0.5871158242225647, | |
| "learning_rate": 9.938441702975689e-06, | |
| "loss": 2.2275, | |
| "num_input_tokens_seen": 38273024, | |
| "step": 146 | |
| }, | |
| { | |
| "epoch": 0.03650360069530668, | |
| "grad_norm": 0.4878631830215454, | |
| "learning_rate": 9.93568132536494e-06, | |
| "loss": 1.9927, | |
| "num_input_tokens_seen": 38535168, | |
| "step": 147 | |
| }, | |
| { | |
| "epoch": 0.03675192450956047, | |
| "grad_norm": 0.6624669432640076, | |
| "learning_rate": 9.932860808034847e-06, | |
| "loss": 1.6445, | |
| "num_input_tokens_seen": 38797312, | |
| "step": 148 | |
| }, | |
| { | |
| "epoch": 0.03700024832381425, | |
| "grad_norm": 0.523557722568512, | |
| "learning_rate": 9.929980185352525e-06, | |
| "loss": 1.9669, | |
| "num_input_tokens_seen": 39059456, | |
| "step": 149 | |
| }, | |
| { | |
| "epoch": 0.037248572138068044, | |
| "grad_norm": 0.3871573805809021, | |
| "learning_rate": 9.927039492417452e-06, | |
| "loss": 1.57, | |
| "num_input_tokens_seen": 39321600, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03749689595232183, | |
| "grad_norm": 0.459677129983902, | |
| "learning_rate": 9.924038765061042e-06, | |
| "loss": 1.7627, | |
| "num_input_tokens_seen": 39583744, | |
| "step": 151 | |
| }, | |
| { | |
| "epoch": 0.03774521976657561, | |
| "grad_norm": 0.7199493646621704, | |
| "learning_rate": 9.92097803984621e-06, | |
| "loss": 1.6882, | |
| "num_input_tokens_seen": 39845888, | |
| "step": 152 | |
| }, | |
| { | |
| "epoch": 0.0379935435808294, | |
| "grad_norm": 0.4936988353729248, | |
| "learning_rate": 9.91785735406693e-06, | |
| "loss": 1.8768, | |
| "num_input_tokens_seen": 40108032, | |
| "step": 153 | |
| }, | |
| { | |
| "epoch": 0.03824186739508319, | |
| "grad_norm": 0.44318658113479614, | |
| "learning_rate": 9.914676745747772e-06, | |
| "loss": 1.6635, | |
| "num_input_tokens_seen": 40370176, | |
| "step": 154 | |
| }, | |
| { | |
| "epoch": 0.03849019120933698, | |
| "grad_norm": 0.438924103975296, | |
| "learning_rate": 9.911436253643445e-06, | |
| "loss": 1.6874, | |
| "num_input_tokens_seen": 40632320, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.03873851502359076, | |
| "grad_norm": 0.37632086873054504, | |
| "learning_rate": 9.908135917238321e-06, | |
| "loss": 2.1325, | |
| "num_input_tokens_seen": 40894464, | |
| "step": 156 | |
| }, | |
| { | |
| "epoch": 0.03898683883784455, | |
| "grad_norm": 0.4754061698913574, | |
| "learning_rate": 9.904775776745959e-06, | |
| "loss": 1.6958, | |
| "num_input_tokens_seen": 41156608, | |
| "step": 157 | |
| }, | |
| { | |
| "epoch": 0.03923516265209834, | |
| "grad_norm": 0.629783570766449, | |
| "learning_rate": 9.901355873108611e-06, | |
| "loss": 1.6854, | |
| "num_input_tokens_seen": 41418752, | |
| "step": 158 | |
| }, | |
| { | |
| "epoch": 0.03948348646635212, | |
| "grad_norm": 0.4472093880176544, | |
| "learning_rate": 9.89787624799672e-06, | |
| "loss": 1.9023, | |
| "num_input_tokens_seen": 41680896, | |
| "step": 159 | |
| }, | |
| { | |
| "epoch": 0.03973181028060591, | |
| "grad_norm": 0.35216960310935974, | |
| "learning_rate": 9.894336943808426e-06, | |
| "loss": 1.9459, | |
| "num_input_tokens_seen": 41943040, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0399801340948597, | |
| "grad_norm": 0.34789201617240906, | |
| "learning_rate": 9.890738003669029e-06, | |
| "loss": 2.0254, | |
| "num_input_tokens_seen": 42205184, | |
| "step": 161 | |
| }, | |
| { | |
| "epoch": 0.04022845790911348, | |
| "grad_norm": 0.5008848309516907, | |
| "learning_rate": 9.887079471430481e-06, | |
| "loss": 1.7256, | |
| "num_input_tokens_seen": 42467328, | |
| "step": 162 | |
| }, | |
| { | |
| "epoch": 0.04047678172336727, | |
| "grad_norm": 0.2768523395061493, | |
| "learning_rate": 9.883361391670841e-06, | |
| "loss": 1.4073, | |
| "num_input_tokens_seen": 42729472, | |
| "step": 163 | |
| }, | |
| { | |
| "epoch": 0.040725105537621056, | |
| "grad_norm": 0.25057297945022583, | |
| "learning_rate": 9.879583809693737e-06, | |
| "loss": 1.8378, | |
| "num_input_tokens_seen": 42991616, | |
| "step": 164 | |
| }, | |
| { | |
| "epoch": 0.04097342935187485, | |
| "grad_norm": 0.34032392501831055, | |
| "learning_rate": 9.875746771527817e-06, | |
| "loss": 2.0236, | |
| "num_input_tokens_seen": 43253760, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.04122175316612863, | |
| "grad_norm": 0.34935250878334045, | |
| "learning_rate": 9.871850323926178e-06, | |
| "loss": 1.25, | |
| "num_input_tokens_seen": 43515904, | |
| "step": 166 | |
| }, | |
| { | |
| "epoch": 0.041470076980382416, | |
| "grad_norm": 0.4536452889442444, | |
| "learning_rate": 9.867894514365802e-06, | |
| "loss": 1.9923, | |
| "num_input_tokens_seen": 43778048, | |
| "step": 167 | |
| }, | |
| { | |
| "epoch": 0.04171840079463621, | |
| "grad_norm": 0.38076460361480713, | |
| "learning_rate": 9.863879391046985e-06, | |
| "loss": 1.6626, | |
| "num_input_tokens_seen": 44040192, | |
| "step": 168 | |
| }, | |
| { | |
| "epoch": 0.04196672460888999, | |
| "grad_norm": 0.4140561521053314, | |
| "learning_rate": 9.859805002892733e-06, | |
| "loss": 1.7342, | |
| "num_input_tokens_seen": 44302336, | |
| "step": 169 | |
| }, | |
| { | |
| "epoch": 0.04221504842314378, | |
| "grad_norm": 0.5397564172744751, | |
| "learning_rate": 9.85567139954818e-06, | |
| "loss": 1.8625, | |
| "num_input_tokens_seen": 44564480, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.042463372237397566, | |
| "grad_norm": 0.2765776216983795, | |
| "learning_rate": 9.851478631379982e-06, | |
| "loss": 1.9361, | |
| "num_input_tokens_seen": 44826624, | |
| "step": 171 | |
| }, | |
| { | |
| "epoch": 0.04271169605165135, | |
| "grad_norm": 0.3303300440311432, | |
| "learning_rate": 9.847226749475696e-06, | |
| "loss": 1.9308, | |
| "num_input_tokens_seen": 45088768, | |
| "step": 172 | |
| }, | |
| { | |
| "epoch": 0.04296001986590514, | |
| "grad_norm": 0.5077419281005859, | |
| "learning_rate": 9.842915805643156e-06, | |
| "loss": 1.8804, | |
| "num_input_tokens_seen": 45350912, | |
| "step": 173 | |
| }, | |
| { | |
| "epoch": 0.043208343680158925, | |
| "grad_norm": 0.5909125208854675, | |
| "learning_rate": 9.838545852409857e-06, | |
| "loss": 1.8626, | |
| "num_input_tokens_seen": 45613056, | |
| "step": 174 | |
| }, | |
| { | |
| "epoch": 0.04345666749441272, | |
| "grad_norm": 0.40436893701553345, | |
| "learning_rate": 9.834116943022299e-06, | |
| "loss": 1.3216, | |
| "num_input_tokens_seen": 45875200, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.0437049913086665, | |
| "grad_norm": 0.2543845772743225, | |
| "learning_rate": 9.829629131445342e-06, | |
| "loss": 1.8692, | |
| "num_input_tokens_seen": 46137344, | |
| "step": 176 | |
| }, | |
| { | |
| "epoch": 0.043953315122920285, | |
| "grad_norm": 0.3154657185077667, | |
| "learning_rate": 9.825082472361558e-06, | |
| "loss": 1.8267, | |
| "num_input_tokens_seen": 46399488, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.044201638937174076, | |
| "grad_norm": 0.2858025133609772, | |
| "learning_rate": 9.82047702117055e-06, | |
| "loss": 2.0557, | |
| "num_input_tokens_seen": 46661632, | |
| "step": 178 | |
| }, | |
| { | |
| "epoch": 0.04444996275142786, | |
| "grad_norm": 0.47114500403404236, | |
| "learning_rate": 9.815812833988292e-06, | |
| "loss": 1.8631, | |
| "num_input_tokens_seen": 46923776, | |
| "step": 179 | |
| }, | |
| { | |
| "epoch": 0.04469828656568165, | |
| "grad_norm": 0.3492976427078247, | |
| "learning_rate": 9.811089967646427e-06, | |
| "loss": 1.6999, | |
| "num_input_tokens_seen": 47185920, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.044946610379935435, | |
| "grad_norm": 0.5230903625488281, | |
| "learning_rate": 9.806308479691595e-06, | |
| "loss": 1.9586, | |
| "num_input_tokens_seen": 47448064, | |
| "step": 181 | |
| }, | |
| { | |
| "epoch": 0.04519493419418922, | |
| "grad_norm": 0.3736109733581543, | |
| "learning_rate": 9.801468428384716e-06, | |
| "loss": 1.6724, | |
| "num_input_tokens_seen": 47710208, | |
| "step": 182 | |
| }, | |
| { | |
| "epoch": 0.04544325800844301, | |
| "grad_norm": 0.38272184133529663, | |
| "learning_rate": 9.796569872700287e-06, | |
| "loss": 2.0805, | |
| "num_input_tokens_seen": 47972352, | |
| "step": 183 | |
| }, | |
| { | |
| "epoch": 0.045691581822696795, | |
| "grad_norm": 0.3838115632534027, | |
| "learning_rate": 9.791612872325667e-06, | |
| "loss": 2.076, | |
| "num_input_tokens_seen": 48234496, | |
| "step": 184 | |
| }, | |
| { | |
| "epoch": 0.045939905636950586, | |
| "grad_norm": 0.39449867606163025, | |
| "learning_rate": 9.786597487660336e-06, | |
| "loss": 1.9271, | |
| "num_input_tokens_seen": 48496640, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.04618822945120437, | |
| "grad_norm": 0.5604011416435242, | |
| "learning_rate": 9.781523779815178e-06, | |
| "loss": 2.0907, | |
| "num_input_tokens_seen": 48758784, | |
| "step": 186 | |
| }, | |
| { | |
| "epoch": 0.04643655326545816, | |
| "grad_norm": 0.756406307220459, | |
| "learning_rate": 9.776391810611719e-06, | |
| "loss": 1.8081, | |
| "num_input_tokens_seen": 49020928, | |
| "step": 187 | |
| }, | |
| { | |
| "epoch": 0.046684877079711945, | |
| "grad_norm": 0.3678906261920929, | |
| "learning_rate": 9.771201642581384e-06, | |
| "loss": 1.2397, | |
| "num_input_tokens_seen": 49283072, | |
| "step": 188 | |
| }, | |
| { | |
| "epoch": 0.04693320089396573, | |
| "grad_norm": 0.4872545599937439, | |
| "learning_rate": 9.765953338964736e-06, | |
| "loss": 1.3951, | |
| "num_input_tokens_seen": 49545216, | |
| "step": 189 | |
| }, | |
| { | |
| "epoch": 0.04718152470821952, | |
| "grad_norm": 0.46098363399505615, | |
| "learning_rate": 9.760646963710694e-06, | |
| "loss": 2.052, | |
| "num_input_tokens_seen": 49807360, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.047429848522473304, | |
| "grad_norm": 0.675818681716919, | |
| "learning_rate": 9.755282581475769e-06, | |
| "loss": 1.7571, | |
| "num_input_tokens_seen": 50069504, | |
| "step": 191 | |
| }, | |
| { | |
| "epoch": 0.047678172336727095, | |
| "grad_norm": 0.6060460209846497, | |
| "learning_rate": 9.749860257623262e-06, | |
| "loss": 1.854, | |
| "num_input_tokens_seen": 50331648, | |
| "step": 192 | |
| }, | |
| { | |
| "epoch": 0.04792649615098088, | |
| "grad_norm": 0.47795215249061584, | |
| "learning_rate": 9.744380058222483e-06, | |
| "loss": 1.7057, | |
| "num_input_tokens_seen": 50593792, | |
| "step": 193 | |
| }, | |
| { | |
| "epoch": 0.048174819965234664, | |
| "grad_norm": 0.5348641872406006, | |
| "learning_rate": 9.73884205004793e-06, | |
| "loss": 1.8599, | |
| "num_input_tokens_seen": 50855936, | |
| "step": 194 | |
| }, | |
| { | |
| "epoch": 0.048423143779488455, | |
| "grad_norm": 0.4470706284046173, | |
| "learning_rate": 9.733246300578482e-06, | |
| "loss": 1.427, | |
| "num_input_tokens_seen": 51118080, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.04867146759374224, | |
| "grad_norm": 0.35019198060035706, | |
| "learning_rate": 9.727592877996585e-06, | |
| "loss": 1.6146, | |
| "num_input_tokens_seen": 51380224, | |
| "step": 196 | |
| }, | |
| { | |
| "epoch": 0.04891979140799603, | |
| "grad_norm": 0.4542747139930725, | |
| "learning_rate": 9.721881851187406e-06, | |
| "loss": 1.8169, | |
| "num_input_tokens_seen": 51642368, | |
| "step": 197 | |
| }, | |
| { | |
| "epoch": 0.049168115222249814, | |
| "grad_norm": 0.5041635632514954, | |
| "learning_rate": 9.716113289738005e-06, | |
| "loss": 1.7434, | |
| "num_input_tokens_seen": 51904512, | |
| "step": 198 | |
| }, | |
| { | |
| "epoch": 0.0494164390365036, | |
| "grad_norm": 0.39864203333854675, | |
| "learning_rate": 9.710287263936485e-06, | |
| "loss": 1.5456, | |
| "num_input_tokens_seen": 52166656, | |
| "step": 199 | |
| }, | |
| { | |
| "epoch": 0.04966476285075739, | |
| "grad_norm": 0.4882585108280182, | |
| "learning_rate": 9.704403844771128e-06, | |
| "loss": 1.5535, | |
| "num_input_tokens_seen": 52428800, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.049913086665011173, | |
| "grad_norm": 0.33271995186805725, | |
| "learning_rate": 9.698463103929542e-06, | |
| "loss": 1.7225, | |
| "num_input_tokens_seen": 52690944, | |
| "step": 201 | |
| }, | |
| { | |
| "epoch": 0.050161410479264965, | |
| "grad_norm": 0.5818848609924316, | |
| "learning_rate": 9.69246511379778e-06, | |
| "loss": 1.8262, | |
| "num_input_tokens_seen": 52953088, | |
| "step": 202 | |
| }, | |
| { | |
| "epoch": 0.05040973429351875, | |
| "grad_norm": 0.3519175946712494, | |
| "learning_rate": 9.68640994745946e-06, | |
| "loss": 1.8536, | |
| "num_input_tokens_seen": 53215232, | |
| "step": 203 | |
| }, | |
| { | |
| "epoch": 0.05065805810777253, | |
| "grad_norm": 0.30881020426750183, | |
| "learning_rate": 9.680297678694867e-06, | |
| "loss": 1.7819, | |
| "num_input_tokens_seen": 53477376, | |
| "step": 204 | |
| }, | |
| { | |
| "epoch": 0.050906381922026324, | |
| "grad_norm": 0.28387659788131714, | |
| "learning_rate": 9.674128381980073e-06, | |
| "loss": 1.6913, | |
| "num_input_tokens_seen": 53739520, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.05115470573628011, | |
| "grad_norm": 0.42218366265296936, | |
| "learning_rate": 9.667902132486009e-06, | |
| "loss": 1.3839, | |
| "num_input_tokens_seen": 54001664, | |
| "step": 206 | |
| }, | |
| { | |
| "epoch": 0.0514030295505339, | |
| "grad_norm": 0.3479291796684265, | |
| "learning_rate": 9.661619006077562e-06, | |
| "loss": 1.7449, | |
| "num_input_tokens_seen": 54263808, | |
| "step": 207 | |
| }, | |
| { | |
| "epoch": 0.05165135336478768, | |
| "grad_norm": 0.41011831164360046, | |
| "learning_rate": 9.655279079312643e-06, | |
| "loss": 1.3836, | |
| "num_input_tokens_seen": 54525952, | |
| "step": 208 | |
| }, | |
| { | |
| "epoch": 0.05189967717904147, | |
| "grad_norm": 0.3655335605144501, | |
| "learning_rate": 9.648882429441258e-06, | |
| "loss": 2.2184, | |
| "num_input_tokens_seen": 54788096, | |
| "step": 209 | |
| }, | |
| { | |
| "epoch": 0.05214800099329526, | |
| "grad_norm": 0.4303296208381653, | |
| "learning_rate": 9.642429134404568e-06, | |
| "loss": 1.8072, | |
| "num_input_tokens_seen": 55050240, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.05239632480754904, | |
| "grad_norm": 0.4718409776687622, | |
| "learning_rate": 9.635919272833938e-06, | |
| "loss": 1.7503, | |
| "num_input_tokens_seen": 55312384, | |
| "step": 211 | |
| }, | |
| { | |
| "epoch": 0.052644648621802834, | |
| "grad_norm": 0.41102349758148193, | |
| "learning_rate": 9.629352924049975e-06, | |
| "loss": 1.5696, | |
| "num_input_tokens_seen": 55574528, | |
| "step": 212 | |
| }, | |
| { | |
| "epoch": 0.05289297243605662, | |
| "grad_norm": 0.40920042991638184, | |
| "learning_rate": 9.622730168061568e-06, | |
| "loss": 1.354, | |
| "num_input_tokens_seen": 55836672, | |
| "step": 213 | |
| }, | |
| { | |
| "epoch": 0.0531412962503104, | |
| "grad_norm": 0.2790515124797821, | |
| "learning_rate": 9.616051085564905e-06, | |
| "loss": 1.6552, | |
| "num_input_tokens_seen": 56098816, | |
| "step": 214 | |
| }, | |
| { | |
| "epoch": 0.05338962006456419, | |
| "grad_norm": 0.708991289138794, | |
| "learning_rate": 9.609315757942504e-06, | |
| "loss": 1.4587, | |
| "num_input_tokens_seen": 56360960, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.05363794387881798, | |
| "grad_norm": 0.5307122468948364, | |
| "learning_rate": 9.602524267262202e-06, | |
| "loss": 2.0549, | |
| "num_input_tokens_seen": 56623104, | |
| "step": 216 | |
| }, | |
| { | |
| "epoch": 0.05388626769307177, | |
| "grad_norm": 0.6132609248161316, | |
| "learning_rate": 9.595676696276173e-06, | |
| "loss": 1.8739, | |
| "num_input_tokens_seen": 56885248, | |
| "step": 217 | |
| }, | |
| { | |
| "epoch": 0.05413459150732555, | |
| "grad_norm": 0.4902276396751404, | |
| "learning_rate": 9.588773128419907e-06, | |
| "loss": 2.0105, | |
| "num_input_tokens_seen": 57147392, | |
| "step": 218 | |
| }, | |
| { | |
| "epoch": 0.054382915321579336, | |
| "grad_norm": 0.40454724431037903, | |
| "learning_rate": 9.581813647811199e-06, | |
| "loss": 1.9691, | |
| "num_input_tokens_seen": 57409536, | |
| "step": 219 | |
| }, | |
| { | |
| "epoch": 0.05463123913583313, | |
| "grad_norm": 0.5375818610191345, | |
| "learning_rate": 9.574798339249124e-06, | |
| "loss": 1.9857, | |
| "num_input_tokens_seen": 57671680, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.05487956295008691, | |
| "grad_norm": 0.31554529070854187, | |
| "learning_rate": 9.567727288213005e-06, | |
| "loss": 1.7783, | |
| "num_input_tokens_seen": 57933824, | |
| "step": 221 | |
| }, | |
| { | |
| "epoch": 0.0551278867643407, | |
| "grad_norm": 0.5682997703552246, | |
| "learning_rate": 9.560600580861366e-06, | |
| "loss": 1.8144, | |
| "num_input_tokens_seen": 58195968, | |
| "step": 222 | |
| }, | |
| { | |
| "epoch": 0.05537621057859449, | |
| "grad_norm": 0.393583208322525, | |
| "learning_rate": 9.553418304030886e-06, | |
| "loss": 1.9838, | |
| "num_input_tokens_seen": 58458112, | |
| "step": 223 | |
| }, | |
| { | |
| "epoch": 0.05562453439284827, | |
| "grad_norm": 0.42172202467918396, | |
| "learning_rate": 9.546180545235344e-06, | |
| "loss": 1.7532, | |
| "num_input_tokens_seen": 58720256, | |
| "step": 224 | |
| }, | |
| { | |
| "epoch": 0.05587285820710206, | |
| "grad_norm": 0.4001232981681824, | |
| "learning_rate": 9.538887392664544e-06, | |
| "loss": 2.2716, | |
| "num_input_tokens_seen": 58982400, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.056121182021355846, | |
| "grad_norm": 0.2886028289794922, | |
| "learning_rate": 9.531538935183252e-06, | |
| "loss": 1.5989, | |
| "num_input_tokens_seen": 59244544, | |
| "step": 226 | |
| }, | |
| { | |
| "epoch": 0.05636950583560964, | |
| "grad_norm": 0.49188050627708435, | |
| "learning_rate": 9.524135262330098e-06, | |
| "loss": 1.7318, | |
| "num_input_tokens_seen": 59506688, | |
| "step": 227 | |
| }, | |
| { | |
| "epoch": 0.05661782964986342, | |
| "grad_norm": 0.46622851490974426, | |
| "learning_rate": 9.516676464316505e-06, | |
| "loss": 1.4116, | |
| "num_input_tokens_seen": 59768832, | |
| "step": 228 | |
| }, | |
| { | |
| "epoch": 0.056866153464117206, | |
| "grad_norm": 0.26139262318611145, | |
| "learning_rate": 9.50916263202557e-06, | |
| "loss": 1.6799, | |
| "num_input_tokens_seen": 60030976, | |
| "step": 229 | |
| }, | |
| { | |
| "epoch": 0.057114477278371, | |
| "grad_norm": 0.4152681827545166, | |
| "learning_rate": 9.501593857010968e-06, | |
| "loss": 2.0024, | |
| "num_input_tokens_seen": 60293120, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.05736280109262478, | |
| "grad_norm": 0.683701753616333, | |
| "learning_rate": 9.493970231495836e-06, | |
| "loss": 1.7395, | |
| "num_input_tokens_seen": 60555264, | |
| "step": 231 | |
| }, | |
| { | |
| "epoch": 0.05761112490687857, | |
| "grad_norm": 0.4206884503364563, | |
| "learning_rate": 9.486291848371642e-06, | |
| "loss": 1.4044, | |
| "num_input_tokens_seen": 60817408, | |
| "step": 232 | |
| }, | |
| { | |
| "epoch": 0.057859448721132356, | |
| "grad_norm": 0.3584212064743042, | |
| "learning_rate": 9.478558801197065e-06, | |
| "loss": 1.6407, | |
| "num_input_tokens_seen": 61079552, | |
| "step": 233 | |
| }, | |
| { | |
| "epoch": 0.05810777253538614, | |
| "grad_norm": 0.3988575041294098, | |
| "learning_rate": 9.470771184196842e-06, | |
| "loss": 1.8871, | |
| "num_input_tokens_seen": 61341696, | |
| "step": 234 | |
| }, | |
| { | |
| "epoch": 0.05835609634963993, | |
| "grad_norm": 0.6429465413093567, | |
| "learning_rate": 9.46292909226063e-06, | |
| "loss": 1.7096, | |
| "num_input_tokens_seen": 61603840, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.058604420163893715, | |
| "grad_norm": 0.5112093091011047, | |
| "learning_rate": 9.45503262094184e-06, | |
| "loss": 1.878, | |
| "num_input_tokens_seen": 61865984, | |
| "step": 236 | |
| }, | |
| { | |
| "epoch": 0.058852743978147506, | |
| "grad_norm": 0.6004856824874878, | |
| "learning_rate": 9.44708186645649e-06, | |
| "loss": 1.73, | |
| "num_input_tokens_seen": 62128128, | |
| "step": 237 | |
| }, | |
| { | |
| "epoch": 0.05910106779240129, | |
| "grad_norm": 0.5572634339332581, | |
| "learning_rate": 9.439076925682006e-06, | |
| "loss": 1.601, | |
| "num_input_tokens_seen": 62390272, | |
| "step": 238 | |
| }, | |
| { | |
| "epoch": 0.05934939160665508, | |
| "grad_norm": 0.7834048271179199, | |
| "learning_rate": 9.431017896156074e-06, | |
| "loss": 1.8971, | |
| "num_input_tokens_seen": 62652416, | |
| "step": 239 | |
| }, | |
| { | |
| "epoch": 0.059597715420908866, | |
| "grad_norm": 0.5589991807937622, | |
| "learning_rate": 9.42290487607542e-06, | |
| "loss": 1.5294, | |
| "num_input_tokens_seen": 62914560, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.05984603923516265, | |
| "grad_norm": 0.48503783345222473, | |
| "learning_rate": 9.414737964294636e-06, | |
| "loss": 1.5151, | |
| "num_input_tokens_seen": 63176704, | |
| "step": 241 | |
| }, | |
| { | |
| "epoch": 0.06009436304941644, | |
| "grad_norm": 0.39491578936576843, | |
| "learning_rate": 9.406517260324962e-06, | |
| "loss": 1.272, | |
| "num_input_tokens_seen": 63438848, | |
| "step": 242 | |
| }, | |
| { | |
| "epoch": 0.060342686863670225, | |
| "grad_norm": 0.5852888822555542, | |
| "learning_rate": 9.398242864333084e-06, | |
| "loss": 1.6314, | |
| "num_input_tokens_seen": 63700992, | |
| "step": 243 | |
| }, | |
| { | |
| "epoch": 0.060591010677924016, | |
| "grad_norm": 0.4342246949672699, | |
| "learning_rate": 9.389914877139903e-06, | |
| "loss": 1.8619, | |
| "num_input_tokens_seen": 63963136, | |
| "step": 244 | |
| }, | |
| { | |
| "epoch": 0.0608393344921778, | |
| "grad_norm": 0.45139801502227783, | |
| "learning_rate": 9.381533400219319e-06, | |
| "loss": 2.0767, | |
| "num_input_tokens_seen": 64225280, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.061087658306431585, | |
| "grad_norm": 0.5253079533576965, | |
| "learning_rate": 9.37309853569698e-06, | |
| "loss": 1.7857, | |
| "num_input_tokens_seen": 64487424, | |
| "step": 246 | |
| }, | |
| { | |
| "epoch": 0.061335982120685376, | |
| "grad_norm": 0.5168160796165466, | |
| "learning_rate": 9.364610386349048e-06, | |
| "loss": 1.7157, | |
| "num_input_tokens_seen": 64749568, | |
| "step": 247 | |
| }, | |
| { | |
| "epoch": 0.06158430593493916, | |
| "grad_norm": 0.6876463890075684, | |
| "learning_rate": 9.356069055600949e-06, | |
| "loss": 1.9186, | |
| "num_input_tokens_seen": 65011712, | |
| "step": 248 | |
| }, | |
| { | |
| "epoch": 0.06183262974919295, | |
| "grad_norm": 0.5097318887710571, | |
| "learning_rate": 9.347474647526095e-06, | |
| "loss": 1.806, | |
| "num_input_tokens_seen": 65273856, | |
| "step": 249 | |
| }, | |
| { | |
| "epoch": 0.062080953563446735, | |
| "grad_norm": 0.4346969425678253, | |
| "learning_rate": 9.338827266844643e-06, | |
| "loss": 1.9837, | |
| "num_input_tokens_seen": 65536000, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.06232927737770052, | |
| "grad_norm": 0.4577252268791199, | |
| "learning_rate": 9.330127018922195e-06, | |
| "loss": 1.9294, | |
| "num_input_tokens_seen": 65798144, | |
| "step": 251 | |
| }, | |
| { | |
| "epoch": 0.06257760119195431, | |
| "grad_norm": 0.5622639656066895, | |
| "learning_rate": 9.321374009768525e-06, | |
| "loss": 1.2883, | |
| "num_input_tokens_seen": 66060288, | |
| "step": 252 | |
| }, | |
| { | |
| "epoch": 0.0628259250062081, | |
| "grad_norm": 0.553583562374115, | |
| "learning_rate": 9.312568346036288e-06, | |
| "loss": 1.7474, | |
| "num_input_tokens_seen": 66322432, | |
| "step": 253 | |
| }, | |
| { | |
| "epoch": 0.06307424882046188, | |
| "grad_norm": 0.6473803520202637, | |
| "learning_rate": 9.30371013501972e-06, | |
| "loss": 1.7102, | |
| "num_input_tokens_seen": 66584576, | |
| "step": 254 | |
| }, | |
| { | |
| "epoch": 0.06332257263471566, | |
| "grad_norm": 0.6553588509559631, | |
| "learning_rate": 9.294799484653323e-06, | |
| "loss": 1.4839, | |
| "num_input_tokens_seen": 66846720, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.06357089644896946, | |
| "grad_norm": 0.5461873412132263, | |
| "learning_rate": 9.285836503510562e-06, | |
| "loss": 2.0798, | |
| "num_input_tokens_seen": 67108864, | |
| "step": 256 | |
| }, | |
| { | |
| "epoch": 0.06381922026322324, | |
| "grad_norm": 0.5196068286895752, | |
| "learning_rate": 9.276821300802535e-06, | |
| "loss": 1.7274, | |
| "num_input_tokens_seen": 67371008, | |
| "step": 257 | |
| }, | |
| { | |
| "epoch": 0.06406754407747703, | |
| "grad_norm": 0.2947503924369812, | |
| "learning_rate": 9.267753986376638e-06, | |
| "loss": 1.8269, | |
| "num_input_tokens_seen": 67633152, | |
| "step": 258 | |
| }, | |
| { | |
| "epoch": 0.06431586789173081, | |
| "grad_norm": 0.41323122382164, | |
| "learning_rate": 9.25863467071524e-06, | |
| "loss": 1.3102, | |
| "num_input_tokens_seen": 67895296, | |
| "step": 259 | |
| }, | |
| { | |
| "epoch": 0.0645641917059846, | |
| "grad_norm": 0.5422347187995911, | |
| "learning_rate": 9.24946346493432e-06, | |
| "loss": 1.7149, | |
| "num_input_tokens_seen": 68157440, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.0648125155202384, | |
| "grad_norm": 0.4071256220340729, | |
| "learning_rate": 9.24024048078213e-06, | |
| "loss": 1.8354, | |
| "num_input_tokens_seen": 68419584, | |
| "step": 261 | |
| }, | |
| { | |
| "epoch": 0.06506083933449218, | |
| "grad_norm": 0.31718364357948303, | |
| "learning_rate": 9.230965830637821e-06, | |
| "loss": 1.6514, | |
| "num_input_tokens_seen": 68681728, | |
| "step": 262 | |
| }, | |
| { | |
| "epoch": 0.06530916314874596, | |
| "grad_norm": 0.5854095816612244, | |
| "learning_rate": 9.221639627510076e-06, | |
| "loss": 1.1938, | |
| "num_input_tokens_seen": 68943872, | |
| "step": 263 | |
| }, | |
| { | |
| "epoch": 0.06555748696299975, | |
| "grad_norm": 0.28129681944847107, | |
| "learning_rate": 9.21226198503574e-06, | |
| "loss": 1.932, | |
| "num_input_tokens_seen": 69206016, | |
| "step": 264 | |
| }, | |
| { | |
| "epoch": 0.06580581077725355, | |
| "grad_norm": 0.39890119433403015, | |
| "learning_rate": 9.202833017478421e-06, | |
| "loss": 2.1795, | |
| "num_input_tokens_seen": 69468160, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.06605413459150733, | |
| "grad_norm": 0.5349065661430359, | |
| "learning_rate": 9.193352839727122e-06, | |
| "loss": 1.7356, | |
| "num_input_tokens_seen": 69730304, | |
| "step": 266 | |
| }, | |
| { | |
| "epoch": 0.06630245840576111, | |
| "grad_norm": 0.5061510801315308, | |
| "learning_rate": 9.18382156729481e-06, | |
| "loss": 1.552, | |
| "num_input_tokens_seen": 69992448, | |
| "step": 267 | |
| }, | |
| { | |
| "epoch": 0.0665507822200149, | |
| "grad_norm": 0.5302243828773499, | |
| "learning_rate": 9.174239316317034e-06, | |
| "loss": 1.6972, | |
| "num_input_tokens_seen": 70254592, | |
| "step": 268 | |
| }, | |
| { | |
| "epoch": 0.06679910603426868, | |
| "grad_norm": 0.4849538803100586, | |
| "learning_rate": 9.164606203550498e-06, | |
| "loss": 1.8502, | |
| "num_input_tokens_seen": 70516736, | |
| "step": 269 | |
| }, | |
| { | |
| "epoch": 0.06704742984852248, | |
| "grad_norm": 0.7993111610412598, | |
| "learning_rate": 9.154922346371641e-06, | |
| "loss": 1.473, | |
| "num_input_tokens_seen": 70778880, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.06729575366277626, | |
| "grad_norm": 0.2985432744026184, | |
| "learning_rate": 9.145187862775208e-06, | |
| "loss": 1.7854, | |
| "num_input_tokens_seen": 71041024, | |
| "step": 271 | |
| }, | |
| { | |
| "epoch": 0.06754407747703005, | |
| "grad_norm": 0.557628333568573, | |
| "learning_rate": 9.13540287137281e-06, | |
| "loss": 1.6575, | |
| "num_input_tokens_seen": 71303168, | |
| "step": 272 | |
| }, | |
| { | |
| "epoch": 0.06779240129128383, | |
| "grad_norm": 0.5635995268821716, | |
| "learning_rate": 9.125567491391476e-06, | |
| "loss": 1.7496, | |
| "num_input_tokens_seen": 71565312, | |
| "step": 273 | |
| }, | |
| { | |
| "epoch": 0.06804072510553762, | |
| "grad_norm": 0.5241788625717163, | |
| "learning_rate": 9.115681842672211e-06, | |
| "loss": 1.4799, | |
| "num_input_tokens_seen": 71827456, | |
| "step": 274 | |
| }, | |
| { | |
| "epoch": 0.06828904891979141, | |
| "grad_norm": 0.7073025107383728, | |
| "learning_rate": 9.10574604566852e-06, | |
| "loss": 2.0472, | |
| "num_input_tokens_seen": 72089600, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.0685373727340452, | |
| "grad_norm": 0.3968837261199951, | |
| "learning_rate": 9.09576022144496e-06, | |
| "loss": 1.2316, | |
| "num_input_tokens_seen": 72351744, | |
| "step": 276 | |
| }, | |
| { | |
| "epoch": 0.06878569654829898, | |
| "grad_norm": 0.42373400926589966, | |
| "learning_rate": 9.085724491675642e-06, | |
| "loss": 1.3935, | |
| "num_input_tokens_seen": 72613888, | |
| "step": 277 | |
| }, | |
| { | |
| "epoch": 0.06903402036255277, | |
| "grad_norm": 0.3875352144241333, | |
| "learning_rate": 9.07563897864277e-06, | |
| "loss": 1.4776, | |
| "num_input_tokens_seen": 72876032, | |
| "step": 278 | |
| }, | |
| { | |
| "epoch": 0.06928234417680655, | |
| "grad_norm": 0.64447420835495, | |
| "learning_rate": 9.065503805235139e-06, | |
| "loss": 1.5065, | |
| "num_input_tokens_seen": 73138176, | |
| "step": 279 | |
| }, | |
| { | |
| "epoch": 0.06953066799106035, | |
| "grad_norm": 0.6507744789123535, | |
| "learning_rate": 9.055319094946633e-06, | |
| "loss": 1.7043, | |
| "num_input_tokens_seen": 73400320, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.06977899180531413, | |
| "grad_norm": 0.6041735410690308, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 1.4371, | |
| "num_input_tokens_seen": 73662464, | |
| "step": 281 | |
| }, | |
| { | |
| "epoch": 0.07002731561956792, | |
| "grad_norm": 0.4756613075733185, | |
| "learning_rate": 9.03480156071901e-06, | |
| "loss": 1.5451, | |
| "num_input_tokens_seen": 73924608, | |
| "step": 282 | |
| }, | |
| { | |
| "epoch": 0.0702756394338217, | |
| "grad_norm": 0.6942863464355469, | |
| "learning_rate": 9.02446898677957e-06, | |
| "loss": 1.1622, | |
| "num_input_tokens_seen": 74186752, | |
| "step": 283 | |
| }, | |
| { | |
| "epoch": 0.07052396324807549, | |
| "grad_norm": 0.5789624452590942, | |
| "learning_rate": 9.014087375955574e-06, | |
| "loss": 2.2199, | |
| "num_input_tokens_seen": 74448896, | |
| "step": 284 | |
| }, | |
| { | |
| "epoch": 0.07077228706232928, | |
| "grad_norm": 0.5487517714500427, | |
| "learning_rate": 9.003656854743667e-06, | |
| "loss": 1.5385, | |
| "num_input_tokens_seen": 74711040, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.07102061087658307, | |
| "grad_norm": 0.34135740995407104, | |
| "learning_rate": 8.993177550236464e-06, | |
| "loss": 1.5421, | |
| "num_input_tokens_seen": 74973184, | |
| "step": 286 | |
| }, | |
| { | |
| "epoch": 0.07126893469083685, | |
| "grad_norm": 0.4900202453136444, | |
| "learning_rate": 8.982649590120982e-06, | |
| "loss": 1.7945, | |
| "num_input_tokens_seen": 75235328, | |
| "step": 287 | |
| }, | |
| { | |
| "epoch": 0.07151725850509064, | |
| "grad_norm": 0.44072678685188293, | |
| "learning_rate": 8.972073102677091e-06, | |
| "loss": 1.8011, | |
| "num_input_tokens_seen": 75497472, | |
| "step": 288 | |
| }, | |
| { | |
| "epoch": 0.07176558231934442, | |
| "grad_norm": 0.4883013069629669, | |
| "learning_rate": 8.961448216775955e-06, | |
| "loss": 1.8165, | |
| "num_input_tokens_seen": 75759616, | |
| "step": 289 | |
| }, | |
| { | |
| "epoch": 0.07201390613359822, | |
| "grad_norm": 0.5138419270515442, | |
| "learning_rate": 8.950775061878453e-06, | |
| "loss": 1.5481, | |
| "num_input_tokens_seen": 76021760, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.072262229947852, | |
| "grad_norm": 0.8689912557601929, | |
| "learning_rate": 8.94005376803361e-06, | |
| "loss": 1.6688, | |
| "num_input_tokens_seen": 76283904, | |
| "step": 291 | |
| }, | |
| { | |
| "epoch": 0.07251055376210579, | |
| "grad_norm": 0.6632862091064453, | |
| "learning_rate": 8.92928446587701e-06, | |
| "loss": 1.6316, | |
| "num_input_tokens_seen": 76546048, | |
| "step": 292 | |
| }, | |
| { | |
| "epoch": 0.07275887757635957, | |
| "grad_norm": 0.5113462209701538, | |
| "learning_rate": 8.9184672866292e-06, | |
| "loss": 1.8658, | |
| "num_input_tokens_seen": 76808192, | |
| "step": 293 | |
| }, | |
| { | |
| "epoch": 0.07300720139061335, | |
| "grad_norm": 0.6166042685508728, | |
| "learning_rate": 8.907602362094094e-06, | |
| "loss": 1.2848, | |
| "num_input_tokens_seen": 77070336, | |
| "step": 294 | |
| }, | |
| { | |
| "epoch": 0.07325552520486715, | |
| "grad_norm": 0.6267765164375305, | |
| "learning_rate": 8.896689824657371e-06, | |
| "loss": 1.5453, | |
| "num_input_tokens_seen": 77332480, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.07350384901912094, | |
| "grad_norm": 0.5441874265670776, | |
| "learning_rate": 8.885729807284855e-06, | |
| "loss": 1.5841, | |
| "num_input_tokens_seen": 77594624, | |
| "step": 296 | |
| }, | |
| { | |
| "epoch": 0.07375217283337472, | |
| "grad_norm": 0.5888817310333252, | |
| "learning_rate": 8.874722443520898e-06, | |
| "loss": 1.9301, | |
| "num_input_tokens_seen": 77856768, | |
| "step": 297 | |
| }, | |
| { | |
| "epoch": 0.0740004966476285, | |
| "grad_norm": 0.8824830055236816, | |
| "learning_rate": 8.863667867486756e-06, | |
| "loss": 1.7341, | |
| "num_input_tokens_seen": 78118912, | |
| "step": 298 | |
| }, | |
| { | |
| "epoch": 0.07424882046188229, | |
| "grad_norm": 0.4109712541103363, | |
| "learning_rate": 8.852566213878947e-06, | |
| "loss": 1.7768, | |
| "num_input_tokens_seen": 78381056, | |
| "step": 299 | |
| }, | |
| { | |
| "epoch": 0.07449714427613609, | |
| "grad_norm": 0.4477173686027527, | |
| "learning_rate": 8.841417617967618e-06, | |
| "loss": 1.3926, | |
| "num_input_tokens_seen": 78643200, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.07474546809038987, | |
| "grad_norm": 0.7767991423606873, | |
| "learning_rate": 8.83022221559489e-06, | |
| "loss": 1.3578, | |
| "num_input_tokens_seen": 78905344, | |
| "step": 301 | |
| }, | |
| { | |
| "epoch": 0.07499379190464366, | |
| "grad_norm": 0.5238236784934998, | |
| "learning_rate": 8.818980143173212e-06, | |
| "loss": 1.7547, | |
| "num_input_tokens_seen": 79167488, | |
| "step": 302 | |
| }, | |
| { | |
| "epoch": 0.07524211571889744, | |
| "grad_norm": 0.4706284999847412, | |
| "learning_rate": 8.807691537683685e-06, | |
| "loss": 2.224, | |
| "num_input_tokens_seen": 79429632, | |
| "step": 303 | |
| }, | |
| { | |
| "epoch": 0.07549043953315122, | |
| "grad_norm": 0.4068174362182617, | |
| "learning_rate": 8.796356536674404e-06, | |
| "loss": 1.8971, | |
| "num_input_tokens_seen": 79691776, | |
| "step": 304 | |
| }, | |
| { | |
| "epoch": 0.07573876334740502, | |
| "grad_norm": 0.36882147192955017, | |
| "learning_rate": 8.784975278258783e-06, | |
| "loss": 1.3618, | |
| "num_input_tokens_seen": 79953920, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.0759870871616588, | |
| "grad_norm": 0.7638546228408813, | |
| "learning_rate": 8.773547901113862e-06, | |
| "loss": 1.4798, | |
| "num_input_tokens_seen": 80216064, | |
| "step": 306 | |
| }, | |
| { | |
| "epoch": 0.07623541097591259, | |
| "grad_norm": 0.7291756868362427, | |
| "learning_rate": 8.762074544478622e-06, | |
| "loss": 1.8117, | |
| "num_input_tokens_seen": 80478208, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 0.07648373479016637, | |
| "grad_norm": 0.35935330390930176, | |
| "learning_rate": 8.750555348152299e-06, | |
| "loss": 1.7963, | |
| "num_input_tokens_seen": 80740352, | |
| "step": 308 | |
| }, | |
| { | |
| "epoch": 0.07673205860442016, | |
| "grad_norm": 0.41468292474746704, | |
| "learning_rate": 8.73899045249266e-06, | |
| "loss": 1.7334, | |
| "num_input_tokens_seen": 81002496, | |
| "step": 309 | |
| }, | |
| { | |
| "epoch": 0.07698038241867396, | |
| "grad_norm": 0.47698289155960083, | |
| "learning_rate": 8.727379998414311e-06, | |
| "loss": 1.5163, | |
| "num_input_tokens_seen": 81264640, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.07722870623292774, | |
| "grad_norm": 0.3247212767601013, | |
| "learning_rate": 8.715724127386971e-06, | |
| "loss": 1.5166, | |
| "num_input_tokens_seen": 81526784, | |
| "step": 311 | |
| }, | |
| { | |
| "epoch": 0.07747703004718152, | |
| "grad_norm": 0.24329149723052979, | |
| "learning_rate": 8.70402298143375e-06, | |
| "loss": 1.1361, | |
| "num_input_tokens_seen": 81788928, | |
| "step": 312 | |
| }, | |
| { | |
| "epoch": 0.07772535386143531, | |
| "grad_norm": 0.4041454493999481, | |
| "learning_rate": 8.692276703129421e-06, | |
| "loss": 1.6928, | |
| "num_input_tokens_seen": 82051072, | |
| "step": 313 | |
| }, | |
| { | |
| "epoch": 0.0779736776756891, | |
| "grad_norm": 0.5690919160842896, | |
| "learning_rate": 8.680485435598674e-06, | |
| "loss": 1.4934, | |
| "num_input_tokens_seen": 82313216, | |
| "step": 314 | |
| }, | |
| { | |
| "epoch": 0.07822200148994289, | |
| "grad_norm": 0.5649420022964478, | |
| "learning_rate": 8.668649322514382e-06, | |
| "loss": 1.4087, | |
| "num_input_tokens_seen": 82575360, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.07847032530419668, | |
| "grad_norm": 0.38145026564598083, | |
| "learning_rate": 8.656768508095853e-06, | |
| "loss": 1.9073, | |
| "num_input_tokens_seen": 82837504, | |
| "step": 316 | |
| }, | |
| { | |
| "epoch": 0.07871864911845046, | |
| "grad_norm": 0.7416847944259644, | |
| "learning_rate": 8.644843137107058e-06, | |
| "loss": 1.4074, | |
| "num_input_tokens_seen": 83099648, | |
| "step": 317 | |
| }, | |
| { | |
| "epoch": 0.07896697293270424, | |
| "grad_norm": 0.5791590213775635, | |
| "learning_rate": 8.632873354854881e-06, | |
| "loss": 1.8003, | |
| "num_input_tokens_seen": 83361792, | |
| "step": 318 | |
| }, | |
| { | |
| "epoch": 0.07921529674695803, | |
| "grad_norm": 0.5541636347770691, | |
| "learning_rate": 8.620859307187339e-06, | |
| "loss": 1.4524, | |
| "num_input_tokens_seen": 83623936, | |
| "step": 319 | |
| }, | |
| { | |
| "epoch": 0.07946362056121183, | |
| "grad_norm": 0.45152053236961365, | |
| "learning_rate": 8.608801140491811e-06, | |
| "loss": 1.9212, | |
| "num_input_tokens_seen": 83886080, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.07971194437546561, | |
| "grad_norm": 0.7486585974693298, | |
| "learning_rate": 8.596699001693257e-06, | |
| "loss": 1.8341, | |
| "num_input_tokens_seen": 84148224, | |
| "step": 321 | |
| }, | |
| { | |
| "epoch": 0.0799602681897194, | |
| "grad_norm": 0.4018547832965851, | |
| "learning_rate": 8.584553038252415e-06, | |
| "loss": 1.6084, | |
| "num_input_tokens_seen": 84410368, | |
| "step": 322 | |
| }, | |
| { | |
| "epoch": 0.08020859200397318, | |
| "grad_norm": 0.5464489459991455, | |
| "learning_rate": 8.572363398164017e-06, | |
| "loss": 1.5227, | |
| "num_input_tokens_seen": 84672512, | |
| "step": 323 | |
| }, | |
| { | |
| "epoch": 0.08045691581822696, | |
| "grad_norm": 0.5198168754577637, | |
| "learning_rate": 8.560130229954985e-06, | |
| "loss": 1.6922, | |
| "num_input_tokens_seen": 84934656, | |
| "step": 324 | |
| }, | |
| { | |
| "epoch": 0.08070523963248076, | |
| "grad_norm": 0.48899322748184204, | |
| "learning_rate": 8.547853682682605e-06, | |
| "loss": 1.6412, | |
| "num_input_tokens_seen": 85196800, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.08095356344673454, | |
| "grad_norm": 0.2365017831325531, | |
| "learning_rate": 8.535533905932739e-06, | |
| "loss": 1.5639, | |
| "num_input_tokens_seen": 85458944, | |
| "step": 326 | |
| }, | |
| { | |
| "epoch": 0.08120188726098833, | |
| "grad_norm": 0.4440731704235077, | |
| "learning_rate": 8.523171049817974e-06, | |
| "loss": 2.0067, | |
| "num_input_tokens_seen": 85721088, | |
| "step": 327 | |
| }, | |
| { | |
| "epoch": 0.08145021107524211, | |
| "grad_norm": 0.591474175453186, | |
| "learning_rate": 8.510765264975813e-06, | |
| "loss": 2.085, | |
| "num_input_tokens_seen": 85983232, | |
| "step": 328 | |
| }, | |
| { | |
| "epoch": 0.0816985348894959, | |
| "grad_norm": 0.8983985781669617, | |
| "learning_rate": 8.498316702566828e-06, | |
| "loss": 2.0327, | |
| "num_input_tokens_seen": 86245376, | |
| "step": 329 | |
| }, | |
| { | |
| "epoch": 0.0819468587037497, | |
| "grad_norm": 0.5473107695579529, | |
| "learning_rate": 8.485825514272824e-06, | |
| "loss": 1.3908, | |
| "num_input_tokens_seen": 86507520, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.08219518251800348, | |
| "grad_norm": 0.4440311789512634, | |
| "learning_rate": 8.473291852294986e-06, | |
| "loss": 1.7376, | |
| "num_input_tokens_seen": 86769664, | |
| "step": 331 | |
| }, | |
| { | |
| "epoch": 0.08244350633225726, | |
| "grad_norm": 0.5826847553253174, | |
| "learning_rate": 8.460715869352035e-06, | |
| "loss": 1.7982, | |
| "num_input_tokens_seen": 87031808, | |
| "step": 332 | |
| }, | |
| { | |
| "epoch": 0.08269183014651105, | |
| "grad_norm": 0.4117896258831024, | |
| "learning_rate": 8.44809771867835e-06, | |
| "loss": 1.9127, | |
| "num_input_tokens_seen": 87293952, | |
| "step": 333 | |
| }, | |
| { | |
| "epoch": 0.08294015396076483, | |
| "grad_norm": 0.6492828726768494, | |
| "learning_rate": 8.435437554022116e-06, | |
| "loss": 1.4407, | |
| "num_input_tokens_seen": 87556096, | |
| "step": 334 | |
| }, | |
| { | |
| "epoch": 0.08318847777501863, | |
| "grad_norm": 0.47931548953056335, | |
| "learning_rate": 8.422735529643445e-06, | |
| "loss": 1.7312, | |
| "num_input_tokens_seen": 87818240, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.08343680158927241, | |
| "grad_norm": 0.45937687158584595, | |
| "learning_rate": 8.409991800312493e-06, | |
| "loss": 1.3507, | |
| "num_input_tokens_seen": 88080384, | |
| "step": 336 | |
| }, | |
| { | |
| "epoch": 0.0836851254035262, | |
| "grad_norm": 0.34280064702033997, | |
| "learning_rate": 8.397206521307584e-06, | |
| "loss": 1.9152, | |
| "num_input_tokens_seen": 88342528, | |
| "step": 337 | |
| }, | |
| { | |
| "epoch": 0.08393344921777998, | |
| "grad_norm": 0.525225043296814, | |
| "learning_rate": 8.384379848413304e-06, | |
| "loss": 1.7714, | |
| "num_input_tokens_seen": 88604672, | |
| "step": 338 | |
| }, | |
| { | |
| "epoch": 0.08418177303203377, | |
| "grad_norm": 0.8012213706970215, | |
| "learning_rate": 8.371511937918616e-06, | |
| "loss": 1.6678, | |
| "num_input_tokens_seen": 88866816, | |
| "step": 339 | |
| }, | |
| { | |
| "epoch": 0.08443009684628756, | |
| "grad_norm": 0.49616944789886475, | |
| "learning_rate": 8.358602946614952e-06, | |
| "loss": 1.6751, | |
| "num_input_tokens_seen": 89128960, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.08467842066054135, | |
| "grad_norm": 0.4202152490615845, | |
| "learning_rate": 8.345653031794292e-06, | |
| "loss": 1.595, | |
| "num_input_tokens_seen": 89391104, | |
| "step": 341 | |
| }, | |
| { | |
| "epoch": 0.08492674447479513, | |
| "grad_norm": 0.35994473099708557, | |
| "learning_rate": 8.332662351247262e-06, | |
| "loss": 1.8082, | |
| "num_input_tokens_seen": 89653248, | |
| "step": 342 | |
| }, | |
| { | |
| "epoch": 0.08517506828904892, | |
| "grad_norm": 0.3768995702266693, | |
| "learning_rate": 8.319631063261209e-06, | |
| "loss": 1.7495, | |
| "num_input_tokens_seen": 89915392, | |
| "step": 343 | |
| }, | |
| { | |
| "epoch": 0.0854233921033027, | |
| "grad_norm": 0.7302326560020447, | |
| "learning_rate": 8.30655932661826e-06, | |
| "loss": 1.335, | |
| "num_input_tokens_seen": 90177536, | |
| "step": 344 | |
| }, | |
| { | |
| "epoch": 0.0856717159175565, | |
| "grad_norm": 0.4386504888534546, | |
| "learning_rate": 8.293447300593402e-06, | |
| "loss": 1.7737, | |
| "num_input_tokens_seen": 90439680, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.08592003973181028, | |
| "grad_norm": 0.7695857286453247, | |
| "learning_rate": 8.280295144952537e-06, | |
| "loss": 1.7856, | |
| "num_input_tokens_seen": 90701824, | |
| "step": 346 | |
| }, | |
| { | |
| "epoch": 0.08616836354606407, | |
| "grad_norm": 0.7740248441696167, | |
| "learning_rate": 8.267103019950529e-06, | |
| "loss": 2.0197, | |
| "num_input_tokens_seen": 90963968, | |
| "step": 347 | |
| }, | |
| { | |
| "epoch": 0.08641668736031785, | |
| "grad_norm": 3.4425835609436035, | |
| "learning_rate": 8.253871086329255e-06, | |
| "loss": 1.7337, | |
| "num_input_tokens_seen": 91226112, | |
| "step": 348 | |
| }, | |
| { | |
| "epoch": 0.08666501117457164, | |
| "grad_norm": 0.5034295916557312, | |
| "learning_rate": 8.240599505315656e-06, | |
| "loss": 1.269, | |
| "num_input_tokens_seen": 91488256, | |
| "step": 349 | |
| }, | |
| { | |
| "epoch": 0.08691333498882543, | |
| "grad_norm": 0.3939118981361389, | |
| "learning_rate": 8.227288438619754e-06, | |
| "loss": 1.7436, | |
| "num_input_tokens_seen": 91750400, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.08716165880307922, | |
| "grad_norm": 0.6885347962379456, | |
| "learning_rate": 8.213938048432697e-06, | |
| "loss": 1.5946, | |
| "num_input_tokens_seen": 92012544, | |
| "step": 351 | |
| }, | |
| { | |
| "epoch": 0.087409982617333, | |
| "grad_norm": 0.4886651337146759, | |
| "learning_rate": 8.200548497424779e-06, | |
| "loss": 1.3196, | |
| "num_input_tokens_seen": 92274688, | |
| "step": 352 | |
| }, | |
| { | |
| "epoch": 0.08765830643158679, | |
| "grad_norm": 0.7113179564476013, | |
| "learning_rate": 8.18711994874345e-06, | |
| "loss": 2.1461, | |
| "num_input_tokens_seen": 92536832, | |
| "step": 353 | |
| }, | |
| { | |
| "epoch": 0.08790663024584057, | |
| "grad_norm": 0.8152286410331726, | |
| "learning_rate": 8.173652566011339e-06, | |
| "loss": 1.6922, | |
| "num_input_tokens_seen": 92798976, | |
| "step": 354 | |
| }, | |
| { | |
| "epoch": 0.08815495406009437, | |
| "grad_norm": 0.4894461929798126, | |
| "learning_rate": 8.160146513324256e-06, | |
| "loss": 1.8319, | |
| "num_input_tokens_seen": 93061120, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.08840327787434815, | |
| "grad_norm": 0.5153379440307617, | |
| "learning_rate": 8.146601955249187e-06, | |
| "loss": 1.6654, | |
| "num_input_tokens_seen": 93323264, | |
| "step": 356 | |
| }, | |
| { | |
| "epoch": 0.08865160168860194, | |
| "grad_norm": 0.5455003380775452, | |
| "learning_rate": 8.133019056822303e-06, | |
| "loss": 1.8757, | |
| "num_input_tokens_seen": 93585408, | |
| "step": 357 | |
| }, | |
| { | |
| "epoch": 0.08889992550285572, | |
| "grad_norm": 0.6758735775947571, | |
| "learning_rate": 8.119397983546932e-06, | |
| "loss": 1.6944, | |
| "num_input_tokens_seen": 93847552, | |
| "step": 358 | |
| }, | |
| { | |
| "epoch": 0.0891482493171095, | |
| "grad_norm": 0.8125549554824829, | |
| "learning_rate": 8.105738901391553e-06, | |
| "loss": 1.4809, | |
| "num_input_tokens_seen": 94109696, | |
| "step": 359 | |
| }, | |
| { | |
| "epoch": 0.0893965731313633, | |
| "grad_norm": 0.5866984724998474, | |
| "learning_rate": 8.092041976787772e-06, | |
| "loss": 1.9641, | |
| "num_input_tokens_seen": 94371840, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.08964489694561709, | |
| "grad_norm": 0.43463000655174255, | |
| "learning_rate": 8.078307376628292e-06, | |
| "loss": 1.5385, | |
| "num_input_tokens_seen": 94633984, | |
| "step": 361 | |
| }, | |
| { | |
| "epoch": 0.08989322075987087, | |
| "grad_norm": 0.7243896126747131, | |
| "learning_rate": 8.064535268264883e-06, | |
| "loss": 1.9196, | |
| "num_input_tokens_seen": 94896128, | |
| "step": 362 | |
| }, | |
| { | |
| "epoch": 0.09014154457412465, | |
| "grad_norm": 0.7336921095848083, | |
| "learning_rate": 8.05072581950634e-06, | |
| "loss": 1.6399, | |
| "num_input_tokens_seen": 95158272, | |
| "step": 363 | |
| }, | |
| { | |
| "epoch": 0.09038986838837844, | |
| "grad_norm": 0.4355528950691223, | |
| "learning_rate": 8.036879198616434e-06, | |
| "loss": 1.3215, | |
| "num_input_tokens_seen": 95420416, | |
| "step": 364 | |
| }, | |
| { | |
| "epoch": 0.09063819220263224, | |
| "grad_norm": 0.4627648591995239, | |
| "learning_rate": 8.022995574311876e-06, | |
| "loss": 1.7113, | |
| "num_input_tokens_seen": 95682560, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.09088651601688602, | |
| "grad_norm": 1.2987405061721802, | |
| "learning_rate": 8.009075115760243e-06, | |
| "loss": 1.5487, | |
| "num_input_tokens_seen": 95944704, | |
| "step": 366 | |
| }, | |
| { | |
| "epoch": 0.0911348398311398, | |
| "grad_norm": 0.6013867855072021, | |
| "learning_rate": 7.99511799257793e-06, | |
| "loss": 1.4665, | |
| "num_input_tokens_seen": 96206848, | |
| "step": 367 | |
| }, | |
| { | |
| "epoch": 0.09138316364539359, | |
| "grad_norm": 0.7376968860626221, | |
| "learning_rate": 7.981124374828079e-06, | |
| "loss": 1.4543, | |
| "num_input_tokens_seen": 96468992, | |
| "step": 368 | |
| }, | |
| { | |
| "epoch": 0.09163148745964737, | |
| "grad_norm": 0.6412230730056763, | |
| "learning_rate": 7.967094433018508e-06, | |
| "loss": 1.2195, | |
| "num_input_tokens_seen": 96731136, | |
| "step": 369 | |
| }, | |
| { | |
| "epoch": 0.09187981127390117, | |
| "grad_norm": 0.3257865905761719, | |
| "learning_rate": 7.953028338099628e-06, | |
| "loss": 1.5656, | |
| "num_input_tokens_seen": 96993280, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.09212813508815496, | |
| "grad_norm": 0.47559216618537903, | |
| "learning_rate": 7.938926261462366e-06, | |
| "loss": 1.6012, | |
| "num_input_tokens_seen": 97255424, | |
| "step": 371 | |
| }, | |
| { | |
| "epoch": 0.09237645890240874, | |
| "grad_norm": 0.45426198840141296, | |
| "learning_rate": 7.92478837493608e-06, | |
| "loss": 1.7031, | |
| "num_input_tokens_seen": 97517568, | |
| "step": 372 | |
| }, | |
| { | |
| "epoch": 0.09262478271666252, | |
| "grad_norm": 0.4942920506000519, | |
| "learning_rate": 7.910614850786448e-06, | |
| "loss": 1.6369, | |
| "num_input_tokens_seen": 97779712, | |
| "step": 373 | |
| }, | |
| { | |
| "epoch": 0.09287310653091632, | |
| "grad_norm": 0.5819427967071533, | |
| "learning_rate": 7.896405861713393e-06, | |
| "loss": 1.7998, | |
| "num_input_tokens_seen": 98041856, | |
| "step": 374 | |
| }, | |
| { | |
| "epoch": 0.0931214303451701, | |
| "grad_norm": 0.42620816826820374, | |
| "learning_rate": 7.882161580848966e-06, | |
| "loss": 1.6103, | |
| "num_input_tokens_seen": 98304000, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.09336975415942389, | |
| "grad_norm": 0.6115924715995789, | |
| "learning_rate": 7.86788218175523e-06, | |
| "loss": 1.8329, | |
| "num_input_tokens_seen": 98566144, | |
| "step": 376 | |
| }, | |
| { | |
| "epoch": 0.09361807797367767, | |
| "grad_norm": 0.9807063341140747, | |
| "learning_rate": 7.85356783842216e-06, | |
| "loss": 1.3716, | |
| "num_input_tokens_seen": 98828288, | |
| "step": 377 | |
| }, | |
| { | |
| "epoch": 0.09386640178793146, | |
| "grad_norm": 0.5305372476577759, | |
| "learning_rate": 7.839218725265507e-06, | |
| "loss": 1.585, | |
| "num_input_tokens_seen": 99090432, | |
| "step": 378 | |
| }, | |
| { | |
| "epoch": 0.09411472560218526, | |
| "grad_norm": 0.7433108687400818, | |
| "learning_rate": 7.82483501712469e-06, | |
| "loss": 1.5462, | |
| "num_input_tokens_seen": 99352576, | |
| "step": 379 | |
| }, | |
| { | |
| "epoch": 0.09436304941643904, | |
| "grad_norm": 0.6521483659744263, | |
| "learning_rate": 7.810416889260653e-06, | |
| "loss": 2.1058, | |
| "num_input_tokens_seen": 99614720, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.09461137323069282, | |
| "grad_norm": 0.6441096663475037, | |
| "learning_rate": 7.795964517353734e-06, | |
| "loss": 1.938, | |
| "num_input_tokens_seen": 99876864, | |
| "step": 381 | |
| }, | |
| { | |
| "epoch": 0.09485969704494661, | |
| "grad_norm": 0.4057358205318451, | |
| "learning_rate": 7.781478077501526e-06, | |
| "loss": 1.5177, | |
| "num_input_tokens_seen": 100139008, | |
| "step": 382 | |
| }, | |
| { | |
| "epoch": 0.09510802085920039, | |
| "grad_norm": 0.5994225144386292, | |
| "learning_rate": 7.76695774621672e-06, | |
| "loss": 1.6127, | |
| "num_input_tokens_seen": 100401152, | |
| "step": 383 | |
| }, | |
| { | |
| "epoch": 0.09535634467345419, | |
| "grad_norm": 0.6396727561950684, | |
| "learning_rate": 7.752403700424978e-06, | |
| "loss": 1.678, | |
| "num_input_tokens_seen": 100663296, | |
| "step": 384 | |
| }, | |
| { | |
| "epoch": 0.09560466848770797, | |
| "grad_norm": 0.647515594959259, | |
| "learning_rate": 7.737816117462752e-06, | |
| "loss": 1.7168, | |
| "num_input_tokens_seen": 100925440, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.09585299230196176, | |
| "grad_norm": 0.5679896473884583, | |
| "learning_rate": 7.723195175075136e-06, | |
| "loss": 1.9103, | |
| "num_input_tokens_seen": 101187584, | |
| "step": 386 | |
| }, | |
| { | |
| "epoch": 0.09610131611621554, | |
| "grad_norm": 0.9553595185279846, | |
| "learning_rate": 7.7085410514137e-06, | |
| "loss": 1.934, | |
| "num_input_tokens_seen": 101449728, | |
| "step": 387 | |
| }, | |
| { | |
| "epoch": 0.09634963993046933, | |
| "grad_norm": 0.3686366677284241, | |
| "learning_rate": 7.693853925034316e-06, | |
| "loss": 2.0843, | |
| "num_input_tokens_seen": 101711872, | |
| "step": 388 | |
| }, | |
| { | |
| "epoch": 0.09659796374472313, | |
| "grad_norm": 0.528319239616394, | |
| "learning_rate": 7.679133974894984e-06, | |
| "loss": 2.077, | |
| "num_input_tokens_seen": 101974016, | |
| "step": 389 | |
| }, | |
| { | |
| "epoch": 0.09684628755897691, | |
| "grad_norm": 0.6407886147499084, | |
| "learning_rate": 7.66438138035365e-06, | |
| "loss": 1.634, | |
| "num_input_tokens_seen": 102236160, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.0970946113732307, | |
| "grad_norm": 0.5554214715957642, | |
| "learning_rate": 7.649596321166024e-06, | |
| "loss": 1.4811, | |
| "num_input_tokens_seen": 102498304, | |
| "step": 391 | |
| }, | |
| { | |
| "epoch": 0.09734293518748448, | |
| "grad_norm": 0.5426738858222961, | |
| "learning_rate": 7.634778977483389e-06, | |
| "loss": 1.6908, | |
| "num_input_tokens_seen": 102760448, | |
| "step": 392 | |
| }, | |
| { | |
| "epoch": 0.09759125900173826, | |
| "grad_norm": 0.7456260323524475, | |
| "learning_rate": 7.619929529850397e-06, | |
| "loss": 1.8275, | |
| "num_input_tokens_seen": 103022592, | |
| "step": 393 | |
| }, | |
| { | |
| "epoch": 0.09783958281599206, | |
| "grad_norm": 0.5138922929763794, | |
| "learning_rate": 7.605048159202884e-06, | |
| "loss": 1.1156, | |
| "num_input_tokens_seen": 103284736, | |
| "step": 394 | |
| }, | |
| { | |
| "epoch": 0.09808790663024584, | |
| "grad_norm": 0.3001045882701874, | |
| "learning_rate": 7.590135046865652e-06, | |
| "loss": 1.198, | |
| "num_input_tokens_seen": 103546880, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.09833623044449963, | |
| "grad_norm": 0.5880023241043091, | |
| "learning_rate": 7.575190374550272e-06, | |
| "loss": 1.4706, | |
| "num_input_tokens_seen": 103809024, | |
| "step": 396 | |
| }, | |
| { | |
| "epoch": 0.09858455425875341, | |
| "grad_norm": 0.3109273910522461, | |
| "learning_rate": 7.560214324352858e-06, | |
| "loss": 1.0782, | |
| "num_input_tokens_seen": 104071168, | |
| "step": 397 | |
| }, | |
| { | |
| "epoch": 0.0988328780730072, | |
| "grad_norm": 0.3918832540512085, | |
| "learning_rate": 7.545207078751858e-06, | |
| "loss": 1.3639, | |
| "num_input_tokens_seen": 104333312, | |
| "step": 398 | |
| }, | |
| { | |
| "epoch": 0.099081201887261, | |
| "grad_norm": 0.6184259653091431, | |
| "learning_rate": 7.530168820605819e-06, | |
| "loss": 2.0244, | |
| "num_input_tokens_seen": 104595456, | |
| "step": 399 | |
| }, | |
| { | |
| "epoch": 0.09932952570151478, | |
| "grad_norm": 0.41290906071662903, | |
| "learning_rate": 7.515099733151177e-06, | |
| "loss": 1.3445, | |
| "num_input_tokens_seen": 104857600, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.09957784951576856, | |
| "grad_norm": 0.5972164273262024, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.7396, | |
| "num_input_tokens_seen": 105119744, | |
| "step": 401 | |
| }, | |
| { | |
| "epoch": 0.09982617333002235, | |
| "grad_norm": 0.49639347195625305, | |
| "learning_rate": 7.484869805137778e-06, | |
| "loss": 1.9205, | |
| "num_input_tokens_seen": 105381888, | |
| "step": 402 | |
| }, | |
| { | |
| "epoch": 0.10007449714427613, | |
| "grad_norm": 0.47210463881492615, | |
| "learning_rate": 7.469709332921155e-06, | |
| "loss": 1.434, | |
| "num_input_tokens_seen": 105644032, | |
| "step": 403 | |
| }, | |
| { | |
| "epoch": 0.10032282095852993, | |
| "grad_norm": 0.5069103837013245, | |
| "learning_rate": 7.454518768075705e-06, | |
| "loss": 1.5317, | |
| "num_input_tokens_seen": 105906176, | |
| "step": 404 | |
| }, | |
| { | |
| "epoch": 0.10057114477278371, | |
| "grad_norm": 0.6772238612174988, | |
| "learning_rate": 7.4392982956936644e-06, | |
| "loss": 1.9896, | |
| "num_input_tokens_seen": 106168320, | |
| "step": 405 | |
| }, | |
| { | |
| "epoch": 0.1008194685870375, | |
| "grad_norm": 0.5503749847412109, | |
| "learning_rate": 7.424048101231687e-06, | |
| "loss": 1.6349, | |
| "num_input_tokens_seen": 106430464, | |
| "step": 406 | |
| }, | |
| { | |
| "epoch": 0.10106779240129128, | |
| "grad_norm": 0.47426870465278625, | |
| "learning_rate": 7.408768370508577e-06, | |
| "loss": 1.221, | |
| "num_input_tokens_seen": 106692608, | |
| "step": 407 | |
| }, | |
| { | |
| "epoch": 0.10131611621554507, | |
| "grad_norm": 0.7207087874412537, | |
| "learning_rate": 7.393459289703035e-06, | |
| "loss": 1.9311, | |
| "num_input_tokens_seen": 106954752, | |
| "step": 408 | |
| }, | |
| { | |
| "epoch": 0.10156444002979886, | |
| "grad_norm": 0.6696469783782959, | |
| "learning_rate": 7.378121045351378e-06, | |
| "loss": 1.2549, | |
| "num_input_tokens_seen": 107216896, | |
| "step": 409 | |
| }, | |
| { | |
| "epoch": 0.10181276384405265, | |
| "grad_norm": 2.1489691734313965, | |
| "learning_rate": 7.362753824345271e-06, | |
| "loss": 1.8569, | |
| "num_input_tokens_seen": 107479040, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.10206108765830643, | |
| "grad_norm": 0.6064687371253967, | |
| "learning_rate": 7.347357813929455e-06, | |
| "loss": 1.571, | |
| "num_input_tokens_seen": 107741184, | |
| "step": 411 | |
| }, | |
| { | |
| "epoch": 0.10230941147256022, | |
| "grad_norm": 0.651612401008606, | |
| "learning_rate": 7.3319332016994575e-06, | |
| "loss": 1.3514, | |
| "num_input_tokens_seen": 108003328, | |
| "step": 412 | |
| }, | |
| { | |
| "epoch": 0.102557735286814, | |
| "grad_norm": 0.2269715964794159, | |
| "learning_rate": 7.31648017559931e-06, | |
| "loss": 1.2449, | |
| "num_input_tokens_seen": 108265472, | |
| "step": 413 | |
| }, | |
| { | |
| "epoch": 0.1028060591010678, | |
| "grad_norm": 1.5659141540527344, | |
| "learning_rate": 7.300998923919259e-06, | |
| "loss": 1.8001, | |
| "num_input_tokens_seen": 108527616, | |
| "step": 414 | |
| }, | |
| { | |
| "epoch": 0.10305438291532158, | |
| "grad_norm": 0.7734239101409912, | |
| "learning_rate": 7.285489635293472e-06, | |
| "loss": 1.5909, | |
| "num_input_tokens_seen": 108789760, | |
| "step": 415 | |
| }, | |
| { | |
| "epoch": 0.10330270672957537, | |
| "grad_norm": 0.5222880244255066, | |
| "learning_rate": 7.269952498697734e-06, | |
| "loss": 1.7375, | |
| "num_input_tokens_seen": 109051904, | |
| "step": 416 | |
| }, | |
| { | |
| "epoch": 0.10355103054382915, | |
| "grad_norm": 0.45977625250816345, | |
| "learning_rate": 7.254387703447154e-06, | |
| "loss": 1.9382, | |
| "num_input_tokens_seen": 109314048, | |
| "step": 417 | |
| }, | |
| { | |
| "epoch": 0.10379935435808293, | |
| "grad_norm": 0.6067866683006287, | |
| "learning_rate": 7.238795439193849e-06, | |
| "loss": 1.5499, | |
| "num_input_tokens_seen": 109576192, | |
| "step": 418 | |
| }, | |
| { | |
| "epoch": 0.10404767817233673, | |
| "grad_norm": 1.0210500955581665, | |
| "learning_rate": 7.223175895924638e-06, | |
| "loss": 2.0725, | |
| "num_input_tokens_seen": 109838336, | |
| "step": 419 | |
| }, | |
| { | |
| "epoch": 0.10429600198659052, | |
| "grad_norm": 0.7185985445976257, | |
| "learning_rate": 7.207529263958727e-06, | |
| "loss": 1.9104, | |
| "num_input_tokens_seen": 110100480, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.1045443258008443, | |
| "grad_norm": 0.9692136645317078, | |
| "learning_rate": 7.191855733945388e-06, | |
| "loss": 1.7128, | |
| "num_input_tokens_seen": 110362624, | |
| "step": 421 | |
| }, | |
| { | |
| "epoch": 0.10479264961509809, | |
| "grad_norm": 0.36912843585014343, | |
| "learning_rate": 7.176155496861639e-06, | |
| "loss": 1.5977, | |
| "num_input_tokens_seen": 110624768, | |
| "step": 422 | |
| }, | |
| { | |
| "epoch": 0.10504097342935187, | |
| "grad_norm": 0.7783231735229492, | |
| "learning_rate": 7.160428744009913e-06, | |
| "loss": 1.5989, | |
| "num_input_tokens_seen": 110886912, | |
| "step": 423 | |
| }, | |
| { | |
| "epoch": 0.10528929724360567, | |
| "grad_norm": 0.3686671853065491, | |
| "learning_rate": 7.1446756670157306e-06, | |
| "loss": 1.887, | |
| "num_input_tokens_seen": 111149056, | |
| "step": 424 | |
| }, | |
| { | |
| "epoch": 0.10553762105785945, | |
| "grad_norm": 0.47263607382774353, | |
| "learning_rate": 7.128896457825364e-06, | |
| "loss": 1.808, | |
| "num_input_tokens_seen": 111411200, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.10578594487211324, | |
| "grad_norm": 0.543540358543396, | |
| "learning_rate": 7.113091308703498e-06, | |
| "loss": 1.7969, | |
| "num_input_tokens_seen": 111673344, | |
| "step": 426 | |
| }, | |
| { | |
| "epoch": 0.10603426868636702, | |
| "grad_norm": 0.672477126121521, | |
| "learning_rate": 7.0972604122308865e-06, | |
| "loss": 1.3285, | |
| "num_input_tokens_seen": 111935488, | |
| "step": 427 | |
| }, | |
| { | |
| "epoch": 0.1062825925006208, | |
| "grad_norm": 0.501299262046814, | |
| "learning_rate": 7.081403961302007e-06, | |
| "loss": 1.3305, | |
| "num_input_tokens_seen": 112197632, | |
| "step": 428 | |
| }, | |
| { | |
| "epoch": 0.1065309163148746, | |
| "grad_norm": 0.4477572441101074, | |
| "learning_rate": 7.06552214912271e-06, | |
| "loss": 1.1045, | |
| "num_input_tokens_seen": 112459776, | |
| "step": 429 | |
| }, | |
| { | |
| "epoch": 0.10677924012912839, | |
| "grad_norm": 0.34857606887817383, | |
| "learning_rate": 7.049615169207864e-06, | |
| "loss": 1.929, | |
| "num_input_tokens_seen": 112721920, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.10702756394338217, | |
| "grad_norm": 0.6203132271766663, | |
| "learning_rate": 7.033683215379002e-06, | |
| "loss": 1.062, | |
| "num_input_tokens_seen": 112984064, | |
| "step": 431 | |
| }, | |
| { | |
| "epoch": 0.10727588775763595, | |
| "grad_norm": 0.5540516376495361, | |
| "learning_rate": 7.0177264817619514e-06, | |
| "loss": 1.7175, | |
| "num_input_tokens_seen": 113246208, | |
| "step": 432 | |
| }, | |
| { | |
| "epoch": 0.10752421157188974, | |
| "grad_norm": 0.4745628833770752, | |
| "learning_rate": 7.0017451627844765e-06, | |
| "loss": 1.8083, | |
| "num_input_tokens_seen": 113508352, | |
| "step": 433 | |
| }, | |
| { | |
| "epoch": 0.10777253538614354, | |
| "grad_norm": 0.6570994257926941, | |
| "learning_rate": 6.985739453173903e-06, | |
| "loss": 1.4396, | |
| "num_input_tokens_seen": 113770496, | |
| "step": 434 | |
| }, | |
| { | |
| "epoch": 0.10802085920039732, | |
| "grad_norm": 2.3753468990325928, | |
| "learning_rate": 6.9697095479547564e-06, | |
| "loss": 1.3002, | |
| "num_input_tokens_seen": 114032640, | |
| "step": 435 | |
| }, | |
| { | |
| "epoch": 0.1082691830146511, | |
| "grad_norm": 0.3089500367641449, | |
| "learning_rate": 6.953655642446368e-06, | |
| "loss": 1.589, | |
| "num_input_tokens_seen": 114294784, | |
| "step": 436 | |
| }, | |
| { | |
| "epoch": 0.10851750682890489, | |
| "grad_norm": 3.394044876098633, | |
| "learning_rate": 6.9375779322605154e-06, | |
| "loss": 1.1472, | |
| "num_input_tokens_seen": 114556928, | |
| "step": 437 | |
| }, | |
| { | |
| "epoch": 0.10876583064315867, | |
| "grad_norm": 0.334686279296875, | |
| "learning_rate": 6.921476613299018e-06, | |
| "loss": 1.9471, | |
| "num_input_tokens_seen": 114819072, | |
| "step": 438 | |
| }, | |
| { | |
| "epoch": 0.10901415445741247, | |
| "grad_norm": 0.7744854092597961, | |
| "learning_rate": 6.905351881751372e-06, | |
| "loss": 1.4141, | |
| "num_input_tokens_seen": 115081216, | |
| "step": 439 | |
| }, | |
| { | |
| "epoch": 0.10926247827166626, | |
| "grad_norm": 0.37837162613868713, | |
| "learning_rate": 6.889203934092337e-06, | |
| "loss": 1.6888, | |
| "num_input_tokens_seen": 115343360, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.10951080208592004, | |
| "grad_norm": 0.6168341636657715, | |
| "learning_rate": 6.873032967079562e-06, | |
| "loss": 1.9082, | |
| "num_input_tokens_seen": 115605504, | |
| "step": 441 | |
| }, | |
| { | |
| "epoch": 0.10975912590017382, | |
| "grad_norm": 0.41162988543510437, | |
| "learning_rate": 6.856839177751175e-06, | |
| "loss": 1.5192, | |
| "num_input_tokens_seen": 115867648, | |
| "step": 442 | |
| }, | |
| { | |
| "epoch": 0.11000744971442761, | |
| "grad_norm": 0.5805467963218689, | |
| "learning_rate": 6.840622763423391e-06, | |
| "loss": 1.8317, | |
| "num_input_tokens_seen": 116129792, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 0.1102557735286814, | |
| "grad_norm": 0.5233989953994751, | |
| "learning_rate": 6.824383921688098e-06, | |
| "loss": 1.273, | |
| "num_input_tokens_seen": 116391936, | |
| "step": 444 | |
| }, | |
| { | |
| "epoch": 0.11050409734293519, | |
| "grad_norm": 0.6940083503723145, | |
| "learning_rate": 6.808122850410461e-06, | |
| "loss": 1.5257, | |
| "num_input_tokens_seen": 116654080, | |
| "step": 445 | |
| }, | |
| { | |
| "epoch": 0.11075242115718897, | |
| "grad_norm": 0.680293619632721, | |
| "learning_rate": 6.7918397477265e-06, | |
| "loss": 1.7634, | |
| "num_input_tokens_seen": 116916224, | |
| "step": 446 | |
| }, | |
| { | |
| "epoch": 0.11100074497144276, | |
| "grad_norm": 0.680514931678772, | |
| "learning_rate": 6.775534812040686e-06, | |
| "loss": 1.9248, | |
| "num_input_tokens_seen": 117178368, | |
| "step": 447 | |
| }, | |
| { | |
| "epoch": 0.11124906878569654, | |
| "grad_norm": 0.6705589890480042, | |
| "learning_rate": 6.759208242023509e-06, | |
| "loss": 1.6782, | |
| "num_input_tokens_seen": 117440512, | |
| "step": 448 | |
| }, | |
| { | |
| "epoch": 0.11149739259995034, | |
| "grad_norm": 0.6143855452537537, | |
| "learning_rate": 6.7428602366090764e-06, | |
| "loss": 1.8117, | |
| "num_input_tokens_seen": 117702656, | |
| "step": 449 | |
| }, | |
| { | |
| "epoch": 0.11174571641420412, | |
| "grad_norm": 0.5517452359199524, | |
| "learning_rate": 6.7264909949926735e-06, | |
| "loss": 1.4715, | |
| "num_input_tokens_seen": 117964800, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.11199404022845791, | |
| "grad_norm": 0.34088805317878723, | |
| "learning_rate": 6.710100716628345e-06, | |
| "loss": 1.6831, | |
| "num_input_tokens_seen": 118226944, | |
| "step": 451 | |
| }, | |
| { | |
| "epoch": 0.11224236404271169, | |
| "grad_norm": 0.5145544409751892, | |
| "learning_rate": 6.693689601226458e-06, | |
| "loss": 1.6246, | |
| "num_input_tokens_seen": 118489088, | |
| "step": 452 | |
| }, | |
| { | |
| "epoch": 0.11249068785696548, | |
| "grad_norm": 0.5433220267295837, | |
| "learning_rate": 6.677257848751276e-06, | |
| "loss": 1.517, | |
| "num_input_tokens_seen": 118751232, | |
| "step": 453 | |
| }, | |
| { | |
| "epoch": 0.11273901167121927, | |
| "grad_norm": 0.6025758385658264, | |
| "learning_rate": 6.6608056594185166e-06, | |
| "loss": 1.9205, | |
| "num_input_tokens_seen": 119013376, | |
| "step": 454 | |
| }, | |
| { | |
| "epoch": 0.11298733548547306, | |
| "grad_norm": 0.5882771015167236, | |
| "learning_rate": 6.644333233692917e-06, | |
| "loss": 1.6951, | |
| "num_input_tokens_seen": 119275520, | |
| "step": 455 | |
| }, | |
| { | |
| "epoch": 0.11323565929972684, | |
| "grad_norm": 0.6837276220321655, | |
| "learning_rate": 6.627840772285784e-06, | |
| "loss": 2.0879, | |
| "num_input_tokens_seen": 119537664, | |
| "step": 456 | |
| }, | |
| { | |
| "epoch": 0.11348398311398063, | |
| "grad_norm": 0.5370259284973145, | |
| "learning_rate": 6.611328476152557e-06, | |
| "loss": 1.6184, | |
| "num_input_tokens_seen": 119799808, | |
| "step": 457 | |
| }, | |
| { | |
| "epoch": 0.11373230692823441, | |
| "grad_norm": 0.4522857367992401, | |
| "learning_rate": 6.594796546490351e-06, | |
| "loss": 1.7773, | |
| "num_input_tokens_seen": 120061952, | |
| "step": 458 | |
| }, | |
| { | |
| "epoch": 0.11398063074248821, | |
| "grad_norm": 0.46354392170906067, | |
| "learning_rate": 6.578245184735513e-06, | |
| "loss": 1.5712, | |
| "num_input_tokens_seen": 120324096, | |
| "step": 459 | |
| }, | |
| { | |
| "epoch": 0.114228954556742, | |
| "grad_norm": 0.686725378036499, | |
| "learning_rate": 6.561674592561164e-06, | |
| "loss": 1.6311, | |
| "num_input_tokens_seen": 120586240, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.11447727837099578, | |
| "grad_norm": 0.22250455617904663, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 1.7059, | |
| "num_input_tokens_seen": 120848384, | |
| "step": 461 | |
| }, | |
| { | |
| "epoch": 0.11472560218524956, | |
| "grad_norm": 0.5717688798904419, | |
| "learning_rate": 6.5284765248155295e-06, | |
| "loss": 1.9078, | |
| "num_input_tokens_seen": 121110528, | |
| "step": 462 | |
| }, | |
| { | |
| "epoch": 0.11497392599950335, | |
| "grad_norm": 0.6517221331596375, | |
| "learning_rate": 6.5118494537522235e-06, | |
| "loss": 1.923, | |
| "num_input_tokens_seen": 121372672, | |
| "step": 463 | |
| }, | |
| { | |
| "epoch": 0.11522224981375714, | |
| "grad_norm": 0.7577219009399414, | |
| "learning_rate": 6.495203961280434e-06, | |
| "loss": 1.5007, | |
| "num_input_tokens_seen": 121634816, | |
| "step": 464 | |
| }, | |
| { | |
| "epoch": 0.11547057362801093, | |
| "grad_norm": 1.1634546518325806, | |
| "learning_rate": 6.4785402502202345e-06, | |
| "loss": 1.7924, | |
| "num_input_tokens_seen": 121896960, | |
| "step": 465 | |
| }, | |
| { | |
| "epoch": 0.11571889744226471, | |
| "grad_norm": 0.5361213088035583, | |
| "learning_rate": 6.461858523613684e-06, | |
| "loss": 1.3429, | |
| "num_input_tokens_seen": 122159104, | |
| "step": 466 | |
| }, | |
| { | |
| "epoch": 0.1159672212565185, | |
| "grad_norm": 0.3826828598976135, | |
| "learning_rate": 6.445158984722358e-06, | |
| "loss": 1.4901, | |
| "num_input_tokens_seen": 122421248, | |
| "step": 467 | |
| }, | |
| { | |
| "epoch": 0.11621554507077228, | |
| "grad_norm": 0.5723513960838318, | |
| "learning_rate": 6.428441837024868e-06, | |
| "loss": 1.8145, | |
| "num_input_tokens_seen": 122683392, | |
| "step": 468 | |
| }, | |
| { | |
| "epoch": 0.11646386888502608, | |
| "grad_norm": 0.6699240803718567, | |
| "learning_rate": 6.411707284214384e-06, | |
| "loss": 1.6751, | |
| "num_input_tokens_seen": 122945536, | |
| "step": 469 | |
| }, | |
| { | |
| "epoch": 0.11671219269927986, | |
| "grad_norm": 0.35479190945625305, | |
| "learning_rate": 6.3949555301961474e-06, | |
| "loss": 1.4937, | |
| "num_input_tokens_seen": 123207680, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.11696051651353365, | |
| "grad_norm": 0.7304947972297668, | |
| "learning_rate": 6.378186779084996e-06, | |
| "loss": 1.5881, | |
| "num_input_tokens_seen": 123469824, | |
| "step": 471 | |
| }, | |
| { | |
| "epoch": 0.11720884032778743, | |
| "grad_norm": 0.4155537784099579, | |
| "learning_rate": 6.361401235202872e-06, | |
| "loss": 1.5931, | |
| "num_input_tokens_seen": 123731968, | |
| "step": 472 | |
| }, | |
| { | |
| "epoch": 0.11745716414204121, | |
| "grad_norm": 0.5789989233016968, | |
| "learning_rate": 6.344599103076329e-06, | |
| "loss": 1.3299, | |
| "num_input_tokens_seen": 123994112, | |
| "step": 473 | |
| }, | |
| { | |
| "epoch": 0.11770548795629501, | |
| "grad_norm": 0.5815244913101196, | |
| "learning_rate": 6.327780587434045e-06, | |
| "loss": 1.7197, | |
| "num_input_tokens_seen": 124256256, | |
| "step": 474 | |
| }, | |
| { | |
| "epoch": 0.1179538117705488, | |
| "grad_norm": 0.7529072165489197, | |
| "learning_rate": 6.310945893204324e-06, | |
| "loss": 1.47, | |
| "num_input_tokens_seen": 124518400, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.11820213558480258, | |
| "grad_norm": 0.7494714856147766, | |
| "learning_rate": 6.294095225512604e-06, | |
| "loss": 1.864, | |
| "num_input_tokens_seen": 124780544, | |
| "step": 476 | |
| }, | |
| { | |
| "epoch": 0.11845045939905637, | |
| "grad_norm": 0.3240576684474945, | |
| "learning_rate": 6.277228789678953e-06, | |
| "loss": 1.5745, | |
| "num_input_tokens_seen": 125042688, | |
| "step": 477 | |
| }, | |
| { | |
| "epoch": 0.11869878321331016, | |
| "grad_norm": 0.5607863068580627, | |
| "learning_rate": 6.26034679121557e-06, | |
| "loss": 1.9548, | |
| "num_input_tokens_seen": 125304832, | |
| "step": 478 | |
| }, | |
| { | |
| "epoch": 0.11894710702756395, | |
| "grad_norm": 0.5693123936653137, | |
| "learning_rate": 6.243449435824276e-06, | |
| "loss": 1.7745, | |
| "num_input_tokens_seen": 125566976, | |
| "step": 479 | |
| }, | |
| { | |
| "epoch": 0.11919543084181773, | |
| "grad_norm": 0.5455982685089111, | |
| "learning_rate": 6.2265369293940135e-06, | |
| "loss": 1.9634, | |
| "num_input_tokens_seen": 125829120, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.11944375465607152, | |
| "grad_norm": 0.4890311658382416, | |
| "learning_rate": 6.209609477998339e-06, | |
| "loss": 2.1942, | |
| "num_input_tokens_seen": 126091264, | |
| "step": 481 | |
| }, | |
| { | |
| "epoch": 0.1196920784703253, | |
| "grad_norm": 0.5301004648208618, | |
| "learning_rate": 6.192667287892905e-06, | |
| "loss": 1.4093, | |
| "num_input_tokens_seen": 126353408, | |
| "step": 482 | |
| }, | |
| { | |
| "epoch": 0.1199404022845791, | |
| "grad_norm": 0.47906139492988586, | |
| "learning_rate": 6.17571056551295e-06, | |
| "loss": 1.7136, | |
| "num_input_tokens_seen": 126615552, | |
| "step": 483 | |
| }, | |
| { | |
| "epoch": 0.12018872609883288, | |
| "grad_norm": 0.6675156354904175, | |
| "learning_rate": 6.158739517470786e-06, | |
| "loss": 1.6023, | |
| "num_input_tokens_seen": 126877696, | |
| "step": 484 | |
| }, | |
| { | |
| "epoch": 0.12043704991308667, | |
| "grad_norm": 0.31835541129112244, | |
| "learning_rate": 6.141754350553279e-06, | |
| "loss": 1.5503, | |
| "num_input_tokens_seen": 127139840, | |
| "step": 485 | |
| }, | |
| { | |
| "epoch": 0.12068537372734045, | |
| "grad_norm": 0.7083136439323425, | |
| "learning_rate": 6.124755271719326e-06, | |
| "loss": 1.5225, | |
| "num_input_tokens_seen": 127401984, | |
| "step": 486 | |
| }, | |
| { | |
| "epoch": 0.12093369754159423, | |
| "grad_norm": 0.4737892746925354, | |
| "learning_rate": 6.107742488097338e-06, | |
| "loss": 1.4856, | |
| "num_input_tokens_seen": 127664128, | |
| "step": 487 | |
| }, | |
| { | |
| "epoch": 0.12118202135584803, | |
| "grad_norm": 0.403909832239151, | |
| "learning_rate": 6.090716206982714e-06, | |
| "loss": 1.5458, | |
| "num_input_tokens_seen": 127926272, | |
| "step": 488 | |
| }, | |
| { | |
| "epoch": 0.12143034517010182, | |
| "grad_norm": 0.6817101240158081, | |
| "learning_rate": 6.073676635835317e-06, | |
| "loss": 1.3755, | |
| "num_input_tokens_seen": 128188416, | |
| "step": 489 | |
| }, | |
| { | |
| "epoch": 0.1216786689843556, | |
| "grad_norm": 0.5082156658172607, | |
| "learning_rate": 6.056623982276945e-06, | |
| "loss": 1.8278, | |
| "num_input_tokens_seen": 128450560, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.12192699279860938, | |
| "grad_norm": 0.4969983696937561, | |
| "learning_rate": 6.039558454088796e-06, | |
| "loss": 2.0705, | |
| "num_input_tokens_seen": 128712704, | |
| "step": 491 | |
| }, | |
| { | |
| "epoch": 0.12217531661286317, | |
| "grad_norm": 0.6239178776741028, | |
| "learning_rate": 6.022480259208951e-06, | |
| "loss": 1.5768, | |
| "num_input_tokens_seen": 128974848, | |
| "step": 492 | |
| }, | |
| { | |
| "epoch": 0.12242364042711697, | |
| "grad_norm": 0.5710934400558472, | |
| "learning_rate": 6.005389605729824e-06, | |
| "loss": 1.6925, | |
| "num_input_tokens_seen": 129236992, | |
| "step": 493 | |
| }, | |
| { | |
| "epoch": 0.12267196424137075, | |
| "grad_norm": 0.5775221586227417, | |
| "learning_rate": 5.988286701895631e-06, | |
| "loss": 1.924, | |
| "num_input_tokens_seen": 129499136, | |
| "step": 494 | |
| }, | |
| { | |
| "epoch": 0.12292028805562454, | |
| "grad_norm": 0.4340408146381378, | |
| "learning_rate": 5.97117175609986e-06, | |
| "loss": 1.791, | |
| "num_input_tokens_seen": 129761280, | |
| "step": 495 | |
| }, | |
| { | |
| "epoch": 0.12316861186987832, | |
| "grad_norm": 0.3268572986125946, | |
| "learning_rate": 5.954044976882725e-06, | |
| "loss": 1.7505, | |
| "num_input_tokens_seen": 130023424, | |
| "step": 496 | |
| }, | |
| { | |
| "epoch": 0.1234169356841321, | |
| "grad_norm": 0.43856051564216614, | |
| "learning_rate": 5.936906572928625e-06, | |
| "loss": 1.3188, | |
| "num_input_tokens_seen": 130285568, | |
| "step": 497 | |
| }, | |
| { | |
| "epoch": 0.1236652594983859, | |
| "grad_norm": 0.459693044424057, | |
| "learning_rate": 5.919756753063601e-06, | |
| "loss": 1.8807, | |
| "num_input_tokens_seen": 130547712, | |
| "step": 498 | |
| }, | |
| { | |
| "epoch": 0.12391358331263969, | |
| "grad_norm": 1.3583054542541504, | |
| "learning_rate": 5.902595726252801e-06, | |
| "loss": 1.5139, | |
| "num_input_tokens_seen": 130809856, | |
| "step": 499 | |
| }, | |
| { | |
| "epoch": 0.12416190712689347, | |
| "grad_norm": 0.4457927644252777, | |
| "learning_rate": 5.885423701597918e-06, | |
| "loss": 1.0955, | |
| "num_input_tokens_seen": 131072000, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.12441023094114725, | |
| "grad_norm": 0.45763128995895386, | |
| "learning_rate": 5.8682408883346535e-06, | |
| "loss": 1.3018, | |
| "num_input_tokens_seen": 131334144, | |
| "step": 501 | |
| }, | |
| { | |
| "epoch": 0.12465855475540104, | |
| "grad_norm": 0.43406641483306885, | |
| "learning_rate": 5.851047495830163e-06, | |
| "loss": 1.8796, | |
| "num_input_tokens_seen": 131596288, | |
| "step": 502 | |
| }, | |
| { | |
| "epoch": 0.12490687856965484, | |
| "grad_norm": 0.6790747046470642, | |
| "learning_rate": 5.8338437335805124e-06, | |
| "loss": 1.7733, | |
| "num_input_tokens_seen": 131858432, | |
| "step": 503 | |
| }, | |
| { | |
| "epoch": 0.12515520238390862, | |
| "grad_norm": 0.469204306602478, | |
| "learning_rate": 5.816629811208112e-06, | |
| "loss": 1.7257, | |
| "num_input_tokens_seen": 132120576, | |
| "step": 504 | |
| }, | |
| { | |
| "epoch": 0.1254035261981624, | |
| "grad_norm": 0.29336878657341003, | |
| "learning_rate": 5.799405938459175e-06, | |
| "loss": 2.0604, | |
| "num_input_tokens_seen": 132382720, | |
| "step": 505 | |
| }, | |
| { | |
| "epoch": 0.1256518500124162, | |
| "grad_norm": 1.0650948286056519, | |
| "learning_rate": 5.782172325201155e-06, | |
| "loss": 1.4833, | |
| "num_input_tokens_seen": 132644864, | |
| "step": 506 | |
| }, | |
| { | |
| "epoch": 0.12590017382667, | |
| "grad_norm": 0.5020011067390442, | |
| "learning_rate": 5.764929181420191e-06, | |
| "loss": 1.9276, | |
| "num_input_tokens_seen": 132907008, | |
| "step": 507 | |
| }, | |
| { | |
| "epoch": 0.12614849764092376, | |
| "grad_norm": 0.623615562915802, | |
| "learning_rate": 5.747676717218549e-06, | |
| "loss": 1.6809, | |
| "num_input_tokens_seen": 133169152, | |
| "step": 508 | |
| }, | |
| { | |
| "epoch": 0.12639682145517755, | |
| "grad_norm": 0.6677452325820923, | |
| "learning_rate": 5.730415142812059e-06, | |
| "loss": 1.6377, | |
| "num_input_tokens_seen": 133431296, | |
| "step": 509 | |
| }, | |
| { | |
| "epoch": 0.12664514526943133, | |
| "grad_norm": 0.5016704201698303, | |
| "learning_rate": 5.7131446685275595e-06, | |
| "loss": 1.4934, | |
| "num_input_tokens_seen": 133693440, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.12689346908368512, | |
| "grad_norm": 0.4135633707046509, | |
| "learning_rate": 5.695865504800328e-06, | |
| "loss": 1.6179, | |
| "num_input_tokens_seen": 133955584, | |
| "step": 511 | |
| }, | |
| { | |
| "epoch": 0.12714179289793892, | |
| "grad_norm": 0.7254384160041809, | |
| "learning_rate": 5.678577862171523e-06, | |
| "loss": 1.5534, | |
| "num_input_tokens_seen": 134217728, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 0.1273901167121927, | |
| "grad_norm": 0.7331421971321106, | |
| "learning_rate": 5.661281951285613e-06, | |
| "loss": 1.7944, | |
| "num_input_tokens_seen": 134479872, | |
| "step": 513 | |
| }, | |
| { | |
| "epoch": 0.1276384405264465, | |
| "grad_norm": 0.6121946573257446, | |
| "learning_rate": 5.643977982887815e-06, | |
| "loss": 1.6006, | |
| "num_input_tokens_seen": 134742016, | |
| "step": 514 | |
| }, | |
| { | |
| "epoch": 0.12788676434070026, | |
| "grad_norm": 0.4421185255050659, | |
| "learning_rate": 5.626666167821522e-06, | |
| "loss": 1.5906, | |
| "num_input_tokens_seen": 135004160, | |
| "step": 515 | |
| }, | |
| { | |
| "epoch": 0.12813508815495406, | |
| "grad_norm": 0.3607276380062103, | |
| "learning_rate": 5.609346717025738e-06, | |
| "loss": 1.7194, | |
| "num_input_tokens_seen": 135266304, | |
| "step": 516 | |
| }, | |
| { | |
| "epoch": 0.12838341196920786, | |
| "grad_norm": 0.66265469789505, | |
| "learning_rate": 5.592019841532507e-06, | |
| "loss": 1.5176, | |
| "num_input_tokens_seen": 135528448, | |
| "step": 517 | |
| }, | |
| { | |
| "epoch": 0.12863173578346163, | |
| "grad_norm": 0.4719207286834717, | |
| "learning_rate": 5.5746857524643335e-06, | |
| "loss": 1.5677, | |
| "num_input_tokens_seen": 135790592, | |
| "step": 518 | |
| }, | |
| { | |
| "epoch": 0.12888005959771542, | |
| "grad_norm": 0.5282115936279297, | |
| "learning_rate": 5.557344661031628e-06, | |
| "loss": 1.6344, | |
| "num_input_tokens_seen": 136052736, | |
| "step": 519 | |
| }, | |
| { | |
| "epoch": 0.1291283834119692, | |
| "grad_norm": 0.3419008255004883, | |
| "learning_rate": 5.539996778530114e-06, | |
| "loss": 1.9051, | |
| "num_input_tokens_seen": 136314880, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.129376707226223, | |
| "grad_norm": 0.7775862812995911, | |
| "learning_rate": 5.522642316338268e-06, | |
| "loss": 1.7739, | |
| "num_input_tokens_seen": 136577024, | |
| "step": 521 | |
| }, | |
| { | |
| "epoch": 0.1296250310404768, | |
| "grad_norm": 0.554291307926178, | |
| "learning_rate": 5.505281485914732e-06, | |
| "loss": 1.6473, | |
| "num_input_tokens_seen": 136839168, | |
| "step": 522 | |
| }, | |
| { | |
| "epoch": 0.12987335485473056, | |
| "grad_norm": 0.5523970127105713, | |
| "learning_rate": 5.487914498795748e-06, | |
| "loss": 1.5672, | |
| "num_input_tokens_seen": 137101312, | |
| "step": 523 | |
| }, | |
| { | |
| "epoch": 0.13012167866898436, | |
| "grad_norm": 0.4398843050003052, | |
| "learning_rate": 5.470541566592573e-06, | |
| "loss": 1.5184, | |
| "num_input_tokens_seen": 137363456, | |
| "step": 524 | |
| }, | |
| { | |
| "epoch": 0.13037000248323813, | |
| "grad_norm": 0.36770564317703247, | |
| "learning_rate": 5.453162900988902e-06, | |
| "loss": 1.272, | |
| "num_input_tokens_seen": 137625600, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.13061832629749193, | |
| "grad_norm": 0.36852288246154785, | |
| "learning_rate": 5.435778713738292e-06, | |
| "loss": 1.914, | |
| "num_input_tokens_seen": 137887744, | |
| "step": 526 | |
| }, | |
| { | |
| "epoch": 0.13086665011174572, | |
| "grad_norm": 0.5804073810577393, | |
| "learning_rate": 5.41838921666158e-06, | |
| "loss": 1.3187, | |
| "num_input_tokens_seen": 138149888, | |
| "step": 527 | |
| }, | |
| { | |
| "epoch": 0.1311149739259995, | |
| "grad_norm": 0.4716220796108246, | |
| "learning_rate": 5.400994621644294e-06, | |
| "loss": 1.6562, | |
| "num_input_tokens_seen": 138412032, | |
| "step": 528 | |
| }, | |
| { | |
| "epoch": 0.1313632977402533, | |
| "grad_norm": 0.6712131500244141, | |
| "learning_rate": 5.383595140634093e-06, | |
| "loss": 1.6972, | |
| "num_input_tokens_seen": 138674176, | |
| "step": 529 | |
| }, | |
| { | |
| "epoch": 0.1316116215545071, | |
| "grad_norm": 0.6651138067245483, | |
| "learning_rate": 5.366190985638159e-06, | |
| "loss": 1.2614, | |
| "num_input_tokens_seen": 138936320, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.13185994536876086, | |
| "grad_norm": 0.6065943241119385, | |
| "learning_rate": 5.348782368720627e-06, | |
| "loss": 1.8296, | |
| "num_input_tokens_seen": 139198464, | |
| "step": 531 | |
| }, | |
| { | |
| "epoch": 0.13210826918301466, | |
| "grad_norm": 0.5409244298934937, | |
| "learning_rate": 5.3313695020000026e-06, | |
| "loss": 1.6437, | |
| "num_input_tokens_seen": 139460608, | |
| "step": 532 | |
| }, | |
| { | |
| "epoch": 0.13235659299726843, | |
| "grad_norm": 0.742667555809021, | |
| "learning_rate": 5.3139525976465675e-06, | |
| "loss": 1.5862, | |
| "num_input_tokens_seen": 139722752, | |
| "step": 533 | |
| }, | |
| { | |
| "epoch": 0.13260491681152223, | |
| "grad_norm": 0.6471251845359802, | |
| "learning_rate": 5.296531867879809e-06, | |
| "loss": 1.6151, | |
| "num_input_tokens_seen": 139984896, | |
| "step": 534 | |
| }, | |
| { | |
| "epoch": 0.13285324062577603, | |
| "grad_norm": 0.643791675567627, | |
| "learning_rate": 5.27910752496582e-06, | |
| "loss": 1.7427, | |
| "num_input_tokens_seen": 140247040, | |
| "step": 535 | |
| }, | |
| { | |
| "epoch": 0.1331015644400298, | |
| "grad_norm": 0.7029093503952026, | |
| "learning_rate": 5.2616797812147205e-06, | |
| "loss": 1.6691, | |
| "num_input_tokens_seen": 140509184, | |
| "step": 536 | |
| }, | |
| { | |
| "epoch": 0.1333498882542836, | |
| "grad_norm": 0.7368614077568054, | |
| "learning_rate": 5.244248848978067e-06, | |
| "loss": 1.9763, | |
| "num_input_tokens_seen": 140771328, | |
| "step": 537 | |
| }, | |
| { | |
| "epoch": 0.13359821206853736, | |
| "grad_norm": 0.7032376527786255, | |
| "learning_rate": 5.226814940646268e-06, | |
| "loss": 1.7725, | |
| "num_input_tokens_seen": 141033472, | |
| "step": 538 | |
| }, | |
| { | |
| "epoch": 0.13384653588279116, | |
| "grad_norm": 0.47285741567611694, | |
| "learning_rate": 5.209378268645998e-06, | |
| "loss": 2.148, | |
| "num_input_tokens_seen": 141295616, | |
| "step": 539 | |
| }, | |
| { | |
| "epoch": 0.13409485969704496, | |
| "grad_norm": 0.6670664548873901, | |
| "learning_rate": 5.1919390454376e-06, | |
| "loss": 1.7662, | |
| "num_input_tokens_seen": 141557760, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.13434318351129873, | |
| "grad_norm": 0.6090880632400513, | |
| "learning_rate": 5.174497483512506e-06, | |
| "loss": 1.2453, | |
| "num_input_tokens_seen": 141819904, | |
| "step": 541 | |
| }, | |
| { | |
| "epoch": 0.13459150732555253, | |
| "grad_norm": 0.48240217566490173, | |
| "learning_rate": 5.157053795390642e-06, | |
| "loss": 1.7743, | |
| "num_input_tokens_seen": 142082048, | |
| "step": 542 | |
| }, | |
| { | |
| "epoch": 0.1348398311398063, | |
| "grad_norm": 0.5195634961128235, | |
| "learning_rate": 5.139608193617846e-06, | |
| "loss": 1.8024, | |
| "num_input_tokens_seen": 142344192, | |
| "step": 543 | |
| }, | |
| { | |
| "epoch": 0.1350881549540601, | |
| "grad_norm": 0.5877946615219116, | |
| "learning_rate": 5.1221608907632665e-06, | |
| "loss": 1.6163, | |
| "num_input_tokens_seen": 142606336, | |
| "step": 544 | |
| }, | |
| { | |
| "epoch": 0.1353364787683139, | |
| "grad_norm": 0.6305245757102966, | |
| "learning_rate": 5.1047120994167855e-06, | |
| "loss": 1.5309, | |
| "num_input_tokens_seen": 142868480, | |
| "step": 545 | |
| }, | |
| { | |
| "epoch": 0.13558480258256767, | |
| "grad_norm": 0.591148853302002, | |
| "learning_rate": 5.087262032186418e-06, | |
| "loss": 1.531, | |
| "num_input_tokens_seen": 143130624, | |
| "step": 546 | |
| }, | |
| { | |
| "epoch": 0.13583312639682146, | |
| "grad_norm": 0.8955023884773254, | |
| "learning_rate": 5.069810901695727e-06, | |
| "loss": 1.7347, | |
| "num_input_tokens_seen": 143392768, | |
| "step": 547 | |
| }, | |
| { | |
| "epoch": 0.13608145021107523, | |
| "grad_norm": 0.5800215005874634, | |
| "learning_rate": 5.05235892058123e-06, | |
| "loss": 1.6724, | |
| "num_input_tokens_seen": 143654912, | |
| "step": 548 | |
| }, | |
| { | |
| "epoch": 0.13632977402532903, | |
| "grad_norm": 0.5544260144233704, | |
| "learning_rate": 5.034906301489808e-06, | |
| "loss": 1.5061, | |
| "num_input_tokens_seen": 143917056, | |
| "step": 549 | |
| }, | |
| { | |
| "epoch": 0.13657809783958283, | |
| "grad_norm": 0.5210686922073364, | |
| "learning_rate": 5.0174532570761194e-06, | |
| "loss": 1.3236, | |
| "num_input_tokens_seen": 144179200, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.1368264216538366, | |
| "grad_norm": 0.39467668533325195, | |
| "learning_rate": 5e-06, | |
| "loss": 1.5716, | |
| "num_input_tokens_seen": 144441344, | |
| "step": 551 | |
| }, | |
| { | |
| "epoch": 0.1370747454680904, | |
| "grad_norm": 0.45690640807151794, | |
| "learning_rate": 4.982546742923883e-06, | |
| "loss": 1.5183, | |
| "num_input_tokens_seen": 144703488, | |
| "step": 552 | |
| }, | |
| { | |
| "epoch": 0.13732306928234417, | |
| "grad_norm": 0.34431830048561096, | |
| "learning_rate": 4.965093698510192e-06, | |
| "loss": 1.7103, | |
| "num_input_tokens_seen": 144965632, | |
| "step": 553 | |
| }, | |
| { | |
| "epoch": 0.13757139309659797, | |
| "grad_norm": 0.6095772385597229, | |
| "learning_rate": 4.9476410794187726e-06, | |
| "loss": 1.79, | |
| "num_input_tokens_seen": 145227776, | |
| "step": 554 | |
| }, | |
| { | |
| "epoch": 0.13781971691085176, | |
| "grad_norm": 0.5050289630889893, | |
| "learning_rate": 4.9301890983042744e-06, | |
| "loss": 1.6136, | |
| "num_input_tokens_seen": 145489920, | |
| "step": 555 | |
| }, | |
| { | |
| "epoch": 0.13806804072510553, | |
| "grad_norm": 0.6285063028335571, | |
| "learning_rate": 4.9127379678135825e-06, | |
| "loss": 1.5999, | |
| "num_input_tokens_seen": 145752064, | |
| "step": 556 | |
| }, | |
| { | |
| "epoch": 0.13831636453935933, | |
| "grad_norm": 0.6678712368011475, | |
| "learning_rate": 4.895287900583216e-06, | |
| "loss": 1.2344, | |
| "num_input_tokens_seen": 146014208, | |
| "step": 557 | |
| }, | |
| { | |
| "epoch": 0.1385646883536131, | |
| "grad_norm": 0.3648228347301483, | |
| "learning_rate": 4.877839109236735e-06, | |
| "loss": 1.5726, | |
| "num_input_tokens_seen": 146276352, | |
| "step": 558 | |
| }, | |
| { | |
| "epoch": 0.1388130121678669, | |
| "grad_norm": 0.5992112755775452, | |
| "learning_rate": 4.860391806382157e-06, | |
| "loss": 1.9771, | |
| "num_input_tokens_seen": 146538496, | |
| "step": 559 | |
| }, | |
| { | |
| "epoch": 0.1390613359821207, | |
| "grad_norm": 0.4710709750652313, | |
| "learning_rate": 4.842946204609359e-06, | |
| "loss": 1.8191, | |
| "num_input_tokens_seen": 146800640, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.13930965979637447, | |
| "grad_norm": 0.5668407678604126, | |
| "learning_rate": 4.825502516487497e-06, | |
| "loss": 1.8406, | |
| "num_input_tokens_seen": 147062784, | |
| "step": 561 | |
| }, | |
| { | |
| "epoch": 0.13955798361062827, | |
| "grad_norm": 0.5589337944984436, | |
| "learning_rate": 4.8080609545624004e-06, | |
| "loss": 1.5411, | |
| "num_input_tokens_seen": 147324928, | |
| "step": 562 | |
| }, | |
| { | |
| "epoch": 0.13980630742488204, | |
| "grad_norm": 0.7744218707084656, | |
| "learning_rate": 4.7906217313540035e-06, | |
| "loss": 1.4392, | |
| "num_input_tokens_seen": 147587072, | |
| "step": 563 | |
| }, | |
| { | |
| "epoch": 0.14005463123913584, | |
| "grad_norm": 0.8113576769828796, | |
| "learning_rate": 4.7731850593537316e-06, | |
| "loss": 1.6712, | |
| "num_input_tokens_seen": 147849216, | |
| "step": 564 | |
| }, | |
| { | |
| "epoch": 0.14030295505338963, | |
| "grad_norm": 0.8065240979194641, | |
| "learning_rate": 4.755751151021934e-06, | |
| "loss": 1.7134, | |
| "num_input_tokens_seen": 148111360, | |
| "step": 565 | |
| }, | |
| { | |
| "epoch": 0.1405512788676434, | |
| "grad_norm": 0.6279537081718445, | |
| "learning_rate": 4.738320218785281e-06, | |
| "loss": 1.6341, | |
| "num_input_tokens_seen": 148373504, | |
| "step": 566 | |
| }, | |
| { | |
| "epoch": 0.1407996026818972, | |
| "grad_norm": 0.34301266074180603, | |
| "learning_rate": 4.720892475034181e-06, | |
| "loss": 1.7529, | |
| "num_input_tokens_seen": 148635648, | |
| "step": 567 | |
| }, | |
| { | |
| "epoch": 0.14104792649615097, | |
| "grad_norm": 0.3987272381782532, | |
| "learning_rate": 4.703468132120193e-06, | |
| "loss": 1.3504, | |
| "num_input_tokens_seen": 148897792, | |
| "step": 568 | |
| }, | |
| { | |
| "epoch": 0.14129625031040477, | |
| "grad_norm": 0.5643488168716431, | |
| "learning_rate": 4.686047402353433e-06, | |
| "loss": 1.6918, | |
| "num_input_tokens_seen": 149159936, | |
| "step": 569 | |
| }, | |
| { | |
| "epoch": 0.14154457412465857, | |
| "grad_norm": 1.1378772258758545, | |
| "learning_rate": 4.668630498000001e-06, | |
| "loss": 1.6232, | |
| "num_input_tokens_seen": 149422080, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.14179289793891234, | |
| "grad_norm": 0.40794894099235535, | |
| "learning_rate": 4.651217631279374e-06, | |
| "loss": 1.2633, | |
| "num_input_tokens_seen": 149684224, | |
| "step": 571 | |
| }, | |
| { | |
| "epoch": 0.14204122175316614, | |
| "grad_norm": 0.40206679701805115, | |
| "learning_rate": 4.6338090143618435e-06, | |
| "loss": 1.7796, | |
| "num_input_tokens_seen": 149946368, | |
| "step": 572 | |
| }, | |
| { | |
| "epoch": 0.1422895455674199, | |
| "grad_norm": 0.6353849768638611, | |
| "learning_rate": 4.6164048593659076e-06, | |
| "loss": 1.5364, | |
| "num_input_tokens_seen": 150208512, | |
| "step": 573 | |
| }, | |
| { | |
| "epoch": 0.1425378693816737, | |
| "grad_norm": 0.5148465037345886, | |
| "learning_rate": 4.5990053783557066e-06, | |
| "loss": 1.5442, | |
| "num_input_tokens_seen": 150470656, | |
| "step": 574 | |
| }, | |
| { | |
| "epoch": 0.1427861931959275, | |
| "grad_norm": 0.5749762058258057, | |
| "learning_rate": 4.581610783338424e-06, | |
| "loss": 1.0381, | |
| "num_input_tokens_seen": 150732800, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.14303451701018127, | |
| "grad_norm": 0.9002466201782227, | |
| "learning_rate": 4.564221286261709e-06, | |
| "loss": 1.4117, | |
| "num_input_tokens_seen": 150994944, | |
| "step": 576 | |
| }, | |
| { | |
| "epoch": 0.14328284082443507, | |
| "grad_norm": 0.3512033224105835, | |
| "learning_rate": 4.546837099011101e-06, | |
| "loss": 1.5649, | |
| "num_input_tokens_seen": 151257088, | |
| "step": 577 | |
| }, | |
| { | |
| "epoch": 0.14353116463868884, | |
| "grad_norm": 0.45879220962524414, | |
| "learning_rate": 4.529458433407429e-06, | |
| "loss": 1.4193, | |
| "num_input_tokens_seen": 151519232, | |
| "step": 578 | |
| }, | |
| { | |
| "epoch": 0.14377948845294264, | |
| "grad_norm": 0.7155461311340332, | |
| "learning_rate": 4.512085501204254e-06, | |
| "loss": 1.5547, | |
| "num_input_tokens_seen": 151781376, | |
| "step": 579 | |
| }, | |
| { | |
| "epoch": 0.14402781226719644, | |
| "grad_norm": 0.6171830892562866, | |
| "learning_rate": 4.494718514085269e-06, | |
| "loss": 1.2821, | |
| "num_input_tokens_seen": 152043520, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.1442761360814502, | |
| "grad_norm": 0.5107810497283936, | |
| "learning_rate": 4.477357683661734e-06, | |
| "loss": 1.6026, | |
| "num_input_tokens_seen": 152305664, | |
| "step": 581 | |
| }, | |
| { | |
| "epoch": 0.144524459895704, | |
| "grad_norm": 0.6672670245170593, | |
| "learning_rate": 4.460003221469886e-06, | |
| "loss": 1.7716, | |
| "num_input_tokens_seen": 152567808, | |
| "step": 582 | |
| }, | |
| { | |
| "epoch": 0.14477278370995778, | |
| "grad_norm": 0.4775781035423279, | |
| "learning_rate": 4.442655338968373e-06, | |
| "loss": 1.3139, | |
| "num_input_tokens_seen": 152829952, | |
| "step": 583 | |
| }, | |
| { | |
| "epoch": 0.14502110752421157, | |
| "grad_norm": 0.665295422077179, | |
| "learning_rate": 4.425314247535668e-06, | |
| "loss": 1.2141, | |
| "num_input_tokens_seen": 153092096, | |
| "step": 584 | |
| }, | |
| { | |
| "epoch": 0.14526943133846537, | |
| "grad_norm": 0.49010828137397766, | |
| "learning_rate": 4.4079801584674955e-06, | |
| "loss": 1.3422, | |
| "num_input_tokens_seen": 153354240, | |
| "step": 585 | |
| }, | |
| { | |
| "epoch": 0.14551775515271914, | |
| "grad_norm": 0.4619687795639038, | |
| "learning_rate": 4.390653282974264e-06, | |
| "loss": 1.5652, | |
| "num_input_tokens_seen": 153616384, | |
| "step": 586 | |
| }, | |
| { | |
| "epoch": 0.14576607896697294, | |
| "grad_norm": 0.37380003929138184, | |
| "learning_rate": 4.373333832178478e-06, | |
| "loss": 1.8029, | |
| "num_input_tokens_seen": 153878528, | |
| "step": 587 | |
| }, | |
| { | |
| "epoch": 0.1460144027812267, | |
| "grad_norm": 0.5546239614486694, | |
| "learning_rate": 4.356022017112187e-06, | |
| "loss": 1.7681, | |
| "num_input_tokens_seen": 154140672, | |
| "step": 588 | |
| }, | |
| { | |
| "epoch": 0.1462627265954805, | |
| "grad_norm": 0.6969411969184875, | |
| "learning_rate": 4.3387180487143875e-06, | |
| "loss": 1.9277, | |
| "num_input_tokens_seen": 154402816, | |
| "step": 589 | |
| }, | |
| { | |
| "epoch": 0.1465110504097343, | |
| "grad_norm": 0.7840688824653625, | |
| "learning_rate": 4.321422137828479e-06, | |
| "loss": 1.6007, | |
| "num_input_tokens_seen": 154664960, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.14675937422398808, | |
| "grad_norm": 0.6813507080078125, | |
| "learning_rate": 4.304134495199675e-06, | |
| "loss": 1.1834, | |
| "num_input_tokens_seen": 154927104, | |
| "step": 591 | |
| }, | |
| { | |
| "epoch": 0.14700769803824187, | |
| "grad_norm": 0.5060350298881531, | |
| "learning_rate": 4.286855331472442e-06, | |
| "loss": 1.4612, | |
| "num_input_tokens_seen": 155189248, | |
| "step": 592 | |
| }, | |
| { | |
| "epoch": 0.14725602185249564, | |
| "grad_norm": 0.5000078678131104, | |
| "learning_rate": 4.269584857187942e-06, | |
| "loss": 1.64, | |
| "num_input_tokens_seen": 155451392, | |
| "step": 593 | |
| }, | |
| { | |
| "epoch": 0.14750434566674944, | |
| "grad_norm": 0.5458803176879883, | |
| "learning_rate": 4.2523232827814534e-06, | |
| "loss": 2.1238, | |
| "num_input_tokens_seen": 155713536, | |
| "step": 594 | |
| }, | |
| { | |
| "epoch": 0.14775266948100324, | |
| "grad_norm": 1.3677194118499756, | |
| "learning_rate": 4.23507081857981e-06, | |
| "loss": 1.5499, | |
| "num_input_tokens_seen": 155975680, | |
| "step": 595 | |
| }, | |
| { | |
| "epoch": 0.148000993295257, | |
| "grad_norm": 0.5004885196685791, | |
| "learning_rate": 4.217827674798845e-06, | |
| "loss": 1.836, | |
| "num_input_tokens_seen": 156237824, | |
| "step": 596 | |
| }, | |
| { | |
| "epoch": 0.1482493171095108, | |
| "grad_norm": 1.3544896841049194, | |
| "learning_rate": 4.200594061540827e-06, | |
| "loss": 1.5202, | |
| "num_input_tokens_seen": 156499968, | |
| "step": 597 | |
| }, | |
| { | |
| "epoch": 0.14849764092376458, | |
| "grad_norm": 0.41308310627937317, | |
| "learning_rate": 4.183370188791891e-06, | |
| "loss": 1.4474, | |
| "num_input_tokens_seen": 156762112, | |
| "step": 598 | |
| }, | |
| { | |
| "epoch": 0.14874596473801838, | |
| "grad_norm": 0.5802090167999268, | |
| "learning_rate": 4.166156266419489e-06, | |
| "loss": 1.8016, | |
| "num_input_tokens_seen": 157024256, | |
| "step": 599 | |
| }, | |
| { | |
| "epoch": 0.14899428855227217, | |
| "grad_norm": 0.5909608602523804, | |
| "learning_rate": 4.148952504169839e-06, | |
| "loss": 1.5757, | |
| "num_input_tokens_seen": 157286400, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.14924261236652595, | |
| "grad_norm": 0.41110658645629883, | |
| "learning_rate": 4.131759111665349e-06, | |
| "loss": 0.8013, | |
| "num_input_tokens_seen": 157548544, | |
| "step": 601 | |
| }, | |
| { | |
| "epoch": 0.14949093618077974, | |
| "grad_norm": 0.5430499911308289, | |
| "learning_rate": 4.114576298402085e-06, | |
| "loss": 1.9595, | |
| "num_input_tokens_seen": 157810688, | |
| "step": 602 | |
| }, | |
| { | |
| "epoch": 0.1497392599950335, | |
| "grad_norm": 0.7195497751235962, | |
| "learning_rate": 4.0974042737472005e-06, | |
| "loss": 1.5623, | |
| "num_input_tokens_seen": 158072832, | |
| "step": 603 | |
| }, | |
| { | |
| "epoch": 0.1499875838092873, | |
| "grad_norm": 0.4989107847213745, | |
| "learning_rate": 4.0802432469364e-06, | |
| "loss": 1.3031, | |
| "num_input_tokens_seen": 158334976, | |
| "step": 604 | |
| }, | |
| { | |
| "epoch": 0.1502359076235411, | |
| "grad_norm": 0.5433792471885681, | |
| "learning_rate": 4.063093427071376e-06, | |
| "loss": 1.5003, | |
| "num_input_tokens_seen": 158597120, | |
| "step": 605 | |
| }, | |
| { | |
| "epoch": 0.15048423143779488, | |
| "grad_norm": 0.3139537274837494, | |
| "learning_rate": 4.045955023117276e-06, | |
| "loss": 1.2943, | |
| "num_input_tokens_seen": 158859264, | |
| "step": 606 | |
| }, | |
| { | |
| "epoch": 0.15073255525204868, | |
| "grad_norm": 0.7295723557472229, | |
| "learning_rate": 4.028828243900141e-06, | |
| "loss": 1.9625, | |
| "num_input_tokens_seen": 159121408, | |
| "step": 607 | |
| }, | |
| { | |
| "epoch": 0.15098087906630245, | |
| "grad_norm": 0.7763230204582214, | |
| "learning_rate": 4.0117132981043695e-06, | |
| "loss": 1.8425, | |
| "num_input_tokens_seen": 159383552, | |
| "step": 608 | |
| }, | |
| { | |
| "epoch": 0.15122920288055625, | |
| "grad_norm": 0.5297269821166992, | |
| "learning_rate": 3.994610394270178e-06, | |
| "loss": 1.6922, | |
| "num_input_tokens_seen": 159645696, | |
| "step": 609 | |
| }, | |
| { | |
| "epoch": 0.15147752669481004, | |
| "grad_norm": 0.4328116476535797, | |
| "learning_rate": 3.977519740791049e-06, | |
| "loss": 0.9763, | |
| "num_input_tokens_seen": 159907840, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.15172585050906381, | |
| "grad_norm": 0.6759671568870544, | |
| "learning_rate": 3.960441545911205e-06, | |
| "loss": 1.7297, | |
| "num_input_tokens_seen": 160169984, | |
| "step": 611 | |
| }, | |
| { | |
| "epoch": 0.1519741743233176, | |
| "grad_norm": 0.44700494408607483, | |
| "learning_rate": 3.943376017723058e-06, | |
| "loss": 1.9346, | |
| "num_input_tokens_seen": 160432128, | |
| "step": 612 | |
| }, | |
| { | |
| "epoch": 0.15222249813757138, | |
| "grad_norm": 0.8407000303268433, | |
| "learning_rate": 3.926323364164684e-06, | |
| "loss": 1.7382, | |
| "num_input_tokens_seen": 160694272, | |
| "step": 613 | |
| }, | |
| { | |
| "epoch": 0.15247082195182518, | |
| "grad_norm": 0.8016761541366577, | |
| "learning_rate": 3.909283793017289e-06, | |
| "loss": 1.7423, | |
| "num_input_tokens_seen": 160956416, | |
| "step": 614 | |
| }, | |
| { | |
| "epoch": 0.15271914576607898, | |
| "grad_norm": 0.414358526468277, | |
| "learning_rate": 3.892257511902664e-06, | |
| "loss": 1.4276, | |
| "num_input_tokens_seen": 161218560, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 0.15296746958033275, | |
| "grad_norm": 1.0210763216018677, | |
| "learning_rate": 3.875244728280676e-06, | |
| "loss": 1.3653, | |
| "num_input_tokens_seen": 161480704, | |
| "step": 616 | |
| }, | |
| { | |
| "epoch": 0.15321579339458655, | |
| "grad_norm": 0.8063709735870361, | |
| "learning_rate": 3.8582456494467214e-06, | |
| "loss": 1.8222, | |
| "num_input_tokens_seen": 161742848, | |
| "step": 617 | |
| }, | |
| { | |
| "epoch": 0.15346411720884032, | |
| "grad_norm": 0.5376055836677551, | |
| "learning_rate": 3.841260482529215e-06, | |
| "loss": 1.7019, | |
| "num_input_tokens_seen": 162004992, | |
| "step": 618 | |
| }, | |
| { | |
| "epoch": 0.15371244102309412, | |
| "grad_norm": 0.5194859504699707, | |
| "learning_rate": 3.82428943448705e-06, | |
| "loss": 1.633, | |
| "num_input_tokens_seen": 162267136, | |
| "step": 619 | |
| }, | |
| { | |
| "epoch": 0.1539607648373479, | |
| "grad_norm": 0.5276075005531311, | |
| "learning_rate": 3.8073327121070968e-06, | |
| "loss": 1.6824, | |
| "num_input_tokens_seen": 162529280, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.15420908865160168, | |
| "grad_norm": 0.7873098254203796, | |
| "learning_rate": 3.790390522001662e-06, | |
| "loss": 1.287, | |
| "num_input_tokens_seen": 162791424, | |
| "step": 621 | |
| }, | |
| { | |
| "epoch": 0.15445741246585548, | |
| "grad_norm": 0.6120622158050537, | |
| "learning_rate": 3.7734630706059873e-06, | |
| "loss": 1.8678, | |
| "num_input_tokens_seen": 163053568, | |
| "step": 622 | |
| }, | |
| { | |
| "epoch": 0.15470573628010925, | |
| "grad_norm": 0.5474843382835388, | |
| "learning_rate": 3.756550564175727e-06, | |
| "loss": 1.4913, | |
| "num_input_tokens_seen": 163315712, | |
| "step": 623 | |
| }, | |
| { | |
| "epoch": 0.15495406009436305, | |
| "grad_norm": 2.4813928604125977, | |
| "learning_rate": 3.7396532087844318e-06, | |
| "loss": 1.5975, | |
| "num_input_tokens_seen": 163577856, | |
| "step": 624 | |
| }, | |
| { | |
| "epoch": 0.15520238390861685, | |
| "grad_norm": 0.4030190408229828, | |
| "learning_rate": 3.7227712103210485e-06, | |
| "loss": 1.3417, | |
| "num_input_tokens_seen": 163840000, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.15545070772287062, | |
| "grad_norm": 0.4890609085559845, | |
| "learning_rate": 3.705904774487396e-06, | |
| "loss": 1.6517, | |
| "num_input_tokens_seen": 164102144, | |
| "step": 626 | |
| }, | |
| { | |
| "epoch": 0.15569903153712442, | |
| "grad_norm": 0.4225277006626129, | |
| "learning_rate": 3.6890541067956775e-06, | |
| "loss": 1.9024, | |
| "num_input_tokens_seen": 164364288, | |
| "step": 627 | |
| }, | |
| { | |
| "epoch": 0.1559473553513782, | |
| "grad_norm": 0.3365168273448944, | |
| "learning_rate": 3.672219412565956e-06, | |
| "loss": 1.8831, | |
| "num_input_tokens_seen": 164626432, | |
| "step": 628 | |
| }, | |
| { | |
| "epoch": 0.15619567916563198, | |
| "grad_norm": 0.46206042170524597, | |
| "learning_rate": 3.655400896923672e-06, | |
| "loss": 1.5472, | |
| "num_input_tokens_seen": 164888576, | |
| "step": 629 | |
| }, | |
| { | |
| "epoch": 0.15644400297988578, | |
| "grad_norm": 0.5152633190155029, | |
| "learning_rate": 3.6385987647971287e-06, | |
| "loss": 1.9021, | |
| "num_input_tokens_seen": 165150720, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.15669232679413955, | |
| "grad_norm": 0.6955782771110535, | |
| "learning_rate": 3.6218132209150047e-06, | |
| "loss": 1.5289, | |
| "num_input_tokens_seen": 165412864, | |
| "step": 631 | |
| }, | |
| { | |
| "epoch": 0.15694065060839335, | |
| "grad_norm": 0.8016681671142578, | |
| "learning_rate": 3.6050444698038547e-06, | |
| "loss": 1.2874, | |
| "num_input_tokens_seen": 165675008, | |
| "step": 632 | |
| }, | |
| { | |
| "epoch": 0.15718897442264712, | |
| "grad_norm": 0.32328078150749207, | |
| "learning_rate": 3.5882927157856175e-06, | |
| "loss": 1.9816, | |
| "num_input_tokens_seen": 165937152, | |
| "step": 633 | |
| }, | |
| { | |
| "epoch": 0.15743729823690092, | |
| "grad_norm": 0.4143851101398468, | |
| "learning_rate": 3.571558162975133e-06, | |
| "loss": 1.4726, | |
| "num_input_tokens_seen": 166199296, | |
| "step": 634 | |
| }, | |
| { | |
| "epoch": 0.15768562205115472, | |
| "grad_norm": 0.6780726909637451, | |
| "learning_rate": 3.5548410152776414e-06, | |
| "loss": 1.5232, | |
| "num_input_tokens_seen": 166461440, | |
| "step": 635 | |
| }, | |
| { | |
| "epoch": 0.1579339458654085, | |
| "grad_norm": 0.4231894314289093, | |
| "learning_rate": 3.538141476386317e-06, | |
| "loss": 1.7631, | |
| "num_input_tokens_seen": 166723584, | |
| "step": 636 | |
| }, | |
| { | |
| "epoch": 0.15818226967966229, | |
| "grad_norm": 0.4781966805458069, | |
| "learning_rate": 3.521459749779769e-06, | |
| "loss": 2.3027, | |
| "num_input_tokens_seen": 166985728, | |
| "step": 637 | |
| }, | |
| { | |
| "epoch": 0.15843059349391606, | |
| "grad_norm": 0.6974207162857056, | |
| "learning_rate": 3.5047960387195673e-06, | |
| "loss": 1.4963, | |
| "num_input_tokens_seen": 167247872, | |
| "step": 638 | |
| }, | |
| { | |
| "epoch": 0.15867891730816985, | |
| "grad_norm": 0.4340938627719879, | |
| "learning_rate": 3.488150546247778e-06, | |
| "loss": 1.6811, | |
| "num_input_tokens_seen": 167510016, | |
| "step": 639 | |
| }, | |
| { | |
| "epoch": 0.15892724112242365, | |
| "grad_norm": 0.6632753014564514, | |
| "learning_rate": 3.471523475184472e-06, | |
| "loss": 2.0226, | |
| "num_input_tokens_seen": 167772160, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.15917556493667742, | |
| "grad_norm": 0.5399497747421265, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 1.6728, | |
| "num_input_tokens_seen": 168034304, | |
| "step": 641 | |
| }, | |
| { | |
| "epoch": 0.15942388875093122, | |
| "grad_norm": 0.6213698387145996, | |
| "learning_rate": 3.4383254074388373e-06, | |
| "loss": 1.7282, | |
| "num_input_tokens_seen": 168296448, | |
| "step": 642 | |
| }, | |
| { | |
| "epoch": 0.159672212565185, | |
| "grad_norm": 0.8171265125274658, | |
| "learning_rate": 3.4217548152644887e-06, | |
| "loss": 1.7681, | |
| "num_input_tokens_seen": 168558592, | |
| "step": 643 | |
| }, | |
| { | |
| "epoch": 0.1599205363794388, | |
| "grad_norm": 0.36624467372894287, | |
| "learning_rate": 3.40520345350965e-06, | |
| "loss": 1.7461, | |
| "num_input_tokens_seen": 168820736, | |
| "step": 644 | |
| }, | |
| { | |
| "epoch": 0.16016886019369259, | |
| "grad_norm": 0.4452555179595947, | |
| "learning_rate": 3.3886715238474454e-06, | |
| "loss": 1.8516, | |
| "num_input_tokens_seen": 169082880, | |
| "step": 645 | |
| }, | |
| { | |
| "epoch": 0.16041718400794636, | |
| "grad_norm": 0.6282974481582642, | |
| "learning_rate": 3.372159227714218e-06, | |
| "loss": 1.589, | |
| "num_input_tokens_seen": 169345024, | |
| "step": 646 | |
| }, | |
| { | |
| "epoch": 0.16066550782220015, | |
| "grad_norm": 0.2544865012168884, | |
| "learning_rate": 3.355666766307084e-06, | |
| "loss": 1.4478, | |
| "num_input_tokens_seen": 169607168, | |
| "step": 647 | |
| }, | |
| { | |
| "epoch": 0.16091383163645392, | |
| "grad_norm": 0.7939302921295166, | |
| "learning_rate": 3.339194340581485e-06, | |
| "loss": 1.5844, | |
| "num_input_tokens_seen": 169869312, | |
| "step": 648 | |
| }, | |
| { | |
| "epoch": 0.16116215545070772, | |
| "grad_norm": 1.1076239347457886, | |
| "learning_rate": 3.322742151248726e-06, | |
| "loss": 1.8774, | |
| "num_input_tokens_seen": 170131456, | |
| "step": 649 | |
| }, | |
| { | |
| "epoch": 0.16141047926496152, | |
| "grad_norm": 0.5885612964630127, | |
| "learning_rate": 3.3063103987735433e-06, | |
| "loss": 1.8922, | |
| "num_input_tokens_seen": 170393600, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.1616588030792153, | |
| "grad_norm": 0.8514074683189392, | |
| "learning_rate": 3.289899283371657e-06, | |
| "loss": 1.4842, | |
| "num_input_tokens_seen": 170655744, | |
| "step": 651 | |
| }, | |
| { | |
| "epoch": 0.1619071268934691, | |
| "grad_norm": 0.6668713092803955, | |
| "learning_rate": 3.273509005007327e-06, | |
| "loss": 1.538, | |
| "num_input_tokens_seen": 170917888, | |
| "step": 652 | |
| }, | |
| { | |
| "epoch": 0.16215545070772286, | |
| "grad_norm": 0.4702228009700775, | |
| "learning_rate": 3.2571397633909252e-06, | |
| "loss": 1.4504, | |
| "num_input_tokens_seen": 171180032, | |
| "step": 653 | |
| }, | |
| { | |
| "epoch": 0.16240377452197666, | |
| "grad_norm": 0.4500584900379181, | |
| "learning_rate": 3.2407917579764914e-06, | |
| "loss": 1.8598, | |
| "num_input_tokens_seen": 171442176, | |
| "step": 654 | |
| }, | |
| { | |
| "epoch": 0.16265209833623046, | |
| "grad_norm": 0.477428674697876, | |
| "learning_rate": 3.224465187959316e-06, | |
| "loss": 1.9269, | |
| "num_input_tokens_seen": 171704320, | |
| "step": 655 | |
| }, | |
| { | |
| "epoch": 0.16290042215048423, | |
| "grad_norm": 0.43787822127342224, | |
| "learning_rate": 3.2081602522734987e-06, | |
| "loss": 1.9365, | |
| "num_input_tokens_seen": 171966464, | |
| "step": 656 | |
| }, | |
| { | |
| "epoch": 0.16314874596473802, | |
| "grad_norm": 0.4032402038574219, | |
| "learning_rate": 3.1918771495895395e-06, | |
| "loss": 1.3458, | |
| "num_input_tokens_seen": 172228608, | |
| "step": 657 | |
| }, | |
| { | |
| "epoch": 0.1633970697789918, | |
| "grad_norm": 0.733826220035553, | |
| "learning_rate": 3.1756160783119015e-06, | |
| "loss": 1.4177, | |
| "num_input_tokens_seen": 172490752, | |
| "step": 658 | |
| }, | |
| { | |
| "epoch": 0.1636453935932456, | |
| "grad_norm": 0.34868526458740234, | |
| "learning_rate": 3.1593772365766107e-06, | |
| "loss": 1.6965, | |
| "num_input_tokens_seen": 172752896, | |
| "step": 659 | |
| }, | |
| { | |
| "epoch": 0.1638937174074994, | |
| "grad_norm": 0.8062167167663574, | |
| "learning_rate": 3.1431608222488276e-06, | |
| "loss": 1.7109, | |
| "num_input_tokens_seen": 173015040, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.16414204122175316, | |
| "grad_norm": 0.6374398469924927, | |
| "learning_rate": 3.12696703292044e-06, | |
| "loss": 1.2467, | |
| "num_input_tokens_seen": 173277184, | |
| "step": 661 | |
| }, | |
| { | |
| "epoch": 0.16439036503600696, | |
| "grad_norm": 0.593471348285675, | |
| "learning_rate": 3.110796065907665e-06, | |
| "loss": 1.2338, | |
| "num_input_tokens_seen": 173539328, | |
| "step": 662 | |
| }, | |
| { | |
| "epoch": 0.16463868885026073, | |
| "grad_norm": 0.7001546621322632, | |
| "learning_rate": 3.09464811824863e-06, | |
| "loss": 1.944, | |
| "num_input_tokens_seen": 173801472, | |
| "step": 663 | |
| }, | |
| { | |
| "epoch": 0.16488701266451453, | |
| "grad_norm": 0.39311012625694275, | |
| "learning_rate": 3.078523386700982e-06, | |
| "loss": 1.8565, | |
| "num_input_tokens_seen": 174063616, | |
| "step": 664 | |
| }, | |
| { | |
| "epoch": 0.16513533647876832, | |
| "grad_norm": 0.5350921750068665, | |
| "learning_rate": 3.0624220677394854e-06, | |
| "loss": 1.7504, | |
| "num_input_tokens_seen": 174325760, | |
| "step": 665 | |
| }, | |
| { | |
| "epoch": 0.1653836602930221, | |
| "grad_norm": 0.38316506147384644, | |
| "learning_rate": 3.0463443575536324e-06, | |
| "loss": 1.6073, | |
| "num_input_tokens_seen": 174587904, | |
| "step": 666 | |
| }, | |
| { | |
| "epoch": 0.1656319841072759, | |
| "grad_norm": 0.7546458840370178, | |
| "learning_rate": 3.030290452045245e-06, | |
| "loss": 1.3026, | |
| "num_input_tokens_seen": 174850048, | |
| "step": 667 | |
| }, | |
| { | |
| "epoch": 0.16588030792152966, | |
| "grad_norm": 0.27675381302833557, | |
| "learning_rate": 3.0142605468260976e-06, | |
| "loss": 1.3484, | |
| "num_input_tokens_seen": 175112192, | |
| "step": 668 | |
| }, | |
| { | |
| "epoch": 0.16612863173578346, | |
| "grad_norm": 0.4194891154766083, | |
| "learning_rate": 2.9982548372155264e-06, | |
| "loss": 1.8019, | |
| "num_input_tokens_seen": 175374336, | |
| "step": 669 | |
| }, | |
| { | |
| "epoch": 0.16637695555003726, | |
| "grad_norm": 0.36900594830513, | |
| "learning_rate": 2.98227351823805e-06, | |
| "loss": 1.5313, | |
| "num_input_tokens_seen": 175636480, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.16662527936429103, | |
| "grad_norm": 0.6106650829315186, | |
| "learning_rate": 2.966316784621e-06, | |
| "loss": 1.6545, | |
| "num_input_tokens_seen": 175898624, | |
| "step": 671 | |
| }, | |
| { | |
| "epoch": 0.16687360317854483, | |
| "grad_norm": 0.3975144624710083, | |
| "learning_rate": 2.9503848307921363e-06, | |
| "loss": 1.8634, | |
| "num_input_tokens_seen": 176160768, | |
| "step": 672 | |
| }, | |
| { | |
| "epoch": 0.1671219269927986, | |
| "grad_norm": 0.5684614777565002, | |
| "learning_rate": 2.934477850877292e-06, | |
| "loss": 1.618, | |
| "num_input_tokens_seen": 176422912, | |
| "step": 673 | |
| }, | |
| { | |
| "epoch": 0.1673702508070524, | |
| "grad_norm": 0.7491419315338135, | |
| "learning_rate": 2.918596038697995e-06, | |
| "loss": 1.8058, | |
| "num_input_tokens_seen": 176685056, | |
| "step": 674 | |
| }, | |
| { | |
| "epoch": 0.1676185746213062, | |
| "grad_norm": 0.36299964785575867, | |
| "learning_rate": 2.9027395877691143e-06, | |
| "loss": 1.6074, | |
| "num_input_tokens_seen": 176947200, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.16786689843555996, | |
| "grad_norm": 1.1680899858474731, | |
| "learning_rate": 2.886908691296504e-06, | |
| "loss": 1.7054, | |
| "num_input_tokens_seen": 177209344, | |
| "step": 676 | |
| }, | |
| { | |
| "epoch": 0.16811522224981376, | |
| "grad_norm": 0.4961852729320526, | |
| "learning_rate": 2.871103542174637e-06, | |
| "loss": 1.8983, | |
| "num_input_tokens_seen": 177471488, | |
| "step": 677 | |
| }, | |
| { | |
| "epoch": 0.16836354606406753, | |
| "grad_norm": 0.42342936992645264, | |
| "learning_rate": 2.8553243329842715e-06, | |
| "loss": 1.6285, | |
| "num_input_tokens_seen": 177733632, | |
| "step": 678 | |
| }, | |
| { | |
| "epoch": 0.16861186987832133, | |
| "grad_norm": 0.6261987686157227, | |
| "learning_rate": 2.839571255990088e-06, | |
| "loss": 1.8729, | |
| "num_input_tokens_seen": 177995776, | |
| "step": 679 | |
| }, | |
| { | |
| "epoch": 0.16886019369257513, | |
| "grad_norm": 0.5163364410400391, | |
| "learning_rate": 2.8238445031383634e-06, | |
| "loss": 1.5881, | |
| "num_input_tokens_seen": 178257920, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.1691085175068289, | |
| "grad_norm": 0.6004268527030945, | |
| "learning_rate": 2.8081442660546126e-06, | |
| "loss": 1.7253, | |
| "num_input_tokens_seen": 178520064, | |
| "step": 681 | |
| }, | |
| { | |
| "epoch": 0.1693568413210827, | |
| "grad_norm": 0.513282299041748, | |
| "learning_rate": 2.7924707360412743e-06, | |
| "loss": 1.3065, | |
| "num_input_tokens_seen": 178782208, | |
| "step": 682 | |
| }, | |
| { | |
| "epoch": 0.16960516513533647, | |
| "grad_norm": 0.508873701095581, | |
| "learning_rate": 2.776824104075364e-06, | |
| "loss": 1.4716, | |
| "num_input_tokens_seen": 179044352, | |
| "step": 683 | |
| }, | |
| { | |
| "epoch": 0.16985348894959026, | |
| "grad_norm": 0.43925005197525024, | |
| "learning_rate": 2.761204560806152e-06, | |
| "loss": 1.7001, | |
| "num_input_tokens_seen": 179306496, | |
| "step": 684 | |
| }, | |
| { | |
| "epoch": 0.17010181276384406, | |
| "grad_norm": 0.5974088907241821, | |
| "learning_rate": 2.7456122965528475e-06, | |
| "loss": 1.6872, | |
| "num_input_tokens_seen": 179568640, | |
| "step": 685 | |
| }, | |
| { | |
| "epoch": 0.17035013657809783, | |
| "grad_norm": 0.6642299890518188, | |
| "learning_rate": 2.7300475013022666e-06, | |
| "loss": 1.6835, | |
| "num_input_tokens_seen": 179830784, | |
| "step": 686 | |
| }, | |
| { | |
| "epoch": 0.17059846039235163, | |
| "grad_norm": 1.514657735824585, | |
| "learning_rate": 2.714510364706531e-06, | |
| "loss": 1.6302, | |
| "num_input_tokens_seen": 180092928, | |
| "step": 687 | |
| }, | |
| { | |
| "epoch": 0.1708467842066054, | |
| "grad_norm": 0.753200113773346, | |
| "learning_rate": 2.699001076080742e-06, | |
| "loss": 1.7994, | |
| "num_input_tokens_seen": 180355072, | |
| "step": 688 | |
| }, | |
| { | |
| "epoch": 0.1710951080208592, | |
| "grad_norm": 0.5442324876785278, | |
| "learning_rate": 2.683519824400693e-06, | |
| "loss": 1.1455, | |
| "num_input_tokens_seen": 180617216, | |
| "step": 689 | |
| }, | |
| { | |
| "epoch": 0.171343431835113, | |
| "grad_norm": 0.42106226086616516, | |
| "learning_rate": 2.6680667983005446e-06, | |
| "loss": 1.4338, | |
| "num_input_tokens_seen": 180879360, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.17159175564936677, | |
| "grad_norm": 0.36291244626045227, | |
| "learning_rate": 2.6526421860705474e-06, | |
| "loss": 1.4588, | |
| "num_input_tokens_seen": 181141504, | |
| "step": 691 | |
| }, | |
| { | |
| "epoch": 0.17184007946362057, | |
| "grad_norm": 0.5528322458267212, | |
| "learning_rate": 2.637246175654731e-06, | |
| "loss": 1.972, | |
| "num_input_tokens_seen": 181403648, | |
| "step": 692 | |
| }, | |
| { | |
| "epoch": 0.17208840327787434, | |
| "grad_norm": 1.1730087995529175, | |
| "learning_rate": 2.6218789546486235e-06, | |
| "loss": 1.4716, | |
| "num_input_tokens_seen": 181665792, | |
| "step": 693 | |
| }, | |
| { | |
| "epoch": 0.17233672709212813, | |
| "grad_norm": 0.28138279914855957, | |
| "learning_rate": 2.6065407102969664e-06, | |
| "loss": 1.9811, | |
| "num_input_tokens_seen": 181927936, | |
| "step": 694 | |
| }, | |
| { | |
| "epoch": 0.17258505090638193, | |
| "grad_norm": 0.585191011428833, | |
| "learning_rate": 2.5912316294914232e-06, | |
| "loss": 1.413, | |
| "num_input_tokens_seen": 182190080, | |
| "step": 695 | |
| }, | |
| { | |
| "epoch": 0.1728333747206357, | |
| "grad_norm": 0.7064807415008545, | |
| "learning_rate": 2.5759518987683154e-06, | |
| "loss": 1.7552, | |
| "num_input_tokens_seen": 182452224, | |
| "step": 696 | |
| }, | |
| { | |
| "epoch": 0.1730816985348895, | |
| "grad_norm": 0.2733915448188782, | |
| "learning_rate": 2.560701704306336e-06, | |
| "loss": 1.5639, | |
| "num_input_tokens_seen": 182714368, | |
| "step": 697 | |
| }, | |
| { | |
| "epoch": 0.17333002234914327, | |
| "grad_norm": 0.37990668416023254, | |
| "learning_rate": 2.545481231924296e-06, | |
| "loss": 2.0107, | |
| "num_input_tokens_seen": 182976512, | |
| "step": 698 | |
| }, | |
| { | |
| "epoch": 0.17357834616339707, | |
| "grad_norm": 0.5895552039146423, | |
| "learning_rate": 2.5302906670788463e-06, | |
| "loss": 2.0406, | |
| "num_input_tokens_seen": 183238656, | |
| "step": 699 | |
| }, | |
| { | |
| "epoch": 0.17382666997765087, | |
| "grad_norm": 0.6895752549171448, | |
| "learning_rate": 2.5151301948622235e-06, | |
| "loss": 1.9766, | |
| "num_input_tokens_seen": 183500800, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.17407499379190464, | |
| "grad_norm": 0.46613720059394836, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 2.0084, | |
| "num_input_tokens_seen": 183762944, | |
| "step": 701 | |
| }, | |
| { | |
| "epoch": 0.17432331760615843, | |
| "grad_norm": 0.5650424957275391, | |
| "learning_rate": 2.484900266848825e-06, | |
| "loss": 1.7718, | |
| "num_input_tokens_seen": 184025088, | |
| "step": 702 | |
| }, | |
| { | |
| "epoch": 0.1745716414204122, | |
| "grad_norm": 0.5093001127243042, | |
| "learning_rate": 2.469831179394182e-06, | |
| "loss": 1.5874, | |
| "num_input_tokens_seen": 184287232, | |
| "step": 703 | |
| }, | |
| { | |
| "epoch": 0.174819965234666, | |
| "grad_norm": 0.7076382040977478, | |
| "learning_rate": 2.4547929212481436e-06, | |
| "loss": 1.5776, | |
| "num_input_tokens_seen": 184549376, | |
| "step": 704 | |
| }, | |
| { | |
| "epoch": 0.1750682890489198, | |
| "grad_norm": 0.7036752700805664, | |
| "learning_rate": 2.4397856756471435e-06, | |
| "loss": 1.0319, | |
| "num_input_tokens_seen": 184811520, | |
| "step": 705 | |
| }, | |
| { | |
| "epoch": 0.17531661286317357, | |
| "grad_norm": 0.6339607238769531, | |
| "learning_rate": 2.424809625449729e-06, | |
| "loss": 1.4841, | |
| "num_input_tokens_seen": 185073664, | |
| "step": 706 | |
| }, | |
| { | |
| "epoch": 0.17556493667742737, | |
| "grad_norm": 0.6772640347480774, | |
| "learning_rate": 2.40986495313435e-06, | |
| "loss": 1.398, | |
| "num_input_tokens_seen": 185335808, | |
| "step": 707 | |
| }, | |
| { | |
| "epoch": 0.17581326049168114, | |
| "grad_norm": 0.626737117767334, | |
| "learning_rate": 2.39495184079712e-06, | |
| "loss": 1.9448, | |
| "num_input_tokens_seen": 185597952, | |
| "step": 708 | |
| }, | |
| { | |
| "epoch": 0.17606158430593494, | |
| "grad_norm": 0.8285679221153259, | |
| "learning_rate": 2.380070470149605e-06, | |
| "loss": 1.596, | |
| "num_input_tokens_seen": 185860096, | |
| "step": 709 | |
| }, | |
| { | |
| "epoch": 0.17630990812018874, | |
| "grad_norm": 0.47030216455459595, | |
| "learning_rate": 2.3652210225166122e-06, | |
| "loss": 1.6729, | |
| "num_input_tokens_seen": 186122240, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.1765582319344425, | |
| "grad_norm": 0.36715853214263916, | |
| "learning_rate": 2.3504036788339763e-06, | |
| "loss": 1.375, | |
| "num_input_tokens_seen": 186384384, | |
| "step": 711 | |
| }, | |
| { | |
| "epoch": 0.1768065557486963, | |
| "grad_norm": 0.5815637707710266, | |
| "learning_rate": 2.3356186196463497e-06, | |
| "loss": 1.6501, | |
| "num_input_tokens_seen": 186646528, | |
| "step": 712 | |
| }, | |
| { | |
| "epoch": 0.17705487956295007, | |
| "grad_norm": 0.5376741290092468, | |
| "learning_rate": 2.320866025105016e-06, | |
| "loss": 1.7278, | |
| "num_input_tokens_seen": 186908672, | |
| "step": 713 | |
| }, | |
| { | |
| "epoch": 0.17730320337720387, | |
| "grad_norm": 0.5446439385414124, | |
| "learning_rate": 2.3061460749656844e-06, | |
| "loss": 1.9617, | |
| "num_input_tokens_seen": 187170816, | |
| "step": 714 | |
| }, | |
| { | |
| "epoch": 0.17755152719145767, | |
| "grad_norm": 0.8022477030754089, | |
| "learning_rate": 2.2914589485863015e-06, | |
| "loss": 1.8491, | |
| "num_input_tokens_seen": 187432960, | |
| "step": 715 | |
| }, | |
| { | |
| "epoch": 0.17779985100571144, | |
| "grad_norm": 0.40645989775657654, | |
| "learning_rate": 2.2768048249248648e-06, | |
| "loss": 1.5563, | |
| "num_input_tokens_seen": 187695104, | |
| "step": 716 | |
| }, | |
| { | |
| "epoch": 0.17804817481996524, | |
| "grad_norm": 0.5382466316223145, | |
| "learning_rate": 2.2621838825372496e-06, | |
| "loss": 1.5754, | |
| "num_input_tokens_seen": 187957248, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 0.178296498634219, | |
| "grad_norm": 0.6198011636734009, | |
| "learning_rate": 2.2475962995750224e-06, | |
| "loss": 1.8925, | |
| "num_input_tokens_seen": 188219392, | |
| "step": 718 | |
| }, | |
| { | |
| "epoch": 0.1785448224484728, | |
| "grad_norm": 0.4357577860355377, | |
| "learning_rate": 2.23304225378328e-06, | |
| "loss": 1.9635, | |
| "num_input_tokens_seen": 188481536, | |
| "step": 719 | |
| }, | |
| { | |
| "epoch": 0.1787931462627266, | |
| "grad_norm": 0.5042324662208557, | |
| "learning_rate": 2.218521922498476e-06, | |
| "loss": 1.4101, | |
| "num_input_tokens_seen": 188743680, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.17904147007698037, | |
| "grad_norm": 0.5827696323394775, | |
| "learning_rate": 2.204035482646267e-06, | |
| "loss": 1.6445, | |
| "num_input_tokens_seen": 189005824, | |
| "step": 721 | |
| }, | |
| { | |
| "epoch": 0.17928979389123417, | |
| "grad_norm": 0.5384161472320557, | |
| "learning_rate": 2.1895831107393485e-06, | |
| "loss": 1.5907, | |
| "num_input_tokens_seen": 189267968, | |
| "step": 722 | |
| }, | |
| { | |
| "epoch": 0.17953811770548794, | |
| "grad_norm": 0.5630956292152405, | |
| "learning_rate": 2.175164982875311e-06, | |
| "loss": 1.4097, | |
| "num_input_tokens_seen": 189530112, | |
| "step": 723 | |
| }, | |
| { | |
| "epoch": 0.17978644151974174, | |
| "grad_norm": 0.43942683935165405, | |
| "learning_rate": 2.1607812747344955e-06, | |
| "loss": 1.393, | |
| "num_input_tokens_seen": 189792256, | |
| "step": 724 | |
| }, | |
| { | |
| "epoch": 0.18003476533399554, | |
| "grad_norm": 0.2822117209434509, | |
| "learning_rate": 2.146432161577842e-06, | |
| "loss": 1.4047, | |
| "num_input_tokens_seen": 190054400, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.1802830891482493, | |
| "grad_norm": 0.7013232707977295, | |
| "learning_rate": 2.132117818244771e-06, | |
| "loss": 1.8612, | |
| "num_input_tokens_seen": 190316544, | |
| "step": 726 | |
| }, | |
| { | |
| "epoch": 0.1805314129625031, | |
| "grad_norm": 0.7166525721549988, | |
| "learning_rate": 2.1178384191510344e-06, | |
| "loss": 1.5652, | |
| "num_input_tokens_seen": 190578688, | |
| "step": 727 | |
| }, | |
| { | |
| "epoch": 0.18077973677675688, | |
| "grad_norm": 0.8852736949920654, | |
| "learning_rate": 2.103594138286607e-06, | |
| "loss": 1.8348, | |
| "num_input_tokens_seen": 190840832, | |
| "step": 728 | |
| }, | |
| { | |
| "epoch": 0.18102806059101068, | |
| "grad_norm": 0.7377064228057861, | |
| "learning_rate": 2.0893851492135536e-06, | |
| "loss": 1.5408, | |
| "num_input_tokens_seen": 191102976, | |
| "step": 729 | |
| }, | |
| { | |
| "epoch": 0.18127638440526447, | |
| "grad_norm": 0.31571272015571594, | |
| "learning_rate": 2.075211625063923e-06, | |
| "loss": 1.4516, | |
| "num_input_tokens_seen": 191365120, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.18152470821951824, | |
| "grad_norm": 0.4377698004245758, | |
| "learning_rate": 2.061073738537635e-06, | |
| "loss": 1.8452, | |
| "num_input_tokens_seen": 191627264, | |
| "step": 731 | |
| }, | |
| { | |
| "epoch": 0.18177303203377204, | |
| "grad_norm": 0.6246635317802429, | |
| "learning_rate": 2.046971661900373e-06, | |
| "loss": 1.0213, | |
| "num_input_tokens_seen": 191889408, | |
| "step": 732 | |
| }, | |
| { | |
| "epoch": 0.1820213558480258, | |
| "grad_norm": 0.3734930157661438, | |
| "learning_rate": 2.0329055669814936e-06, | |
| "loss": 1.3397, | |
| "num_input_tokens_seen": 192151552, | |
| "step": 733 | |
| }, | |
| { | |
| "epoch": 0.1822696796622796, | |
| "grad_norm": 0.6088233590126038, | |
| "learning_rate": 2.0188756251719204e-06, | |
| "loss": 1.5803, | |
| "num_input_tokens_seen": 192413696, | |
| "step": 734 | |
| }, | |
| { | |
| "epoch": 0.1825180034765334, | |
| "grad_norm": 0.6044638156890869, | |
| "learning_rate": 2.0048820074220716e-06, | |
| "loss": 1.629, | |
| "num_input_tokens_seen": 192675840, | |
| "step": 735 | |
| }, | |
| { | |
| "epoch": 0.18276632729078718, | |
| "grad_norm": 0.5411587357521057, | |
| "learning_rate": 1.990924884239758e-06, | |
| "loss": 1.5093, | |
| "num_input_tokens_seen": 192937984, | |
| "step": 736 | |
| }, | |
| { | |
| "epoch": 0.18301465110504098, | |
| "grad_norm": 0.7263090014457703, | |
| "learning_rate": 1.977004425688126e-06, | |
| "loss": 1.6338, | |
| "num_input_tokens_seen": 193200128, | |
| "step": 737 | |
| }, | |
| { | |
| "epoch": 0.18326297491929475, | |
| "grad_norm": 0.5330092310905457, | |
| "learning_rate": 1.9631208013835677e-06, | |
| "loss": 1.6223, | |
| "num_input_tokens_seen": 193462272, | |
| "step": 738 | |
| }, | |
| { | |
| "epoch": 0.18351129873354854, | |
| "grad_norm": 0.8732761740684509, | |
| "learning_rate": 1.9492741804936623e-06, | |
| "loss": 1.81, | |
| "num_input_tokens_seen": 193724416, | |
| "step": 739 | |
| }, | |
| { | |
| "epoch": 0.18375962254780234, | |
| "grad_norm": 0.4876832067966461, | |
| "learning_rate": 1.9354647317351187e-06, | |
| "loss": 1.8895, | |
| "num_input_tokens_seen": 193986560, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.1840079463620561, | |
| "grad_norm": 0.5221810340881348, | |
| "learning_rate": 1.9216926233717087e-06, | |
| "loss": 1.7537, | |
| "num_input_tokens_seen": 194248704, | |
| "step": 741 | |
| }, | |
| { | |
| "epoch": 0.1842562701763099, | |
| "grad_norm": 0.7166823744773865, | |
| "learning_rate": 1.90795802321223e-06, | |
| "loss": 1.6196, | |
| "num_input_tokens_seen": 194510848, | |
| "step": 742 | |
| }, | |
| { | |
| "epoch": 0.1845045939905637, | |
| "grad_norm": 0.5422106981277466, | |
| "learning_rate": 1.8942610986084487e-06, | |
| "loss": 1.7422, | |
| "num_input_tokens_seen": 194772992, | |
| "step": 743 | |
| }, | |
| { | |
| "epoch": 0.18475291780481748, | |
| "grad_norm": 0.5047271847724915, | |
| "learning_rate": 1.8806020164530702e-06, | |
| "loss": 1.1779, | |
| "num_input_tokens_seen": 195035136, | |
| "step": 744 | |
| }, | |
| { | |
| "epoch": 0.18500124161907128, | |
| "grad_norm": 0.6293126344680786, | |
| "learning_rate": 1.8669809431776991e-06, | |
| "loss": 1.923, | |
| "num_input_tokens_seen": 195297280, | |
| "step": 745 | |
| }, | |
| { | |
| "epoch": 0.18524956543332505, | |
| "grad_norm": 0.41052141785621643, | |
| "learning_rate": 1.8533980447508138e-06, | |
| "loss": 1.3557, | |
| "num_input_tokens_seen": 195559424, | |
| "step": 746 | |
| }, | |
| { | |
| "epoch": 0.18549788924757885, | |
| "grad_norm": 0.45604202151298523, | |
| "learning_rate": 1.8398534866757455e-06, | |
| "loss": 1.7005, | |
| "num_input_tokens_seen": 195821568, | |
| "step": 747 | |
| }, | |
| { | |
| "epoch": 0.18574621306183264, | |
| "grad_norm": 0.730992317199707, | |
| "learning_rate": 1.8263474339886628e-06, | |
| "loss": 2.0785, | |
| "num_input_tokens_seen": 196083712, | |
| "step": 748 | |
| }, | |
| { | |
| "epoch": 0.1859945368760864, | |
| "grad_norm": 0.5063241124153137, | |
| "learning_rate": 1.8128800512565514e-06, | |
| "loss": 2.1056, | |
| "num_input_tokens_seen": 196345856, | |
| "step": 749 | |
| }, | |
| { | |
| "epoch": 0.1862428606903402, | |
| "grad_norm": 0.2811354100704193, | |
| "learning_rate": 1.799451502575222e-06, | |
| "loss": 1.2958, | |
| "num_input_tokens_seen": 196608000, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.18649118450459398, | |
| "grad_norm": 0.5314778089523315, | |
| "learning_rate": 1.7860619515673034e-06, | |
| "loss": 1.7808, | |
| "num_input_tokens_seen": 196870144, | |
| "step": 751 | |
| }, | |
| { | |
| "epoch": 0.18673950831884778, | |
| "grad_norm": 1.0328506231307983, | |
| "learning_rate": 1.7727115613802465e-06, | |
| "loss": 2.0584, | |
| "num_input_tokens_seen": 197132288, | |
| "step": 752 | |
| }, | |
| { | |
| "epoch": 0.18698783213310158, | |
| "grad_norm": 0.7677520513534546, | |
| "learning_rate": 1.7594004946843458e-06, | |
| "loss": 1.6937, | |
| "num_input_tokens_seen": 197394432, | |
| "step": 753 | |
| }, | |
| { | |
| "epoch": 0.18723615594735535, | |
| "grad_norm": 0.6427842974662781, | |
| "learning_rate": 1.746128913670746e-06, | |
| "loss": 1.8869, | |
| "num_input_tokens_seen": 197656576, | |
| "step": 754 | |
| }, | |
| { | |
| "epoch": 0.18748447976160915, | |
| "grad_norm": 1.0200343132019043, | |
| "learning_rate": 1.7328969800494727e-06, | |
| "loss": 1.796, | |
| "num_input_tokens_seen": 197918720, | |
| "step": 755 | |
| }, | |
| { | |
| "epoch": 0.18773280357586292, | |
| "grad_norm": 0.8236029148101807, | |
| "learning_rate": 1.7197048550474643e-06, | |
| "loss": 1.6866, | |
| "num_input_tokens_seen": 198180864, | |
| "step": 756 | |
| }, | |
| { | |
| "epoch": 0.18798112739011671, | |
| "grad_norm": 1.2460148334503174, | |
| "learning_rate": 1.7065526994065973e-06, | |
| "loss": 1.3428, | |
| "num_input_tokens_seen": 198443008, | |
| "step": 757 | |
| }, | |
| { | |
| "epoch": 0.1882294512043705, | |
| "grad_norm": 0.4800860285758972, | |
| "learning_rate": 1.6934406733817417e-06, | |
| "loss": 1.4296, | |
| "num_input_tokens_seen": 198705152, | |
| "step": 758 | |
| }, | |
| { | |
| "epoch": 0.18847777501862428, | |
| "grad_norm": 0.9592916965484619, | |
| "learning_rate": 1.680368936738792e-06, | |
| "loss": 1.4531, | |
| "num_input_tokens_seen": 198967296, | |
| "step": 759 | |
| }, | |
| { | |
| "epoch": 0.18872609883287808, | |
| "grad_norm": 0.6796224117279053, | |
| "learning_rate": 1.6673376487527382e-06, | |
| "loss": 1.4354, | |
| "num_input_tokens_seen": 199229440, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.18897442264713185, | |
| "grad_norm": 0.6231174468994141, | |
| "learning_rate": 1.6543469682057105e-06, | |
| "loss": 1.2075, | |
| "num_input_tokens_seen": 199491584, | |
| "step": 761 | |
| }, | |
| { | |
| "epoch": 0.18922274646138565, | |
| "grad_norm": 0.7283173203468323, | |
| "learning_rate": 1.6413970533850498e-06, | |
| "loss": 1.7713, | |
| "num_input_tokens_seen": 199753728, | |
| "step": 762 | |
| }, | |
| { | |
| "epoch": 0.18947107027563945, | |
| "grad_norm": 0.6808333396911621, | |
| "learning_rate": 1.6284880620813847e-06, | |
| "loss": 1.7076, | |
| "num_input_tokens_seen": 200015872, | |
| "step": 763 | |
| }, | |
| { | |
| "epoch": 0.18971939408989322, | |
| "grad_norm": 0.7591480612754822, | |
| "learning_rate": 1.6156201515866971e-06, | |
| "loss": 1.4767, | |
| "num_input_tokens_seen": 200278016, | |
| "step": 764 | |
| }, | |
| { | |
| "epoch": 0.18996771790414702, | |
| "grad_norm": 3.4821579456329346, | |
| "learning_rate": 1.6027934786924187e-06, | |
| "loss": 1.7879, | |
| "num_input_tokens_seen": 200540160, | |
| "step": 765 | |
| }, | |
| { | |
| "epoch": 0.19021604171840079, | |
| "grad_norm": 0.5467571020126343, | |
| "learning_rate": 1.5900081996875083e-06, | |
| "loss": 1.6919, | |
| "num_input_tokens_seen": 200802304, | |
| "step": 766 | |
| }, | |
| { | |
| "epoch": 0.19046436553265458, | |
| "grad_norm": 0.4840015172958374, | |
| "learning_rate": 1.5772644703565564e-06, | |
| "loss": 1.9006, | |
| "num_input_tokens_seen": 201064448, | |
| "step": 767 | |
| }, | |
| { | |
| "epoch": 0.19071268934690838, | |
| "grad_norm": 0.4922867715358734, | |
| "learning_rate": 1.5645624459778858e-06, | |
| "loss": 1.505, | |
| "num_input_tokens_seen": 201326592, | |
| "step": 768 | |
| }, | |
| { | |
| "epoch": 0.19096101316116215, | |
| "grad_norm": 0.8669015169143677, | |
| "learning_rate": 1.551902281321651e-06, | |
| "loss": 1.5521, | |
| "num_input_tokens_seen": 201588736, | |
| "step": 769 | |
| }, | |
| { | |
| "epoch": 0.19120933697541595, | |
| "grad_norm": 0.7580779194831848, | |
| "learning_rate": 1.5392841306479667e-06, | |
| "loss": 1.5425, | |
| "num_input_tokens_seen": 201850880, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.19145766078966972, | |
| "grad_norm": 0.5388744473457336, | |
| "learning_rate": 1.5267081477050132e-06, | |
| "loss": 1.6623, | |
| "num_input_tokens_seen": 202113024, | |
| "step": 771 | |
| }, | |
| { | |
| "epoch": 0.19170598460392352, | |
| "grad_norm": 0.36039191484451294, | |
| "learning_rate": 1.514174485727178e-06, | |
| "loss": 1.9833, | |
| "num_input_tokens_seen": 202375168, | |
| "step": 772 | |
| }, | |
| { | |
| "epoch": 0.19195430841817732, | |
| "grad_norm": 0.7689981460571289, | |
| "learning_rate": 1.5016832974331725e-06, | |
| "loss": 1.9371, | |
| "num_input_tokens_seen": 202637312, | |
| "step": 773 | |
| }, | |
| { | |
| "epoch": 0.1922026322324311, | |
| "grad_norm": 0.510267436504364, | |
| "learning_rate": 1.489234735024188e-06, | |
| "loss": 1.7589, | |
| "num_input_tokens_seen": 202899456, | |
| "step": 774 | |
| }, | |
| { | |
| "epoch": 0.19245095604668488, | |
| "grad_norm": 1.7721202373504639, | |
| "learning_rate": 1.4768289501820265e-06, | |
| "loss": 1.8343, | |
| "num_input_tokens_seen": 203161600, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.19269927986093865, | |
| "grad_norm": 0.35707518458366394, | |
| "learning_rate": 1.4644660940672628e-06, | |
| "loss": 1.3319, | |
| "num_input_tokens_seen": 203423744, | |
| "step": 776 | |
| }, | |
| { | |
| "epoch": 0.19294760367519245, | |
| "grad_norm": 0.39053982496261597, | |
| "learning_rate": 1.4521463173173966e-06, | |
| "loss": 1.4868, | |
| "num_input_tokens_seen": 203685888, | |
| "step": 777 | |
| }, | |
| { | |
| "epoch": 0.19319592748944625, | |
| "grad_norm": 1.0973213911056519, | |
| "learning_rate": 1.4398697700450181e-06, | |
| "loss": 1.2248, | |
| "num_input_tokens_seen": 203948032, | |
| "step": 778 | |
| }, | |
| { | |
| "epoch": 0.19344425130370002, | |
| "grad_norm": 0.4421512186527252, | |
| "learning_rate": 1.4276366018359845e-06, | |
| "loss": 1.513, | |
| "num_input_tokens_seen": 204210176, | |
| "step": 779 | |
| }, | |
| { | |
| "epoch": 0.19369257511795382, | |
| "grad_norm": 0.5916955471038818, | |
| "learning_rate": 1.4154469617475864e-06, | |
| "loss": 1.5881, | |
| "num_input_tokens_seen": 204472320, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.1939408989322076, | |
| "grad_norm": 0.749496340751648, | |
| "learning_rate": 1.4033009983067454e-06, | |
| "loss": 2.0316, | |
| "num_input_tokens_seen": 204734464, | |
| "step": 781 | |
| }, | |
| { | |
| "epoch": 0.1941892227464614, | |
| "grad_norm": 0.4848249554634094, | |
| "learning_rate": 1.3911988595081894e-06, | |
| "loss": 1.5584, | |
| "num_input_tokens_seen": 204996608, | |
| "step": 782 | |
| }, | |
| { | |
| "epoch": 0.19443754656071519, | |
| "grad_norm": 0.5584369897842407, | |
| "learning_rate": 1.3791406928126638e-06, | |
| "loss": 1.6737, | |
| "num_input_tokens_seen": 205258752, | |
| "step": 783 | |
| }, | |
| { | |
| "epoch": 0.19468587037496896, | |
| "grad_norm": 0.7734516263008118, | |
| "learning_rate": 1.3671266451451209e-06, | |
| "loss": 1.7325, | |
| "num_input_tokens_seen": 205520896, | |
| "step": 784 | |
| }, | |
| { | |
| "epoch": 0.19493419418922275, | |
| "grad_norm": 0.4235021471977234, | |
| "learning_rate": 1.3551568628929434e-06, | |
| "loss": 1.7884, | |
| "num_input_tokens_seen": 205783040, | |
| "step": 785 | |
| }, | |
| { | |
| "epoch": 0.19518251800347652, | |
| "grad_norm": 0.5882217288017273, | |
| "learning_rate": 1.3432314919041478e-06, | |
| "loss": 1.5367, | |
| "num_input_tokens_seen": 206045184, | |
| "step": 786 | |
| }, | |
| { | |
| "epoch": 0.19543084181773032, | |
| "grad_norm": 0.382315456867218, | |
| "learning_rate": 1.3313506774856177e-06, | |
| "loss": 1.562, | |
| "num_input_tokens_seen": 206307328, | |
| "step": 787 | |
| }, | |
| { | |
| "epoch": 0.19567916563198412, | |
| "grad_norm": 0.5313207507133484, | |
| "learning_rate": 1.3195145644013286e-06, | |
| "loss": 0.9386, | |
| "num_input_tokens_seen": 206569472, | |
| "step": 788 | |
| }, | |
| { | |
| "epoch": 0.1959274894462379, | |
| "grad_norm": 0.5512835383415222, | |
| "learning_rate": 1.3077232968705805e-06, | |
| "loss": 1.3328, | |
| "num_input_tokens_seen": 206831616, | |
| "step": 789 | |
| }, | |
| { | |
| "epoch": 0.1961758132604917, | |
| "grad_norm": 0.6115958094596863, | |
| "learning_rate": 1.2959770185662502e-06, | |
| "loss": 1.6127, | |
| "num_input_tokens_seen": 207093760, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.19642413707474546, | |
| "grad_norm": 1.8349878787994385, | |
| "learning_rate": 1.2842758726130283e-06, | |
| "loss": 1.3873, | |
| "num_input_tokens_seen": 207355904, | |
| "step": 791 | |
| }, | |
| { | |
| "epoch": 0.19667246088899926, | |
| "grad_norm": 0.6167082786560059, | |
| "learning_rate": 1.2726200015856893e-06, | |
| "loss": 1.6641, | |
| "num_input_tokens_seen": 207618048, | |
| "step": 792 | |
| }, | |
| { | |
| "epoch": 0.19692078470325305, | |
| "grad_norm": 0.27391648292541504, | |
| "learning_rate": 1.2610095475073415e-06, | |
| "loss": 1.7774, | |
| "num_input_tokens_seen": 207880192, | |
| "step": 793 | |
| }, | |
| { | |
| "epoch": 0.19716910851750682, | |
| "grad_norm": 0.4807204306125641, | |
| "learning_rate": 1.2494446518477022e-06, | |
| "loss": 1.5564, | |
| "num_input_tokens_seen": 208142336, | |
| "step": 794 | |
| }, | |
| { | |
| "epoch": 0.19741743233176062, | |
| "grad_norm": 0.3716016113758087, | |
| "learning_rate": 1.2379254555213788e-06, | |
| "loss": 1.6801, | |
| "num_input_tokens_seen": 208404480, | |
| "step": 795 | |
| }, | |
| { | |
| "epoch": 0.1976657561460144, | |
| "grad_norm": 0.6262674331665039, | |
| "learning_rate": 1.22645209888614e-06, | |
| "loss": 1.6579, | |
| "num_input_tokens_seen": 208666624, | |
| "step": 796 | |
| }, | |
| { | |
| "epoch": 0.1979140799602682, | |
| "grad_norm": 0.49892279505729675, | |
| "learning_rate": 1.2150247217412186e-06, | |
| "loss": 1.4113, | |
| "num_input_tokens_seen": 208928768, | |
| "step": 797 | |
| }, | |
| { | |
| "epoch": 0.198162403774522, | |
| "grad_norm": 0.28231680393218994, | |
| "learning_rate": 1.203643463325596e-06, | |
| "loss": 1.2046, | |
| "num_input_tokens_seen": 209190912, | |
| "step": 798 | |
| }, | |
| { | |
| "epoch": 0.19841072758877576, | |
| "grad_norm": 0.39441466331481934, | |
| "learning_rate": 1.1923084623163172e-06, | |
| "loss": 1.25, | |
| "num_input_tokens_seen": 209453056, | |
| "step": 799 | |
| }, | |
| { | |
| "epoch": 0.19865905140302956, | |
| "grad_norm": 0.8825608491897583, | |
| "learning_rate": 1.1810198568267906e-06, | |
| "loss": 1.8506, | |
| "num_input_tokens_seen": 209715200, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.19890737521728333, | |
| "grad_norm": 0.3593462109565735, | |
| "learning_rate": 1.1697777844051105e-06, | |
| "loss": 0.9988, | |
| "num_input_tokens_seen": 209977344, | |
| "step": 801 | |
| }, | |
| { | |
| "epoch": 0.19915569903153713, | |
| "grad_norm": 0.42397427558898926, | |
| "learning_rate": 1.1585823820323845e-06, | |
| "loss": 1.5294, | |
| "num_input_tokens_seen": 210239488, | |
| "step": 802 | |
| }, | |
| { | |
| "epoch": 0.19940402284579092, | |
| "grad_norm": 0.5862644910812378, | |
| "learning_rate": 1.1474337861210543e-06, | |
| "loss": 1.8455, | |
| "num_input_tokens_seen": 210501632, | |
| "step": 803 | |
| }, | |
| { | |
| "epoch": 0.1996523466600447, | |
| "grad_norm": 0.7144994139671326, | |
| "learning_rate": 1.136332132513245e-06, | |
| "loss": 1.6364, | |
| "num_input_tokens_seen": 210763776, | |
| "step": 804 | |
| }, | |
| { | |
| "epoch": 0.1999006704742985, | |
| "grad_norm": 0.6182805299758911, | |
| "learning_rate": 1.1252775564791023e-06, | |
| "loss": 1.533, | |
| "num_input_tokens_seen": 211025920, | |
| "step": 805 | |
| }, | |
| { | |
| "epoch": 0.20014899428855226, | |
| "grad_norm": 2.216693878173828, | |
| "learning_rate": 1.1142701927151456e-06, | |
| "loss": 1.8744, | |
| "num_input_tokens_seen": 211288064, | |
| "step": 806 | |
| }, | |
| { | |
| "epoch": 0.20039731810280606, | |
| "grad_norm": 0.4277917444705963, | |
| "learning_rate": 1.1033101753426285e-06, | |
| "loss": 1.5751, | |
| "num_input_tokens_seen": 211550208, | |
| "step": 807 | |
| }, | |
| { | |
| "epoch": 0.20064564191705986, | |
| "grad_norm": 0.5398479104042053, | |
| "learning_rate": 1.0923976379059059e-06, | |
| "loss": 1.5959, | |
| "num_input_tokens_seen": 211812352, | |
| "step": 808 | |
| }, | |
| { | |
| "epoch": 0.20089396573131363, | |
| "grad_norm": 0.38512706756591797, | |
| "learning_rate": 1.0815327133708015e-06, | |
| "loss": 1.5632, | |
| "num_input_tokens_seen": 212074496, | |
| "step": 809 | |
| }, | |
| { | |
| "epoch": 0.20114228954556743, | |
| "grad_norm": 0.28112220764160156, | |
| "learning_rate": 1.0707155341229902e-06, | |
| "loss": 1.5852, | |
| "num_input_tokens_seen": 212336640, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.2013906133598212, | |
| "grad_norm": 0.3636101186275482, | |
| "learning_rate": 1.0599462319663906e-06, | |
| "loss": 1.659, | |
| "num_input_tokens_seen": 212598784, | |
| "step": 811 | |
| }, | |
| { | |
| "epoch": 0.201638937174075, | |
| "grad_norm": 0.632411003112793, | |
| "learning_rate": 1.049224938121548e-06, | |
| "loss": 1.7422, | |
| "num_input_tokens_seen": 212860928, | |
| "step": 812 | |
| }, | |
| { | |
| "epoch": 0.2018872609883288, | |
| "grad_norm": 0.4831806719303131, | |
| "learning_rate": 1.0385517832240472e-06, | |
| "loss": 1.6995, | |
| "num_input_tokens_seen": 213123072, | |
| "step": 813 | |
| }, | |
| { | |
| "epoch": 0.20213558480258256, | |
| "grad_norm": 0.6856269836425781, | |
| "learning_rate": 1.0279268973229089e-06, | |
| "loss": 1.4744, | |
| "num_input_tokens_seen": 213385216, | |
| "step": 814 | |
| }, | |
| { | |
| "epoch": 0.20238390861683636, | |
| "grad_norm": 0.706402599811554, | |
| "learning_rate": 1.0173504098790188e-06, | |
| "loss": 1.806, | |
| "num_input_tokens_seen": 213647360, | |
| "step": 815 | |
| }, | |
| { | |
| "epoch": 0.20263223243109013, | |
| "grad_norm": 0.6212208271026611, | |
| "learning_rate": 1.006822449763537e-06, | |
| "loss": 1.4372, | |
| "num_input_tokens_seen": 213909504, | |
| "step": 816 | |
| }, | |
| { | |
| "epoch": 0.20288055624534393, | |
| "grad_norm": 0.4880361258983612, | |
| "learning_rate": 9.963431452563331e-07, | |
| "loss": 1.7287, | |
| "num_input_tokens_seen": 214171648, | |
| "step": 817 | |
| }, | |
| { | |
| "epoch": 0.20312888005959773, | |
| "grad_norm": 0.5508049726486206, | |
| "learning_rate": 9.859126240444284e-07, | |
| "loss": 1.4213, | |
| "num_input_tokens_seen": 214433792, | |
| "step": 818 | |
| }, | |
| { | |
| "epoch": 0.2033772038738515, | |
| "grad_norm": 0.40056681632995605, | |
| "learning_rate": 9.7553101322043e-07, | |
| "loss": 1.6258, | |
| "num_input_tokens_seen": 214695936, | |
| "step": 819 | |
| }, | |
| { | |
| "epoch": 0.2036255276881053, | |
| "grad_norm": 0.5356477499008179, | |
| "learning_rate": 9.651984392809916e-07, | |
| "loss": 1.5275, | |
| "num_input_tokens_seen": 214958080, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.20387385150235907, | |
| "grad_norm": 0.7192147374153137, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 1.675, | |
| "num_input_tokens_seen": 215220224, | |
| "step": 821 | |
| }, | |
| { | |
| "epoch": 0.20412217531661286, | |
| "grad_norm": 0.6497499942779541, | |
| "learning_rate": 9.446809050533679e-07, | |
| "loss": 2.0607, | |
| "num_input_tokens_seen": 215482368, | |
| "step": 822 | |
| }, | |
| { | |
| "epoch": 0.20437049913086666, | |
| "grad_norm": 0.6447398662567139, | |
| "learning_rate": 9.344961947648624e-07, | |
| "loss": 1.3855, | |
| "num_input_tokens_seen": 215744512, | |
| "step": 823 | |
| }, | |
| { | |
| "epoch": 0.20461882294512043, | |
| "grad_norm": 1.1430552005767822, | |
| "learning_rate": 9.243610213572285e-07, | |
| "loss": 1.6178, | |
| "num_input_tokens_seen": 216006656, | |
| "step": 824 | |
| }, | |
| { | |
| "epoch": 0.20486714675937423, | |
| "grad_norm": 0.6385335922241211, | |
| "learning_rate": 9.142755083243577e-07, | |
| "loss": 1.5856, | |
| "num_input_tokens_seen": 216268800, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.205115470573628, | |
| "grad_norm": 1.0095096826553345, | |
| "learning_rate": 9.042397785550405e-07, | |
| "loss": 1.6267, | |
| "num_input_tokens_seen": 216530944, | |
| "step": 826 | |
| }, | |
| { | |
| "epoch": 0.2053637943878818, | |
| "grad_norm": 0.7737463712692261, | |
| "learning_rate": 8.942539543314799e-07, | |
| "loss": 1.3607, | |
| "num_input_tokens_seen": 216793088, | |
| "step": 827 | |
| }, | |
| { | |
| "epoch": 0.2056121182021356, | |
| "grad_norm": 0.6710413694381714, | |
| "learning_rate": 8.843181573277904e-07, | |
| "loss": 1.7918, | |
| "num_input_tokens_seen": 217055232, | |
| "step": 828 | |
| }, | |
| { | |
| "epoch": 0.20586044201638937, | |
| "grad_norm": 0.5380450487136841, | |
| "learning_rate": 8.744325086085248e-07, | |
| "loss": 1.8734, | |
| "num_input_tokens_seen": 217317376, | |
| "step": 829 | |
| }, | |
| { | |
| "epoch": 0.20610876583064316, | |
| "grad_norm": 0.769334614276886, | |
| "learning_rate": 8.645971286271903e-07, | |
| "loss": 1.4816, | |
| "num_input_tokens_seen": 217579520, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.20635708964489693, | |
| "grad_norm": 0.49632272124290466, | |
| "learning_rate": 8.54812137224792e-07, | |
| "loss": 1.7042, | |
| "num_input_tokens_seen": 217841664, | |
| "step": 831 | |
| }, | |
| { | |
| "epoch": 0.20660541345915073, | |
| "grad_norm": 0.30258211493492126, | |
| "learning_rate": 8.450776536283594e-07, | |
| "loss": 1.5544, | |
| "num_input_tokens_seen": 218103808, | |
| "step": 832 | |
| }, | |
| { | |
| "epoch": 0.20685373727340453, | |
| "grad_norm": 0.5039138793945312, | |
| "learning_rate": 8.353937964495029e-07, | |
| "loss": 1.6497, | |
| "num_input_tokens_seen": 218365952, | |
| "step": 833 | |
| }, | |
| { | |
| "epoch": 0.2071020610876583, | |
| "grad_norm": 0.5678662657737732, | |
| "learning_rate": 8.25760683682968e-07, | |
| "loss": 1.9249, | |
| "num_input_tokens_seen": 218628096, | |
| "step": 834 | |
| }, | |
| { | |
| "epoch": 0.2073503849019121, | |
| "grad_norm": 0.7532708644866943, | |
| "learning_rate": 8.161784327051919e-07, | |
| "loss": 1.5489, | |
| "num_input_tokens_seen": 218890240, | |
| "step": 835 | |
| }, | |
| { | |
| "epoch": 0.20759870871616587, | |
| "grad_norm": 0.3733159303665161, | |
| "learning_rate": 8.066471602728804e-07, | |
| "loss": 2.1036, | |
| "num_input_tokens_seen": 219152384, | |
| "step": 836 | |
| }, | |
| { | |
| "epoch": 0.20784703253041967, | |
| "grad_norm": 0.52272629737854, | |
| "learning_rate": 7.971669825215789e-07, | |
| "loss": 1.5633, | |
| "num_input_tokens_seen": 219414528, | |
| "step": 837 | |
| }, | |
| { | |
| "epoch": 0.20809535634467347, | |
| "grad_norm": 0.6050902605056763, | |
| "learning_rate": 7.877380149642628e-07, | |
| "loss": 1.4245, | |
| "num_input_tokens_seen": 219676672, | |
| "step": 838 | |
| }, | |
| { | |
| "epoch": 0.20834368015892724, | |
| "grad_norm": 0.6302130222320557, | |
| "learning_rate": 7.783603724899258e-07, | |
| "loss": 1.3682, | |
| "num_input_tokens_seen": 219938816, | |
| "step": 839 | |
| }, | |
| { | |
| "epoch": 0.20859200397318103, | |
| "grad_norm": 0.2699492871761322, | |
| "learning_rate": 7.690341693621805e-07, | |
| "loss": 1.344, | |
| "num_input_tokens_seen": 220200960, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.2088403277874348, | |
| "grad_norm": 0.7535718679428101, | |
| "learning_rate": 7.597595192178702e-07, | |
| "loss": 1.751, | |
| "num_input_tokens_seen": 220463104, | |
| "step": 841 | |
| }, | |
| { | |
| "epoch": 0.2090886516016886, | |
| "grad_norm": 0.9196535348892212, | |
| "learning_rate": 7.505365350656813e-07, | |
| "loss": 1.6558, | |
| "num_input_tokens_seen": 220725248, | |
| "step": 842 | |
| }, | |
| { | |
| "epoch": 0.2093369754159424, | |
| "grad_norm": 0.6124866604804993, | |
| "learning_rate": 7.413653292847617e-07, | |
| "loss": 1.4843, | |
| "num_input_tokens_seen": 220987392, | |
| "step": 843 | |
| }, | |
| { | |
| "epoch": 0.20958529923019617, | |
| "grad_norm": 0.830053448677063, | |
| "learning_rate": 7.322460136233622e-07, | |
| "loss": 1.583, | |
| "num_input_tokens_seen": 221249536, | |
| "step": 844 | |
| }, | |
| { | |
| "epoch": 0.20983362304444997, | |
| "grad_norm": 0.7714657783508301, | |
| "learning_rate": 7.23178699197467e-07, | |
| "loss": 1.763, | |
| "num_input_tokens_seen": 221511680, | |
| "step": 845 | |
| }, | |
| { | |
| "epoch": 0.21008194685870374, | |
| "grad_norm": 0.3930104970932007, | |
| "learning_rate": 7.141634964894389e-07, | |
| "loss": 1.381, | |
| "num_input_tokens_seen": 221773824, | |
| "step": 846 | |
| }, | |
| { | |
| "epoch": 0.21033027067295754, | |
| "grad_norm": 0.6444476246833801, | |
| "learning_rate": 7.052005153466779e-07, | |
| "loss": 1.7138, | |
| "num_input_tokens_seen": 222035968, | |
| "step": 847 | |
| }, | |
| { | |
| "epoch": 0.21057859448721133, | |
| "grad_norm": 0.7626250982284546, | |
| "learning_rate": 6.962898649802824e-07, | |
| "loss": 1.3164, | |
| "num_input_tokens_seen": 222298112, | |
| "step": 848 | |
| }, | |
| { | |
| "epoch": 0.2108269183014651, | |
| "grad_norm": 0.5761337876319885, | |
| "learning_rate": 6.874316539637127e-07, | |
| "loss": 1.4375, | |
| "num_input_tokens_seen": 222560256, | |
| "step": 849 | |
| }, | |
| { | |
| "epoch": 0.2110752421157189, | |
| "grad_norm": 0.5399318337440491, | |
| "learning_rate": 6.786259902314768e-07, | |
| "loss": 1.5317, | |
| "num_input_tokens_seen": 222822400, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.21132356592997267, | |
| "grad_norm": 0.6818238496780396, | |
| "learning_rate": 6.698729810778065e-07, | |
| "loss": 1.5059, | |
| "num_input_tokens_seen": 223084544, | |
| "step": 851 | |
| }, | |
| { | |
| "epoch": 0.21157188974422647, | |
| "grad_norm": 0.5061662197113037, | |
| "learning_rate": 6.611727331553585e-07, | |
| "loss": 1.7645, | |
| "num_input_tokens_seen": 223346688, | |
| "step": 852 | |
| }, | |
| { | |
| "epoch": 0.21182021355848027, | |
| "grad_norm": 0.7583996057510376, | |
| "learning_rate": 6.52525352473905e-07, | |
| "loss": 1.7479, | |
| "num_input_tokens_seen": 223608832, | |
| "step": 853 | |
| }, | |
| { | |
| "epoch": 0.21206853737273404, | |
| "grad_norm": 0.4888990819454193, | |
| "learning_rate": 6.439309443990532e-07, | |
| "loss": 1.4111, | |
| "num_input_tokens_seen": 223870976, | |
| "step": 854 | |
| }, | |
| { | |
| "epoch": 0.21231686118698784, | |
| "grad_norm": 0.5152997374534607, | |
| "learning_rate": 6.353896136509524e-07, | |
| "loss": 1.4035, | |
| "num_input_tokens_seen": 224133120, | |
| "step": 855 | |
| }, | |
| { | |
| "epoch": 0.2125651850012416, | |
| "grad_norm": 0.8078181147575378, | |
| "learning_rate": 6.269014643030214e-07, | |
| "loss": 1.5448, | |
| "num_input_tokens_seen": 224395264, | |
| "step": 856 | |
| }, | |
| { | |
| "epoch": 0.2128135088154954, | |
| "grad_norm": 0.38689664006233215, | |
| "learning_rate": 6.184665997806832e-07, | |
| "loss": 1.5432, | |
| "num_input_tokens_seen": 224657408, | |
| "step": 857 | |
| }, | |
| { | |
| "epoch": 0.2130618326297492, | |
| "grad_norm": 0.5154587626457214, | |
| "learning_rate": 6.100851228600974e-07, | |
| "loss": 1.6356, | |
| "num_input_tokens_seen": 224919552, | |
| "step": 858 | |
| }, | |
| { | |
| "epoch": 0.21331015644400297, | |
| "grad_norm": 0.7129220366477966, | |
| "learning_rate": 6.017571356669183e-07, | |
| "loss": 1.4454, | |
| "num_input_tokens_seen": 225181696, | |
| "step": 859 | |
| }, | |
| { | |
| "epoch": 0.21355848025825677, | |
| "grad_norm": 0.4863054156303406, | |
| "learning_rate": 5.934827396750392e-07, | |
| "loss": 1.6839, | |
| "num_input_tokens_seen": 225443840, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.21380680407251054, | |
| "grad_norm": 0.461911678314209, | |
| "learning_rate": 5.852620357053651e-07, | |
| "loss": 1.4632, | |
| "num_input_tokens_seen": 225705984, | |
| "step": 861 | |
| }, | |
| { | |
| "epoch": 0.21405512788676434, | |
| "grad_norm": 0.4267142415046692, | |
| "learning_rate": 5.770951239245803e-07, | |
| "loss": 1.5694, | |
| "num_input_tokens_seen": 225968128, | |
| "step": 862 | |
| }, | |
| { | |
| "epoch": 0.21430345170101814, | |
| "grad_norm": 0.4966636300086975, | |
| "learning_rate": 5.689821038439264e-07, | |
| "loss": 1.5516, | |
| "num_input_tokens_seen": 226230272, | |
| "step": 863 | |
| }, | |
| { | |
| "epoch": 0.2145517755152719, | |
| "grad_norm": 0.5140483379364014, | |
| "learning_rate": 5.609230743179939e-07, | |
| "loss": 1.3778, | |
| "num_input_tokens_seen": 226492416, | |
| "step": 864 | |
| }, | |
| { | |
| "epoch": 0.2148000993295257, | |
| "grad_norm": 0.6450092196464539, | |
| "learning_rate": 5.529181335435124e-07, | |
| "loss": 1.3893, | |
| "num_input_tokens_seen": 226754560, | |
| "step": 865 | |
| }, | |
| { | |
| "epoch": 0.21504842314377948, | |
| "grad_norm": 0.5973859429359436, | |
| "learning_rate": 5.449673790581611e-07, | |
| "loss": 1.5149, | |
| "num_input_tokens_seen": 227016704, | |
| "step": 866 | |
| }, | |
| { | |
| "epoch": 0.21529674695803327, | |
| "grad_norm": 1.7493269443511963, | |
| "learning_rate": 5.370709077393721e-07, | |
| "loss": 1.5618, | |
| "num_input_tokens_seen": 227278848, | |
| "step": 867 | |
| }, | |
| { | |
| "epoch": 0.21554507077228707, | |
| "grad_norm": 0.4318649172782898, | |
| "learning_rate": 5.292288158031595e-07, | |
| "loss": 1.1686, | |
| "num_input_tokens_seen": 227540992, | |
| "step": 868 | |
| }, | |
| { | |
| "epoch": 0.21579339458654084, | |
| "grad_norm": 0.3847927749156952, | |
| "learning_rate": 5.214411988029355e-07, | |
| "loss": 1.7999, | |
| "num_input_tokens_seen": 227803136, | |
| "step": 869 | |
| }, | |
| { | |
| "epoch": 0.21604171840079464, | |
| "grad_norm": 0.596502423286438, | |
| "learning_rate": 5.137081516283582e-07, | |
| "loss": 1.5796, | |
| "num_input_tokens_seen": 228065280, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.2162900422150484, | |
| "grad_norm": 0.6176612377166748, | |
| "learning_rate": 5.06029768504166e-07, | |
| "loss": 1.7902, | |
| "num_input_tokens_seen": 228327424, | |
| "step": 871 | |
| }, | |
| { | |
| "epoch": 0.2165383660293022, | |
| "grad_norm": 0.6072035431861877, | |
| "learning_rate": 4.984061429890324e-07, | |
| "loss": 1.7899, | |
| "num_input_tokens_seen": 228589568, | |
| "step": 872 | |
| }, | |
| { | |
| "epoch": 0.216786689843556, | |
| "grad_norm": 0.3984832167625427, | |
| "learning_rate": 4.908373679744316e-07, | |
| "loss": 1.9725, | |
| "num_input_tokens_seen": 228851712, | |
| "step": 873 | |
| }, | |
| { | |
| "epoch": 0.21703501365780978, | |
| "grad_norm": 0.7739282250404358, | |
| "learning_rate": 4.833235356834959e-07, | |
| "loss": 1.8129, | |
| "num_input_tokens_seen": 229113856, | |
| "step": 874 | |
| }, | |
| { | |
| "epoch": 0.21728333747206358, | |
| "grad_norm": 1.2236608266830444, | |
| "learning_rate": 4.758647376699033e-07, | |
| "loss": 1.7323, | |
| "num_input_tokens_seen": 229376000, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.21753166128631735, | |
| "grad_norm": 0.541125476360321, | |
| "learning_rate": 4.6846106481675035e-07, | |
| "loss": 1.4017, | |
| "num_input_tokens_seen": 229638144, | |
| "step": 876 | |
| }, | |
| { | |
| "epoch": 0.21777998510057114, | |
| "grad_norm": 0.6922534704208374, | |
| "learning_rate": 4.6111260733545714e-07, | |
| "loss": 1.4963, | |
| "num_input_tokens_seen": 229900288, | |
| "step": 877 | |
| }, | |
| { | |
| "epoch": 0.21802830891482494, | |
| "grad_norm": 0.5298182368278503, | |
| "learning_rate": 4.538194547646574e-07, | |
| "loss": 1.2116, | |
| "num_input_tokens_seen": 230162432, | |
| "step": 878 | |
| }, | |
| { | |
| "epoch": 0.2182766327290787, | |
| "grad_norm": 0.6427643299102783, | |
| "learning_rate": 4.4658169596911493e-07, | |
| "loss": 1.4518, | |
| "num_input_tokens_seen": 230424576, | |
| "step": 879 | |
| }, | |
| { | |
| "epoch": 0.2185249565433325, | |
| "grad_norm": 0.5809391736984253, | |
| "learning_rate": 4.3939941913863525e-07, | |
| "loss": 1.5274, | |
| "num_input_tokens_seen": 230686720, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.21877328035758628, | |
| "grad_norm": 0.7898019552230835, | |
| "learning_rate": 4.322727117869951e-07, | |
| "loss": 1.4542, | |
| "num_input_tokens_seen": 230948864, | |
| "step": 881 | |
| }, | |
| { | |
| "epoch": 0.21902160417184008, | |
| "grad_norm": 0.3369694650173187, | |
| "learning_rate": 4.2520166075087635e-07, | |
| "loss": 1.7991, | |
| "num_input_tokens_seen": 231211008, | |
| "step": 882 | |
| }, | |
| { | |
| "epoch": 0.21926992798609388, | |
| "grad_norm": 0.9025521874427795, | |
| "learning_rate": 4.1818635218880186e-07, | |
| "loss": 1.5178, | |
| "num_input_tokens_seen": 231473152, | |
| "step": 883 | |
| }, | |
| { | |
| "epoch": 0.21951825180034765, | |
| "grad_norm": 0.5789931416511536, | |
| "learning_rate": 4.112268715800943e-07, | |
| "loss": 1.7304, | |
| "num_input_tokens_seen": 231735296, | |
| "step": 884 | |
| }, | |
| { | |
| "epoch": 0.21976657561460144, | |
| "grad_norm": 0.6976189613342285, | |
| "learning_rate": 4.043233037238281e-07, | |
| "loss": 1.6488, | |
| "num_input_tokens_seen": 231997440, | |
| "step": 885 | |
| }, | |
| { | |
| "epoch": 0.22001489942885522, | |
| "grad_norm": 0.49333396553993225, | |
| "learning_rate": 3.9747573273779816e-07, | |
| "loss": 1.2766, | |
| "num_input_tokens_seen": 232259584, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 0.220263223243109, | |
| "grad_norm": 0.44112178683280945, | |
| "learning_rate": 3.90684242057498e-07, | |
| "loss": 2.2126, | |
| "num_input_tokens_seen": 232521728, | |
| "step": 887 | |
| }, | |
| { | |
| "epoch": 0.2205115470573628, | |
| "grad_norm": 0.4824700951576233, | |
| "learning_rate": 3.8394891443509554e-07, | |
| "loss": 1.4844, | |
| "num_input_tokens_seen": 232783872, | |
| "step": 888 | |
| }, | |
| { | |
| "epoch": 0.22075987087161658, | |
| "grad_norm": 0.9592105746269226, | |
| "learning_rate": 3.772698319384349e-07, | |
| "loss": 1.4548, | |
| "num_input_tokens_seen": 233046016, | |
| "step": 889 | |
| }, | |
| { | |
| "epoch": 0.22100819468587038, | |
| "grad_norm": 0.6596522927284241, | |
| "learning_rate": 3.7064707595002636e-07, | |
| "loss": 1.9353, | |
| "num_input_tokens_seen": 233308160, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.22125651850012415, | |
| "grad_norm": 0.5860907435417175, | |
| "learning_rate": 3.6408072716606346e-07, | |
| "loss": 1.7116, | |
| "num_input_tokens_seen": 233570304, | |
| "step": 891 | |
| }, | |
| { | |
| "epoch": 0.22150484231437795, | |
| "grad_norm": 0.5942659974098206, | |
| "learning_rate": 3.575708655954324e-07, | |
| "loss": 1.5085, | |
| "num_input_tokens_seen": 233832448, | |
| "step": 892 | |
| }, | |
| { | |
| "epoch": 0.22175316612863175, | |
| "grad_norm": 0.45090603828430176, | |
| "learning_rate": 3.511175705587433e-07, | |
| "loss": 2.0349, | |
| "num_input_tokens_seen": 234094592, | |
| "step": 893 | |
| }, | |
| { | |
| "epoch": 0.22200148994288552, | |
| "grad_norm": 0.4501633942127228, | |
| "learning_rate": 3.4472092068735917e-07, | |
| "loss": 1.6038, | |
| "num_input_tokens_seen": 234356736, | |
| "step": 894 | |
| }, | |
| { | |
| "epoch": 0.22224981375713931, | |
| "grad_norm": 0.6762533783912659, | |
| "learning_rate": 3.3838099392243915e-07, | |
| "loss": 1.9386, | |
| "num_input_tokens_seen": 234618880, | |
| "step": 895 | |
| }, | |
| { | |
| "epoch": 0.22249813757139308, | |
| "grad_norm": 0.447121798992157, | |
| "learning_rate": 3.320978675139919e-07, | |
| "loss": 1.4892, | |
| "num_input_tokens_seen": 234881024, | |
| "step": 896 | |
| }, | |
| { | |
| "epoch": 0.22274646138564688, | |
| "grad_norm": 0.45953160524368286, | |
| "learning_rate": 3.258716180199278e-07, | |
| "loss": 1.8319, | |
| "num_input_tokens_seen": 235143168, | |
| "step": 897 | |
| }, | |
| { | |
| "epoch": 0.22299478519990068, | |
| "grad_norm": 0.6440572142601013, | |
| "learning_rate": 3.1970232130513365e-07, | |
| "loss": 1.515, | |
| "num_input_tokens_seen": 235405312, | |
| "step": 898 | |
| }, | |
| { | |
| "epoch": 0.22324310901415445, | |
| "grad_norm": 0.5581231117248535, | |
| "learning_rate": 3.135900525405428e-07, | |
| "loss": 1.4006, | |
| "num_input_tokens_seen": 235667456, | |
| "step": 899 | |
| }, | |
| { | |
| "epoch": 0.22349143282840825, | |
| "grad_norm": 0.8089503645896912, | |
| "learning_rate": 3.0753488620222037e-07, | |
| "loss": 1.9274, | |
| "num_input_tokens_seen": 235929600, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.22373975664266202, | |
| "grad_norm": 0.3819998502731323, | |
| "learning_rate": 3.015368960704584e-07, | |
| "loss": 1.5894, | |
| "num_input_tokens_seen": 236191744, | |
| "step": 901 | |
| }, | |
| { | |
| "epoch": 0.22398808045691582, | |
| "grad_norm": 0.27509671449661255, | |
| "learning_rate": 2.9559615522887275e-07, | |
| "loss": 1.4556, | |
| "num_input_tokens_seen": 236453888, | |
| "step": 902 | |
| }, | |
| { | |
| "epoch": 0.22423640427116961, | |
| "grad_norm": 0.4570426344871521, | |
| "learning_rate": 2.8971273606351656e-07, | |
| "loss": 1.6122, | |
| "num_input_tokens_seen": 236716032, | |
| "step": 903 | |
| }, | |
| { | |
| "epoch": 0.22448472808542339, | |
| "grad_norm": 0.557512104511261, | |
| "learning_rate": 2.838867102619952e-07, | |
| "loss": 1.3736, | |
| "num_input_tokens_seen": 236978176, | |
| "step": 904 | |
| }, | |
| { | |
| "epoch": 0.22473305189967718, | |
| "grad_norm": 0.9721599221229553, | |
| "learning_rate": 2.7811814881259503e-07, | |
| "loss": 1.5408, | |
| "num_input_tokens_seen": 237240320, | |
| "step": 905 | |
| }, | |
| { | |
| "epoch": 0.22498137571393095, | |
| "grad_norm": 0.34721148014068604, | |
| "learning_rate": 2.724071220034158e-07, | |
| "loss": 1.3573, | |
| "num_input_tokens_seen": 237502464, | |
| "step": 906 | |
| }, | |
| { | |
| "epoch": 0.22522969952818475, | |
| "grad_norm": 0.5350072979927063, | |
| "learning_rate": 2.6675369942151864e-07, | |
| "loss": 1.7557, | |
| "num_input_tokens_seen": 237764608, | |
| "step": 907 | |
| }, | |
| { | |
| "epoch": 0.22547802334243855, | |
| "grad_norm": 0.5631807446479797, | |
| "learning_rate": 2.611579499520722e-07, | |
| "loss": 1.7951, | |
| "num_input_tokens_seen": 238026752, | |
| "step": 908 | |
| }, | |
| { | |
| "epoch": 0.22572634715669232, | |
| "grad_norm": 0.731895387172699, | |
| "learning_rate": 2.556199417775174e-07, | |
| "loss": 1.3442, | |
| "num_input_tokens_seen": 238288896, | |
| "step": 909 | |
| }, | |
| { | |
| "epoch": 0.22597467097094612, | |
| "grad_norm": 0.5491323471069336, | |
| "learning_rate": 2.5013974237673824e-07, | |
| "loss": 1.932, | |
| "num_input_tokens_seen": 238551040, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.2262229947851999, | |
| "grad_norm": 0.3442050814628601, | |
| "learning_rate": 2.447174185242324e-07, | |
| "loss": 1.6905, | |
| "num_input_tokens_seen": 238813184, | |
| "step": 911 | |
| }, | |
| { | |
| "epoch": 0.22647131859945369, | |
| "grad_norm": 0.7306151390075684, | |
| "learning_rate": 2.3935303628930705e-07, | |
| "loss": 1.4804, | |
| "num_input_tokens_seen": 239075328, | |
| "step": 912 | |
| }, | |
| { | |
| "epoch": 0.22671964241370748, | |
| "grad_norm": 0.5416999459266663, | |
| "learning_rate": 2.3404666103526542e-07, | |
| "loss": 1.6624, | |
| "num_input_tokens_seen": 239337472, | |
| "step": 913 | |
| }, | |
| { | |
| "epoch": 0.22696796622796125, | |
| "grad_norm": 0.37114378809928894, | |
| "learning_rate": 2.287983574186159e-07, | |
| "loss": 1.8494, | |
| "num_input_tokens_seen": 239599616, | |
| "step": 914 | |
| }, | |
| { | |
| "epoch": 0.22721629004221505, | |
| "grad_norm": 0.6947669386863708, | |
| "learning_rate": 2.2360818938828189e-07, | |
| "loss": 1.5021, | |
| "num_input_tokens_seen": 239861760, | |
| "step": 915 | |
| }, | |
| { | |
| "epoch": 0.22746461385646882, | |
| "grad_norm": 0.5789608955383301, | |
| "learning_rate": 2.1847622018482283e-07, | |
| "loss": 1.9683, | |
| "num_input_tokens_seen": 240123904, | |
| "step": 916 | |
| }, | |
| { | |
| "epoch": 0.22771293767072262, | |
| "grad_norm": 0.6739006638526917, | |
| "learning_rate": 2.134025123396638e-07, | |
| "loss": 2.1382, | |
| "num_input_tokens_seen": 240386048, | |
| "step": 917 | |
| }, | |
| { | |
| "epoch": 0.22796126148497642, | |
| "grad_norm": 0.7561383247375488, | |
| "learning_rate": 2.083871276743338e-07, | |
| "loss": 1.423, | |
| "num_input_tokens_seen": 240648192, | |
| "step": 918 | |
| }, | |
| { | |
| "epoch": 0.2282095852992302, | |
| "grad_norm": 0.7975893616676331, | |
| "learning_rate": 2.0343012729971244e-07, | |
| "loss": 1.4102, | |
| "num_input_tokens_seen": 240910336, | |
| "step": 919 | |
| }, | |
| { | |
| "epoch": 0.228457909113484, | |
| "grad_norm": 0.2659681737422943, | |
| "learning_rate": 1.9853157161528468e-07, | |
| "loss": 1.215, | |
| "num_input_tokens_seen": 241172480, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.22870623292773776, | |
| "grad_norm": 0.3225981593132019, | |
| "learning_rate": 1.9369152030840553e-07, | |
| "loss": 1.7634, | |
| "num_input_tokens_seen": 241434624, | |
| "step": 921 | |
| }, | |
| { | |
| "epoch": 0.22895455674199156, | |
| "grad_norm": 0.7171019911766052, | |
| "learning_rate": 1.8891003235357307e-07, | |
| "loss": 1.7829, | |
| "num_input_tokens_seen": 241696768, | |
| "step": 922 | |
| }, | |
| { | |
| "epoch": 0.22920288055624535, | |
| "grad_norm": 0.5440613031387329, | |
| "learning_rate": 1.841871660117095e-07, | |
| "loss": 1.3598, | |
| "num_input_tokens_seen": 241958912, | |
| "step": 923 | |
| }, | |
| { | |
| "epoch": 0.22945120437049912, | |
| "grad_norm": 0.359244167804718, | |
| "learning_rate": 1.7952297882945e-07, | |
| "loss": 1.5261, | |
| "num_input_tokens_seen": 242221056, | |
| "step": 924 | |
| }, | |
| { | |
| "epoch": 0.22969952818475292, | |
| "grad_norm": 0.7204708456993103, | |
| "learning_rate": 1.7491752763844294e-07, | |
| "loss": 1.7172, | |
| "num_input_tokens_seen": 242483200, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.2299478519990067, | |
| "grad_norm": 0.4921867847442627, | |
| "learning_rate": 1.7037086855465902e-07, | |
| "loss": 1.8377, | |
| "num_input_tokens_seen": 242745344, | |
| "step": 926 | |
| }, | |
| { | |
| "epoch": 0.2301961758132605, | |
| "grad_norm": 0.8633773326873779, | |
| "learning_rate": 1.6588305697770313e-07, | |
| "loss": 1.4806, | |
| "num_input_tokens_seen": 243007488, | |
| "step": 927 | |
| }, | |
| { | |
| "epoch": 0.2304444996275143, | |
| "grad_norm": 0.5622784495353699, | |
| "learning_rate": 1.6145414759014433e-07, | |
| "loss": 1.5533, | |
| "num_input_tokens_seen": 243269632, | |
| "step": 928 | |
| }, | |
| { | |
| "epoch": 0.23069282344176806, | |
| "grad_norm": 0.5299321413040161, | |
| "learning_rate": 1.5708419435684463e-07, | |
| "loss": 1.3532, | |
| "num_input_tokens_seen": 243531776, | |
| "step": 929 | |
| }, | |
| { | |
| "epoch": 0.23094114725602186, | |
| "grad_norm": 0.6882240772247314, | |
| "learning_rate": 1.5277325052430569e-07, | |
| "loss": 1.7824, | |
| "num_input_tokens_seen": 243793920, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.23118947107027563, | |
| "grad_norm": 0.431749552488327, | |
| "learning_rate": 1.4852136862001766e-07, | |
| "loss": 1.5325, | |
| "num_input_tokens_seen": 244056064, | |
| "step": 931 | |
| }, | |
| { | |
| "epoch": 0.23143779488452942, | |
| "grad_norm": 0.5995936393737793, | |
| "learning_rate": 1.4432860045182019e-07, | |
| "loss": 1.855, | |
| "num_input_tokens_seen": 244318208, | |
| "step": 932 | |
| }, | |
| { | |
| "epoch": 0.23168611869878322, | |
| "grad_norm": 0.7233447432518005, | |
| "learning_rate": 1.4019499710726913e-07, | |
| "loss": 1.6507, | |
| "num_input_tokens_seen": 244580352, | |
| "step": 933 | |
| }, | |
| { | |
| "epoch": 0.231934442513037, | |
| "grad_norm": 0.54053795337677, | |
| "learning_rate": 1.3612060895301759e-07, | |
| "loss": 1.8987, | |
| "num_input_tokens_seen": 244842496, | |
| "step": 934 | |
| }, | |
| { | |
| "epoch": 0.2321827663272908, | |
| "grad_norm": 0.3651261031627655, | |
| "learning_rate": 1.3210548563419857e-07, | |
| "loss": 1.4466, | |
| "num_input_tokens_seen": 245104640, | |
| "step": 935 | |
| }, | |
| { | |
| "epoch": 0.23243109014154456, | |
| "grad_norm": 0.597426176071167, | |
| "learning_rate": 1.2814967607382433e-07, | |
| "loss": 1.6555, | |
| "num_input_tokens_seen": 245366784, | |
| "step": 936 | |
| }, | |
| { | |
| "epoch": 0.23267941395579836, | |
| "grad_norm": 0.4557691216468811, | |
| "learning_rate": 1.2425322847218368e-07, | |
| "loss": 1.3507, | |
| "num_input_tokens_seen": 245628928, | |
| "step": 937 | |
| }, | |
| { | |
| "epoch": 0.23292773777005216, | |
| "grad_norm": 0.5856966376304626, | |
| "learning_rate": 1.2041619030626283e-07, | |
| "loss": 1.5985, | |
| "num_input_tokens_seen": 245891072, | |
| "step": 938 | |
| }, | |
| { | |
| "epoch": 0.23317606158430593, | |
| "grad_norm": 0.5499093532562256, | |
| "learning_rate": 1.166386083291604e-07, | |
| "loss": 1.9703, | |
| "num_input_tokens_seen": 246153216, | |
| "step": 939 | |
| }, | |
| { | |
| "epoch": 0.23342438539855973, | |
| "grad_norm": 0.5963953733444214, | |
| "learning_rate": 1.1292052856952063e-07, | |
| "loss": 1.5363, | |
| "num_input_tokens_seen": 246415360, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.2336727092128135, | |
| "grad_norm": 0.5307541489601135, | |
| "learning_rate": 1.0926199633097156e-07, | |
| "loss": 1.2944, | |
| "num_input_tokens_seen": 246677504, | |
| "step": 941 | |
| }, | |
| { | |
| "epoch": 0.2339210330270673, | |
| "grad_norm": 0.5369905233383179, | |
| "learning_rate": 1.0566305619157502e-07, | |
| "loss": 1.933, | |
| "num_input_tokens_seen": 246939648, | |
| "step": 942 | |
| }, | |
| { | |
| "epoch": 0.2341693568413211, | |
| "grad_norm": 1.9757884740829468, | |
| "learning_rate": 1.0212375200327973e-07, | |
| "loss": 1.6174, | |
| "num_input_tokens_seen": 247201792, | |
| "step": 943 | |
| }, | |
| { | |
| "epoch": 0.23441768065557486, | |
| "grad_norm": 0.5642454028129578, | |
| "learning_rate": 9.864412689139124e-08, | |
| "loss": 1.2, | |
| "num_input_tokens_seen": 247463936, | |
| "step": 944 | |
| }, | |
| { | |
| "epoch": 0.23466600446982866, | |
| "grad_norm": 0.316659152507782, | |
| "learning_rate": 9.522422325404234e-08, | |
| "loss": 1.8678, | |
| "num_input_tokens_seen": 247726080, | |
| "step": 945 | |
| }, | |
| { | |
| "epoch": 0.23491432828408243, | |
| "grad_norm": 0.4380717873573303, | |
| "learning_rate": 9.186408276168012e-08, | |
| "loss": 1.4458, | |
| "num_input_tokens_seen": 247988224, | |
| "step": 946 | |
| }, | |
| { | |
| "epoch": 0.23516265209833623, | |
| "grad_norm": 0.5788005590438843, | |
| "learning_rate": 8.856374635655696e-08, | |
| "loss": 1.5094, | |
| "num_input_tokens_seen": 248250368, | |
| "step": 947 | |
| }, | |
| { | |
| "epoch": 0.23541097591259003, | |
| "grad_norm": 0.6096988320350647, | |
| "learning_rate": 8.53232542522292e-08, | |
| "loss": 1.5393, | |
| "num_input_tokens_seen": 248512512, | |
| "step": 948 | |
| }, | |
| { | |
| "epoch": 0.2356592997268438, | |
| "grad_norm": 0.5101311802864075, | |
| "learning_rate": 8.214264593307097e-08, | |
| "loss": 1.6412, | |
| "num_input_tokens_seen": 248774656, | |
| "step": 949 | |
| }, | |
| { | |
| "epoch": 0.2359076235410976, | |
| "grad_norm": 0.4224371314048767, | |
| "learning_rate": 7.90219601537906e-08, | |
| "loss": 1.4671, | |
| "num_input_tokens_seen": 249036800, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.23615594735535136, | |
| "grad_norm": 0.5831036567687988, | |
| "learning_rate": 7.59612349389599e-08, | |
| "loss": 1.4406, | |
| "num_input_tokens_seen": 249298944, | |
| "step": 951 | |
| }, | |
| { | |
| "epoch": 0.23640427116960516, | |
| "grad_norm": 0.7039021849632263, | |
| "learning_rate": 7.296050758254958e-08, | |
| "loss": 1.7773, | |
| "num_input_tokens_seen": 249561088, | |
| "step": 952 | |
| }, | |
| { | |
| "epoch": 0.23665259498385896, | |
| "grad_norm": 0.5700446367263794, | |
| "learning_rate": 7.001981464747565e-08, | |
| "loss": 1.4874, | |
| "num_input_tokens_seen": 249823232, | |
| "step": 953 | |
| }, | |
| { | |
| "epoch": 0.23690091879811273, | |
| "grad_norm": 0.6082141995429993, | |
| "learning_rate": 6.713919196515317e-08, | |
| "loss": 1.5502, | |
| "num_input_tokens_seen": 250085376, | |
| "step": 954 | |
| }, | |
| { | |
| "epoch": 0.23714924261236653, | |
| "grad_norm": 0.5807713866233826, | |
| "learning_rate": 6.431867463506047e-08, | |
| "loss": 1.6924, | |
| "num_input_tokens_seen": 250347520, | |
| "step": 955 | |
| }, | |
| { | |
| "epoch": 0.23739756642662033, | |
| "grad_norm": 0.6795780658721924, | |
| "learning_rate": 6.15582970243117e-08, | |
| "loss": 1.6181, | |
| "num_input_tokens_seen": 250609664, | |
| "step": 956 | |
| }, | |
| { | |
| "epoch": 0.2376458902408741, | |
| "grad_norm": 0.5901414155960083, | |
| "learning_rate": 5.8858092767236084e-08, | |
| "loss": 1.6287, | |
| "num_input_tokens_seen": 250871808, | |
| "step": 957 | |
| }, | |
| { | |
| "epoch": 0.2378942140551279, | |
| "grad_norm": 0.258759081363678, | |
| "learning_rate": 5.621809476497098e-08, | |
| "loss": 1.5631, | |
| "num_input_tokens_seen": 251133952, | |
| "step": 958 | |
| }, | |
| { | |
| "epoch": 0.23814253786938167, | |
| "grad_norm": 0.793224036693573, | |
| "learning_rate": 5.363833518505834e-08, | |
| "loss": 1.6065, | |
| "num_input_tokens_seen": 251396096, | |
| "step": 959 | |
| }, | |
| { | |
| "epoch": 0.23839086168363546, | |
| "grad_norm": 0.541074275970459, | |
| "learning_rate": 5.111884546105506e-08, | |
| "loss": 1.7784, | |
| "num_input_tokens_seen": 251658240, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.23863918549788926, | |
| "grad_norm": 0.6888409852981567, | |
| "learning_rate": 4.865965629214819e-08, | |
| "loss": 1.4175, | |
| "num_input_tokens_seen": 251920384, | |
| "step": 961 | |
| }, | |
| { | |
| "epoch": 0.23888750931214303, | |
| "grad_norm": 0.5229154825210571, | |
| "learning_rate": 4.626079764278202e-08, | |
| "loss": 1.7039, | |
| "num_input_tokens_seen": 252182528, | |
| "step": 962 | |
| }, | |
| { | |
| "epoch": 0.23913583312639683, | |
| "grad_norm": 0.43334439396858215, | |
| "learning_rate": 4.392229874229159e-08, | |
| "loss": 1.6586, | |
| "num_input_tokens_seen": 252444672, | |
| "step": 963 | |
| }, | |
| { | |
| "epoch": 0.2393841569406506, | |
| "grad_norm": 0.5404706597328186, | |
| "learning_rate": 4.164418808454806e-08, | |
| "loss": 1.5866, | |
| "num_input_tokens_seen": 252706816, | |
| "step": 964 | |
| }, | |
| { | |
| "epoch": 0.2396324807549044, | |
| "grad_norm": 0.31539681553840637, | |
| "learning_rate": 3.9426493427611177e-08, | |
| "loss": 1.2445, | |
| "num_input_tokens_seen": 252968960, | |
| "step": 965 | |
| }, | |
| { | |
| "epoch": 0.2398808045691582, | |
| "grad_norm": 0.767345130443573, | |
| "learning_rate": 3.726924179339009e-08, | |
| "loss": 1.6509, | |
| "num_input_tokens_seen": 253231104, | |
| "step": 966 | |
| }, | |
| { | |
| "epoch": 0.24012912838341197, | |
| "grad_norm": 0.5601321458816528, | |
| "learning_rate": 3.517245946731529e-08, | |
| "loss": 1.6218, | |
| "num_input_tokens_seen": 253493248, | |
| "step": 967 | |
| }, | |
| { | |
| "epoch": 0.24037745219766576, | |
| "grad_norm": 0.6398811936378479, | |
| "learning_rate": 3.313617199801777e-08, | |
| "loss": 1.8179, | |
| "num_input_tokens_seen": 253755392, | |
| "step": 968 | |
| }, | |
| { | |
| "epoch": 0.24062577601191953, | |
| "grad_norm": 0.3753248155117035, | |
| "learning_rate": 3.1160404197018155e-08, | |
| "loss": 1.6866, | |
| "num_input_tokens_seen": 254017536, | |
| "step": 969 | |
| }, | |
| { | |
| "epoch": 0.24087409982617333, | |
| "grad_norm": 0.7169692516326904, | |
| "learning_rate": 2.9245180138423033e-08, | |
| "loss": 1.6297, | |
| "num_input_tokens_seen": 254279680, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.24112242364042713, | |
| "grad_norm": 0.501290500164032, | |
| "learning_rate": 2.7390523158633552e-08, | |
| "loss": 1.3324, | |
| "num_input_tokens_seen": 254541824, | |
| "step": 971 | |
| }, | |
| { | |
| "epoch": 0.2413707474546809, | |
| "grad_norm": 0.4676488935947418, | |
| "learning_rate": 2.5596455856058966e-08, | |
| "loss": 1.3584, | |
| "num_input_tokens_seen": 254803968, | |
| "step": 972 | |
| }, | |
| { | |
| "epoch": 0.2416190712689347, | |
| "grad_norm": 0.40131956338882446, | |
| "learning_rate": 2.386300009084408e-08, | |
| "loss": 1.0066, | |
| "num_input_tokens_seen": 255066112, | |
| "step": 973 | |
| }, | |
| { | |
| "epoch": 0.24186739508318847, | |
| "grad_norm": 0.45223063230514526, | |
| "learning_rate": 2.219017698460002e-08, | |
| "loss": 1.7419, | |
| "num_input_tokens_seen": 255328256, | |
| "step": 974 | |
| }, | |
| { | |
| "epoch": 0.24211571889744227, | |
| "grad_norm": 0.48078829050064087, | |
| "learning_rate": 2.057800692014833e-08, | |
| "loss": 1.7454, | |
| "num_input_tokens_seen": 255590400, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.24236404271169606, | |
| "grad_norm": 0.3801480531692505, | |
| "learning_rate": 1.9026509541272276e-08, | |
| "loss": 1.542, | |
| "num_input_tokens_seen": 255852544, | |
| "step": 976 | |
| }, | |
| { | |
| "epoch": 0.24261236652594984, | |
| "grad_norm": 0.3696509301662445, | |
| "learning_rate": 1.753570375247815e-08, | |
| "loss": 1.8456, | |
| "num_input_tokens_seen": 256114688, | |
| "step": 977 | |
| }, | |
| { | |
| "epoch": 0.24286069034020363, | |
| "grad_norm": 0.3742285966873169, | |
| "learning_rate": 1.610560771876435e-08, | |
| "loss": 1.3322, | |
| "num_input_tokens_seen": 256376832, | |
| "step": 978 | |
| }, | |
| { | |
| "epoch": 0.2431090141544574, | |
| "grad_norm": 0.9268859624862671, | |
| "learning_rate": 1.4736238865398766e-08, | |
| "loss": 1.9955, | |
| "num_input_tokens_seen": 256638976, | |
| "step": 979 | |
| }, | |
| { | |
| "epoch": 0.2433573379687112, | |
| "grad_norm": 0.7358083128929138, | |
| "learning_rate": 1.3427613877709523e-08, | |
| "loss": 1.6458, | |
| "num_input_tokens_seen": 256901120, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.243605661782965, | |
| "grad_norm": 0.4992476999759674, | |
| "learning_rate": 1.2179748700879013e-08, | |
| "loss": 1.7698, | |
| "num_input_tokens_seen": 257163264, | |
| "step": 981 | |
| }, | |
| { | |
| "epoch": 0.24385398559721877, | |
| "grad_norm": 0.7254119515419006, | |
| "learning_rate": 1.0992658539750179e-08, | |
| "loss": 2.0594, | |
| "num_input_tokens_seen": 257425408, | |
| "step": 982 | |
| }, | |
| { | |
| "epoch": 0.24410230941147257, | |
| "grad_norm": 0.30243805050849915, | |
| "learning_rate": 9.866357858642206e-09, | |
| "loss": 1.6328, | |
| "num_input_tokens_seen": 257687552, | |
| "step": 983 | |
| }, | |
| { | |
| "epoch": 0.24435063322572634, | |
| "grad_norm": 0.3717341721057892, | |
| "learning_rate": 8.800860381173448e-09, | |
| "loss": 1.7149, | |
| "num_input_tokens_seen": 257949696, | |
| "step": 984 | |
| }, | |
| { | |
| "epoch": 0.24459895703998014, | |
| "grad_norm": 0.6060426831245422, | |
| "learning_rate": 7.796179090094891e-09, | |
| "loss": 1.4753, | |
| "num_input_tokens_seen": 258211840, | |
| "step": 985 | |
| }, | |
| { | |
| "epoch": 0.24484728085423393, | |
| "grad_norm": 0.5001364350318909, | |
| "learning_rate": 6.852326227130835e-09, | |
| "loss": 1.6607, | |
| "num_input_tokens_seen": 258473984, | |
| "step": 986 | |
| }, | |
| { | |
| "epoch": 0.2450956046684877, | |
| "grad_norm": 0.41138938069343567, | |
| "learning_rate": 5.969313292830126e-09, | |
| "loss": 1.5122, | |
| "num_input_tokens_seen": 258736128, | |
| "step": 987 | |
| }, | |
| { | |
| "epoch": 0.2453439284827415, | |
| "grad_norm": 0.5986543893814087, | |
| "learning_rate": 5.147151046426824e-09, | |
| "loss": 1.3974, | |
| "num_input_tokens_seen": 258998272, | |
| "step": 988 | |
| }, | |
| { | |
| "epoch": 0.24559225229699527, | |
| "grad_norm": 0.3890846073627472, | |
| "learning_rate": 4.385849505708084e-09, | |
| "loss": 1.7548, | |
| "num_input_tokens_seen": 259260416, | |
| "step": 989 | |
| }, | |
| { | |
| "epoch": 0.24584057611124907, | |
| "grad_norm": 0.5105006694793701, | |
| "learning_rate": 3.685417946894254e-09, | |
| "loss": 1.4885, | |
| "num_input_tokens_seen": 259522560, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.24608889992550287, | |
| "grad_norm": 0.5231227278709412, | |
| "learning_rate": 3.0458649045211897e-09, | |
| "loss": 1.488, | |
| "num_input_tokens_seen": 259784704, | |
| "step": 991 | |
| }, | |
| { | |
| "epoch": 0.24633722373975664, | |
| "grad_norm": 0.5039011240005493, | |
| "learning_rate": 2.4671981713420003e-09, | |
| "loss": 2.0, | |
| "num_input_tokens_seen": 260046848, | |
| "step": 992 | |
| }, | |
| { | |
| "epoch": 0.24658554755401044, | |
| "grad_norm": 0.8183209300041199, | |
| "learning_rate": 1.9494247982282386e-09, | |
| "loss": 1.5233, | |
| "num_input_tokens_seen": 260308992, | |
| "step": 993 | |
| }, | |
| { | |
| "epoch": 0.2468338713682642, | |
| "grad_norm": 0.34673362970352173, | |
| "learning_rate": 1.4925510940844157e-09, | |
| "loss": 1.2279, | |
| "num_input_tokens_seen": 260571136, | |
| "step": 994 | |
| }, | |
| { | |
| "epoch": 0.247082195182518, | |
| "grad_norm": 0.6855907440185547, | |
| "learning_rate": 1.096582625772502e-09, | |
| "loss": 1.3346, | |
| "num_input_tokens_seen": 260833280, | |
| "step": 995 | |
| }, | |
| { | |
| "epoch": 0.2473305189967718, | |
| "grad_norm": 0.5691891312599182, | |
| "learning_rate": 7.615242180436521e-10, | |
| "loss": 1.3504, | |
| "num_input_tokens_seen": 261095424, | |
| "step": 996 | |
| }, | |
| { | |
| "epoch": 0.24757884281102557, | |
| "grad_norm": 0.49807822704315186, | |
| "learning_rate": 4.87379953478806e-10, | |
| "loss": 2.1568, | |
| "num_input_tokens_seen": 261357568, | |
| "step": 997 | |
| }, | |
| { | |
| "epoch": 0.24782716662527937, | |
| "grad_norm": 0.4466933310031891, | |
| "learning_rate": 2.741531724392843e-10, | |
| "loss": 1.4098, | |
| "num_input_tokens_seen": 261619712, | |
| "step": 998 | |
| }, | |
| { | |
| "epoch": 0.24807549043953314, | |
| "grad_norm": 0.6643083691596985, | |
| "learning_rate": 1.2184647302626585e-10, | |
| "loss": 1.6152, | |
| "num_input_tokens_seen": 261881856, | |
| "step": 999 | |
| }, | |
| { | |
| "epoch": 0.24832381425378694, | |
| "grad_norm": 0.5675874352455139, | |
| "learning_rate": 3.0461711048035415e-11, | |
| "loss": 1.2485, | |
| "num_input_tokens_seen": 262144000, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 1000, | |
| "num_input_tokens_seen": 262144000, | |
| "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": 418759311360000.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |