| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 9.944281524926687, |
| "eval_steps": 500, |
| "global_step": 1700, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.005865102639296188, |
| "grad_norm": 37.9880537632157, |
| "learning_rate": 7.843137254901962e-07, |
| "loss": 2.3824, |
| "mean_token_accuracy": 0.5152561776340008, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.011730205278592375, |
| "grad_norm": 38.24663692242419, |
| "learning_rate": 1.5686274509803923e-06, |
| "loss": 2.458, |
| "mean_token_accuracy": 0.5099295005202293, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.017595307917888565, |
| "grad_norm": 34.01933715185712, |
| "learning_rate": 2.3529411764705885e-06, |
| "loss": 2.3636, |
| "mean_token_accuracy": 0.5083074681460857, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.02346041055718475, |
| "grad_norm": 27.051177114583112, |
| "learning_rate": 3.1372549019607846e-06, |
| "loss": 2.251, |
| "mean_token_accuracy": 0.5226383097469807, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.02932551319648094, |
| "grad_norm": 19.727174289533878, |
| "learning_rate": 3.92156862745098e-06, |
| "loss": 1.998, |
| "mean_token_accuracy": 0.555543951690197, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.03519061583577713, |
| "grad_norm": 21.744702794564137, |
| "learning_rate": 4.705882352941177e-06, |
| "loss": 1.7848, |
| "mean_token_accuracy": 0.592386782169342, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.04105571847507331, |
| "grad_norm": 17.275924410129907, |
| "learning_rate": 5.4901960784313735e-06, |
| "loss": 1.7557, |
| "mean_token_accuracy": 0.6163813918828964, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.0469208211143695, |
| "grad_norm": 10.019425176366797, |
| "learning_rate": 6.274509803921569e-06, |
| "loss": 1.5142, |
| "mean_token_accuracy": 0.6524599567055702, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.05278592375366569, |
| "grad_norm": 9.550167622452179, |
| "learning_rate": 7.058823529411766e-06, |
| "loss": 1.3688, |
| "mean_token_accuracy": 0.6706466227769852, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.05865102639296188, |
| "grad_norm": 7.641040982752429, |
| "learning_rate": 7.84313725490196e-06, |
| "loss": 1.3224, |
| "mean_token_accuracy": 0.6872824132442474, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.06451612903225806, |
| "grad_norm": 8.570091560611116, |
| "learning_rate": 8.627450980392157e-06, |
| "loss": 1.2134, |
| "mean_token_accuracy": 0.7061515673995018, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.07038123167155426, |
| "grad_norm": 11.290944541776646, |
| "learning_rate": 9.411764705882354e-06, |
| "loss": 1.2342, |
| "mean_token_accuracy": 0.69711734354496, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.07624633431085044, |
| "grad_norm": 7.038682211553209, |
| "learning_rate": 1.0196078431372549e-05, |
| "loss": 1.1575, |
| "mean_token_accuracy": 0.7149083167314529, |
| "step": 13 |
| }, |
| { |
| "epoch": 0.08211143695014662, |
| "grad_norm": 6.932933409214858, |
| "learning_rate": 1.0980392156862747e-05, |
| "loss": 1.2858, |
| "mean_token_accuracy": 0.6853161156177521, |
| "step": 14 |
| }, |
| { |
| "epoch": 0.08797653958944282, |
| "grad_norm": 5.731782601062065, |
| "learning_rate": 1.1764705882352942e-05, |
| "loss": 1.2554, |
| "mean_token_accuracy": 0.6931049451231956, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.093841642228739, |
| "grad_norm": 4.916389732621989, |
| "learning_rate": 1.2549019607843138e-05, |
| "loss": 1.148, |
| "mean_token_accuracy": 0.7178131565451622, |
| "step": 16 |
| }, |
| { |
| "epoch": 0.09970674486803519, |
| "grad_norm": 4.330030082475362, |
| "learning_rate": 1.3333333333333333e-05, |
| "loss": 1.0816, |
| "mean_token_accuracy": 0.7251480892300606, |
| "step": 17 |
| }, |
| { |
| "epoch": 0.10557184750733138, |
| "grad_norm": 3.649363120902478, |
| "learning_rate": 1.4117647058823532e-05, |
| "loss": 1.0693, |
| "mean_token_accuracy": 0.7300560250878334, |
| "step": 18 |
| }, |
| { |
| "epoch": 0.11143695014662756, |
| "grad_norm": 4.1519920206320196, |
| "learning_rate": 1.4901960784313726e-05, |
| "loss": 1.2506, |
| "mean_token_accuracy": 0.6863887533545494, |
| "step": 19 |
| }, |
| { |
| "epoch": 0.11730205278592376, |
| "grad_norm": 3.8767361271495604, |
| "learning_rate": 1.568627450980392e-05, |
| "loss": 1.121, |
| "mean_token_accuracy": 0.7109393775463104, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.12316715542521994, |
| "grad_norm": 3.6104844493465396, |
| "learning_rate": 1.647058823529412e-05, |
| "loss": 1.0827, |
| "mean_token_accuracy": 0.7218014225363731, |
| "step": 21 |
| }, |
| { |
| "epoch": 0.12903225806451613, |
| "grad_norm": 4.007119265101829, |
| "learning_rate": 1.7254901960784314e-05, |
| "loss": 1.1092, |
| "mean_token_accuracy": 0.7199599072337151, |
| "step": 22 |
| }, |
| { |
| "epoch": 0.1348973607038123, |
| "grad_norm": 3.6042930404260085, |
| "learning_rate": 1.8039215686274513e-05, |
| "loss": 1.0332, |
| "mean_token_accuracy": 0.7422607615590096, |
| "step": 23 |
| }, |
| { |
| "epoch": 0.14076246334310852, |
| "grad_norm": 4.219241012714524, |
| "learning_rate": 1.8823529411764708e-05, |
| "loss": 1.0517, |
| "mean_token_accuracy": 0.74069644510746, |
| "step": 24 |
| }, |
| { |
| "epoch": 0.1466275659824047, |
| "grad_norm": 3.9305087432057513, |
| "learning_rate": 1.9607843137254903e-05, |
| "loss": 1.0245, |
| "mean_token_accuracy": 0.7364556193351746, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.15249266862170088, |
| "grad_norm": 4.6730992254929635, |
| "learning_rate": 2.0392156862745097e-05, |
| "loss": 1.0677, |
| "mean_token_accuracy": 0.7419489920139313, |
| "step": 26 |
| }, |
| { |
| "epoch": 0.15835777126099707, |
| "grad_norm": 3.785097641304545, |
| "learning_rate": 2.1176470588235296e-05, |
| "loss": 1.0868, |
| "mean_token_accuracy": 0.7323751673102379, |
| "step": 27 |
| }, |
| { |
| "epoch": 0.16422287390029325, |
| "grad_norm": 3.481309479312975, |
| "learning_rate": 2.1960784313725494e-05, |
| "loss": 0.9842, |
| "mean_token_accuracy": 0.7453407794237137, |
| "step": 28 |
| }, |
| { |
| "epoch": 0.17008797653958943, |
| "grad_norm": 3.6592311495703087, |
| "learning_rate": 2.274509803921569e-05, |
| "loss": 1.0105, |
| "mean_token_accuracy": 0.7409603744745255, |
| "step": 29 |
| }, |
| { |
| "epoch": 0.17595307917888564, |
| "grad_norm": 4.514364484724581, |
| "learning_rate": 2.3529411764705884e-05, |
| "loss": 1.1021, |
| "mean_token_accuracy": 0.7238170579075813, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.18181818181818182, |
| "grad_norm": 3.463973104001894, |
| "learning_rate": 2.431372549019608e-05, |
| "loss": 1.2255, |
| "mean_token_accuracy": 0.7069308832287788, |
| "step": 31 |
| }, |
| { |
| "epoch": 0.187683284457478, |
| "grad_norm": 3.6412915937094206, |
| "learning_rate": 2.5098039215686277e-05, |
| "loss": 0.979, |
| "mean_token_accuracy": 0.7486892268061638, |
| "step": 32 |
| }, |
| { |
| "epoch": 0.1935483870967742, |
| "grad_norm": 3.771238738745046, |
| "learning_rate": 2.5882352941176475e-05, |
| "loss": 1.0749, |
| "mean_token_accuracy": 0.7376544252038002, |
| "step": 33 |
| }, |
| { |
| "epoch": 0.19941348973607037, |
| "grad_norm": 2.849785727292785, |
| "learning_rate": 2.6666666666666667e-05, |
| "loss": 0.9826, |
| "mean_token_accuracy": 0.7478941157460213, |
| "step": 34 |
| }, |
| { |
| "epoch": 0.20527859237536658, |
| "grad_norm": 3.0734278923556877, |
| "learning_rate": 2.7450980392156865e-05, |
| "loss": 1.0049, |
| "mean_token_accuracy": 0.7469039931893349, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.21114369501466276, |
| "grad_norm": 4.114646538131496, |
| "learning_rate": 2.8235294117647063e-05, |
| "loss": 1.0529, |
| "mean_token_accuracy": 0.7404080405831337, |
| "step": 36 |
| }, |
| { |
| "epoch": 0.21700879765395895, |
| "grad_norm": 3.3388236941344567, |
| "learning_rate": 2.9019607843137258e-05, |
| "loss": 0.9828, |
| "mean_token_accuracy": 0.7534837573766708, |
| "step": 37 |
| }, |
| { |
| "epoch": 0.22287390029325513, |
| "grad_norm": 3.4638437496108825, |
| "learning_rate": 2.9803921568627453e-05, |
| "loss": 0.9247, |
| "mean_token_accuracy": 0.7604290992021561, |
| "step": 38 |
| }, |
| { |
| "epoch": 0.2287390029325513, |
| "grad_norm": 3.7752117816398703, |
| "learning_rate": 3.0588235294117644e-05, |
| "loss": 1.1895, |
| "mean_token_accuracy": 0.7074295058846474, |
| "step": 39 |
| }, |
| { |
| "epoch": 0.23460410557184752, |
| "grad_norm": 3.528996257191355, |
| "learning_rate": 3.137254901960784e-05, |
| "loss": 0.9425, |
| "mean_token_accuracy": 0.7592396438121796, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.2404692082111437, |
| "grad_norm": 3.0732857130253364, |
| "learning_rate": 3.215686274509804e-05, |
| "loss": 0.9358, |
| "mean_token_accuracy": 0.7570799216628075, |
| "step": 41 |
| }, |
| { |
| "epoch": 0.24633431085043989, |
| "grad_norm": 3.279368475473708, |
| "learning_rate": 3.294117647058824e-05, |
| "loss": 0.8826, |
| "mean_token_accuracy": 0.7769674882292747, |
| "step": 42 |
| }, |
| { |
| "epoch": 0.25219941348973607, |
| "grad_norm": 3.443187648731257, |
| "learning_rate": 3.372549019607844e-05, |
| "loss": 0.797, |
| "mean_token_accuracy": 0.7896388620138168, |
| "step": 43 |
| }, |
| { |
| "epoch": 0.25806451612903225, |
| "grad_norm": 3.0279904907512933, |
| "learning_rate": 3.450980392156863e-05, |
| "loss": 0.9077, |
| "mean_token_accuracy": 0.7659174352884293, |
| "step": 44 |
| }, |
| { |
| "epoch": 0.26392961876832843, |
| "grad_norm": 3.2577062755111563, |
| "learning_rate": 3.529411764705883e-05, |
| "loss": 0.8252, |
| "mean_token_accuracy": 0.7776849120855331, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.2697947214076246, |
| "grad_norm": 3.3968975278177354, |
| "learning_rate": 3.6078431372549025e-05, |
| "loss": 0.9826, |
| "mean_token_accuracy": 0.7461246326565742, |
| "step": 46 |
| }, |
| { |
| "epoch": 0.2756598240469208, |
| "grad_norm": 3.151238810305185, |
| "learning_rate": 3.686274509803922e-05, |
| "loss": 0.9504, |
| "mean_token_accuracy": 0.754719465970993, |
| "step": 47 |
| }, |
| { |
| "epoch": 0.28152492668621704, |
| "grad_norm": 2.989913005627508, |
| "learning_rate": 3.7647058823529415e-05, |
| "loss": 0.8824, |
| "mean_token_accuracy": 0.7735645473003387, |
| "step": 48 |
| }, |
| { |
| "epoch": 0.2873900293255132, |
| "grad_norm": 3.0581268945006874, |
| "learning_rate": 3.8431372549019614e-05, |
| "loss": 0.8797, |
| "mean_token_accuracy": 0.7825532108545303, |
| "step": 49 |
| }, |
| { |
| "epoch": 0.2932551319648094, |
| "grad_norm": 3.3747466422512318, |
| "learning_rate": 3.9215686274509805e-05, |
| "loss": 1.0821, |
| "mean_token_accuracy": 0.7373353093862534, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.2991202346041056, |
| "grad_norm": 2.750915239042727, |
| "learning_rate": 4e-05, |
| "loss": 0.8237, |
| "mean_token_accuracy": 0.7809458151459694, |
| "step": 51 |
| }, |
| { |
| "epoch": 0.30498533724340177, |
| "grad_norm": 3.1589022742143533, |
| "learning_rate": 3.999996733363487e-05, |
| "loss": 0.9686, |
| "mean_token_accuracy": 0.759947344660759, |
| "step": 52 |
| }, |
| { |
| "epoch": 0.31085043988269795, |
| "grad_norm": 2.9486143286261512, |
| "learning_rate": 3.9999869334658026e-05, |
| "loss": 0.8867, |
| "mean_token_accuracy": 0.7693730369210243, |
| "step": 53 |
| }, |
| { |
| "epoch": 0.31671554252199413, |
| "grad_norm": 2.871851544463913, |
| "learning_rate": 3.9999706003425177e-05, |
| "loss": 0.9387, |
| "mean_token_accuracy": 0.7589974477887154, |
| "step": 54 |
| }, |
| { |
| "epoch": 0.3225806451612903, |
| "grad_norm": 3.450921621641314, |
| "learning_rate": 3.999947734052915e-05, |
| "loss": 1.0382, |
| "mean_token_accuracy": 0.7438068389892578, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.3284457478005865, |
| "grad_norm": 2.887445480842238, |
| "learning_rate": 3.999918334679989e-05, |
| "loss": 0.9559, |
| "mean_token_accuracy": 0.7529247477650642, |
| "step": 56 |
| }, |
| { |
| "epoch": 0.3343108504398827, |
| "grad_norm": 3.0892814108067017, |
| "learning_rate": 3.999882402330448e-05, |
| "loss": 0.8971, |
| "mean_token_accuracy": 0.7540364935994148, |
| "step": 57 |
| }, |
| { |
| "epoch": 0.34017595307917886, |
| "grad_norm": 3.0094437217519134, |
| "learning_rate": 3.999839937134712e-05, |
| "loss": 0.8167, |
| "mean_token_accuracy": 0.7749749794602394, |
| "step": 58 |
| }, |
| { |
| "epoch": 0.3460410557184751, |
| "grad_norm": 3.3487134647597356, |
| "learning_rate": 3.999790939246912e-05, |
| "loss": 1.0873, |
| "mean_token_accuracy": 0.7266764640808105, |
| "step": 59 |
| }, |
| { |
| "epoch": 0.3519061583577713, |
| "grad_norm": 2.6453420164279966, |
| "learning_rate": 3.999735408844892e-05, |
| "loss": 0.8314, |
| "mean_token_accuracy": 0.7851419448852539, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.35777126099706746, |
| "grad_norm": 2.616232246648729, |
| "learning_rate": 3.999673346130203e-05, |
| "loss": 0.9273, |
| "mean_token_accuracy": 0.7678155675530434, |
| "step": 61 |
| }, |
| { |
| "epoch": 0.36363636363636365, |
| "grad_norm": 2.7639102371481785, |
| "learning_rate": 3.999604751328109e-05, |
| "loss": 0.7851, |
| "mean_token_accuracy": 0.7944702953100204, |
| "step": 62 |
| }, |
| { |
| "epoch": 0.36950146627565983, |
| "grad_norm": 2.9253735230565963, |
| "learning_rate": 3.999529624687581e-05, |
| "loss": 0.7166, |
| "mean_token_accuracy": 0.812786877155304, |
| "step": 63 |
| }, |
| { |
| "epoch": 0.375366568914956, |
| "grad_norm": 3.035668751194949, |
| "learning_rate": 3.999447966481298e-05, |
| "loss": 0.8926, |
| "mean_token_accuracy": 0.7874413877725601, |
| "step": 64 |
| }, |
| { |
| "epoch": 0.3812316715542522, |
| "grad_norm": 3.081461551291182, |
| "learning_rate": 3.999359777005647e-05, |
| "loss": 0.9703, |
| "mean_token_accuracy": 0.7480718046426773, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.3870967741935484, |
| "grad_norm": 2.8533613171820695, |
| "learning_rate": 3.999265056580719e-05, |
| "loss": 0.7026, |
| "mean_token_accuracy": 0.8061640858650208, |
| "step": 66 |
| }, |
| { |
| "epoch": 0.39296187683284456, |
| "grad_norm": 3.962990986339149, |
| "learning_rate": 3.999163805550313e-05, |
| "loss": 1.0364, |
| "mean_token_accuracy": 0.7610009163618088, |
| "step": 67 |
| }, |
| { |
| "epoch": 0.39882697947214074, |
| "grad_norm": 4.444865136952274, |
| "learning_rate": 3.9990560242819274e-05, |
| "loss": 0.9392, |
| "mean_token_accuracy": 0.7688358500599861, |
| "step": 68 |
| }, |
| { |
| "epoch": 0.4046920821114369, |
| "grad_norm": 3.3184784161882837, |
| "learning_rate": 3.9989417131667647e-05, |
| "loss": 0.78, |
| "mean_token_accuracy": 0.8103457912802696, |
| "step": 69 |
| }, |
| { |
| "epoch": 0.41055718475073316, |
| "grad_norm": 2.7543975612278193, |
| "learning_rate": 3.9988208726197293e-05, |
| "loss": 0.7794, |
| "mean_token_accuracy": 0.7881907448172569, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.41642228739002934, |
| "grad_norm": 3.511969410814499, |
| "learning_rate": 3.998693503079423e-05, |
| "loss": 0.9841, |
| "mean_token_accuracy": 0.7602343857288361, |
| "step": 71 |
| }, |
| { |
| "epoch": 0.4222873900293255, |
| "grad_norm": 3.189897347653094, |
| "learning_rate": 3.998559605008146e-05, |
| "loss": 0.8277, |
| "mean_token_accuracy": 0.7756155356764793, |
| "step": 72 |
| }, |
| { |
| "epoch": 0.4281524926686217, |
| "grad_norm": 2.9550650318433926, |
| "learning_rate": 3.9984191788918936e-05, |
| "loss": 0.8583, |
| "mean_token_accuracy": 0.7815645411610603, |
| "step": 73 |
| }, |
| { |
| "epoch": 0.4340175953079179, |
| "grad_norm": 3.119757664916935, |
| "learning_rate": 3.998272225240356e-05, |
| "loss": 0.9466, |
| "mean_token_accuracy": 0.7682439014315605, |
| "step": 74 |
| }, |
| { |
| "epoch": 0.4398826979472141, |
| "grad_norm": 3.031490133308079, |
| "learning_rate": 3.9981187445869165e-05, |
| "loss": 0.7991, |
| "mean_token_accuracy": 0.8088371828198433, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.44574780058651026, |
| "grad_norm": 2.9007072042172592, |
| "learning_rate": 3.9979587374886466e-05, |
| "loss": 0.9103, |
| "mean_token_accuracy": 0.7687933221459389, |
| "step": 76 |
| }, |
| { |
| "epoch": 0.45161290322580644, |
| "grad_norm": 38.67934100607019, |
| "learning_rate": 3.997792204526309e-05, |
| "loss": 0.9832, |
| "mean_token_accuracy": 0.7548127546906471, |
| "step": 77 |
| }, |
| { |
| "epoch": 0.4574780058651026, |
| "grad_norm": 3.3035061898149007, |
| "learning_rate": 3.99761914630435e-05, |
| "loss": 0.7777, |
| "mean_token_accuracy": 0.7979958653450012, |
| "step": 78 |
| }, |
| { |
| "epoch": 0.4633431085043988, |
| "grad_norm": 22.781762493620928, |
| "learning_rate": 3.997439563450901e-05, |
| "loss": 0.8503, |
| "mean_token_accuracy": 0.7586963549256325, |
| "step": 79 |
| }, |
| { |
| "epoch": 0.46920821114369504, |
| "grad_norm": 2.7622593230896664, |
| "learning_rate": 3.997253456617775e-05, |
| "loss": 0.79, |
| "mean_token_accuracy": 0.7944292947649956, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.4750733137829912, |
| "grad_norm": 2.5762465699762074, |
| "learning_rate": 3.997060826480465e-05, |
| "loss": 0.6844, |
| "mean_token_accuracy": 0.8140356242656708, |
| "step": 81 |
| }, |
| { |
| "epoch": 0.4809384164222874, |
| "grad_norm": 2.8204659759274575, |
| "learning_rate": 3.9968616737381414e-05, |
| "loss": 0.8264, |
| "mean_token_accuracy": 0.7992580607533455, |
| "step": 82 |
| }, |
| { |
| "epoch": 0.4868035190615836, |
| "grad_norm": 2.841335055037953, |
| "learning_rate": 3.996655999113647e-05, |
| "loss": 0.6823, |
| "mean_token_accuracy": 0.82578344643116, |
| "step": 83 |
| }, |
| { |
| "epoch": 0.49266862170087977, |
| "grad_norm": 2.8147807305657264, |
| "learning_rate": 3.9964438033534994e-05, |
| "loss": 0.6119, |
| "mean_token_accuracy": 0.8287858068943024, |
| "step": 84 |
| }, |
| { |
| "epoch": 0.49853372434017595, |
| "grad_norm": 2.376089124661705, |
| "learning_rate": 3.996225087227881e-05, |
| "loss": 0.7493, |
| "mean_token_accuracy": 0.8083062320947647, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.5043988269794721, |
| "grad_norm": 2.544616939836254, |
| "learning_rate": 3.995999851530645e-05, |
| "loss": 0.7059, |
| "mean_token_accuracy": 0.8272803351283073, |
| "step": 86 |
| }, |
| { |
| "epoch": 0.5102639296187683, |
| "grad_norm": 2.3739375156900784, |
| "learning_rate": 3.995768097079305e-05, |
| "loss": 0.7219, |
| "mean_token_accuracy": 0.8119369223713875, |
| "step": 87 |
| }, |
| { |
| "epoch": 0.5161290322580645, |
| "grad_norm": 2.724016943326451, |
| "learning_rate": 3.9955298247150365e-05, |
| "loss": 0.9042, |
| "mean_token_accuracy": 0.7662067860364914, |
| "step": 88 |
| }, |
| { |
| "epoch": 0.5219941348973607, |
| "grad_norm": 2.4239661286688463, |
| "learning_rate": 3.9952850353026715e-05, |
| "loss": 0.7767, |
| "mean_token_accuracy": 0.7790317609906197, |
| "step": 89 |
| }, |
| { |
| "epoch": 0.5278592375366569, |
| "grad_norm": 2.665098789911307, |
| "learning_rate": 3.9950337297306976e-05, |
| "loss": 0.7754, |
| "mean_token_accuracy": 0.8018990531563759, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.533724340175953, |
| "grad_norm": 2.8426441072209805, |
| "learning_rate": 3.994775908911251e-05, |
| "loss": 0.858, |
| "mean_token_accuracy": 0.7857545912265778, |
| "step": 91 |
| }, |
| { |
| "epoch": 0.5395894428152492, |
| "grad_norm": 2.436499001766652, |
| "learning_rate": 3.9945115737801183e-05, |
| "loss": 0.688, |
| "mean_token_accuracy": 0.8172339051961899, |
| "step": 92 |
| }, |
| { |
| "epoch": 0.5454545454545454, |
| "grad_norm": 2.5390866336120874, |
| "learning_rate": 3.99424072529673e-05, |
| "loss": 0.8688, |
| "mean_token_accuracy": 0.7890106663107872, |
| "step": 93 |
| }, |
| { |
| "epoch": 0.5513196480938416, |
| "grad_norm": 2.6076783165281094, |
| "learning_rate": 3.993963364444155e-05, |
| "loss": 0.7134, |
| "mean_token_accuracy": 0.8137485533952713, |
| "step": 94 |
| }, |
| { |
| "epoch": 0.5571847507331378, |
| "grad_norm": 2.4257871259207993, |
| "learning_rate": 3.9936794922291015e-05, |
| "loss": 0.8723, |
| "mean_token_accuracy": 0.7773057669401169, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.5630498533724341, |
| "grad_norm": 2.8574887984110875, |
| "learning_rate": 3.993389109681912e-05, |
| "loss": 0.788, |
| "mean_token_accuracy": 0.7993652150034904, |
| "step": 96 |
| }, |
| { |
| "epoch": 0.5689149560117303, |
| "grad_norm": 2.616691569677792, |
| "learning_rate": 3.993092217856557e-05, |
| "loss": 0.6777, |
| "mean_token_accuracy": 0.8250965252518654, |
| "step": 97 |
| }, |
| { |
| "epoch": 0.5747800586510264, |
| "grad_norm": 2.6843846148715405, |
| "learning_rate": 3.9927888178306346e-05, |
| "loss": 0.8095, |
| "mean_token_accuracy": 0.803053617477417, |
| "step": 98 |
| }, |
| { |
| "epoch": 0.5806451612903226, |
| "grad_norm": 2.5522882845707833, |
| "learning_rate": 3.992478910705364e-05, |
| "loss": 0.7908, |
| "mean_token_accuracy": 0.7967691794037819, |
| "step": 99 |
| }, |
| { |
| "epoch": 0.5865102639296188, |
| "grad_norm": 2.5520682672510016, |
| "learning_rate": 3.992162497605583e-05, |
| "loss": 0.6946, |
| "mean_token_accuracy": 0.8279445469379425, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.592375366568915, |
| "grad_norm": 2.578013850702768, |
| "learning_rate": 3.991839579679742e-05, |
| "loss": 0.7428, |
| "mean_token_accuracy": 0.8000684455037117, |
| "step": 101 |
| }, |
| { |
| "epoch": 0.5982404692082112, |
| "grad_norm": 2.3830631117684575, |
| "learning_rate": 3.991510158099905e-05, |
| "loss": 0.5722, |
| "mean_token_accuracy": 0.8460334986448288, |
| "step": 102 |
| }, |
| { |
| "epoch": 0.6041055718475073, |
| "grad_norm": 2.414928415499407, |
| "learning_rate": 3.991174234061738e-05, |
| "loss": 0.6108, |
| "mean_token_accuracy": 0.8433133065700531, |
| "step": 103 |
| }, |
| { |
| "epoch": 0.6099706744868035, |
| "grad_norm": 2.509706778446123, |
| "learning_rate": 3.9908318087845104e-05, |
| "loss": 0.7385, |
| "mean_token_accuracy": 0.8071222379803658, |
| "step": 104 |
| }, |
| { |
| "epoch": 0.6158357771260997, |
| "grad_norm": 2.6079854919350964, |
| "learning_rate": 3.990482883511086e-05, |
| "loss": 0.5505, |
| "mean_token_accuracy": 0.852523498237133, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.6217008797653959, |
| "grad_norm": 2.4027206543454045, |
| "learning_rate": 3.990127459507924e-05, |
| "loss": 0.6085, |
| "mean_token_accuracy": 0.8315910547971725, |
| "step": 106 |
| }, |
| { |
| "epoch": 0.6275659824046921, |
| "grad_norm": 2.4987169867308654, |
| "learning_rate": 3.98976553806507e-05, |
| "loss": 0.5936, |
| "mean_token_accuracy": 0.8380607068538666, |
| "step": 107 |
| }, |
| { |
| "epoch": 0.6334310850439883, |
| "grad_norm": 2.4015675582275002, |
| "learning_rate": 3.989397120496152e-05, |
| "loss": 0.4922, |
| "mean_token_accuracy": 0.87723558396101, |
| "step": 108 |
| }, |
| { |
| "epoch": 0.6392961876832844, |
| "grad_norm": 2.3732266526127455, |
| "learning_rate": 3.989022208138377e-05, |
| "loss": 0.56, |
| "mean_token_accuracy": 0.8504580110311508, |
| "step": 109 |
| }, |
| { |
| "epoch": 0.6451612903225806, |
| "grad_norm": 2.8710876340305647, |
| "learning_rate": 3.9886408023525256e-05, |
| "loss": 0.7691, |
| "mean_token_accuracy": 0.8154280558228493, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.6510263929618768, |
| "grad_norm": 2.8221688147494093, |
| "learning_rate": 3.9882529045229475e-05, |
| "loss": 0.8413, |
| "mean_token_accuracy": 0.7811410203576088, |
| "step": 111 |
| }, |
| { |
| "epoch": 0.656891495601173, |
| "grad_norm": 2.5505094230738092, |
| "learning_rate": 3.987858516057554e-05, |
| "loss": 0.5915, |
| "mean_token_accuracy": 0.844106875360012, |
| "step": 112 |
| }, |
| { |
| "epoch": 0.6627565982404692, |
| "grad_norm": 2.7933909899663676, |
| "learning_rate": 3.9874576383878165e-05, |
| "loss": 0.6512, |
| "mean_token_accuracy": 0.8320295438170433, |
| "step": 113 |
| }, |
| { |
| "epoch": 0.6686217008797654, |
| "grad_norm": 2.3083034683512342, |
| "learning_rate": 3.9870502729687594e-05, |
| "loss": 0.6401, |
| "mean_token_accuracy": 0.8332142606377602, |
| "step": 114 |
| }, |
| { |
| "epoch": 0.6744868035190615, |
| "grad_norm": 2.621814147997228, |
| "learning_rate": 3.986636421278954e-05, |
| "loss": 0.6927, |
| "mean_token_accuracy": 0.8254417553544044, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.6803519061583577, |
| "grad_norm": 2.2582220425128785, |
| "learning_rate": 3.986216084820515e-05, |
| "loss": 0.5051, |
| "mean_token_accuracy": 0.8626674264669418, |
| "step": 116 |
| }, |
| { |
| "epoch": 0.6862170087976539, |
| "grad_norm": 2.521627222816184, |
| "learning_rate": 3.985789265119095e-05, |
| "loss": 0.5789, |
| "mean_token_accuracy": 0.8454054147005081, |
| "step": 117 |
| }, |
| { |
| "epoch": 0.6920821114369502, |
| "grad_norm": 2.1375840083749145, |
| "learning_rate": 3.985355963723875e-05, |
| "loss": 0.483, |
| "mean_token_accuracy": 0.8748066648840904, |
| "step": 118 |
| }, |
| { |
| "epoch": 0.6979472140762464, |
| "grad_norm": 3.7422524710601444, |
| "learning_rate": 3.9849161822075655e-05, |
| "loss": 0.5609, |
| "mean_token_accuracy": 0.8508216217160225, |
| "step": 119 |
| }, |
| { |
| "epoch": 0.7038123167155426, |
| "grad_norm": 2.350290493183303, |
| "learning_rate": 3.984469922166396e-05, |
| "loss": 0.6774, |
| "mean_token_accuracy": 0.8322641178965569, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.7096774193548387, |
| "grad_norm": 3.5137372539507252, |
| "learning_rate": 3.984017185220109e-05, |
| "loss": 0.8092, |
| "mean_token_accuracy": 0.8016931265592575, |
| "step": 121 |
| }, |
| { |
| "epoch": 0.7155425219941349, |
| "grad_norm": 2.5192379831163567, |
| "learning_rate": 3.9835579730119576e-05, |
| "loss": 0.7129, |
| "mean_token_accuracy": 0.818251371383667, |
| "step": 122 |
| }, |
| { |
| "epoch": 0.7214076246334311, |
| "grad_norm": 2.193025994665411, |
| "learning_rate": 3.9830922872086974e-05, |
| "loss": 0.6943, |
| "mean_token_accuracy": 0.8356373012065887, |
| "step": 123 |
| }, |
| { |
| "epoch": 0.7272727272727273, |
| "grad_norm": 2.685832581829903, |
| "learning_rate": 3.9826201295005784e-05, |
| "loss": 0.7694, |
| "mean_token_accuracy": 0.809048131108284, |
| "step": 124 |
| }, |
| { |
| "epoch": 0.7331378299120235, |
| "grad_norm": 2.5160714877492736, |
| "learning_rate": 3.982141501601343e-05, |
| "loss": 0.7365, |
| "mean_token_accuracy": 0.8147779926657677, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.7390029325513197, |
| "grad_norm": 2.237880574653323, |
| "learning_rate": 3.9816564052482164e-05, |
| "loss": 0.6554, |
| "mean_token_accuracy": 0.8241963237524033, |
| "step": 126 |
| }, |
| { |
| "epoch": 0.7448680351906158, |
| "grad_norm": 2.174659296975228, |
| "learning_rate": 3.981164842201904e-05, |
| "loss": 0.709, |
| "mean_token_accuracy": 0.826836347579956, |
| "step": 127 |
| }, |
| { |
| "epoch": 0.750733137829912, |
| "grad_norm": 2.4261092807260836, |
| "learning_rate": 3.9806668142465804e-05, |
| "loss": 0.7414, |
| "mean_token_accuracy": 0.8207696005702019, |
| "step": 128 |
| }, |
| { |
| "epoch": 0.7565982404692082, |
| "grad_norm": 2.721891836616963, |
| "learning_rate": 3.9801623231898856e-05, |
| "loss": 0.5605, |
| "mean_token_accuracy": 0.8457466587424278, |
| "step": 129 |
| }, |
| { |
| "epoch": 0.7624633431085044, |
| "grad_norm": 2.3378897432690726, |
| "learning_rate": 3.9796513708629186e-05, |
| "loss": 0.5664, |
| "mean_token_accuracy": 0.8508183881640434, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.7683284457478006, |
| "grad_norm": 2.3272679541979198, |
| "learning_rate": 3.979133959120229e-05, |
| "loss": 0.5489, |
| "mean_token_accuracy": 0.8570074439048767, |
| "step": 131 |
| }, |
| { |
| "epoch": 0.7741935483870968, |
| "grad_norm": 2.315567352712671, |
| "learning_rate": 3.9786100898398145e-05, |
| "loss": 0.576, |
| "mean_token_accuracy": 0.8477486073970795, |
| "step": 132 |
| }, |
| { |
| "epoch": 0.7800586510263929, |
| "grad_norm": 2.5536758744972543, |
| "learning_rate": 3.9780797649231085e-05, |
| "loss": 0.6087, |
| "mean_token_accuracy": 0.8472266495227814, |
| "step": 133 |
| }, |
| { |
| "epoch": 0.7859237536656891, |
| "grad_norm": 2.518398139484913, |
| "learning_rate": 3.9775429862949745e-05, |
| "loss": 0.7258, |
| "mean_token_accuracy": 0.8246461376547813, |
| "step": 134 |
| }, |
| { |
| "epoch": 0.7917888563049853, |
| "grad_norm": 2.532155725945346, |
| "learning_rate": 3.976999755903704e-05, |
| "loss": 0.7288, |
| "mean_token_accuracy": 0.8153877630829811, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.7976539589442815, |
| "grad_norm": 2.3151492007502483, |
| "learning_rate": 3.976450075721003e-05, |
| "loss": 0.5781, |
| "mean_token_accuracy": 0.855253241956234, |
| "step": 136 |
| }, |
| { |
| "epoch": 0.8035190615835777, |
| "grad_norm": 2.844190481561306, |
| "learning_rate": 3.975893947741989e-05, |
| "loss": 0.5248, |
| "mean_token_accuracy": 0.8630795776844025, |
| "step": 137 |
| }, |
| { |
| "epoch": 0.8093841642228738, |
| "grad_norm": 2.315966717331691, |
| "learning_rate": 3.9753313739851824e-05, |
| "loss": 0.6877, |
| "mean_token_accuracy": 0.8183143883943558, |
| "step": 138 |
| }, |
| { |
| "epoch": 0.8152492668621701, |
| "grad_norm": 2.32614866768996, |
| "learning_rate": 3.974762356492498e-05, |
| "loss": 0.8115, |
| "mean_token_accuracy": 0.8048359602689743, |
| "step": 139 |
| }, |
| { |
| "epoch": 0.8211143695014663, |
| "grad_norm": 2.7089994032119775, |
| "learning_rate": 3.974186897329239e-05, |
| "loss": 0.5536, |
| "mean_token_accuracy": 0.8649086877703667, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.8269794721407625, |
| "grad_norm": 2.4396347849087587, |
| "learning_rate": 3.97360499858409e-05, |
| "loss": 0.5594, |
| "mean_token_accuracy": 0.8538892492651939, |
| "step": 141 |
| }, |
| { |
| "epoch": 0.8328445747800587, |
| "grad_norm": 2.696807756771278, |
| "learning_rate": 3.9730166623691096e-05, |
| "loss": 0.7182, |
| "mean_token_accuracy": 0.8146277740597725, |
| "step": 142 |
| }, |
| { |
| "epoch": 0.8387096774193549, |
| "grad_norm": 2.307485749164851, |
| "learning_rate": 3.9724218908197194e-05, |
| "loss": 0.5172, |
| "mean_token_accuracy": 0.8577979356050491, |
| "step": 143 |
| }, |
| { |
| "epoch": 0.844574780058651, |
| "grad_norm": 2.9013073880532487, |
| "learning_rate": 3.971820686094701e-05, |
| "loss": 0.8143, |
| "mean_token_accuracy": 0.8073533028364182, |
| "step": 144 |
| }, |
| { |
| "epoch": 0.8504398826979472, |
| "grad_norm": 2.545940900051437, |
| "learning_rate": 3.971213050376183e-05, |
| "loss": 0.6929, |
| "mean_token_accuracy": 0.8187995925545692, |
| "step": 145 |
| }, |
| { |
| "epoch": 0.8563049853372434, |
| "grad_norm": 2.07164598138888, |
| "learning_rate": 3.9705989858696387e-05, |
| "loss": 0.5164, |
| "mean_token_accuracy": 0.8661198765039444, |
| "step": 146 |
| }, |
| { |
| "epoch": 0.8621700879765396, |
| "grad_norm": 1.9877579647660435, |
| "learning_rate": 3.969978494803876e-05, |
| "loss": 0.504, |
| "mean_token_accuracy": 0.8651574477553368, |
| "step": 147 |
| }, |
| { |
| "epoch": 0.8680351906158358, |
| "grad_norm": 2.164735875266452, |
| "learning_rate": 3.969351579431024e-05, |
| "loss": 0.5236, |
| "mean_token_accuracy": 0.8638859316706657, |
| "step": 148 |
| }, |
| { |
| "epoch": 0.873900293255132, |
| "grad_norm": 2.387480098965745, |
| "learning_rate": 3.968718242026533e-05, |
| "loss": 0.5327, |
| "mean_token_accuracy": 0.8672320023179054, |
| "step": 149 |
| }, |
| { |
| "epoch": 0.8797653958944281, |
| "grad_norm": 1.7906670972986842, |
| "learning_rate": 3.968078484889163e-05, |
| "loss": 0.398, |
| "mean_token_accuracy": 0.8894071653485298, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.8856304985337243, |
| "grad_norm": 2.720776873508094, |
| "learning_rate": 3.9674323103409736e-05, |
| "loss": 0.6053, |
| "mean_token_accuracy": 0.8414165899157524, |
| "step": 151 |
| }, |
| { |
| "epoch": 0.8914956011730205, |
| "grad_norm": 2.340371554995659, |
| "learning_rate": 3.966779720727317e-05, |
| "loss": 0.6905, |
| "mean_token_accuracy": 0.8298128694295883, |
| "step": 152 |
| }, |
| { |
| "epoch": 0.8973607038123167, |
| "grad_norm": 2.222842499416126, |
| "learning_rate": 3.9661207184168305e-05, |
| "loss": 0.538, |
| "mean_token_accuracy": 0.852678582072258, |
| "step": 153 |
| }, |
| { |
| "epoch": 0.9032258064516129, |
| "grad_norm": 2.307131700118274, |
| "learning_rate": 3.9654553058014265e-05, |
| "loss": 0.6771, |
| "mean_token_accuracy": 0.8301350399851799, |
| "step": 154 |
| }, |
| { |
| "epoch": 0.9090909090909091, |
| "grad_norm": 2.383888745225798, |
| "learning_rate": 3.9647834852962825e-05, |
| "loss": 0.5538, |
| "mean_token_accuracy": 0.8536617681384087, |
| "step": 155 |
| }, |
| { |
| "epoch": 0.9149560117302052, |
| "grad_norm": 5.137805263388332, |
| "learning_rate": 3.964105259339838e-05, |
| "loss": 0.7932, |
| "mean_token_accuracy": 0.7996788993477821, |
| "step": 156 |
| }, |
| { |
| "epoch": 0.9208211143695014, |
| "grad_norm": 2.161972657457864, |
| "learning_rate": 3.9634206303937773e-05, |
| "loss": 0.4423, |
| "mean_token_accuracy": 0.8784089833498001, |
| "step": 157 |
| }, |
| { |
| "epoch": 0.9266862170087976, |
| "grad_norm": 1.7747982918472702, |
| "learning_rate": 3.962729600943028e-05, |
| "loss": 0.454, |
| "mean_token_accuracy": 0.8777899146080017, |
| "step": 158 |
| }, |
| { |
| "epoch": 0.9325513196480938, |
| "grad_norm": 1.994086972253065, |
| "learning_rate": 3.962032173495748e-05, |
| "loss": 0.4916, |
| "mean_token_accuracy": 0.8769926801323891, |
| "step": 159 |
| }, |
| { |
| "epoch": 0.9384164222873901, |
| "grad_norm": 2.0290404806475317, |
| "learning_rate": 3.961328350583316e-05, |
| "loss": 0.4613, |
| "mean_token_accuracy": 0.8767556101083755, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.9442815249266863, |
| "grad_norm": 2.2184277122166987, |
| "learning_rate": 3.960618134760327e-05, |
| "loss": 0.6018, |
| "mean_token_accuracy": 0.8447824791073799, |
| "step": 161 |
| }, |
| { |
| "epoch": 0.9501466275659824, |
| "grad_norm": 1.8714319974846567, |
| "learning_rate": 3.959901528604575e-05, |
| "loss": 0.3716, |
| "mean_token_accuracy": 0.8887424990534782, |
| "step": 162 |
| }, |
| { |
| "epoch": 0.9560117302052786, |
| "grad_norm": 2.1972929020277974, |
| "learning_rate": 3.959178534717053e-05, |
| "loss": 0.6059, |
| "mean_token_accuracy": 0.8424908146262169, |
| "step": 163 |
| }, |
| { |
| "epoch": 0.9618768328445748, |
| "grad_norm": 1.9980815359087727, |
| "learning_rate": 3.9584491557219366e-05, |
| "loss": 0.5901, |
| "mean_token_accuracy": 0.8520945236086845, |
| "step": 164 |
| }, |
| { |
| "epoch": 0.967741935483871, |
| "grad_norm": 2.072248270926409, |
| "learning_rate": 3.957713394266576e-05, |
| "loss": 0.5486, |
| "mean_token_accuracy": 0.8482609316706657, |
| "step": 165 |
| }, |
| { |
| "epoch": 0.9736070381231672, |
| "grad_norm": 2.1173865352854455, |
| "learning_rate": 3.956971253021489e-05, |
| "loss": 0.4607, |
| "mean_token_accuracy": 0.8749275654554367, |
| "step": 166 |
| }, |
| { |
| "epoch": 0.9794721407624634, |
| "grad_norm": 1.9428629083216018, |
| "learning_rate": 3.956222734680348e-05, |
| "loss": 0.5424, |
| "mean_token_accuracy": 0.857122503221035, |
| "step": 167 |
| }, |
| { |
| "epoch": 0.9853372434017595, |
| "grad_norm": 2.1694805344323673, |
| "learning_rate": 3.955467841959972e-05, |
| "loss": 0.5818, |
| "mean_token_accuracy": 0.8583057522773743, |
| "step": 168 |
| }, |
| { |
| "epoch": 0.9912023460410557, |
| "grad_norm": 2.1011172758309984, |
| "learning_rate": 3.954706577600318e-05, |
| "loss": 0.5309, |
| "mean_token_accuracy": 0.8498675376176834, |
| "step": 169 |
| }, |
| { |
| "epoch": 0.9970674486803519, |
| "grad_norm": 2.135249455720304, |
| "learning_rate": 3.953938944364467e-05, |
| "loss": 0.6643, |
| "mean_token_accuracy": 0.8334744796156883, |
| "step": 170 |
| }, |
| { |
| "epoch": 1.0, |
| "grad_norm": 2.135249455720304, |
| "learning_rate": 3.953164945038618e-05, |
| "loss": 0.5537, |
| "mean_token_accuracy": 0.8696076571941376, |
| "step": 171 |
| }, |
| { |
| "epoch": 1.0058651026392962, |
| "grad_norm": 2.9426546093236556, |
| "learning_rate": 3.952384582432076e-05, |
| "loss": 0.3773, |
| "mean_token_accuracy": 0.8955628573894501, |
| "step": 172 |
| }, |
| { |
| "epoch": 1.0117302052785924, |
| "grad_norm": 1.9429159271699736, |
| "learning_rate": 3.9515978593772426e-05, |
| "loss": 0.3063, |
| "mean_token_accuracy": 0.9107492417097092, |
| "step": 173 |
| }, |
| { |
| "epoch": 1.0175953079178885, |
| "grad_norm": 2.0141991872288383, |
| "learning_rate": 3.9508047787296034e-05, |
| "loss": 0.2379, |
| "mean_token_accuracy": 0.9283656999468803, |
| "step": 174 |
| }, |
| { |
| "epoch": 1.0234604105571847, |
| "grad_norm": 1.626380022632123, |
| "learning_rate": 3.9500053433677226e-05, |
| "loss": 0.2344, |
| "mean_token_accuracy": 0.9287891238927841, |
| "step": 175 |
| }, |
| { |
| "epoch": 1.029325513196481, |
| "grad_norm": 2.373020615301983, |
| "learning_rate": 3.949199556193226e-05, |
| "loss": 0.3377, |
| "mean_token_accuracy": 0.9061623066663742, |
| "step": 176 |
| }, |
| { |
| "epoch": 1.035190615835777, |
| "grad_norm": 2.1356888697655325, |
| "learning_rate": 3.948387420130796e-05, |
| "loss": 0.2294, |
| "mean_token_accuracy": 0.9320363029837608, |
| "step": 177 |
| }, |
| { |
| "epoch": 1.0410557184750733, |
| "grad_norm": 1.795075757224302, |
| "learning_rate": 3.94756893812816e-05, |
| "loss": 0.3389, |
| "mean_token_accuracy": 0.9035566374659538, |
| "step": 178 |
| }, |
| { |
| "epoch": 1.0469208211143695, |
| "grad_norm": 2.025624174532658, |
| "learning_rate": 3.946744113156075e-05, |
| "loss": 0.269, |
| "mean_token_accuracy": 0.9122130498290062, |
| "step": 179 |
| }, |
| { |
| "epoch": 1.0527859237536656, |
| "grad_norm": 2.0849133530495467, |
| "learning_rate": 3.945912948208324e-05, |
| "loss": 0.4147, |
| "mean_token_accuracy": 0.8821691945195198, |
| "step": 180 |
| }, |
| { |
| "epoch": 1.0586510263929618, |
| "grad_norm": 2.3538480856162236, |
| "learning_rate": 3.9450754463016994e-05, |
| "loss": 0.3542, |
| "mean_token_accuracy": 0.9003543704748154, |
| "step": 181 |
| }, |
| { |
| "epoch": 1.064516129032258, |
| "grad_norm": 2.0146157111462637, |
| "learning_rate": 3.9442316104759955e-05, |
| "loss": 0.3418, |
| "mean_token_accuracy": 0.9114131703972816, |
| "step": 182 |
| }, |
| { |
| "epoch": 1.0703812316715542, |
| "grad_norm": 1.5651301109137348, |
| "learning_rate": 3.943381443793994e-05, |
| "loss": 0.3668, |
| "mean_token_accuracy": 0.9008131772279739, |
| "step": 183 |
| }, |
| { |
| "epoch": 1.0762463343108504, |
| "grad_norm": 2.9788519961880753, |
| "learning_rate": 3.9425249493414585e-05, |
| "loss": 0.4622, |
| "mean_token_accuracy": 0.8579861670732498, |
| "step": 184 |
| }, |
| { |
| "epoch": 1.0821114369501466, |
| "grad_norm": 139.27043531147197, |
| "learning_rate": 3.941662130227118e-05, |
| "loss": 0.4682, |
| "mean_token_accuracy": 0.8681460916996002, |
| "step": 185 |
| }, |
| { |
| "epoch": 1.0879765395894427, |
| "grad_norm": 2.5171759946289662, |
| "learning_rate": 3.940792989582654e-05, |
| "loss": 0.3631, |
| "mean_token_accuracy": 0.8955680355429649, |
| "step": 186 |
| }, |
| { |
| "epoch": 1.093841642228739, |
| "grad_norm": 2.142201626535042, |
| "learning_rate": 3.939917530562701e-05, |
| "loss": 0.2754, |
| "mean_token_accuracy": 0.9177270233631134, |
| "step": 187 |
| }, |
| { |
| "epoch": 1.099706744868035, |
| "grad_norm": 1.9141489035930843, |
| "learning_rate": 3.939035756344818e-05, |
| "loss": 0.3297, |
| "mean_token_accuracy": 0.9090648591518402, |
| "step": 188 |
| }, |
| { |
| "epoch": 1.1055718475073313, |
| "grad_norm": 2.0379286037072895, |
| "learning_rate": 3.93814767012949e-05, |
| "loss": 0.3305, |
| "mean_token_accuracy": 0.9021382927894592, |
| "step": 189 |
| }, |
| { |
| "epoch": 1.1114369501466275, |
| "grad_norm": 1.7753703302965071, |
| "learning_rate": 3.937253275140113e-05, |
| "loss": 0.2498, |
| "mean_token_accuracy": 0.9244972839951515, |
| "step": 190 |
| }, |
| { |
| "epoch": 1.1173020527859236, |
| "grad_norm": 2.180640664647315, |
| "learning_rate": 3.936352574622978e-05, |
| "loss": 0.2766, |
| "mean_token_accuracy": 0.9234517589211464, |
| "step": 191 |
| }, |
| { |
| "epoch": 1.1231671554252198, |
| "grad_norm": 1.5381199668110206, |
| "learning_rate": 3.9354455718472646e-05, |
| "loss": 0.3604, |
| "mean_token_accuracy": 0.8974525555968285, |
| "step": 192 |
| }, |
| { |
| "epoch": 1.129032258064516, |
| "grad_norm": 2.1119703774116343, |
| "learning_rate": 3.934532270105026e-05, |
| "loss": 0.3612, |
| "mean_token_accuracy": 0.9062921851873398, |
| "step": 193 |
| }, |
| { |
| "epoch": 1.1348973607038122, |
| "grad_norm": 2.0957303962988205, |
| "learning_rate": 3.933612672711179e-05, |
| "loss": 0.3643, |
| "mean_token_accuracy": 0.8999098464846611, |
| "step": 194 |
| }, |
| { |
| "epoch": 1.1407624633431086, |
| "grad_norm": 1.9050538760986877, |
| "learning_rate": 3.9326867830034915e-05, |
| "loss": 0.3696, |
| "mean_token_accuracy": 0.8904466778039932, |
| "step": 195 |
| }, |
| { |
| "epoch": 1.1466275659824048, |
| "grad_norm": 2.0245298774846123, |
| "learning_rate": 3.931754604342568e-05, |
| "loss": 0.294, |
| "mean_token_accuracy": 0.9096431136131287, |
| "step": 196 |
| }, |
| { |
| "epoch": 1.152492668621701, |
| "grad_norm": 1.748128150837437, |
| "learning_rate": 3.930816140111842e-05, |
| "loss": 0.2688, |
| "mean_token_accuracy": 0.9198426976799965, |
| "step": 197 |
| }, |
| { |
| "epoch": 1.1583577712609971, |
| "grad_norm": 2.0707144710674763, |
| "learning_rate": 3.929871393717558e-05, |
| "loss": 0.3557, |
| "mean_token_accuracy": 0.9080502316355705, |
| "step": 198 |
| }, |
| { |
| "epoch": 1.1642228739002933, |
| "grad_norm": 2.672512494774031, |
| "learning_rate": 3.9289203685887644e-05, |
| "loss": 0.399, |
| "mean_token_accuracy": 0.8905297890305519, |
| "step": 199 |
| }, |
| { |
| "epoch": 1.1700879765395895, |
| "grad_norm": 1.818463575818881, |
| "learning_rate": 3.927963068177299e-05, |
| "loss": 0.3702, |
| "mean_token_accuracy": 0.8925187587738037, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.1759530791788857, |
| "grad_norm": 1.8940957765717514, |
| "learning_rate": 3.926999495957775e-05, |
| "loss": 0.4394, |
| "mean_token_accuracy": 0.8725065067410469, |
| "step": 201 |
| }, |
| { |
| "epoch": 1.1818181818181819, |
| "grad_norm": 1.9020997930436756, |
| "learning_rate": 3.9260296554275704e-05, |
| "loss": 0.461, |
| "mean_token_accuracy": 0.880850076675415, |
| "step": 202 |
| }, |
| { |
| "epoch": 1.187683284457478, |
| "grad_norm": 1.795499779219037, |
| "learning_rate": 3.925053550106815e-05, |
| "loss": 0.3238, |
| "mean_token_accuracy": 0.9072358906269073, |
| "step": 203 |
| }, |
| { |
| "epoch": 1.1935483870967742, |
| "grad_norm": 1.7087252975022835, |
| "learning_rate": 3.9240711835383766e-05, |
| "loss": 0.2935, |
| "mean_token_accuracy": 0.9104657173156738, |
| "step": 204 |
| }, |
| { |
| "epoch": 1.1994134897360704, |
| "grad_norm": 1.6303327633815248, |
| "learning_rate": 3.9230825592878494e-05, |
| "loss": 0.3019, |
| "mean_token_accuracy": 0.9101001620292664, |
| "step": 205 |
| }, |
| { |
| "epoch": 1.2052785923753666, |
| "grad_norm": 1.7889524668856331, |
| "learning_rate": 3.92208768094354e-05, |
| "loss": 0.3232, |
| "mean_token_accuracy": 0.9161754846572876, |
| "step": 206 |
| }, |
| { |
| "epoch": 1.2111436950146628, |
| "grad_norm": 1.8625830016750662, |
| "learning_rate": 3.921086552116455e-05, |
| "loss": 0.2943, |
| "mean_token_accuracy": 0.9140777736902237, |
| "step": 207 |
| }, |
| { |
| "epoch": 1.217008797653959, |
| "grad_norm": 2.08984197350988, |
| "learning_rate": 3.920079176440288e-05, |
| "loss": 0.2892, |
| "mean_token_accuracy": 0.9188559651374817, |
| "step": 208 |
| }, |
| { |
| "epoch": 1.2228739002932552, |
| "grad_norm": 1.911462834786022, |
| "learning_rate": 3.9190655575714045e-05, |
| "loss": 0.425, |
| "mean_token_accuracy": 0.8878646790981293, |
| "step": 209 |
| }, |
| { |
| "epoch": 1.2287390029325513, |
| "grad_norm": 2.1199749653836246, |
| "learning_rate": 3.918045699188833e-05, |
| "loss": 0.3309, |
| "mean_token_accuracy": 0.9033946841955185, |
| "step": 210 |
| }, |
| { |
| "epoch": 1.2346041055718475, |
| "grad_norm": 1.7772550268734622, |
| "learning_rate": 3.9170196049942474e-05, |
| "loss": 0.2935, |
| "mean_token_accuracy": 0.9201069548726082, |
| "step": 211 |
| }, |
| { |
| "epoch": 1.2404692082111437, |
| "grad_norm": 1.4880613708640376, |
| "learning_rate": 3.915987278711954e-05, |
| "loss": 0.2814, |
| "mean_token_accuracy": 0.9159248098731041, |
| "step": 212 |
| }, |
| { |
| "epoch": 1.2463343108504399, |
| "grad_norm": 1.4341780634467447, |
| "learning_rate": 3.914948724088883e-05, |
| "loss": 0.3993, |
| "mean_token_accuracy": 0.8969456627964973, |
| "step": 213 |
| }, |
| { |
| "epoch": 1.252199413489736, |
| "grad_norm": 1.9915246600304684, |
| "learning_rate": 3.913903944894565e-05, |
| "loss": 0.3357, |
| "mean_token_accuracy": 0.9005481451749802, |
| "step": 214 |
| }, |
| { |
| "epoch": 1.2580645161290323, |
| "grad_norm": 1.580420874953109, |
| "learning_rate": 3.912852944921129e-05, |
| "loss": 0.2969, |
| "mean_token_accuracy": 0.9120687544345856, |
| "step": 215 |
| }, |
| { |
| "epoch": 1.2639296187683284, |
| "grad_norm": 1.750899975898394, |
| "learning_rate": 3.911795727983279e-05, |
| "loss": 0.3287, |
| "mean_token_accuracy": 0.907410055398941, |
| "step": 216 |
| }, |
| { |
| "epoch": 1.2697947214076246, |
| "grad_norm": 1.928943141809165, |
| "learning_rate": 3.910732297918285e-05, |
| "loss": 0.3847, |
| "mean_token_accuracy": 0.8974480405449867, |
| "step": 217 |
| }, |
| { |
| "epoch": 1.2756598240469208, |
| "grad_norm": 2.1252213170886898, |
| "learning_rate": 3.90966265858597e-05, |
| "loss": 0.3873, |
| "mean_token_accuracy": 0.9002740904688835, |
| "step": 218 |
| }, |
| { |
| "epoch": 1.281524926686217, |
| "grad_norm": 2.109343454012867, |
| "learning_rate": 3.908586813868693e-05, |
| "loss": 0.403, |
| "mean_token_accuracy": 0.8951247781515121, |
| "step": 219 |
| }, |
| { |
| "epoch": 1.2873900293255132, |
| "grad_norm": 2.061638595149616, |
| "learning_rate": 3.9075047676713354e-05, |
| "loss": 0.3771, |
| "mean_token_accuracy": 0.896357998251915, |
| "step": 220 |
| }, |
| { |
| "epoch": 1.2932551319648093, |
| "grad_norm": 1.7021693465570895, |
| "learning_rate": 3.9064165239212874e-05, |
| "loss": 0.3778, |
| "mean_token_accuracy": 0.89422857016325, |
| "step": 221 |
| }, |
| { |
| "epoch": 1.2991202346041055, |
| "grad_norm": 1.849147955241084, |
| "learning_rate": 3.905322086568434e-05, |
| "loss": 0.3871, |
| "mean_token_accuracy": 0.8929040059447289, |
| "step": 222 |
| }, |
| { |
| "epoch": 1.3049853372434017, |
| "grad_norm": 2.0252993158406034, |
| "learning_rate": 3.904221459585142e-05, |
| "loss": 0.3396, |
| "mean_token_accuracy": 0.9043144136667252, |
| "step": 223 |
| }, |
| { |
| "epoch": 1.310850439882698, |
| "grad_norm": 1.9166105249433603, |
| "learning_rate": 3.903114646966242e-05, |
| "loss": 0.3879, |
| "mean_token_accuracy": 0.8941874876618385, |
| "step": 224 |
| }, |
| { |
| "epoch": 1.316715542521994, |
| "grad_norm": 1.8159618403624833, |
| "learning_rate": 3.9020016527290166e-05, |
| "loss": 0.3898, |
| "mean_token_accuracy": 0.886252149939537, |
| "step": 225 |
| }, |
| { |
| "epoch": 1.3225806451612903, |
| "grad_norm": 1.8271070306390285, |
| "learning_rate": 3.900882480913185e-05, |
| "loss": 0.2508, |
| "mean_token_accuracy": 0.9200474843382835, |
| "step": 226 |
| }, |
| { |
| "epoch": 1.3284457478005864, |
| "grad_norm": 1.8641984333480377, |
| "learning_rate": 3.899757135580891e-05, |
| "loss": 0.4347, |
| "mean_token_accuracy": 0.8843434602022171, |
| "step": 227 |
| }, |
| { |
| "epoch": 1.3343108504398826, |
| "grad_norm": 1.9751688939339136, |
| "learning_rate": 3.898625620816681e-05, |
| "loss": 0.3196, |
| "mean_token_accuracy": 0.9012826457619667, |
| "step": 228 |
| }, |
| { |
| "epoch": 1.3401759530791788, |
| "grad_norm": 1.7860530094904565, |
| "learning_rate": 3.8974879407275e-05, |
| "loss": 0.4468, |
| "mean_token_accuracy": 0.8767973035573959, |
| "step": 229 |
| }, |
| { |
| "epoch": 1.3460410557184752, |
| "grad_norm": 1.94722176291669, |
| "learning_rate": 3.896344099442663e-05, |
| "loss": 0.3302, |
| "mean_token_accuracy": 0.9074369296431541, |
| "step": 230 |
| }, |
| { |
| "epoch": 1.3519061583577714, |
| "grad_norm": 1.6187074828159356, |
| "learning_rate": 3.895194101113855e-05, |
| "loss": 0.2696, |
| "mean_token_accuracy": 0.9088193848729134, |
| "step": 231 |
| }, |
| { |
| "epoch": 1.3577712609970676, |
| "grad_norm": 2.6096489592144936, |
| "learning_rate": 3.894037949915104e-05, |
| "loss": 0.2944, |
| "mean_token_accuracy": 0.9228176847100258, |
| "step": 232 |
| }, |
| { |
| "epoch": 1.3636363636363638, |
| "grad_norm": 1.5634486259914928, |
| "learning_rate": 3.8928756500427735e-05, |
| "loss": 0.3238, |
| "mean_token_accuracy": 0.8987634629011154, |
| "step": 233 |
| }, |
| { |
| "epoch": 1.36950146627566, |
| "grad_norm": 1.9297888485342156, |
| "learning_rate": 3.89170720571554e-05, |
| "loss": 0.2825, |
| "mean_token_accuracy": 0.919132649898529, |
| "step": 234 |
| }, |
| { |
| "epoch": 1.3753665689149561, |
| "grad_norm": 5.705912737037372, |
| "learning_rate": 3.890532621174387e-05, |
| "loss": 0.309, |
| "mean_token_accuracy": 0.9044925644993782, |
| "step": 235 |
| }, |
| { |
| "epoch": 1.3812316715542523, |
| "grad_norm": 1.8759082661293862, |
| "learning_rate": 3.8893519006825806e-05, |
| "loss": 0.3026, |
| "mean_token_accuracy": 0.9114593118429184, |
| "step": 236 |
| }, |
| { |
| "epoch": 1.3870967741935485, |
| "grad_norm": 3.0350786549552233, |
| "learning_rate": 3.88816504852566e-05, |
| "loss": 0.2832, |
| "mean_token_accuracy": 0.9205159991979599, |
| "step": 237 |
| }, |
| { |
| "epoch": 1.3929618768328447, |
| "grad_norm": 1.8811808391254248, |
| "learning_rate": 3.886972069011419e-05, |
| "loss": 0.495, |
| "mean_token_accuracy": 0.8736753240227699, |
| "step": 238 |
| }, |
| { |
| "epoch": 1.3988269794721409, |
| "grad_norm": 2.326861975246291, |
| "learning_rate": 3.885772966469891e-05, |
| "loss": 0.3113, |
| "mean_token_accuracy": 0.9055031910538673, |
| "step": 239 |
| }, |
| { |
| "epoch": 1.404692082111437, |
| "grad_norm": 1.6166513093632866, |
| "learning_rate": 3.884567745253335e-05, |
| "loss": 0.2422, |
| "mean_token_accuracy": 0.9216142147779465, |
| "step": 240 |
| }, |
| { |
| "epoch": 1.4105571847507332, |
| "grad_norm": 1.6509216370463153, |
| "learning_rate": 3.8833564097362157e-05, |
| "loss": 0.375, |
| "mean_token_accuracy": 0.8933239132165909, |
| "step": 241 |
| }, |
| { |
| "epoch": 1.4164222873900294, |
| "grad_norm": 1.5963842065424707, |
| "learning_rate": 3.8821389643151924e-05, |
| "loss": 0.2731, |
| "mean_token_accuracy": 0.9260216429829597, |
| "step": 242 |
| }, |
| { |
| "epoch": 1.4222873900293256, |
| "grad_norm": 1.7409972319657108, |
| "learning_rate": 3.880915413409102e-05, |
| "loss": 0.2994, |
| "mean_token_accuracy": 0.9160123020410538, |
| "step": 243 |
| }, |
| { |
| "epoch": 1.4281524926686218, |
| "grad_norm": 1.685305669968149, |
| "learning_rate": 3.879685761458938e-05, |
| "loss": 0.3998, |
| "mean_token_accuracy": 0.8791949227452278, |
| "step": 244 |
| }, |
| { |
| "epoch": 1.434017595307918, |
| "grad_norm": 1.714247881724903, |
| "learning_rate": 3.8784500129278405e-05, |
| "loss": 0.2456, |
| "mean_token_accuracy": 0.9248116835951805, |
| "step": 245 |
| }, |
| { |
| "epoch": 1.4398826979472141, |
| "grad_norm": 1.8283775935111375, |
| "learning_rate": 3.877208172301079e-05, |
| "loss": 0.4024, |
| "mean_token_accuracy": 0.8830369934439659, |
| "step": 246 |
| }, |
| { |
| "epoch": 1.4457478005865103, |
| "grad_norm": 1.641693773681782, |
| "learning_rate": 3.875960244086032e-05, |
| "loss": 0.2956, |
| "mean_token_accuracy": 0.9141576886177063, |
| "step": 247 |
| }, |
| { |
| "epoch": 1.4516129032258065, |
| "grad_norm": 1.8072855331044935, |
| "learning_rate": 3.8747062328121756e-05, |
| "loss": 0.3248, |
| "mean_token_accuracy": 0.9176624119281769, |
| "step": 248 |
| }, |
| { |
| "epoch": 1.4574780058651027, |
| "grad_norm": 1.4529714307869996, |
| "learning_rate": 3.873446143031064e-05, |
| "loss": 0.233, |
| "mean_token_accuracy": 0.9335721209645271, |
| "step": 249 |
| }, |
| { |
| "epoch": 1.4633431085043989, |
| "grad_norm": 1.6109952281207667, |
| "learning_rate": 3.872179979316314e-05, |
| "loss": 0.2647, |
| "mean_token_accuracy": 0.9189906045794487, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.469208211143695, |
| "grad_norm": 1.5387664784956696, |
| "learning_rate": 3.870907746263589e-05, |
| "loss": 0.2368, |
| "mean_token_accuracy": 0.9255321696400642, |
| "step": 251 |
| }, |
| { |
| "epoch": 1.4750733137829912, |
| "grad_norm": 1.5682341766556274, |
| "learning_rate": 3.869629448490582e-05, |
| "loss": 0.3074, |
| "mean_token_accuracy": 0.9108378365635872, |
| "step": 252 |
| }, |
| { |
| "epoch": 1.4809384164222874, |
| "grad_norm": 1.605199961656554, |
| "learning_rate": 3.868345090636995e-05, |
| "loss": 0.3372, |
| "mean_token_accuracy": 0.9136556684970856, |
| "step": 253 |
| }, |
| { |
| "epoch": 1.4868035190615836, |
| "grad_norm": 1.702260159704336, |
| "learning_rate": 3.867054677364531e-05, |
| "loss": 0.2964, |
| "mean_token_accuracy": 0.9146860465407372, |
| "step": 254 |
| }, |
| { |
| "epoch": 1.4926686217008798, |
| "grad_norm": 1.6758389465527221, |
| "learning_rate": 3.865758213356868e-05, |
| "loss": 0.3302, |
| "mean_token_accuracy": 0.9049453809857368, |
| "step": 255 |
| }, |
| { |
| "epoch": 1.498533724340176, |
| "grad_norm": 1.8470944243244563, |
| "learning_rate": 3.8644557033196456e-05, |
| "loss": 0.308, |
| "mean_token_accuracy": 0.9096508920192719, |
| "step": 256 |
| }, |
| { |
| "epoch": 1.5043988269794721, |
| "grad_norm": 1.6459334975457287, |
| "learning_rate": 3.8631471519804514e-05, |
| "loss": 0.3409, |
| "mean_token_accuracy": 0.908280074596405, |
| "step": 257 |
| }, |
| { |
| "epoch": 1.5102639296187683, |
| "grad_norm": 1.8846190933749478, |
| "learning_rate": 3.861832564088797e-05, |
| "loss": 0.3908, |
| "mean_token_accuracy": 0.8908302560448647, |
| "step": 258 |
| }, |
| { |
| "epoch": 1.5161290322580645, |
| "grad_norm": 1.8194930732382166, |
| "learning_rate": 3.860511944416105e-05, |
| "loss": 0.237, |
| "mean_token_accuracy": 0.9297190383076668, |
| "step": 259 |
| }, |
| { |
| "epoch": 1.5219941348973607, |
| "grad_norm": 1.4686546503831466, |
| "learning_rate": 3.859185297755693e-05, |
| "loss": 0.2434, |
| "mean_token_accuracy": 0.926492266356945, |
| "step": 260 |
| }, |
| { |
| "epoch": 1.5278592375366569, |
| "grad_norm": 1.4178478581133294, |
| "learning_rate": 3.857852628922751e-05, |
| "loss": 0.2247, |
| "mean_token_accuracy": 0.9361571744084358, |
| "step": 261 |
| }, |
| { |
| "epoch": 1.533724340175953, |
| "grad_norm": 1.8264634652027574, |
| "learning_rate": 3.856513942754329e-05, |
| "loss": 0.2798, |
| "mean_token_accuracy": 0.9201556444168091, |
| "step": 262 |
| }, |
| { |
| "epoch": 1.5395894428152492, |
| "grad_norm": 1.3877603216406522, |
| "learning_rate": 3.8551692441093183e-05, |
| "loss": 0.2084, |
| "mean_token_accuracy": 0.9382101222872734, |
| "step": 263 |
| }, |
| { |
| "epoch": 1.5454545454545454, |
| "grad_norm": 2.1242475529664406, |
| "learning_rate": 3.85381853786843e-05, |
| "loss": 0.3805, |
| "mean_token_accuracy": 0.8912002816796303, |
| "step": 264 |
| }, |
| { |
| "epoch": 1.5513196480938416, |
| "grad_norm": 1.9343373311067464, |
| "learning_rate": 3.852461828934184e-05, |
| "loss": 0.3576, |
| "mean_token_accuracy": 0.9037280976772308, |
| "step": 265 |
| }, |
| { |
| "epoch": 1.5571847507331378, |
| "grad_norm": 1.7197714668657997, |
| "learning_rate": 3.851099122230885e-05, |
| "loss": 0.2661, |
| "mean_token_accuracy": 0.9237689301371574, |
| "step": 266 |
| }, |
| { |
| "epoch": 1.563049853372434, |
| "grad_norm": 1.2968944947332304, |
| "learning_rate": 3.849730422704608e-05, |
| "loss": 0.367, |
| "mean_token_accuracy": 0.9015661999583244, |
| "step": 267 |
| }, |
| { |
| "epoch": 1.5689149560117301, |
| "grad_norm": 1.8354778354820311, |
| "learning_rate": 3.84835573532318e-05, |
| "loss": 0.2307, |
| "mean_token_accuracy": 0.930214174091816, |
| "step": 268 |
| }, |
| { |
| "epoch": 1.5747800586510263, |
| "grad_norm": 1.6095719868962666, |
| "learning_rate": 3.84697506507616e-05, |
| "loss": 0.3754, |
| "mean_token_accuracy": 0.8950481489300728, |
| "step": 269 |
| }, |
| { |
| "epoch": 1.5806451612903225, |
| "grad_norm": 1.8589562104326827, |
| "learning_rate": 3.845588416974824e-05, |
| "loss": 0.3538, |
| "mean_token_accuracy": 0.9128340929746628, |
| "step": 270 |
| }, |
| { |
| "epoch": 1.5865102639296187, |
| "grad_norm": 1.5115174690077389, |
| "learning_rate": 3.844195796052144e-05, |
| "loss": 0.2958, |
| "mean_token_accuracy": 0.9182360097765923, |
| "step": 271 |
| }, |
| { |
| "epoch": 1.5923753665689149, |
| "grad_norm": 1.5391526339443062, |
| "learning_rate": 3.8427972073627724e-05, |
| "loss": 0.4294, |
| "mean_token_accuracy": 0.886161781847477, |
| "step": 272 |
| }, |
| { |
| "epoch": 1.598240469208211, |
| "grad_norm": 1.7890963365765244, |
| "learning_rate": 3.841392655983021e-05, |
| "loss": 0.2038, |
| "mean_token_accuracy": 0.9358106032013893, |
| "step": 273 |
| }, |
| { |
| "epoch": 1.6041055718475072, |
| "grad_norm": 1.0409480351181137, |
| "learning_rate": 3.8399821470108444e-05, |
| "loss": 0.169, |
| "mean_token_accuracy": 0.9508898928761482, |
| "step": 274 |
| }, |
| { |
| "epoch": 1.6099706744868034, |
| "grad_norm": 1.69462838247509, |
| "learning_rate": 3.838565685565819e-05, |
| "loss": 0.4235, |
| "mean_token_accuracy": 0.8907356783747673, |
| "step": 275 |
| }, |
| { |
| "epoch": 1.6158357771260996, |
| "grad_norm": 1.6504210584720351, |
| "learning_rate": 3.8371432767891295e-05, |
| "loss": 0.3019, |
| "mean_token_accuracy": 0.9208194762468338, |
| "step": 276 |
| }, |
| { |
| "epoch": 1.6217008797653958, |
| "grad_norm": 1.5605291392635074, |
| "learning_rate": 3.8357149258435444e-05, |
| "loss": 0.2417, |
| "mean_token_accuracy": 0.9278599768877029, |
| "step": 277 |
| }, |
| { |
| "epoch": 1.627565982404692, |
| "grad_norm": 1.5359970078910663, |
| "learning_rate": 3.8342806379134005e-05, |
| "loss": 0.3813, |
| "mean_token_accuracy": 0.8966976255178452, |
| "step": 278 |
| }, |
| { |
| "epoch": 1.6334310850439882, |
| "grad_norm": 1.6548981878718405, |
| "learning_rate": 3.8328404182045854e-05, |
| "loss": 0.3248, |
| "mean_token_accuracy": 0.9139015227556229, |
| "step": 279 |
| }, |
| { |
| "epoch": 1.6392961876832843, |
| "grad_norm": 1.791651867333591, |
| "learning_rate": 3.831394271944512e-05, |
| "loss": 0.3067, |
| "mean_token_accuracy": 0.9152898713946342, |
| "step": 280 |
| }, |
| { |
| "epoch": 1.6451612903225805, |
| "grad_norm": 1.5338974063867743, |
| "learning_rate": 3.82994220438211e-05, |
| "loss": 0.3007, |
| "mean_token_accuracy": 0.9149986058473587, |
| "step": 281 |
| }, |
| { |
| "epoch": 1.6510263929618767, |
| "grad_norm": 1.6743377942352997, |
| "learning_rate": 3.828484220787797e-05, |
| "loss": 0.313, |
| "mean_token_accuracy": 0.9125666543841362, |
| "step": 282 |
| }, |
| { |
| "epoch": 1.6568914956011729, |
| "grad_norm": 1.87863609348132, |
| "learning_rate": 3.8270203264534644e-05, |
| "loss": 0.4001, |
| "mean_token_accuracy": 0.89353808760643, |
| "step": 283 |
| }, |
| { |
| "epoch": 1.662756598240469, |
| "grad_norm": 1.5221720369596754, |
| "learning_rate": 3.8255505266924585e-05, |
| "loss": 0.2979, |
| "mean_token_accuracy": 0.9145095869898796, |
| "step": 284 |
| }, |
| { |
| "epoch": 1.6686217008797652, |
| "grad_norm": 1.4436482743787307, |
| "learning_rate": 3.824074826839557e-05, |
| "loss": 0.234, |
| "mean_token_accuracy": 0.935015395283699, |
| "step": 285 |
| }, |
| { |
| "epoch": 1.6744868035190614, |
| "grad_norm": 2.0983241426301733, |
| "learning_rate": 3.822593232250956e-05, |
| "loss": 0.4151, |
| "mean_token_accuracy": 0.8874623849987984, |
| "step": 286 |
| }, |
| { |
| "epoch": 1.6803519061583576, |
| "grad_norm": 2.091453827833945, |
| "learning_rate": 3.8211057483042446e-05, |
| "loss": 0.4583, |
| "mean_token_accuracy": 0.8864308521151543, |
| "step": 287 |
| }, |
| { |
| "epoch": 1.6862170087976538, |
| "grad_norm": 1.7623769296533551, |
| "learning_rate": 3.8196123803983895e-05, |
| "loss": 0.3116, |
| "mean_token_accuracy": 0.9158060252666473, |
| "step": 288 |
| }, |
| { |
| "epoch": 1.6920821114369502, |
| "grad_norm": 1.8634816515022323, |
| "learning_rate": 3.818113133953712e-05, |
| "loss": 0.2798, |
| "mean_token_accuracy": 0.9182194173336029, |
| "step": 289 |
| }, |
| { |
| "epoch": 1.6979472140762464, |
| "grad_norm": 1.3844096892784188, |
| "learning_rate": 3.816608014411872e-05, |
| "loss": 0.2108, |
| "mean_token_accuracy": 0.9366880431771278, |
| "step": 290 |
| }, |
| { |
| "epoch": 1.7038123167155426, |
| "grad_norm": 1.374168812023236, |
| "learning_rate": 3.815097027235845e-05, |
| "loss": 0.2938, |
| "mean_token_accuracy": 0.9153807386755943, |
| "step": 291 |
| }, |
| { |
| "epoch": 1.7096774193548387, |
| "grad_norm": 1.7034775235235637, |
| "learning_rate": 3.813580177909906e-05, |
| "loss": 0.2667, |
| "mean_token_accuracy": 0.9222086817026138, |
| "step": 292 |
| }, |
| { |
| "epoch": 1.715542521994135, |
| "grad_norm": 1.3790984180175314, |
| "learning_rate": 3.8120574719396023e-05, |
| "loss": 0.2556, |
| "mean_token_accuracy": 0.9333324581384659, |
| "step": 293 |
| }, |
| { |
| "epoch": 1.721407624633431, |
| "grad_norm": 1.8884841762010651, |
| "learning_rate": 3.810528914851745e-05, |
| "loss": 0.3924, |
| "mean_token_accuracy": 0.8967092782258987, |
| "step": 294 |
| }, |
| { |
| "epoch": 1.7272727272727273, |
| "grad_norm": 1.7491440284079216, |
| "learning_rate": 3.808994512194376e-05, |
| "loss": 0.341, |
| "mean_token_accuracy": 0.8986316025257111, |
| "step": 295 |
| }, |
| { |
| "epoch": 1.7331378299120235, |
| "grad_norm": 1.7932797238017746, |
| "learning_rate": 3.807454269536758e-05, |
| "loss": 0.3458, |
| "mean_token_accuracy": 0.9050753563642502, |
| "step": 296 |
| }, |
| { |
| "epoch": 1.7390029325513197, |
| "grad_norm": 1.6441635146631224, |
| "learning_rate": 3.805908192469351e-05, |
| "loss": 0.2323, |
| "mean_token_accuracy": 0.9215081483125687, |
| "step": 297 |
| }, |
| { |
| "epoch": 1.7448680351906158, |
| "grad_norm": 1.9068409230817305, |
| "learning_rate": 3.80435628660379e-05, |
| "loss": 0.318, |
| "mean_token_accuracy": 0.9142180681228638, |
| "step": 298 |
| }, |
| { |
| "epoch": 1.750733137829912, |
| "grad_norm": 1.5615974684408795, |
| "learning_rate": 3.802798557572867e-05, |
| "loss": 0.3187, |
| "mean_token_accuracy": 0.9167973101139069, |
| "step": 299 |
| }, |
| { |
| "epoch": 1.7565982404692082, |
| "grad_norm": 1.8792330981634289, |
| "learning_rate": 3.801235011030506e-05, |
| "loss": 0.3168, |
| "mean_token_accuracy": 0.9097247943282127, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.7624633431085044, |
| "grad_norm": 1.4882463951833638, |
| "learning_rate": 3.799665652651754e-05, |
| "loss": 0.1745, |
| "mean_token_accuracy": 0.9463199898600578, |
| "step": 301 |
| }, |
| { |
| "epoch": 1.7683284457478006, |
| "grad_norm": 1.3776003810458817, |
| "learning_rate": 3.7980904881327446e-05, |
| "loss": 0.259, |
| "mean_token_accuracy": 0.9295109435915947, |
| "step": 302 |
| }, |
| { |
| "epoch": 1.7741935483870968, |
| "grad_norm": 1.804906347600171, |
| "learning_rate": 3.796509523190691e-05, |
| "loss": 0.2784, |
| "mean_token_accuracy": 0.9167697057127953, |
| "step": 303 |
| }, |
| { |
| "epoch": 1.780058651026393, |
| "grad_norm": 1.269707072306634, |
| "learning_rate": 3.794922763563857e-05, |
| "loss": 0.2092, |
| "mean_token_accuracy": 0.9398507922887802, |
| "step": 304 |
| }, |
| { |
| "epoch": 1.7859237536656891, |
| "grad_norm": 1.8243916364746902, |
| "learning_rate": 3.793330215011538e-05, |
| "loss": 0.3314, |
| "mean_token_accuracy": 0.923354484140873, |
| "step": 305 |
| }, |
| { |
| "epoch": 1.7917888563049853, |
| "grad_norm": 1.7139096688789461, |
| "learning_rate": 3.791731883314043e-05, |
| "loss": 0.2919, |
| "mean_token_accuracy": 0.9158714264631271, |
| "step": 306 |
| }, |
| { |
| "epoch": 1.7976539589442815, |
| "grad_norm": 1.5960616358194517, |
| "learning_rate": 3.790127774272671e-05, |
| "loss": 0.2381, |
| "mean_token_accuracy": 0.9304629862308502, |
| "step": 307 |
| }, |
| { |
| "epoch": 1.8035190615835777, |
| "grad_norm": 1.5533548503357937, |
| "learning_rate": 3.7885178937096884e-05, |
| "loss": 0.3685, |
| "mean_token_accuracy": 0.8978663310408592, |
| "step": 308 |
| }, |
| { |
| "epoch": 1.8093841642228738, |
| "grad_norm": 1.7461610002504417, |
| "learning_rate": 3.7869022474683125e-05, |
| "loss": 0.4383, |
| "mean_token_accuracy": 0.9004004076123238, |
| "step": 309 |
| }, |
| { |
| "epoch": 1.8152492668621703, |
| "grad_norm": 2.06432042277161, |
| "learning_rate": 3.7852808414126876e-05, |
| "loss": 0.352, |
| "mean_token_accuracy": 0.9019398987293243, |
| "step": 310 |
| }, |
| { |
| "epoch": 1.8211143695014664, |
| "grad_norm": 1.4176538924862974, |
| "learning_rate": 3.783653681427861e-05, |
| "loss": 0.2086, |
| "mean_token_accuracy": 0.9427406489849091, |
| "step": 311 |
| }, |
| { |
| "epoch": 1.8269794721407626, |
| "grad_norm": 1.335202318172332, |
| "learning_rate": 3.7820207734197676e-05, |
| "loss": 0.3102, |
| "mean_token_accuracy": 0.9114719554781914, |
| "step": 312 |
| }, |
| { |
| "epoch": 1.8328445747800588, |
| "grad_norm": 1.507155874356392, |
| "learning_rate": 3.780382123315203e-05, |
| "loss": 0.2132, |
| "mean_token_accuracy": 0.9400037527084351, |
| "step": 313 |
| }, |
| { |
| "epoch": 1.838709677419355, |
| "grad_norm": 1.3042920075399829, |
| "learning_rate": 3.778737737061807e-05, |
| "loss": 0.2946, |
| "mean_token_accuracy": 0.9200368896126747, |
| "step": 314 |
| }, |
| { |
| "epoch": 1.8445747800586512, |
| "grad_norm": 1.5791832331088969, |
| "learning_rate": 3.777087620628035e-05, |
| "loss": 0.2362, |
| "mean_token_accuracy": 0.9357219859957695, |
| "step": 315 |
| }, |
| { |
| "epoch": 1.8504398826979473, |
| "grad_norm": 1.5908555105002338, |
| "learning_rate": 3.775431780003145e-05, |
| "loss": 0.2167, |
| "mean_token_accuracy": 0.9437434077262878, |
| "step": 316 |
| }, |
| { |
| "epoch": 1.8563049853372435, |
| "grad_norm": 1.4150651589598287, |
| "learning_rate": 3.7737702211971684e-05, |
| "loss": 0.266, |
| "mean_token_accuracy": 0.9321496710181236, |
| "step": 317 |
| }, |
| { |
| "epoch": 1.8621700879765397, |
| "grad_norm": 2.0256566853788027, |
| "learning_rate": 3.772102950240895e-05, |
| "loss": 0.2481, |
| "mean_token_accuracy": 0.9347328022122383, |
| "step": 318 |
| }, |
| { |
| "epoch": 1.868035190615836, |
| "grad_norm": 1.5023088590721538, |
| "learning_rate": 3.770429973185842e-05, |
| "loss": 0.2938, |
| "mean_token_accuracy": 0.9203558340668678, |
| "step": 319 |
| }, |
| { |
| "epoch": 1.873900293255132, |
| "grad_norm": 1.496439833933689, |
| "learning_rate": 3.768751296104243e-05, |
| "loss": 0.1895, |
| "mean_token_accuracy": 0.9429217278957367, |
| "step": 320 |
| }, |
| { |
| "epoch": 1.8797653958944283, |
| "grad_norm": 1.1444559280831719, |
| "learning_rate": 3.767066925089017e-05, |
| "loss": 0.284, |
| "mean_token_accuracy": 0.9179976284503937, |
| "step": 321 |
| }, |
| { |
| "epoch": 1.8856304985337244, |
| "grad_norm": 1.520002548329364, |
| "learning_rate": 3.765376866253749e-05, |
| "loss": 0.2249, |
| "mean_token_accuracy": 0.9298429787158966, |
| "step": 322 |
| }, |
| { |
| "epoch": 1.8914956011730206, |
| "grad_norm": 1.6152013282405222, |
| "learning_rate": 3.763681125732672e-05, |
| "loss": 0.2711, |
| "mean_token_accuracy": 0.9168659150600433, |
| "step": 323 |
| }, |
| { |
| "epoch": 1.8973607038123168, |
| "grad_norm": 1.6738843600847169, |
| "learning_rate": 3.7619797096806386e-05, |
| "loss": 0.2835, |
| "mean_token_accuracy": 0.920739158987999, |
| "step": 324 |
| }, |
| { |
| "epoch": 1.903225806451613, |
| "grad_norm": 1.468790562074948, |
| "learning_rate": 3.7602726242731016e-05, |
| "loss": 0.3202, |
| "mean_token_accuracy": 0.916345439851284, |
| "step": 325 |
| }, |
| { |
| "epoch": 1.9090909090909092, |
| "grad_norm": 1.540640147913931, |
| "learning_rate": 3.758559875706092e-05, |
| "loss": 0.2337, |
| "mean_token_accuracy": 0.9352636113762856, |
| "step": 326 |
| }, |
| { |
| "epoch": 1.9149560117302054, |
| "grad_norm": 1.2452611699041465, |
| "learning_rate": 3.756841470196195e-05, |
| "loss": 0.321, |
| "mean_token_accuracy": 0.9145397022366524, |
| "step": 327 |
| }, |
| { |
| "epoch": 1.9208211143695015, |
| "grad_norm": 1.4066519231199601, |
| "learning_rate": 3.7551174139805284e-05, |
| "loss": 0.3281, |
| "mean_token_accuracy": 0.9094234853982925, |
| "step": 328 |
| }, |
| { |
| "epoch": 1.9266862170087977, |
| "grad_norm": 1.5838261059071022, |
| "learning_rate": 3.75338771331672e-05, |
| "loss": 0.3144, |
| "mean_token_accuracy": 0.910196490585804, |
| "step": 329 |
| }, |
| { |
| "epoch": 1.932551319648094, |
| "grad_norm": 1.4176124121116533, |
| "learning_rate": 3.7516523744828856e-05, |
| "loss": 0.3585, |
| "mean_token_accuracy": 0.9048479348421097, |
| "step": 330 |
| }, |
| { |
| "epoch": 1.93841642228739, |
| "grad_norm": 1.6180761569415234, |
| "learning_rate": 3.7499114037776036e-05, |
| "loss": 0.2809, |
| "mean_token_accuracy": 0.9143272861838341, |
| "step": 331 |
| }, |
| { |
| "epoch": 1.9442815249266863, |
| "grad_norm": 1.6370252877103721, |
| "learning_rate": 3.748164807519894e-05, |
| "loss": 0.4283, |
| "mean_token_accuracy": 0.8924917504191399, |
| "step": 332 |
| }, |
| { |
| "epoch": 1.9501466275659824, |
| "grad_norm": 2.0716920896437254, |
| "learning_rate": 3.746412592049197e-05, |
| "loss": 0.3132, |
| "mean_token_accuracy": 0.9136724919080734, |
| "step": 333 |
| }, |
| { |
| "epoch": 1.9560117302052786, |
| "grad_norm": 1.340735087489091, |
| "learning_rate": 3.7446547637253464e-05, |
| "loss": 0.2091, |
| "mean_token_accuracy": 0.9418945610523224, |
| "step": 334 |
| }, |
| { |
| "epoch": 1.9618768328445748, |
| "grad_norm": 1.6719209132212014, |
| "learning_rate": 3.742891328928549e-05, |
| "loss": 0.2879, |
| "mean_token_accuracy": 0.9235949739813805, |
| "step": 335 |
| }, |
| { |
| "epoch": 1.967741935483871, |
| "grad_norm": 1.147281989168185, |
| "learning_rate": 3.74112229405936e-05, |
| "loss": 0.2679, |
| "mean_token_accuracy": 0.9211752265691757, |
| "step": 336 |
| }, |
| { |
| "epoch": 1.9736070381231672, |
| "grad_norm": 1.3481384626672739, |
| "learning_rate": 3.739347665538664e-05, |
| "loss": 0.2892, |
| "mean_token_accuracy": 0.9232519641518593, |
| "step": 337 |
| }, |
| { |
| "epoch": 1.9794721407624634, |
| "grad_norm": 1.62371246747971, |
| "learning_rate": 3.7375674498076445e-05, |
| "loss": 0.3896, |
| "mean_token_accuracy": 0.8951458856463432, |
| "step": 338 |
| }, |
| { |
| "epoch": 1.9853372434017595, |
| "grad_norm": 1.6604679516789678, |
| "learning_rate": 3.7357816533277646e-05, |
| "loss": 0.2822, |
| "mean_token_accuracy": 0.9289601370692253, |
| "step": 339 |
| }, |
| { |
| "epoch": 1.9912023460410557, |
| "grad_norm": 1.4263291403576979, |
| "learning_rate": 3.733990282580745e-05, |
| "loss": 0.2715, |
| "mean_token_accuracy": 0.9229650124907494, |
| "step": 340 |
| }, |
| { |
| "epoch": 1.997067448680352, |
| "grad_norm": 1.747667099197608, |
| "learning_rate": 3.732193344068539e-05, |
| "loss": 0.307, |
| "mean_token_accuracy": 0.9177920147776604, |
| "step": 341 |
| }, |
| { |
| "epoch": 2.0, |
| "grad_norm": 2.381256341303474, |
| "learning_rate": 3.7303908443133054e-05, |
| "loss": 0.1861, |
| "mean_token_accuracy": 0.9418904036283493, |
| "step": 342 |
| }, |
| { |
| "epoch": 2.005865102639296, |
| "grad_norm": 1.4058318833471946, |
| "learning_rate": 3.728582789857393e-05, |
| "loss": 0.1791, |
| "mean_token_accuracy": 0.95208640396595, |
| "step": 343 |
| }, |
| { |
| "epoch": 2.0117302052785924, |
| "grad_norm": 1.3080268747508232, |
| "learning_rate": 3.726769187263308e-05, |
| "loss": 0.2021, |
| "mean_token_accuracy": 0.9402620419859886, |
| "step": 344 |
| }, |
| { |
| "epoch": 2.0175953079178885, |
| "grad_norm": 1.1752970803269882, |
| "learning_rate": 3.724950043113695e-05, |
| "loss": 0.1354, |
| "mean_token_accuracy": 0.9612007439136505, |
| "step": 345 |
| }, |
| { |
| "epoch": 2.0234604105571847, |
| "grad_norm": 1.2121178056268758, |
| "learning_rate": 3.723125364011313e-05, |
| "loss": 0.1272, |
| "mean_token_accuracy": 0.9641102254390717, |
| "step": 346 |
| }, |
| { |
| "epoch": 2.029325513196481, |
| "grad_norm": 1.5579896750905702, |
| "learning_rate": 3.7212951565790094e-05, |
| "loss": 0.1594, |
| "mean_token_accuracy": 0.9491528794169426, |
| "step": 347 |
| }, |
| { |
| "epoch": 2.035190615835777, |
| "grad_norm": 1.6099605117684852, |
| "learning_rate": 3.7194594274597e-05, |
| "loss": 0.1617, |
| "mean_token_accuracy": 0.9526640698313713, |
| "step": 348 |
| }, |
| { |
| "epoch": 2.0410557184750733, |
| "grad_norm": 1.5932197664707426, |
| "learning_rate": 3.7176181833163385e-05, |
| "loss": 0.1908, |
| "mean_token_accuracy": 0.9443105757236481, |
| "step": 349 |
| }, |
| { |
| "epoch": 2.0469208211143695, |
| "grad_norm": 1.418900526462659, |
| "learning_rate": 3.7157714308318966e-05, |
| "loss": 0.1557, |
| "mean_token_accuracy": 0.9594366997480392, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.0527859237536656, |
| "grad_norm": 1.3139191474546121, |
| "learning_rate": 3.713919176709343e-05, |
| "loss": 0.1671, |
| "mean_token_accuracy": 0.9532913491129875, |
| "step": 351 |
| }, |
| { |
| "epoch": 2.058651026392962, |
| "grad_norm": 1.1508507293987567, |
| "learning_rate": 3.712061427671609e-05, |
| "loss": 0.1363, |
| "mean_token_accuracy": 0.9612403735518456, |
| "step": 352 |
| }, |
| { |
| "epoch": 2.064516129032258, |
| "grad_norm": 1.5612158263654403, |
| "learning_rate": 3.710198190461575e-05, |
| "loss": 0.1613, |
| "mean_token_accuracy": 0.9548765048384666, |
| "step": 353 |
| }, |
| { |
| "epoch": 2.070381231671554, |
| "grad_norm": 1.2155961492327827, |
| "learning_rate": 3.7083294718420394e-05, |
| "loss": 0.1573, |
| "mean_token_accuracy": 0.951531894505024, |
| "step": 354 |
| }, |
| { |
| "epoch": 2.0762463343108504, |
| "grad_norm": 1.5294208187687017, |
| "learning_rate": 3.706455278595696e-05, |
| "loss": 0.1628, |
| "mean_token_accuracy": 0.9525769129395485, |
| "step": 355 |
| }, |
| { |
| "epoch": 2.0821114369501466, |
| "grad_norm": 1.482122437822726, |
| "learning_rate": 3.7045756175251086e-05, |
| "loss": 0.1678, |
| "mean_token_accuracy": 0.9500371441245079, |
| "step": 356 |
| }, |
| { |
| "epoch": 2.0879765395894427, |
| "grad_norm": 1.1697605549768837, |
| "learning_rate": 3.7026904954526884e-05, |
| "loss": 0.1359, |
| "mean_token_accuracy": 0.9565827995538712, |
| "step": 357 |
| }, |
| { |
| "epoch": 2.093841642228739, |
| "grad_norm": 1.2020120209369713, |
| "learning_rate": 3.7007999192206676e-05, |
| "loss": 0.1433, |
| "mean_token_accuracy": 0.9575584605336189, |
| "step": 358 |
| }, |
| { |
| "epoch": 2.099706744868035, |
| "grad_norm": 1.144292059243363, |
| "learning_rate": 3.698903895691073e-05, |
| "loss": 0.1611, |
| "mean_token_accuracy": 0.9512758925557137, |
| "step": 359 |
| }, |
| { |
| "epoch": 2.1055718475073313, |
| "grad_norm": 1.4488296727051815, |
| "learning_rate": 3.697002431745706e-05, |
| "loss": 0.1646, |
| "mean_token_accuracy": 0.9537394344806671, |
| "step": 360 |
| }, |
| { |
| "epoch": 2.1114369501466275, |
| "grad_norm": 1.311459494656687, |
| "learning_rate": 3.695095534286111e-05, |
| "loss": 0.1752, |
| "mean_token_accuracy": 0.9506743401288986, |
| "step": 361 |
| }, |
| { |
| "epoch": 2.1173020527859236, |
| "grad_norm": 1.1579677983869936, |
| "learning_rate": 3.693183210233557e-05, |
| "loss": 0.1485, |
| "mean_token_accuracy": 0.9572027623653412, |
| "step": 362 |
| }, |
| { |
| "epoch": 2.12316715542522, |
| "grad_norm": 1.3670234083261403, |
| "learning_rate": 3.691265466529007e-05, |
| "loss": 0.1597, |
| "mean_token_accuracy": 0.9484404474496841, |
| "step": 363 |
| }, |
| { |
| "epoch": 2.129032258064516, |
| "grad_norm": 1.198713935476129, |
| "learning_rate": 3.689342310133097e-05, |
| "loss": 0.1412, |
| "mean_token_accuracy": 0.9606487452983856, |
| "step": 364 |
| }, |
| { |
| "epoch": 2.134897360703812, |
| "grad_norm": 1.5849456974588698, |
| "learning_rate": 3.687413748026108e-05, |
| "loss": 0.1752, |
| "mean_token_accuracy": 0.9527452364563942, |
| "step": 365 |
| }, |
| { |
| "epoch": 2.1407624633431084, |
| "grad_norm": 1.1717821506314905, |
| "learning_rate": 3.68547978720794e-05, |
| "loss": 0.1506, |
| "mean_token_accuracy": 0.9555543065071106, |
| "step": 366 |
| }, |
| { |
| "epoch": 2.1466275659824046, |
| "grad_norm": 1.2840089722257935, |
| "learning_rate": 3.683540434698093e-05, |
| "loss": 0.158, |
| "mean_token_accuracy": 0.9536146819591522, |
| "step": 367 |
| }, |
| { |
| "epoch": 2.1524926686217007, |
| "grad_norm": 1.3393472371316106, |
| "learning_rate": 3.681595697535629e-05, |
| "loss": 0.1443, |
| "mean_token_accuracy": 0.959295816719532, |
| "step": 368 |
| }, |
| { |
| "epoch": 2.158357771260997, |
| "grad_norm": 1.2426306397717, |
| "learning_rate": 3.6796455827791614e-05, |
| "loss": 0.1314, |
| "mean_token_accuracy": 0.9598246365785599, |
| "step": 369 |
| }, |
| { |
| "epoch": 2.164222873900293, |
| "grad_norm": 1.4126630090119772, |
| "learning_rate": 3.677690097506819e-05, |
| "loss": 0.1659, |
| "mean_token_accuracy": 0.9537074118852615, |
| "step": 370 |
| }, |
| { |
| "epoch": 2.1700879765395893, |
| "grad_norm": 1.3683138743411407, |
| "learning_rate": 3.6757292488162224e-05, |
| "loss": 0.166, |
| "mean_token_accuracy": 0.951523669064045, |
| "step": 371 |
| }, |
| { |
| "epoch": 2.1759530791788855, |
| "grad_norm": 1.4416888125441545, |
| "learning_rate": 3.673763043824461e-05, |
| "loss": 0.1892, |
| "mean_token_accuracy": 0.9457840546965599, |
| "step": 372 |
| }, |
| { |
| "epoch": 2.1818181818181817, |
| "grad_norm": 1.394980107167206, |
| "learning_rate": 3.671791489668065e-05, |
| "loss": 0.1634, |
| "mean_token_accuracy": 0.9523271024227142, |
| "step": 373 |
| }, |
| { |
| "epoch": 2.187683284457478, |
| "grad_norm": 1.2232114963409995, |
| "learning_rate": 3.6698145935029794e-05, |
| "loss": 0.1403, |
| "mean_token_accuracy": 0.9606116563081741, |
| "step": 374 |
| }, |
| { |
| "epoch": 2.193548387096774, |
| "grad_norm": 1.4676627974529237, |
| "learning_rate": 3.66783236250454e-05, |
| "loss": 0.1568, |
| "mean_token_accuracy": 0.9536681324243546, |
| "step": 375 |
| }, |
| { |
| "epoch": 2.19941348973607, |
| "grad_norm": 1.454629264354781, |
| "learning_rate": 3.665844803867443e-05, |
| "loss": 0.1879, |
| "mean_token_accuracy": 0.948579914867878, |
| "step": 376 |
| }, |
| { |
| "epoch": 2.2052785923753664, |
| "grad_norm": 1.449142524225023, |
| "learning_rate": 3.663851924805725e-05, |
| "loss": 0.1754, |
| "mean_token_accuracy": 0.9484867602586746, |
| "step": 377 |
| }, |
| { |
| "epoch": 2.2111436950146626, |
| "grad_norm": 1.2527495507514164, |
| "learning_rate": 3.66185373255273e-05, |
| "loss": 0.1642, |
| "mean_token_accuracy": 0.949437327682972, |
| "step": 378 |
| }, |
| { |
| "epoch": 2.2170087976539588, |
| "grad_norm": 1.0280532148483927, |
| "learning_rate": 3.6598502343610906e-05, |
| "loss": 0.1376, |
| "mean_token_accuracy": 0.9621856659650803, |
| "step": 379 |
| }, |
| { |
| "epoch": 2.222873900293255, |
| "grad_norm": 1.5389105332308326, |
| "learning_rate": 3.657841437502697e-05, |
| "loss": 0.2034, |
| "mean_token_accuracy": 0.9333431124687195, |
| "step": 380 |
| }, |
| { |
| "epoch": 2.228739002932551, |
| "grad_norm": 1.3670480368678344, |
| "learning_rate": 3.6558273492686686e-05, |
| "loss": 0.1718, |
| "mean_token_accuracy": 0.9464050829410553, |
| "step": 381 |
| }, |
| { |
| "epoch": 2.2346041055718473, |
| "grad_norm": 1.183493824096973, |
| "learning_rate": 3.6538079769693334e-05, |
| "loss": 0.1427, |
| "mean_token_accuracy": 0.9561670497059822, |
| "step": 382 |
| }, |
| { |
| "epoch": 2.2404692082111435, |
| "grad_norm": 1.0132265198889023, |
| "learning_rate": 3.6517833279341954e-05, |
| "loss": 0.1216, |
| "mean_token_accuracy": 0.9647147804498672, |
| "step": 383 |
| }, |
| { |
| "epoch": 2.2463343108504397, |
| "grad_norm": 1.2169060218138956, |
| "learning_rate": 3.649753409511916e-05, |
| "loss": 0.1347, |
| "mean_token_accuracy": 0.9609787911176682, |
| "step": 384 |
| }, |
| { |
| "epoch": 2.252199413489736, |
| "grad_norm": 1.467320488504986, |
| "learning_rate": 3.6477182290702766e-05, |
| "loss": 0.1898, |
| "mean_token_accuracy": 0.945230670273304, |
| "step": 385 |
| }, |
| { |
| "epoch": 2.258064516129032, |
| "grad_norm": 1.3016584136231526, |
| "learning_rate": 3.645677793996161e-05, |
| "loss": 0.1682, |
| "mean_token_accuracy": 0.9491082802414894, |
| "step": 386 |
| }, |
| { |
| "epoch": 2.263929618768328, |
| "grad_norm": 1.285509412490406, |
| "learning_rate": 3.643632111695525e-05, |
| "loss": 0.1583, |
| "mean_token_accuracy": 0.9523500502109528, |
| "step": 387 |
| }, |
| { |
| "epoch": 2.2697947214076244, |
| "grad_norm": 1.3664830453923649, |
| "learning_rate": 3.6415811895933685e-05, |
| "loss": 0.1749, |
| "mean_token_accuracy": 0.9494151324033737, |
| "step": 388 |
| }, |
| { |
| "epoch": 2.2756598240469206, |
| "grad_norm": 1.1957263297883518, |
| "learning_rate": 3.639525035133712e-05, |
| "loss": 0.1299, |
| "mean_token_accuracy": 0.964408628642559, |
| "step": 389 |
| }, |
| { |
| "epoch": 2.281524926686217, |
| "grad_norm": 1.4050014432096367, |
| "learning_rate": 3.637463655779563e-05, |
| "loss": 0.1712, |
| "mean_token_accuracy": 0.951262354850769, |
| "step": 390 |
| }, |
| { |
| "epoch": 2.2873900293255134, |
| "grad_norm": 1.2409827279857322, |
| "learning_rate": 3.6353970590128975e-05, |
| "loss": 0.1535, |
| "mean_token_accuracy": 0.9573537707328796, |
| "step": 391 |
| }, |
| { |
| "epoch": 2.2932551319648096, |
| "grad_norm": 1.1811796197757145, |
| "learning_rate": 3.633325252334628e-05, |
| "loss": 0.1593, |
| "mean_token_accuracy": 0.9544741660356522, |
| "step": 392 |
| }, |
| { |
| "epoch": 2.2991202346041058, |
| "grad_norm": 1.4371670107191854, |
| "learning_rate": 3.6312482432645746e-05, |
| "loss": 0.1796, |
| "mean_token_accuracy": 0.9452351406216621, |
| "step": 393 |
| }, |
| { |
| "epoch": 2.304985337243402, |
| "grad_norm": 1.3934811764793158, |
| "learning_rate": 3.6291660393414414e-05, |
| "loss": 0.1535, |
| "mean_token_accuracy": 0.9559235870838165, |
| "step": 394 |
| }, |
| { |
| "epoch": 2.310850439882698, |
| "grad_norm": 1.4259479703893028, |
| "learning_rate": 3.6270786481227885e-05, |
| "loss": 0.1751, |
| "mean_token_accuracy": 0.9490588009357452, |
| "step": 395 |
| }, |
| { |
| "epoch": 2.3167155425219943, |
| "grad_norm": 1.3992750205909668, |
| "learning_rate": 3.624986077185003e-05, |
| "loss": 0.1763, |
| "mean_token_accuracy": 0.9504696577787399, |
| "step": 396 |
| }, |
| { |
| "epoch": 2.3225806451612905, |
| "grad_norm": 1.1506772929960787, |
| "learning_rate": 3.622888334123272e-05, |
| "loss": 0.1445, |
| "mean_token_accuracy": 0.9598350897431374, |
| "step": 397 |
| }, |
| { |
| "epoch": 2.3284457478005867, |
| "grad_norm": 1.2826340913795922, |
| "learning_rate": 3.620785426551555e-05, |
| "loss": 0.154, |
| "mean_token_accuracy": 0.9541028887033463, |
| "step": 398 |
| }, |
| { |
| "epoch": 2.334310850439883, |
| "grad_norm": 1.154037385683219, |
| "learning_rate": 3.618677362102558e-05, |
| "loss": 0.1237, |
| "mean_token_accuracy": 0.9641017764806747, |
| "step": 399 |
| }, |
| { |
| "epoch": 2.340175953079179, |
| "grad_norm": 1.5501617825015497, |
| "learning_rate": 3.616564148427703e-05, |
| "loss": 0.1634, |
| "mean_token_accuracy": 0.950783371925354, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.346041055718475, |
| "grad_norm": 1.3857185206015648, |
| "learning_rate": 3.614445793197103e-05, |
| "loss": 0.1666, |
| "mean_token_accuracy": 0.9557419568300247, |
| "step": 401 |
| }, |
| { |
| "epoch": 2.3519061583577714, |
| "grad_norm": 1.4872535829714033, |
| "learning_rate": 3.61232230409953e-05, |
| "loss": 0.1606, |
| "mean_token_accuracy": 0.9534048959612846, |
| "step": 402 |
| }, |
| { |
| "epoch": 2.3577712609970676, |
| "grad_norm": 1.3796518663478101, |
| "learning_rate": 3.6101936888423936e-05, |
| "loss": 0.1766, |
| "mean_token_accuracy": 0.9547050073742867, |
| "step": 403 |
| }, |
| { |
| "epoch": 2.3636363636363638, |
| "grad_norm": 1.1751577653503666, |
| "learning_rate": 3.6080599551517076e-05, |
| "loss": 0.1601, |
| "mean_token_accuracy": 0.954358346760273, |
| "step": 404 |
| }, |
| { |
| "epoch": 2.36950146627566, |
| "grad_norm": 1.3861933824324206, |
| "learning_rate": 3.605921110772063e-05, |
| "loss": 0.17, |
| "mean_token_accuracy": 0.9526757672429085, |
| "step": 405 |
| }, |
| { |
| "epoch": 2.375366568914956, |
| "grad_norm": 1.3179185241316302, |
| "learning_rate": 3.603777163466601e-05, |
| "loss": 0.1599, |
| "mean_token_accuracy": 0.9561528638005257, |
| "step": 406 |
| }, |
| { |
| "epoch": 2.3812316715542523, |
| "grad_norm": 1.209038746705086, |
| "learning_rate": 3.6016281210169844e-05, |
| "loss": 0.1734, |
| "mean_token_accuracy": 0.9518474340438843, |
| "step": 407 |
| }, |
| { |
| "epoch": 2.3870967741935485, |
| "grad_norm": 1.3778876028119813, |
| "learning_rate": 3.599473991223369e-05, |
| "loss": 0.168, |
| "mean_token_accuracy": 0.9560379460453987, |
| "step": 408 |
| }, |
| { |
| "epoch": 2.3929618768328447, |
| "grad_norm": 1.1460376456761232, |
| "learning_rate": 3.5973147819043765e-05, |
| "loss": 0.1727, |
| "mean_token_accuracy": 0.9465153738856316, |
| "step": 409 |
| }, |
| { |
| "epoch": 2.398826979472141, |
| "grad_norm": 1.2468196399221245, |
| "learning_rate": 3.595150500897065e-05, |
| "loss": 0.1954, |
| "mean_token_accuracy": 0.9417481794953346, |
| "step": 410 |
| }, |
| { |
| "epoch": 2.404692082111437, |
| "grad_norm": 1.291756928304674, |
| "learning_rate": 3.5929811560569e-05, |
| "loss": 0.1736, |
| "mean_token_accuracy": 0.9531151354312897, |
| "step": 411 |
| }, |
| { |
| "epoch": 2.410557184750733, |
| "grad_norm": 0.9431878971402365, |
| "learning_rate": 3.590806755257726e-05, |
| "loss": 0.1344, |
| "mean_token_accuracy": 0.956610195338726, |
| "step": 412 |
| }, |
| { |
| "epoch": 2.4164222873900294, |
| "grad_norm": 1.1558042696519284, |
| "learning_rate": 3.5886273063917426e-05, |
| "loss": 0.1494, |
| "mean_token_accuracy": 0.951548233628273, |
| "step": 413 |
| }, |
| { |
| "epoch": 2.4222873900293256, |
| "grad_norm": 1.5001844599940708, |
| "learning_rate": 3.586442817369467e-05, |
| "loss": 0.1635, |
| "mean_token_accuracy": 0.9464687779545784, |
| "step": 414 |
| }, |
| { |
| "epoch": 2.4281524926686218, |
| "grad_norm": 1.0155866534384104, |
| "learning_rate": 3.5842532961197114e-05, |
| "loss": 0.1273, |
| "mean_token_accuracy": 0.9602777808904648, |
| "step": 415 |
| }, |
| { |
| "epoch": 2.434017595307918, |
| "grad_norm": 1.5871630279548767, |
| "learning_rate": 3.582058750589555e-05, |
| "loss": 0.1898, |
| "mean_token_accuracy": 0.9440827742218971, |
| "step": 416 |
| }, |
| { |
| "epoch": 2.439882697947214, |
| "grad_norm": 1.6902190906292036, |
| "learning_rate": 3.579859188744311e-05, |
| "loss": 0.2219, |
| "mean_token_accuracy": 0.9334882199764252, |
| "step": 417 |
| }, |
| { |
| "epoch": 2.4457478005865103, |
| "grad_norm": 1.5061195306058557, |
| "learning_rate": 3.5776546185675014e-05, |
| "loss": 0.1789, |
| "mean_token_accuracy": 0.9478380531072617, |
| "step": 418 |
| }, |
| { |
| "epoch": 2.4516129032258065, |
| "grad_norm": 1.5587729299927646, |
| "learning_rate": 3.5754450480608244e-05, |
| "loss": 0.1854, |
| "mean_token_accuracy": 0.9462536200881004, |
| "step": 419 |
| }, |
| { |
| "epoch": 2.4574780058651027, |
| "grad_norm": 1.4376717265649912, |
| "learning_rate": 3.5732304852441294e-05, |
| "loss": 0.1903, |
| "mean_token_accuracy": 0.9399577379226685, |
| "step": 420 |
| }, |
| { |
| "epoch": 2.463343108504399, |
| "grad_norm": 1.6157233488459077, |
| "learning_rate": 3.571010938155386e-05, |
| "loss": 0.2223, |
| "mean_token_accuracy": 0.9368812292814255, |
| "step": 421 |
| }, |
| { |
| "epoch": 2.469208211143695, |
| "grad_norm": 1.5802906558158325, |
| "learning_rate": 3.5687864148506515e-05, |
| "loss": 0.1722, |
| "mean_token_accuracy": 0.9450098648667336, |
| "step": 422 |
| }, |
| { |
| "epoch": 2.4750733137829912, |
| "grad_norm": 1.676334985706252, |
| "learning_rate": 3.566556923404048e-05, |
| "loss": 0.1412, |
| "mean_token_accuracy": 0.9557937532663345, |
| "step": 423 |
| }, |
| { |
| "epoch": 2.4809384164222874, |
| "grad_norm": 1.127094474337832, |
| "learning_rate": 3.5643224719077294e-05, |
| "loss": 0.1393, |
| "mean_token_accuracy": 0.9604131132364273, |
| "step": 424 |
| }, |
| { |
| "epoch": 2.4868035190615836, |
| "grad_norm": 1.3114913834919428, |
| "learning_rate": 3.5620830684718515e-05, |
| "loss": 0.1644, |
| "mean_token_accuracy": 0.9522961899638176, |
| "step": 425 |
| }, |
| { |
| "epoch": 2.4926686217008798, |
| "grad_norm": 1.1702325818953316, |
| "learning_rate": 3.5598387212245456e-05, |
| "loss": 0.1488, |
| "mean_token_accuracy": 0.9550611451268196, |
| "step": 426 |
| }, |
| { |
| "epoch": 2.498533724340176, |
| "grad_norm": 1.3403047895969575, |
| "learning_rate": 3.5575894383118846e-05, |
| "loss": 0.1787, |
| "mean_token_accuracy": 0.9506218433380127, |
| "step": 427 |
| }, |
| { |
| "epoch": 2.504398826979472, |
| "grad_norm": 1.2216800382995856, |
| "learning_rate": 3.5553352278978574e-05, |
| "loss": 0.1558, |
| "mean_token_accuracy": 0.9495013952255249, |
| "step": 428 |
| }, |
| { |
| "epoch": 2.5102639296187683, |
| "grad_norm": 1.243593690786214, |
| "learning_rate": 3.553076098164337e-05, |
| "loss": 0.1425, |
| "mean_token_accuracy": 0.9575006663799286, |
| "step": 429 |
| }, |
| { |
| "epoch": 2.5161290322580645, |
| "grad_norm": 1.1984832556836194, |
| "learning_rate": 3.5508120573110516e-05, |
| "loss": 0.1614, |
| "mean_token_accuracy": 0.9521933421492577, |
| "step": 430 |
| }, |
| { |
| "epoch": 2.5219941348973607, |
| "grad_norm": 1.190960324660938, |
| "learning_rate": 3.548543113555557e-05, |
| "loss": 0.1304, |
| "mean_token_accuracy": 0.9650034531950951, |
| "step": 431 |
| }, |
| { |
| "epoch": 2.527859237536657, |
| "grad_norm": 1.2663063521365974, |
| "learning_rate": 3.5462692751332014e-05, |
| "loss": 0.1505, |
| "mean_token_accuracy": 0.9575837999582291, |
| "step": 432 |
| }, |
| { |
| "epoch": 2.533724340175953, |
| "grad_norm": 1.0193172996429314, |
| "learning_rate": 3.5439905502970996e-05, |
| "loss": 0.1106, |
| "mean_token_accuracy": 0.9644302129745483, |
| "step": 433 |
| }, |
| { |
| "epoch": 2.5395894428152492, |
| "grad_norm": 1.369428546273513, |
| "learning_rate": 3.541706947318103e-05, |
| "loss": 0.1645, |
| "mean_token_accuracy": 0.954724870622158, |
| "step": 434 |
| }, |
| { |
| "epoch": 2.5454545454545454, |
| "grad_norm": 1.483217761683716, |
| "learning_rate": 3.539418474484768e-05, |
| "loss": 0.1845, |
| "mean_token_accuracy": 0.9467028453946114, |
| "step": 435 |
| }, |
| { |
| "epoch": 2.5513196480938416, |
| "grad_norm": 1.4574276394557277, |
| "learning_rate": 3.537125140103327e-05, |
| "loss": 0.1648, |
| "mean_token_accuracy": 0.9520954340696335, |
| "step": 436 |
| }, |
| { |
| "epoch": 2.557184750733138, |
| "grad_norm": 1.1343411307366602, |
| "learning_rate": 3.534826952497657e-05, |
| "loss": 0.1405, |
| "mean_token_accuracy": 0.9605788439512253, |
| "step": 437 |
| }, |
| { |
| "epoch": 2.563049853372434, |
| "grad_norm": 1.514912796637678, |
| "learning_rate": 3.5325239200092505e-05, |
| "loss": 0.1757, |
| "mean_token_accuracy": 0.9462239667773247, |
| "step": 438 |
| }, |
| { |
| "epoch": 2.56891495601173, |
| "grad_norm": 1.18115144712489, |
| "learning_rate": 3.5302160509971866e-05, |
| "loss": 0.1685, |
| "mean_token_accuracy": 0.9481217116117477, |
| "step": 439 |
| }, |
| { |
| "epoch": 2.5747800586510263, |
| "grad_norm": 1.4046582203069407, |
| "learning_rate": 3.5279033538380974e-05, |
| "loss": 0.1703, |
| "mean_token_accuracy": 0.951741062104702, |
| "step": 440 |
| }, |
| { |
| "epoch": 2.5806451612903225, |
| "grad_norm": 1.0803369653160437, |
| "learning_rate": 3.5255858369261385e-05, |
| "loss": 0.1139, |
| "mean_token_accuracy": 0.9662863165140152, |
| "step": 441 |
| }, |
| { |
| "epoch": 2.5865102639296187, |
| "grad_norm": 1.5965941102064563, |
| "learning_rate": 3.523263508672961e-05, |
| "loss": 0.1896, |
| "mean_token_accuracy": 0.9497494995594025, |
| "step": 442 |
| }, |
| { |
| "epoch": 2.592375366568915, |
| "grad_norm": 1.1603543822071827, |
| "learning_rate": 3.520936377507679e-05, |
| "loss": 0.1526, |
| "mean_token_accuracy": 0.9524945765733719, |
| "step": 443 |
| }, |
| { |
| "epoch": 2.598240469208211, |
| "grad_norm": 1.4268486498262112, |
| "learning_rate": 3.5186044518768376e-05, |
| "loss": 0.1856, |
| "mean_token_accuracy": 0.9400829747319221, |
| "step": 444 |
| }, |
| { |
| "epoch": 2.6041055718475072, |
| "grad_norm": 1.3811688946855898, |
| "learning_rate": 3.5162677402443864e-05, |
| "loss": 0.1716, |
| "mean_token_accuracy": 0.9469016790390015, |
| "step": 445 |
| }, |
| { |
| "epoch": 2.6099706744868034, |
| "grad_norm": 1.3500359157080903, |
| "learning_rate": 3.513926251091644e-05, |
| "loss": 0.168, |
| "mean_token_accuracy": 0.9493364244699478, |
| "step": 446 |
| }, |
| { |
| "epoch": 2.6158357771260996, |
| "grad_norm": 1.2057292019423687, |
| "learning_rate": 3.51157999291727e-05, |
| "loss": 0.1643, |
| "mean_token_accuracy": 0.9480642750859261, |
| "step": 447 |
| }, |
| { |
| "epoch": 2.621700879765396, |
| "grad_norm": 1.6243160945531778, |
| "learning_rate": 3.509228974237235e-05, |
| "loss": 0.2073, |
| "mean_token_accuracy": 0.9356926083564758, |
| "step": 448 |
| }, |
| { |
| "epoch": 2.627565982404692, |
| "grad_norm": 1.2687211559386322, |
| "learning_rate": 3.506873203584787e-05, |
| "loss": 0.1671, |
| "mean_token_accuracy": 0.9515552073717117, |
| "step": 449 |
| }, |
| { |
| "epoch": 2.633431085043988, |
| "grad_norm": 0.9855010264474293, |
| "learning_rate": 3.504512689510422e-05, |
| "loss": 0.124, |
| "mean_token_accuracy": 0.9672811701893806, |
| "step": 450 |
| }, |
| { |
| "epoch": 2.6392961876832843, |
| "grad_norm": 1.1552540803707831, |
| "learning_rate": 3.5021474405818525e-05, |
| "loss": 0.1327, |
| "mean_token_accuracy": 0.9567637592554092, |
| "step": 451 |
| }, |
| { |
| "epoch": 2.6451612903225805, |
| "grad_norm": 1.378193372806992, |
| "learning_rate": 3.499777465383977e-05, |
| "loss": 0.1734, |
| "mean_token_accuracy": 0.9506984949111938, |
| "step": 452 |
| }, |
| { |
| "epoch": 2.6510263929618767, |
| "grad_norm": 1.425693391123194, |
| "learning_rate": 3.497402772518848e-05, |
| "loss": 0.1919, |
| "mean_token_accuracy": 0.9396786019206047, |
| "step": 453 |
| }, |
| { |
| "epoch": 2.656891495601173, |
| "grad_norm": 1.2031173797533838, |
| "learning_rate": 3.4950233706056415e-05, |
| "loss": 0.1421, |
| "mean_token_accuracy": 0.9579765349626541, |
| "step": 454 |
| }, |
| { |
| "epoch": 2.662756598240469, |
| "grad_norm": 1.470261873197383, |
| "learning_rate": 3.4926392682806265e-05, |
| "loss": 0.1859, |
| "mean_token_accuracy": 0.9434613659977913, |
| "step": 455 |
| }, |
| { |
| "epoch": 2.6686217008797652, |
| "grad_norm": 1.366478758555936, |
| "learning_rate": 3.490250474197131e-05, |
| "loss": 0.1796, |
| "mean_token_accuracy": 0.9481052234768867, |
| "step": 456 |
| }, |
| { |
| "epoch": 2.6744868035190614, |
| "grad_norm": 1.1912300344703033, |
| "learning_rate": 3.4878569970255116e-05, |
| "loss": 0.146, |
| "mean_token_accuracy": 0.9556678831577301, |
| "step": 457 |
| }, |
| { |
| "epoch": 2.6803519061583576, |
| "grad_norm": 1.254578474168094, |
| "learning_rate": 3.485458845453125e-05, |
| "loss": 0.1638, |
| "mean_token_accuracy": 0.9488549754023552, |
| "step": 458 |
| }, |
| { |
| "epoch": 2.686217008797654, |
| "grad_norm": 1.1552424595084878, |
| "learning_rate": 3.483056028184293e-05, |
| "loss": 0.1226, |
| "mean_token_accuracy": 0.9643560871481895, |
| "step": 459 |
| }, |
| { |
| "epoch": 2.6920821114369504, |
| "grad_norm": 1.222050122616804, |
| "learning_rate": 3.4806485539402716e-05, |
| "loss": 0.1702, |
| "mean_token_accuracy": 0.9485805332660675, |
| "step": 460 |
| }, |
| { |
| "epoch": 2.6979472140762466, |
| "grad_norm": 1.04173325799313, |
| "learning_rate": 3.4782364314592186e-05, |
| "loss": 0.1315, |
| "mean_token_accuracy": 0.9575633853673935, |
| "step": 461 |
| }, |
| { |
| "epoch": 2.703812316715543, |
| "grad_norm": 1.2620647522862372, |
| "learning_rate": 3.475819669496167e-05, |
| "loss": 0.1386, |
| "mean_token_accuracy": 0.9566176012158394, |
| "step": 462 |
| }, |
| { |
| "epoch": 2.709677419354839, |
| "grad_norm": 1.1878640456791556, |
| "learning_rate": 3.473398276822985e-05, |
| "loss": 0.1583, |
| "mean_token_accuracy": 0.9529377073049545, |
| "step": 463 |
| }, |
| { |
| "epoch": 2.715542521994135, |
| "grad_norm": 1.417678695883431, |
| "learning_rate": 3.47097226222835e-05, |
| "loss": 0.1802, |
| "mean_token_accuracy": 0.948061428964138, |
| "step": 464 |
| }, |
| { |
| "epoch": 2.7214076246334313, |
| "grad_norm": 1.3277295409980292, |
| "learning_rate": 3.468541634517716e-05, |
| "loss": 0.1663, |
| "mean_token_accuracy": 0.9515725001692772, |
| "step": 465 |
| }, |
| { |
| "epoch": 2.7272727272727275, |
| "grad_norm": 1.0754314703112438, |
| "learning_rate": 3.4661064025132796e-05, |
| "loss": 0.1313, |
| "mean_token_accuracy": 0.9582964032888412, |
| "step": 466 |
| }, |
| { |
| "epoch": 2.7331378299120237, |
| "grad_norm": 1.4666907651133738, |
| "learning_rate": 3.463666575053949e-05, |
| "loss": 0.2119, |
| "mean_token_accuracy": 0.9404854699969292, |
| "step": 467 |
| }, |
| { |
| "epoch": 2.73900293255132, |
| "grad_norm": 0.9664273130964783, |
| "learning_rate": 3.4612221609953126e-05, |
| "loss": 0.123, |
| "mean_token_accuracy": 0.9659903347492218, |
| "step": 468 |
| }, |
| { |
| "epoch": 2.744868035190616, |
| "grad_norm": 1.1357008791720598, |
| "learning_rate": 3.4587731692096065e-05, |
| "loss": 0.1531, |
| "mean_token_accuracy": 0.9576428085565567, |
| "step": 469 |
| }, |
| { |
| "epoch": 2.7507331378299122, |
| "grad_norm": 1.3120260141761082, |
| "learning_rate": 3.4563196085856815e-05, |
| "loss": 0.1869, |
| "mean_token_accuracy": 0.9426525309681892, |
| "step": 470 |
| }, |
| { |
| "epoch": 2.7565982404692084, |
| "grad_norm": 1.3740403971580124, |
| "learning_rate": 3.4538614880289724e-05, |
| "loss": 0.2036, |
| "mean_token_accuracy": 0.9509467408061028, |
| "step": 471 |
| }, |
| { |
| "epoch": 2.7624633431085046, |
| "grad_norm": 1.0963128912837212, |
| "learning_rate": 3.4513988164614635e-05, |
| "loss": 0.1398, |
| "mean_token_accuracy": 0.9593295454978943, |
| "step": 472 |
| }, |
| { |
| "epoch": 2.768328445747801, |
| "grad_norm": 1.1019956064171137, |
| "learning_rate": 3.4489316028216584e-05, |
| "loss": 0.1247, |
| "mean_token_accuracy": 0.961910292506218, |
| "step": 473 |
| }, |
| { |
| "epoch": 2.774193548387097, |
| "grad_norm": 1.0889658684678445, |
| "learning_rate": 3.446459856064545e-05, |
| "loss": 0.1416, |
| "mean_token_accuracy": 0.9593067914247513, |
| "step": 474 |
| }, |
| { |
| "epoch": 2.780058651026393, |
| "grad_norm": 1.5364222822362106, |
| "learning_rate": 3.443983585161568e-05, |
| "loss": 0.2065, |
| "mean_token_accuracy": 0.9389885291457176, |
| "step": 475 |
| }, |
| { |
| "epoch": 2.7859237536656893, |
| "grad_norm": 1.2105587532674789, |
| "learning_rate": 3.441502799100588e-05, |
| "loss": 0.1433, |
| "mean_token_accuracy": 0.95948126912117, |
| "step": 476 |
| }, |
| { |
| "epoch": 2.7917888563049855, |
| "grad_norm": 1.2951438817508967, |
| "learning_rate": 3.439017506885858e-05, |
| "loss": 0.1646, |
| "mean_token_accuracy": 0.9550016522407532, |
| "step": 477 |
| }, |
| { |
| "epoch": 2.7976539589442817, |
| "grad_norm": 1.311465052855291, |
| "learning_rate": 3.436527717537985e-05, |
| "loss": 0.1637, |
| "mean_token_accuracy": 0.9561468809843063, |
| "step": 478 |
| }, |
| { |
| "epoch": 2.803519061583578, |
| "grad_norm": 1.2479330923352838, |
| "learning_rate": 3.434033440093899e-05, |
| "loss": 0.1831, |
| "mean_token_accuracy": 0.9408740624785423, |
| "step": 479 |
| }, |
| { |
| "epoch": 2.809384164222874, |
| "grad_norm": 1.418713289265348, |
| "learning_rate": 3.431534683606818e-05, |
| "loss": 0.1842, |
| "mean_token_accuracy": 0.9517565071582794, |
| "step": 480 |
| }, |
| { |
| "epoch": 2.8152492668621703, |
| "grad_norm": 1.080464369466574, |
| "learning_rate": 3.4290314571462214e-05, |
| "loss": 0.149, |
| "mean_token_accuracy": 0.9588718563318253, |
| "step": 481 |
| }, |
| { |
| "epoch": 2.8211143695014664, |
| "grad_norm": 1.0261580719738286, |
| "learning_rate": 3.426523769797808e-05, |
| "loss": 0.1343, |
| "mean_token_accuracy": 0.9594571813941002, |
| "step": 482 |
| }, |
| { |
| "epoch": 2.8269794721407626, |
| "grad_norm": 1.256975848089233, |
| "learning_rate": 3.424011630663472e-05, |
| "loss": 0.1617, |
| "mean_token_accuracy": 0.9473337456583977, |
| "step": 483 |
| }, |
| { |
| "epoch": 2.832844574780059, |
| "grad_norm": 1.1887187248938638, |
| "learning_rate": 3.421495048861262e-05, |
| "loss": 0.1579, |
| "mean_token_accuracy": 0.9534508436918259, |
| "step": 484 |
| }, |
| { |
| "epoch": 2.838709677419355, |
| "grad_norm": 1.108974947781916, |
| "learning_rate": 3.418974033525355e-05, |
| "loss": 0.1456, |
| "mean_token_accuracy": 0.9567419737577438, |
| "step": 485 |
| }, |
| { |
| "epoch": 2.844574780058651, |
| "grad_norm": 1.3884218537085193, |
| "learning_rate": 3.416448593806019e-05, |
| "loss": 0.1734, |
| "mean_token_accuracy": 0.9510295391082764, |
| "step": 486 |
| }, |
| { |
| "epoch": 2.8504398826979473, |
| "grad_norm": 1.265301003883797, |
| "learning_rate": 3.4139187388695774e-05, |
| "loss": 0.152, |
| "mean_token_accuracy": 0.9507285058498383, |
| "step": 487 |
| }, |
| { |
| "epoch": 2.8563049853372435, |
| "grad_norm": 1.4518823332516295, |
| "learning_rate": 3.411384477898385e-05, |
| "loss": 0.1708, |
| "mean_token_accuracy": 0.9520754367113113, |
| "step": 488 |
| }, |
| { |
| "epoch": 2.8621700879765397, |
| "grad_norm": 1.3170349542649433, |
| "learning_rate": 3.408845820090784e-05, |
| "loss": 0.1505, |
| "mean_token_accuracy": 0.9542975649237633, |
| "step": 489 |
| }, |
| { |
| "epoch": 2.868035190615836, |
| "grad_norm": 1.4862687077718277, |
| "learning_rate": 3.406302774661077e-05, |
| "loss": 0.1879, |
| "mean_token_accuracy": 0.9435409009456635, |
| "step": 490 |
| }, |
| { |
| "epoch": 2.873900293255132, |
| "grad_norm": 1.5510248888013005, |
| "learning_rate": 3.403755350839492e-05, |
| "loss": 0.1953, |
| "mean_token_accuracy": 0.9470630958676338, |
| "step": 491 |
| }, |
| { |
| "epoch": 2.8797653958944283, |
| "grad_norm": 0.9083867690185883, |
| "learning_rate": 3.401203557872149e-05, |
| "loss": 0.1102, |
| "mean_token_accuracy": 0.9688790738582611, |
| "step": 492 |
| }, |
| { |
| "epoch": 2.8856304985337244, |
| "grad_norm": 1.20388441326265, |
| "learning_rate": 3.398647405021026e-05, |
| "loss": 0.157, |
| "mean_token_accuracy": 0.9560961946845055, |
| "step": 493 |
| }, |
| { |
| "epoch": 2.8914956011730206, |
| "grad_norm": 1.6131126124579498, |
| "learning_rate": 3.396086901563925e-05, |
| "loss": 0.2093, |
| "mean_token_accuracy": 0.9383601620793343, |
| "step": 494 |
| }, |
| { |
| "epoch": 2.897360703812317, |
| "grad_norm": 1.1132311008689093, |
| "learning_rate": 3.3935220567944395e-05, |
| "loss": 0.1368, |
| "mean_token_accuracy": 0.9590755850076675, |
| "step": 495 |
| }, |
| { |
| "epoch": 2.903225806451613, |
| "grad_norm": 1.388157178476272, |
| "learning_rate": 3.39095288002192e-05, |
| "loss": 0.1933, |
| "mean_token_accuracy": 0.9421152919530869, |
| "step": 496 |
| }, |
| { |
| "epoch": 2.909090909090909, |
| "grad_norm": 1.2419877458073016, |
| "learning_rate": 3.3883793805714406e-05, |
| "loss": 0.1441, |
| "mean_token_accuracy": 0.95684465020895, |
| "step": 497 |
| }, |
| { |
| "epoch": 2.9149560117302054, |
| "grad_norm": 1.2687959153746118, |
| "learning_rate": 3.3858015677837656e-05, |
| "loss": 0.1952, |
| "mean_token_accuracy": 0.9452904909849167, |
| "step": 498 |
| }, |
| { |
| "epoch": 2.9208211143695015, |
| "grad_norm": 1.3664534250202576, |
| "learning_rate": 3.3832194510153126e-05, |
| "loss": 0.1753, |
| "mean_token_accuracy": 0.9477646723389626, |
| "step": 499 |
| }, |
| { |
| "epoch": 2.9266862170087977, |
| "grad_norm": 1.2649573147861883, |
| "learning_rate": 3.380633039638125e-05, |
| "loss": 0.1555, |
| "mean_token_accuracy": 0.9552437961101532, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.932551319648094, |
| "grad_norm": 1.461470546166254, |
| "learning_rate": 3.37804234303983e-05, |
| "loss": 0.1846, |
| "mean_token_accuracy": 0.9439187347888947, |
| "step": 501 |
| }, |
| { |
| "epoch": 2.93841642228739, |
| "grad_norm": 1.3620091302607829, |
| "learning_rate": 3.37544737062361e-05, |
| "loss": 0.1803, |
| "mean_token_accuracy": 0.9506632015109062, |
| "step": 502 |
| }, |
| { |
| "epoch": 2.9442815249266863, |
| "grad_norm": 1.3089948493246146, |
| "learning_rate": 3.372848131808167e-05, |
| "loss": 0.1635, |
| "mean_token_accuracy": 0.9532084316015244, |
| "step": 503 |
| }, |
| { |
| "epoch": 2.9501466275659824, |
| "grad_norm": 1.4021607966733816, |
| "learning_rate": 3.370244636027688e-05, |
| "loss": 0.1589, |
| "mean_token_accuracy": 0.9532099440693855, |
| "step": 504 |
| }, |
| { |
| "epoch": 2.9560117302052786, |
| "grad_norm": 1.273314099966914, |
| "learning_rate": 3.367636892731812e-05, |
| "loss": 0.1536, |
| "mean_token_accuracy": 0.9473722502589226, |
| "step": 505 |
| }, |
| { |
| "epoch": 2.961876832844575, |
| "grad_norm": 1.2111921824318914, |
| "learning_rate": 3.365024911385593e-05, |
| "loss": 0.1473, |
| "mean_token_accuracy": 0.9612649232149124, |
| "step": 506 |
| }, |
| { |
| "epoch": 2.967741935483871, |
| "grad_norm": 1.1166189528554271, |
| "learning_rate": 3.362408701469469e-05, |
| "loss": 0.1512, |
| "mean_token_accuracy": 0.9526806995272636, |
| "step": 507 |
| }, |
| { |
| "epoch": 2.973607038123167, |
| "grad_norm": 1.536757210363506, |
| "learning_rate": 3.359788272479225e-05, |
| "loss": 0.1924, |
| "mean_token_accuracy": 0.9464055821299553, |
| "step": 508 |
| }, |
| { |
| "epoch": 2.9794721407624634, |
| "grad_norm": 1.2454395159603193, |
| "learning_rate": 3.35716363392596e-05, |
| "loss": 0.1672, |
| "mean_token_accuracy": 0.9483352527022362, |
| "step": 509 |
| }, |
| { |
| "epoch": 2.9853372434017595, |
| "grad_norm": 1.3846359032452442, |
| "learning_rate": 3.354534795336052e-05, |
| "loss": 0.2416, |
| "mean_token_accuracy": 0.9301293268799782, |
| "step": 510 |
| }, |
| { |
| "epoch": 2.9912023460410557, |
| "grad_norm": 1.0907635693009343, |
| "learning_rate": 3.351901766251123e-05, |
| "loss": 0.1584, |
| "mean_token_accuracy": 0.9516775086522102, |
| "step": 511 |
| }, |
| { |
| "epoch": 2.997067448680352, |
| "grad_norm": 1.52351732920836, |
| "learning_rate": 3.349264556228006e-05, |
| "loss": 0.2106, |
| "mean_token_accuracy": 0.9392689317464828, |
| "step": 512 |
| }, |
| { |
| "epoch": 3.0, |
| "grad_norm": 1.52351732920836, |
| "learning_rate": 3.3466231748387077e-05, |
| "loss": 0.2709, |
| "mean_token_accuracy": 0.9210451692342758, |
| "step": 513 |
| }, |
| { |
| "epoch": 3.005865102639296, |
| "grad_norm": 1.968651229970697, |
| "learning_rate": 3.343977631670376e-05, |
| "loss": 0.1029, |
| "mean_token_accuracy": 0.9711232706904411, |
| "step": 514 |
| }, |
| { |
| "epoch": 3.0117302052785924, |
| "grad_norm": 0.9652696996950184, |
| "learning_rate": 3.341327936325264e-05, |
| "loss": 0.1143, |
| "mean_token_accuracy": 0.9680498614907265, |
| "step": 515 |
| }, |
| { |
| "epoch": 3.0175953079178885, |
| "grad_norm": 0.8502990782157536, |
| "learning_rate": 3.338674098420695e-05, |
| "loss": 0.0908, |
| "mean_token_accuracy": 0.9716523513197899, |
| "step": 516 |
| }, |
| { |
| "epoch": 3.0234604105571847, |
| "grad_norm": 0.7630744145217659, |
| "learning_rate": 3.33601612758903e-05, |
| "loss": 0.0976, |
| "mean_token_accuracy": 0.970447264611721, |
| "step": 517 |
| }, |
| { |
| "epoch": 3.029325513196481, |
| "grad_norm": 0.81504254903722, |
| "learning_rate": 3.3333540334776286e-05, |
| "loss": 0.1127, |
| "mean_token_accuracy": 0.9646006375551224, |
| "step": 518 |
| }, |
| { |
| "epoch": 3.035190615835777, |
| "grad_norm": 0.9343172049366141, |
| "learning_rate": 3.330687825748818e-05, |
| "loss": 0.1117, |
| "mean_token_accuracy": 0.9674835652112961, |
| "step": 519 |
| }, |
| { |
| "epoch": 3.0410557184750733, |
| "grad_norm": 1.1971850042909595, |
| "learning_rate": 3.328017514079855e-05, |
| "loss": 0.1253, |
| "mean_token_accuracy": 0.9672354459762573, |
| "step": 520 |
| }, |
| { |
| "epoch": 3.0469208211143695, |
| "grad_norm": 1.0563212992287103, |
| "learning_rate": 3.325343108162893e-05, |
| "loss": 0.0988, |
| "mean_token_accuracy": 0.9684354662895203, |
| "step": 521 |
| }, |
| { |
| "epoch": 3.0527859237536656, |
| "grad_norm": 1.0716926109268614, |
| "learning_rate": 3.3226646177049446e-05, |
| "loss": 0.1124, |
| "mean_token_accuracy": 0.9679635167121887, |
| "step": 522 |
| }, |
| { |
| "epoch": 3.058651026392962, |
| "grad_norm": 1.1051242844259859, |
| "learning_rate": 3.3199820524278485e-05, |
| "loss": 0.115, |
| "mean_token_accuracy": 0.9673113599419594, |
| "step": 523 |
| }, |
| { |
| "epoch": 3.064516129032258, |
| "grad_norm": 1.106421479204272, |
| "learning_rate": 3.317295422068234e-05, |
| "loss": 0.1172, |
| "mean_token_accuracy": 0.9651734456419945, |
| "step": 524 |
| }, |
| { |
| "epoch": 3.070381231671554, |
| "grad_norm": 1.1415664510277006, |
| "learning_rate": 3.314604736377484e-05, |
| "loss": 0.1021, |
| "mean_token_accuracy": 0.9700004607439041, |
| "step": 525 |
| }, |
| { |
| "epoch": 3.0762463343108504, |
| "grad_norm": 0.9404143331641928, |
| "learning_rate": 3.3119100051217005e-05, |
| "loss": 0.0886, |
| "mean_token_accuracy": 0.975829653441906, |
| "step": 526 |
| }, |
| { |
| "epoch": 3.0821114369501466, |
| "grad_norm": 1.1187988373557514, |
| "learning_rate": 3.3092112380816696e-05, |
| "loss": 0.1185, |
| "mean_token_accuracy": 0.9644615799188614, |
| "step": 527 |
| }, |
| { |
| "epoch": 3.0879765395894427, |
| "grad_norm": 1.0020657220144769, |
| "learning_rate": 3.306508445052826e-05, |
| "loss": 0.1211, |
| "mean_token_accuracy": 0.964887946844101, |
| "step": 528 |
| }, |
| { |
| "epoch": 3.093841642228739, |
| "grad_norm": 1.2143706108607386, |
| "learning_rate": 3.303801635845216e-05, |
| "loss": 0.113, |
| "mean_token_accuracy": 0.9642840325832367, |
| "step": 529 |
| }, |
| { |
| "epoch": 3.099706744868035, |
| "grad_norm": 0.9975861638054916, |
| "learning_rate": 3.301090820283465e-05, |
| "loss": 0.1149, |
| "mean_token_accuracy": 0.9669056162238121, |
| "step": 530 |
| }, |
| { |
| "epoch": 3.1055718475073313, |
| "grad_norm": 1.0802501908744115, |
| "learning_rate": 3.298376008206739e-05, |
| "loss": 0.1124, |
| "mean_token_accuracy": 0.9703796878457069, |
| "step": 531 |
| }, |
| { |
| "epoch": 3.1114369501466275, |
| "grad_norm": 0.8021624899339075, |
| "learning_rate": 3.295657209468707e-05, |
| "loss": 0.0943, |
| "mean_token_accuracy": 0.9735233038663864, |
| "step": 532 |
| }, |
| { |
| "epoch": 3.1173020527859236, |
| "grad_norm": 0.9633823163777017, |
| "learning_rate": 3.2929344339375125e-05, |
| "loss": 0.1189, |
| "mean_token_accuracy": 0.9634987413883209, |
| "step": 533 |
| }, |
| { |
| "epoch": 3.12316715542522, |
| "grad_norm": 0.9351429992484981, |
| "learning_rate": 3.290207691495731e-05, |
| "loss": 0.1223, |
| "mean_token_accuracy": 0.9647831618785858, |
| "step": 534 |
| }, |
| { |
| "epoch": 3.129032258064516, |
| "grad_norm": 1.0205424257089983, |
| "learning_rate": 3.2874769920403355e-05, |
| "loss": 0.1094, |
| "mean_token_accuracy": 0.9677336141467094, |
| "step": 535 |
| }, |
| { |
| "epoch": 3.134897360703812, |
| "grad_norm": 0.7996391695402355, |
| "learning_rate": 3.2847423454826616e-05, |
| "loss": 0.1029, |
| "mean_token_accuracy": 0.9708555638790131, |
| "step": 536 |
| }, |
| { |
| "epoch": 3.1407624633431084, |
| "grad_norm": 0.9929429090487744, |
| "learning_rate": 3.2820037617483734e-05, |
| "loss": 0.1326, |
| "mean_token_accuracy": 0.9639134034514427, |
| "step": 537 |
| }, |
| { |
| "epoch": 3.1466275659824046, |
| "grad_norm": 1.0550635107253659, |
| "learning_rate": 3.2792612507774224e-05, |
| "loss": 0.1091, |
| "mean_token_accuracy": 0.9677369222044945, |
| "step": 538 |
| }, |
| { |
| "epoch": 3.1524926686217007, |
| "grad_norm": 0.9231451013069485, |
| "learning_rate": 3.2765148225240176e-05, |
| "loss": 0.1127, |
| "mean_token_accuracy": 0.9681195095181465, |
| "step": 539 |
| }, |
| { |
| "epoch": 3.158357771260997, |
| "grad_norm": 0.862498716572109, |
| "learning_rate": 3.273764486956583e-05, |
| "loss": 0.1109, |
| "mean_token_accuracy": 0.9684896096587181, |
| "step": 540 |
| }, |
| { |
| "epoch": 3.164222873900293, |
| "grad_norm": 1.0956873032349619, |
| "learning_rate": 3.2710102540577256e-05, |
| "loss": 0.1088, |
| "mean_token_accuracy": 0.9692259877920151, |
| "step": 541 |
| }, |
| { |
| "epoch": 3.1700879765395893, |
| "grad_norm": 1.0839458966945006, |
| "learning_rate": 3.268252133824198e-05, |
| "loss": 0.1313, |
| "mean_token_accuracy": 0.9646385759115219, |
| "step": 542 |
| }, |
| { |
| "epoch": 3.1759530791788855, |
| "grad_norm": 0.9457995681638467, |
| "learning_rate": 3.2654901362668656e-05, |
| "loss": 0.1034, |
| "mean_token_accuracy": 0.9699193686246872, |
| "step": 543 |
| }, |
| { |
| "epoch": 3.1818181818181817, |
| "grad_norm": 0.9874968177745931, |
| "learning_rate": 3.262724271410661e-05, |
| "loss": 0.1211, |
| "mean_token_accuracy": 0.9654932543635368, |
| "step": 544 |
| }, |
| { |
| "epoch": 3.187683284457478, |
| "grad_norm": 1.1532260866014505, |
| "learning_rate": 3.2599545492945584e-05, |
| "loss": 0.1291, |
| "mean_token_accuracy": 0.9629618749022484, |
| "step": 545 |
| }, |
| { |
| "epoch": 3.193548387096774, |
| "grad_norm": 1.244455403777776, |
| "learning_rate": 3.257180979971529e-05, |
| "loss": 0.1133, |
| "mean_token_accuracy": 0.9672550708055496, |
| "step": 546 |
| }, |
| { |
| "epoch": 3.19941348973607, |
| "grad_norm": 0.9864752841266905, |
| "learning_rate": 3.25440357350851e-05, |
| "loss": 0.1285, |
| "mean_token_accuracy": 0.9629417359828949, |
| "step": 547 |
| }, |
| { |
| "epoch": 3.2052785923753664, |
| "grad_norm": 1.1105194518868626, |
| "learning_rate": 3.251622339986366e-05, |
| "loss": 0.1348, |
| "mean_token_accuracy": 0.9636048302054405, |
| "step": 548 |
| }, |
| { |
| "epoch": 3.2111436950146626, |
| "grad_norm": 1.273551629134977, |
| "learning_rate": 3.24883728949985e-05, |
| "loss": 0.1324, |
| "mean_token_accuracy": 0.9609309211373329, |
| "step": 549 |
| }, |
| { |
| "epoch": 3.2170087976539588, |
| "grad_norm": 0.9952288620484804, |
| "learning_rate": 3.2460484321575714e-05, |
| "loss": 0.1098, |
| "mean_token_accuracy": 0.9686953574419022, |
| "step": 550 |
| }, |
| { |
| "epoch": 3.222873900293255, |
| "grad_norm": 0.9799228318089337, |
| "learning_rate": 3.2432557780819556e-05, |
| "loss": 0.1036, |
| "mean_token_accuracy": 0.9690500125288963, |
| "step": 551 |
| }, |
| { |
| "epoch": 3.228739002932551, |
| "grad_norm": 1.0078911048435029, |
| "learning_rate": 3.240459337409209e-05, |
| "loss": 0.1305, |
| "mean_token_accuracy": 0.9617227241396904, |
| "step": 552 |
| }, |
| { |
| "epoch": 3.2346041055718473, |
| "grad_norm": 0.948818618424717, |
| "learning_rate": 3.237659120289282e-05, |
| "loss": 0.1127, |
| "mean_token_accuracy": 0.9691289365291595, |
| "step": 553 |
| }, |
| { |
| "epoch": 3.2404692082111435, |
| "grad_norm": 1.2609074258141768, |
| "learning_rate": 3.2348551368858315e-05, |
| "loss": 0.1118, |
| "mean_token_accuracy": 0.9663236141204834, |
| "step": 554 |
| }, |
| { |
| "epoch": 3.2463343108504397, |
| "grad_norm": 0.986737754077552, |
| "learning_rate": 3.2320473973761845e-05, |
| "loss": 0.1086, |
| "mean_token_accuracy": 0.9680015295743942, |
| "step": 555 |
| }, |
| { |
| "epoch": 3.252199413489736, |
| "grad_norm": 0.9498740915078302, |
| "learning_rate": 3.229235911951303e-05, |
| "loss": 0.1131, |
| "mean_token_accuracy": 0.9682961478829384, |
| "step": 556 |
| }, |
| { |
| "epoch": 3.258064516129032, |
| "grad_norm": 0.975893859118113, |
| "learning_rate": 3.2264206908157425e-05, |
| "loss": 0.097, |
| "mean_token_accuracy": 0.9698783755302429, |
| "step": 557 |
| }, |
| { |
| "epoch": 3.263929618768328, |
| "grad_norm": 0.8112438014718453, |
| "learning_rate": 3.2236017441876185e-05, |
| "loss": 0.1277, |
| "mean_token_accuracy": 0.9649044126272202, |
| "step": 558 |
| }, |
| { |
| "epoch": 3.2697947214076244, |
| "grad_norm": 1.233497752038787, |
| "learning_rate": 3.220779082298569e-05, |
| "loss": 0.1244, |
| "mean_token_accuracy": 0.9652732387185097, |
| "step": 559 |
| }, |
| { |
| "epoch": 3.2756598240469206, |
| "grad_norm": 1.2473037646309517, |
| "learning_rate": 3.2179527153937165e-05, |
| "loss": 0.1388, |
| "mean_token_accuracy": 0.9597837403416634, |
| "step": 560 |
| }, |
| { |
| "epoch": 3.281524926686217, |
| "grad_norm": 1.1321059040397468, |
| "learning_rate": 3.2151226537316315e-05, |
| "loss": 0.1021, |
| "mean_token_accuracy": 0.9714441522955894, |
| "step": 561 |
| }, |
| { |
| "epoch": 3.2873900293255134, |
| "grad_norm": 0.8602666974497257, |
| "learning_rate": 3.212288907584296e-05, |
| "loss": 0.1064, |
| "mean_token_accuracy": 0.9680186361074448, |
| "step": 562 |
| }, |
| { |
| "epoch": 3.2932551319648096, |
| "grad_norm": 1.2042098687516025, |
| "learning_rate": 3.209451487237062e-05, |
| "loss": 0.1371, |
| "mean_token_accuracy": 0.9599383175373077, |
| "step": 563 |
| }, |
| { |
| "epoch": 3.2991202346041058, |
| "grad_norm": 0.9050169219632497, |
| "learning_rate": 3.206610402988621e-05, |
| "loss": 0.1065, |
| "mean_token_accuracy": 0.9682442918419838, |
| "step": 564 |
| }, |
| { |
| "epoch": 3.304985337243402, |
| "grad_norm": 1.026829641767951, |
| "learning_rate": 3.20376566515096e-05, |
| "loss": 0.1183, |
| "mean_token_accuracy": 0.9679248631000519, |
| "step": 565 |
| }, |
| { |
| "epoch": 3.310850439882698, |
| "grad_norm": 0.9674573819125384, |
| "learning_rate": 3.20091728404933e-05, |
| "loss": 0.0955, |
| "mean_token_accuracy": 0.9733124375343323, |
| "step": 566 |
| }, |
| { |
| "epoch": 3.3167155425219943, |
| "grad_norm": 0.8804094604877748, |
| "learning_rate": 3.1980652700222024e-05, |
| "loss": 0.111, |
| "mean_token_accuracy": 0.968389168381691, |
| "step": 567 |
| }, |
| { |
| "epoch": 3.3225806451612905, |
| "grad_norm": 0.8181882227316067, |
| "learning_rate": 3.195209633421237e-05, |
| "loss": 0.1057, |
| "mean_token_accuracy": 0.9647178426384926, |
| "step": 568 |
| }, |
| { |
| "epoch": 3.3284457478005867, |
| "grad_norm": 1.144091624189587, |
| "learning_rate": 3.192350384611242e-05, |
| "loss": 0.1263, |
| "mean_token_accuracy": 0.960628017783165, |
| "step": 569 |
| }, |
| { |
| "epoch": 3.334310850439883, |
| "grad_norm": 0.8750690128095869, |
| "learning_rate": 3.1894875339701354e-05, |
| "loss": 0.1055, |
| "mean_token_accuracy": 0.9733807370066643, |
| "step": 570 |
| }, |
| { |
| "epoch": 3.340175953079179, |
| "grad_norm": 0.9491730861419487, |
| "learning_rate": 3.186621091888909e-05, |
| "loss": 0.123, |
| "mean_token_accuracy": 0.9650392830371857, |
| "step": 571 |
| }, |
| { |
| "epoch": 3.346041055718475, |
| "grad_norm": 0.8267533896847664, |
| "learning_rate": 3.183751068771588e-05, |
| "loss": 0.1136, |
| "mean_token_accuracy": 0.9666124507784843, |
| "step": 572 |
| }, |
| { |
| "epoch": 3.3519061583577714, |
| "grad_norm": 1.0647393991266463, |
| "learning_rate": 3.180877475035199e-05, |
| "loss": 0.1184, |
| "mean_token_accuracy": 0.9674052000045776, |
| "step": 573 |
| }, |
| { |
| "epoch": 3.3577712609970676, |
| "grad_norm": 0.8434998247171931, |
| "learning_rate": 3.178000321109727e-05, |
| "loss": 0.1183, |
| "mean_token_accuracy": 0.9672171697020531, |
| "step": 574 |
| }, |
| { |
| "epoch": 3.3636363636363638, |
| "grad_norm": 1.8503993478263725, |
| "learning_rate": 3.175119617438078e-05, |
| "loss": 0.126, |
| "mean_token_accuracy": 0.9652078375220299, |
| "step": 575 |
| }, |
| { |
| "epoch": 3.36950146627566, |
| "grad_norm": 1.2024058090106011, |
| "learning_rate": 3.172235374476043e-05, |
| "loss": 0.1164, |
| "mean_token_accuracy": 0.9678644984960556, |
| "step": 576 |
| }, |
| { |
| "epoch": 3.375366568914956, |
| "grad_norm": 1.0479012272568091, |
| "learning_rate": 3.169347602692259e-05, |
| "loss": 0.144, |
| "mean_token_accuracy": 0.9602736532688141, |
| "step": 577 |
| }, |
| { |
| "epoch": 3.3812316715542523, |
| "grad_norm": 1.2562006259403447, |
| "learning_rate": 3.166456312568171e-05, |
| "loss": 0.1198, |
| "mean_token_accuracy": 0.9649272710084915, |
| "step": 578 |
| }, |
| { |
| "epoch": 3.3870967741935485, |
| "grad_norm": 1.0474486488431458, |
| "learning_rate": 3.1635615145979955e-05, |
| "loss": 0.1279, |
| "mean_token_accuracy": 0.9652384221553802, |
| "step": 579 |
| }, |
| { |
| "epoch": 3.3929618768328447, |
| "grad_norm": 0.9124821179146846, |
| "learning_rate": 3.160663219288679e-05, |
| "loss": 0.1068, |
| "mean_token_accuracy": 0.9672473296523094, |
| "step": 580 |
| }, |
| { |
| "epoch": 3.398826979472141, |
| "grad_norm": 0.9757202501702933, |
| "learning_rate": 3.157761437159863e-05, |
| "loss": 0.13, |
| "mean_token_accuracy": 0.9603447467088699, |
| "step": 581 |
| }, |
| { |
| "epoch": 3.404692082111437, |
| "grad_norm": 1.0652616179562135, |
| "learning_rate": 3.1548561787438445e-05, |
| "loss": 0.1038, |
| "mean_token_accuracy": 0.9710996374487877, |
| "step": 582 |
| }, |
| { |
| "epoch": 3.410557184750733, |
| "grad_norm": 0.836489733941965, |
| "learning_rate": 3.15194745458554e-05, |
| "loss": 0.1073, |
| "mean_token_accuracy": 0.9714136347174644, |
| "step": 583 |
| }, |
| { |
| "epoch": 3.4164222873900294, |
| "grad_norm": 1.0714963240647486, |
| "learning_rate": 3.149035275242441e-05, |
| "loss": 0.1094, |
| "mean_token_accuracy": 0.9690913036465645, |
| "step": 584 |
| }, |
| { |
| "epoch": 3.4222873900293256, |
| "grad_norm": 0.9137331585277465, |
| "learning_rate": 3.1461196512845834e-05, |
| "loss": 0.1144, |
| "mean_token_accuracy": 0.9658253341913223, |
| "step": 585 |
| }, |
| { |
| "epoch": 3.4281524926686218, |
| "grad_norm": 0.9997324531190634, |
| "learning_rate": 3.143200593294504e-05, |
| "loss": 0.1186, |
| "mean_token_accuracy": 0.9656195119023323, |
| "step": 586 |
| }, |
| { |
| "epoch": 3.434017595307918, |
| "grad_norm": 1.1040122559087995, |
| "learning_rate": 3.1402781118672065e-05, |
| "loss": 0.113, |
| "mean_token_accuracy": 0.9666641429066658, |
| "step": 587 |
| }, |
| { |
| "epoch": 3.439882697947214, |
| "grad_norm": 1.0199551083482483, |
| "learning_rate": 3.137352217610115e-05, |
| "loss": 0.1136, |
| "mean_token_accuracy": 0.9654843956232071, |
| "step": 588 |
| }, |
| { |
| "epoch": 3.4457478005865103, |
| "grad_norm": 0.7932841443360936, |
| "learning_rate": 3.1344229211430465e-05, |
| "loss": 0.1118, |
| "mean_token_accuracy": 0.9717729911208153, |
| "step": 589 |
| }, |
| { |
| "epoch": 3.4516129032258065, |
| "grad_norm": 1.0038381415796183, |
| "learning_rate": 3.131490233098164e-05, |
| "loss": 0.0892, |
| "mean_token_accuracy": 0.9750974550843239, |
| "step": 590 |
| }, |
| { |
| "epoch": 3.4574780058651027, |
| "grad_norm": 0.9161828715428822, |
| "learning_rate": 3.1285541641199383e-05, |
| "loss": 0.1179, |
| "mean_token_accuracy": 0.9669305682182312, |
| "step": 591 |
| }, |
| { |
| "epoch": 3.463343108504399, |
| "grad_norm": 1.0353554299516425, |
| "learning_rate": 3.1256147248651166e-05, |
| "loss": 0.1037, |
| "mean_token_accuracy": 0.9700469970703125, |
| "step": 592 |
| }, |
| { |
| "epoch": 3.469208211143695, |
| "grad_norm": 0.8583882324406463, |
| "learning_rate": 3.122671926002675e-05, |
| "loss": 0.1116, |
| "mean_token_accuracy": 0.9654911234974861, |
| "step": 593 |
| }, |
| { |
| "epoch": 3.4750733137829912, |
| "grad_norm": 0.8653675322495964, |
| "learning_rate": 3.119725778213785e-05, |
| "loss": 0.1131, |
| "mean_token_accuracy": 0.964490219950676, |
| "step": 594 |
| }, |
| { |
| "epoch": 3.4809384164222874, |
| "grad_norm": 1.1050450659698694, |
| "learning_rate": 3.116776292191774e-05, |
| "loss": 0.1248, |
| "mean_token_accuracy": 0.9631328731775284, |
| "step": 595 |
| }, |
| { |
| "epoch": 3.4868035190615836, |
| "grad_norm": 0.9206209235146391, |
| "learning_rate": 3.1138234786420834e-05, |
| "loss": 0.1006, |
| "mean_token_accuracy": 0.9688453301787376, |
| "step": 596 |
| }, |
| { |
| "epoch": 3.4926686217008798, |
| "grad_norm": 0.9717559056575034, |
| "learning_rate": 3.110867348282235e-05, |
| "loss": 0.1285, |
| "mean_token_accuracy": 0.9620684534311295, |
| "step": 597 |
| }, |
| { |
| "epoch": 3.498533724340176, |
| "grad_norm": 1.0752755933385176, |
| "learning_rate": 3.107907911841787e-05, |
| "loss": 0.1042, |
| "mean_token_accuracy": 0.9659099653363228, |
| "step": 598 |
| }, |
| { |
| "epoch": 3.504398826979472, |
| "grad_norm": 0.7770239700047303, |
| "learning_rate": 3.104945180062301e-05, |
| "loss": 0.1076, |
| "mean_token_accuracy": 0.9701974913477898, |
| "step": 599 |
| }, |
| { |
| "epoch": 3.5102639296187683, |
| "grad_norm": 1.109185174777014, |
| "learning_rate": 3.1019791636972936e-05, |
| "loss": 0.1048, |
| "mean_token_accuracy": 0.966381847858429, |
| "step": 600 |
| }, |
| { |
| "epoch": 3.5161290322580645, |
| "grad_norm": 1.0263635177331654, |
| "learning_rate": 3.099009873512208e-05, |
| "loss": 0.1346, |
| "mean_token_accuracy": 0.9632927849888802, |
| "step": 601 |
| }, |
| { |
| "epoch": 3.5219941348973607, |
| "grad_norm": 0.871857986594143, |
| "learning_rate": 3.0960373202843685e-05, |
| "loss": 0.0982, |
| "mean_token_accuracy": 0.9723653644323349, |
| "step": 602 |
| }, |
| { |
| "epoch": 3.527859237536657, |
| "grad_norm": 1.143952454054944, |
| "learning_rate": 3.093061514802943e-05, |
| "loss": 0.1194, |
| "mean_token_accuracy": 0.9627049937844276, |
| "step": 603 |
| }, |
| { |
| "epoch": 3.533724340175953, |
| "grad_norm": 1.0299654159664773, |
| "learning_rate": 3.090082467868901e-05, |
| "loss": 0.0984, |
| "mean_token_accuracy": 0.9705034419894218, |
| "step": 604 |
| }, |
| { |
| "epoch": 3.5395894428152492, |
| "grad_norm": 0.9442694873564053, |
| "learning_rate": 3.087100190294983e-05, |
| "loss": 0.1195, |
| "mean_token_accuracy": 0.9644537046551704, |
| "step": 605 |
| }, |
| { |
| "epoch": 3.5454545454545454, |
| "grad_norm": 1.0579964676689142, |
| "learning_rate": 3.0841146929056505e-05, |
| "loss": 0.124, |
| "mean_token_accuracy": 0.9656395390629768, |
| "step": 606 |
| }, |
| { |
| "epoch": 3.5513196480938416, |
| "grad_norm": 1.0119617464563753, |
| "learning_rate": 3.0811259865370535e-05, |
| "loss": 0.1025, |
| "mean_token_accuracy": 0.9686230942606926, |
| "step": 607 |
| }, |
| { |
| "epoch": 3.557184750733138, |
| "grad_norm": 1.0545508663891536, |
| "learning_rate": 3.07813408203699e-05, |
| "loss": 0.1114, |
| "mean_token_accuracy": 0.9672858342528343, |
| "step": 608 |
| }, |
| { |
| "epoch": 3.563049853372434, |
| "grad_norm": 0.83374859697724, |
| "learning_rate": 3.075138990264863e-05, |
| "loss": 0.134, |
| "mean_token_accuracy": 0.9622107297182083, |
| "step": 609 |
| }, |
| { |
| "epoch": 3.56891495601173, |
| "grad_norm": 0.9945934991118207, |
| "learning_rate": 3.072140722091648e-05, |
| "loss": 0.0984, |
| "mean_token_accuracy": 0.9695856347680092, |
| "step": 610 |
| }, |
| { |
| "epoch": 3.5747800586510263, |
| "grad_norm": 0.9385842099807644, |
| "learning_rate": 3.0691392883998455e-05, |
| "loss": 0.1245, |
| "mean_token_accuracy": 0.9652091339230537, |
| "step": 611 |
| }, |
| { |
| "epoch": 3.5806451612903225, |
| "grad_norm": 0.9443437934567439, |
| "learning_rate": 3.0661347000834496e-05, |
| "loss": 0.1139, |
| "mean_token_accuracy": 0.9681995660066605, |
| "step": 612 |
| }, |
| { |
| "epoch": 3.5865102639296187, |
| "grad_norm": 0.9825906807831453, |
| "learning_rate": 3.063126968047901e-05, |
| "loss": 0.1165, |
| "mean_token_accuracy": 0.9647257775068283, |
| "step": 613 |
| }, |
| { |
| "epoch": 3.592375366568915, |
| "grad_norm": 0.9344625985940249, |
| "learning_rate": 3.060116103210053e-05, |
| "loss": 0.0927, |
| "mean_token_accuracy": 0.9714125767350197, |
| "step": 614 |
| }, |
| { |
| "epoch": 3.598240469208211, |
| "grad_norm": 0.8666974286644824, |
| "learning_rate": 3.057102116498129e-05, |
| "loss": 0.1037, |
| "mean_token_accuracy": 0.9673436060547829, |
| "step": 615 |
| }, |
| { |
| "epoch": 3.6041055718475072, |
| "grad_norm": 2.226359878211702, |
| "learning_rate": 3.0540850188516826e-05, |
| "loss": 0.1174, |
| "mean_token_accuracy": 0.9670251458883286, |
| "step": 616 |
| }, |
| { |
| "epoch": 3.6099706744868034, |
| "grad_norm": 0.9103387358090266, |
| "learning_rate": 3.051064821221561e-05, |
| "loss": 0.0985, |
| "mean_token_accuracy": 0.9705724716186523, |
| "step": 617 |
| }, |
| { |
| "epoch": 3.6158357771260996, |
| "grad_norm": 1.0486044217213084, |
| "learning_rate": 3.0480415345698606e-05, |
| "loss": 0.1383, |
| "mean_token_accuracy": 0.9586537033319473, |
| "step": 618 |
| }, |
| { |
| "epoch": 3.621700879765396, |
| "grad_norm": 1.0576298255454961, |
| "learning_rate": 3.045015169869892e-05, |
| "loss": 0.1036, |
| "mean_token_accuracy": 0.9723232910037041, |
| "step": 619 |
| }, |
| { |
| "epoch": 3.627565982404692, |
| "grad_norm": 0.9867562775894735, |
| "learning_rate": 3.0419857381061355e-05, |
| "loss": 0.1179, |
| "mean_token_accuracy": 0.9649086743593216, |
| "step": 620 |
| }, |
| { |
| "epoch": 3.633431085043988, |
| "grad_norm": 0.8724859401368507, |
| "learning_rate": 3.0389532502742066e-05, |
| "loss": 0.0978, |
| "mean_token_accuracy": 0.9671208187937737, |
| "step": 621 |
| }, |
| { |
| "epoch": 3.6392961876832843, |
| "grad_norm": 1.07839803120773, |
| "learning_rate": 3.0359177173808104e-05, |
| "loss": 0.1221, |
| "mean_token_accuracy": 0.9660301432013512, |
| "step": 622 |
| }, |
| { |
| "epoch": 3.6451612903225805, |
| "grad_norm": 1.0170718623865844, |
| "learning_rate": 3.032879150443705e-05, |
| "loss": 0.1105, |
| "mean_token_accuracy": 0.9689130410552025, |
| "step": 623 |
| }, |
| { |
| "epoch": 3.6510263929618767, |
| "grad_norm": 0.9733375577875363, |
| "learning_rate": 3.029837560491662e-05, |
| "loss": 0.0968, |
| "mean_token_accuracy": 0.9714087471365929, |
| "step": 624 |
| }, |
| { |
| "epoch": 3.656891495601173, |
| "grad_norm": 1.0174522668129806, |
| "learning_rate": 3.0267929585644236e-05, |
| "loss": 0.1192, |
| "mean_token_accuracy": 0.9647278562188148, |
| "step": 625 |
| }, |
| { |
| "epoch": 3.662756598240469, |
| "grad_norm": 1.0062347655942014, |
| "learning_rate": 3.0237453557126656e-05, |
| "loss": 0.1081, |
| "mean_token_accuracy": 0.9678944423794746, |
| "step": 626 |
| }, |
| { |
| "epoch": 3.6686217008797652, |
| "grad_norm": 0.9967334120614507, |
| "learning_rate": 3.020694762997956e-05, |
| "loss": 0.1125, |
| "mean_token_accuracy": 0.9661891385912895, |
| "step": 627 |
| }, |
| { |
| "epoch": 3.6744868035190614, |
| "grad_norm": 0.9244227695101611, |
| "learning_rate": 3.017641191492714e-05, |
| "loss": 0.0937, |
| "mean_token_accuracy": 0.9720464572310448, |
| "step": 628 |
| }, |
| { |
| "epoch": 3.6803519061583576, |
| "grad_norm": 1.002358011210733, |
| "learning_rate": 3.0145846522801703e-05, |
| "loss": 0.0919, |
| "mean_token_accuracy": 0.9704943671822548, |
| "step": 629 |
| }, |
| { |
| "epoch": 3.686217008797654, |
| "grad_norm": 1.198277332535796, |
| "learning_rate": 3.0115251564543287e-05, |
| "loss": 0.1403, |
| "mean_token_accuracy": 0.9590641185641289, |
| "step": 630 |
| }, |
| { |
| "epoch": 3.6920821114369504, |
| "grad_norm": 1.3056710213263667, |
| "learning_rate": 3.008462715119922e-05, |
| "loss": 0.158, |
| "mean_token_accuracy": 0.9538592919707298, |
| "step": 631 |
| }, |
| { |
| "epoch": 3.6979472140762466, |
| "grad_norm": 1.3780337572816563, |
| "learning_rate": 3.0053973393923768e-05, |
| "loss": 0.1009, |
| "mean_token_accuracy": 0.9703397899866104, |
| "step": 632 |
| }, |
| { |
| "epoch": 3.703812316715543, |
| "grad_norm": 0.8557816240918312, |
| "learning_rate": 3.0023290403977694e-05, |
| "loss": 0.1209, |
| "mean_token_accuracy": 0.9657327905297279, |
| "step": 633 |
| }, |
| { |
| "epoch": 3.709677419354839, |
| "grad_norm": 0.9844224729335839, |
| "learning_rate": 2.9992578292727842e-05, |
| "loss": 0.1179, |
| "mean_token_accuracy": 0.9640586525201797, |
| "step": 634 |
| }, |
| { |
| "epoch": 3.715542521994135, |
| "grad_norm": 0.9674484215989431, |
| "learning_rate": 2.9961837171646778e-05, |
| "loss": 0.1136, |
| "mean_token_accuracy": 0.9681580066680908, |
| "step": 635 |
| }, |
| { |
| "epoch": 3.7214076246334313, |
| "grad_norm": 0.9424755969637976, |
| "learning_rate": 2.993106715231237e-05, |
| "loss": 0.1201, |
| "mean_token_accuracy": 0.9686867296695709, |
| "step": 636 |
| }, |
| { |
| "epoch": 3.7272727272727275, |
| "grad_norm": 0.9455408526650082, |
| "learning_rate": 2.9900268346407336e-05, |
| "loss": 0.1317, |
| "mean_token_accuracy": 0.9632778465747833, |
| "step": 637 |
| }, |
| { |
| "epoch": 3.7331378299120237, |
| "grad_norm": 1.1249676030385811, |
| "learning_rate": 2.986944086571893e-05, |
| "loss": 0.1395, |
| "mean_token_accuracy": 0.9588330909609795, |
| "step": 638 |
| }, |
| { |
| "epoch": 3.73900293255132, |
| "grad_norm": 1.0055233050654055, |
| "learning_rate": 2.983858482213843e-05, |
| "loss": 0.0966, |
| "mean_token_accuracy": 0.9707036763429642, |
| "step": 639 |
| }, |
| { |
| "epoch": 3.744868035190616, |
| "grad_norm": 0.7933758824565834, |
| "learning_rate": 2.9807700327660834e-05, |
| "loss": 0.1108, |
| "mean_token_accuracy": 0.9678425192832947, |
| "step": 640 |
| }, |
| { |
| "epoch": 3.7507331378299122, |
| "grad_norm": 0.8528929707688316, |
| "learning_rate": 2.977678749438437e-05, |
| "loss": 0.1145, |
| "mean_token_accuracy": 0.9663086980581284, |
| "step": 641 |
| }, |
| { |
| "epoch": 3.7565982404692084, |
| "grad_norm": 0.9774312078342523, |
| "learning_rate": 2.9745846434510146e-05, |
| "loss": 0.1084, |
| "mean_token_accuracy": 0.9694355204701424, |
| "step": 642 |
| }, |
| { |
| "epoch": 3.7624633431085046, |
| "grad_norm": 0.9193243474398831, |
| "learning_rate": 2.9714877260341705e-05, |
| "loss": 0.1268, |
| "mean_token_accuracy": 0.9626642465591431, |
| "step": 643 |
| }, |
| { |
| "epoch": 3.768328445747801, |
| "grad_norm": 0.8728109093263364, |
| "learning_rate": 2.9683880084284648e-05, |
| "loss": 0.0955, |
| "mean_token_accuracy": 0.9732156321406364, |
| "step": 644 |
| }, |
| { |
| "epoch": 3.774193548387097, |
| "grad_norm": 0.9244646931723717, |
| "learning_rate": 2.96528550188462e-05, |
| "loss": 0.1175, |
| "mean_token_accuracy": 0.9670339375734329, |
| "step": 645 |
| }, |
| { |
| "epoch": 3.780058651026393, |
| "grad_norm": 0.8008396977844219, |
| "learning_rate": 2.962180217663483e-05, |
| "loss": 0.1114, |
| "mean_token_accuracy": 0.9655383676290512, |
| "step": 646 |
| }, |
| { |
| "epoch": 3.7859237536656893, |
| "grad_norm": 1.0307500015042614, |
| "learning_rate": 2.95907216703598e-05, |
| "loss": 0.1124, |
| "mean_token_accuracy": 0.9662497565150261, |
| "step": 647 |
| }, |
| { |
| "epoch": 3.7917888563049855, |
| "grad_norm": 1.0372077539310007, |
| "learning_rate": 2.9559613612830797e-05, |
| "loss": 0.1255, |
| "mean_token_accuracy": 0.961214154958725, |
| "step": 648 |
| }, |
| { |
| "epoch": 3.7976539589442817, |
| "grad_norm": 0.8351390987420513, |
| "learning_rate": 2.952847811695751e-05, |
| "loss": 0.1121, |
| "mean_token_accuracy": 0.9706973433494568, |
| "step": 649 |
| }, |
| { |
| "epoch": 3.803519061583578, |
| "grad_norm": 0.9879339227027757, |
| "learning_rate": 2.9497315295749218e-05, |
| "loss": 0.116, |
| "mean_token_accuracy": 0.9665387272834778, |
| "step": 650 |
| }, |
| { |
| "epoch": 3.809384164222874, |
| "grad_norm": 1.2087606003229365, |
| "learning_rate": 2.9466125262314368e-05, |
| "loss": 0.142, |
| "mean_token_accuracy": 0.9571318477392197, |
| "step": 651 |
| }, |
| { |
| "epoch": 3.8152492668621703, |
| "grad_norm": 0.9043237278983707, |
| "learning_rate": 2.9434908129860193e-05, |
| "loss": 0.1054, |
| "mean_token_accuracy": 0.9690318033099174, |
| "step": 652 |
| }, |
| { |
| "epoch": 3.8211143695014664, |
| "grad_norm": 1.2355269720420694, |
| "learning_rate": 2.9403664011692276e-05, |
| "loss": 0.1375, |
| "mean_token_accuracy": 0.9594130963087082, |
| "step": 653 |
| }, |
| { |
| "epoch": 3.8269794721407626, |
| "grad_norm": 0.9958573729656797, |
| "learning_rate": 2.9372393021214134e-05, |
| "loss": 0.1399, |
| "mean_token_accuracy": 0.9584333077073097, |
| "step": 654 |
| }, |
| { |
| "epoch": 3.832844574780059, |
| "grad_norm": 1.2287650649576085, |
| "learning_rate": 2.9341095271926842e-05, |
| "loss": 0.1284, |
| "mean_token_accuracy": 0.9632050767540932, |
| "step": 655 |
| }, |
| { |
| "epoch": 3.838709677419355, |
| "grad_norm": 1.1734165312438198, |
| "learning_rate": 2.930977087742859e-05, |
| "loss": 0.1023, |
| "mean_token_accuracy": 0.9691994562745094, |
| "step": 656 |
| }, |
| { |
| "epoch": 3.844574780058651, |
| "grad_norm": 0.8472146928331651, |
| "learning_rate": 2.9278419951414277e-05, |
| "loss": 0.1158, |
| "mean_token_accuracy": 0.9662778377532959, |
| "step": 657 |
| }, |
| { |
| "epoch": 3.8504398826979473, |
| "grad_norm": 0.9489012330648977, |
| "learning_rate": 2.9247042607675105e-05, |
| "loss": 0.1195, |
| "mean_token_accuracy": 0.9632801786065102, |
| "step": 658 |
| }, |
| { |
| "epoch": 3.8563049853372435, |
| "grad_norm": 0.8468422513424982, |
| "learning_rate": 2.9215638960098164e-05, |
| "loss": 0.073, |
| "mean_token_accuracy": 0.9786935448646545, |
| "step": 659 |
| }, |
| { |
| "epoch": 3.8621700879765397, |
| "grad_norm": 0.6091605564057077, |
| "learning_rate": 2.9184209122665996e-05, |
| "loss": 0.0966, |
| "mean_token_accuracy": 0.969777375459671, |
| "step": 660 |
| }, |
| { |
| "epoch": 3.868035190615836, |
| "grad_norm": 0.7295390267906454, |
| "learning_rate": 2.915275320945623e-05, |
| "loss": 0.1271, |
| "mean_token_accuracy": 0.9638236686587334, |
| "step": 661 |
| }, |
| { |
| "epoch": 3.873900293255132, |
| "grad_norm": 1.2158300799396626, |
| "learning_rate": 2.9121271334641127e-05, |
| "loss": 0.1282, |
| "mean_token_accuracy": 0.9644179865717888, |
| "step": 662 |
| }, |
| { |
| "epoch": 3.8797653958944283, |
| "grad_norm": 1.0737471767682187, |
| "learning_rate": 2.908976361248717e-05, |
| "loss": 0.114, |
| "mean_token_accuracy": 0.9729373753070831, |
| "step": 663 |
| }, |
| { |
| "epoch": 3.8856304985337244, |
| "grad_norm": 0.7938043248994715, |
| "learning_rate": 2.9058230157354674e-05, |
| "loss": 0.1261, |
| "mean_token_accuracy": 0.9626899287104607, |
| "step": 664 |
| }, |
| { |
| "epoch": 3.8914956011730206, |
| "grad_norm": 1.1900366046432855, |
| "learning_rate": 2.902667108369734e-05, |
| "loss": 0.1219, |
| "mean_token_accuracy": 0.9647004157304764, |
| "step": 665 |
| }, |
| { |
| "epoch": 3.897360703812317, |
| "grad_norm": 0.9392537748131257, |
| "learning_rate": 2.8995086506061862e-05, |
| "loss": 0.1062, |
| "mean_token_accuracy": 0.9695572704076767, |
| "step": 666 |
| }, |
| { |
| "epoch": 3.903225806451613, |
| "grad_norm": 0.8882779542609907, |
| "learning_rate": 2.896347653908749e-05, |
| "loss": 0.098, |
| "mean_token_accuracy": 0.973405510187149, |
| "step": 667 |
| }, |
| { |
| "epoch": 3.909090909090909, |
| "grad_norm": 0.7571815374914855, |
| "learning_rate": 2.8931841297505657e-05, |
| "loss": 0.0982, |
| "mean_token_accuracy": 0.969622477889061, |
| "step": 668 |
| }, |
| { |
| "epoch": 3.9149560117302054, |
| "grad_norm": 0.8781968094346194, |
| "learning_rate": 2.8900180896139503e-05, |
| "loss": 0.0988, |
| "mean_token_accuracy": 0.972535714507103, |
| "step": 669 |
| }, |
| { |
| "epoch": 3.9208211143695015, |
| "grad_norm": 0.981652722231685, |
| "learning_rate": 2.8868495449903498e-05, |
| "loss": 0.0809, |
| "mean_token_accuracy": 0.9754110649228096, |
| "step": 670 |
| }, |
| { |
| "epoch": 3.9266862170087977, |
| "grad_norm": 0.7083811647983249, |
| "learning_rate": 2.8836785073803014e-05, |
| "loss": 0.0993, |
| "mean_token_accuracy": 0.9723174721002579, |
| "step": 671 |
| }, |
| { |
| "epoch": 3.932551319648094, |
| "grad_norm": 0.7916889704987639, |
| "learning_rate": 2.880504988293391e-05, |
| "loss": 0.1041, |
| "mean_token_accuracy": 0.968935064971447, |
| "step": 672 |
| }, |
| { |
| "epoch": 3.93841642228739, |
| "grad_norm": 0.8461912090206244, |
| "learning_rate": 2.8773289992482115e-05, |
| "loss": 0.1058, |
| "mean_token_accuracy": 0.9667421951889992, |
| "step": 673 |
| }, |
| { |
| "epoch": 3.9442815249266863, |
| "grad_norm": 0.821497051407434, |
| "learning_rate": 2.87415055177232e-05, |
| "loss": 0.1099, |
| "mean_token_accuracy": 0.9673136919736862, |
| "step": 674 |
| }, |
| { |
| "epoch": 3.9501466275659824, |
| "grad_norm": 0.7737302184142852, |
| "learning_rate": 2.870969657402197e-05, |
| "loss": 0.1204, |
| "mean_token_accuracy": 0.9651020839810371, |
| "step": 675 |
| }, |
| { |
| "epoch": 3.9560117302052786, |
| "grad_norm": 1.0755731560585788, |
| "learning_rate": 2.867786327683205e-05, |
| "loss": 0.153, |
| "mean_token_accuracy": 0.9559778422117233, |
| "step": 676 |
| }, |
| { |
| "epoch": 3.961876832844575, |
| "grad_norm": 1.072752247884178, |
| "learning_rate": 2.864600574169545e-05, |
| "loss": 0.1122, |
| "mean_token_accuracy": 0.9674321562051773, |
| "step": 677 |
| }, |
| { |
| "epoch": 3.967741935483871, |
| "grad_norm": 0.9687439947338238, |
| "learning_rate": 2.861412408424216e-05, |
| "loss": 0.1152, |
| "mean_token_accuracy": 0.9655726253986359, |
| "step": 678 |
| }, |
| { |
| "epoch": 3.973607038123167, |
| "grad_norm": 1.2078607637774967, |
| "learning_rate": 2.8582218420189706e-05, |
| "loss": 0.1288, |
| "mean_token_accuracy": 0.9655884131789207, |
| "step": 679 |
| }, |
| { |
| "epoch": 3.9794721407624634, |
| "grad_norm": 1.067708348114871, |
| "learning_rate": 2.855028886534278e-05, |
| "loss": 0.1357, |
| "mean_token_accuracy": 0.9624500647187233, |
| "step": 680 |
| }, |
| { |
| "epoch": 3.9853372434017595, |
| "grad_norm": 1.0105927291093553, |
| "learning_rate": 2.851833553559276e-05, |
| "loss": 0.1121, |
| "mean_token_accuracy": 0.9678521081805229, |
| "step": 681 |
| }, |
| { |
| "epoch": 3.9912023460410557, |
| "grad_norm": 0.9189958182692042, |
| "learning_rate": 2.848635854691733e-05, |
| "loss": 0.1068, |
| "mean_token_accuracy": 0.9670966193079948, |
| "step": 682 |
| }, |
| { |
| "epoch": 3.997067448680352, |
| "grad_norm": 1.0148596552604907, |
| "learning_rate": 2.8454358015380046e-05, |
| "loss": 0.0923, |
| "mean_token_accuracy": 0.9698840975761414, |
| "step": 683 |
| }, |
| { |
| "epoch": 4.0, |
| "grad_norm": 1.8462979410466998, |
| "learning_rate": 2.8422334057129913e-05, |
| "loss": 0.1143, |
| "mean_token_accuracy": 0.9644208699464798, |
| "step": 684 |
| }, |
| { |
| "epoch": 4.005865102639296, |
| "grad_norm": 0.8309715222349474, |
| "learning_rate": 2.8390286788400967e-05, |
| "loss": 0.0824, |
| "mean_token_accuracy": 0.9704834669828415, |
| "step": 685 |
| }, |
| { |
| "epoch": 4.011730205278592, |
| "grad_norm": 0.870173230690534, |
| "learning_rate": 2.8358216325511847e-05, |
| "loss": 0.0762, |
| "mean_token_accuracy": 0.9775184169411659, |
| "step": 686 |
| }, |
| { |
| "epoch": 4.0175953079178885, |
| "grad_norm": 0.8724933903065529, |
| "learning_rate": 2.832612278486538e-05, |
| "loss": 0.1006, |
| "mean_token_accuracy": 0.9713100343942642, |
| "step": 687 |
| }, |
| { |
| "epoch": 4.023460410557185, |
| "grad_norm": 0.7725998310377216, |
| "learning_rate": 2.8294006282948165e-05, |
| "loss": 0.0825, |
| "mean_token_accuracy": 0.9770268797874451, |
| "step": 688 |
| }, |
| { |
| "epoch": 4.029325513196481, |
| "grad_norm": 0.9213705846046193, |
| "learning_rate": 2.8261866936330123e-05, |
| "loss": 0.0928, |
| "mean_token_accuracy": 0.9697828590869904, |
| "step": 689 |
| }, |
| { |
| "epoch": 4.035190615835777, |
| "grad_norm": 0.9164311785394971, |
| "learning_rate": 2.8229704861664113e-05, |
| "loss": 0.0884, |
| "mean_token_accuracy": 0.974254809319973, |
| "step": 690 |
| }, |
| { |
| "epoch": 4.041055718475073, |
| "grad_norm": 0.9964223054765102, |
| "learning_rate": 2.8197520175685462e-05, |
| "loss": 0.0928, |
| "mean_token_accuracy": 0.9761571735143661, |
| "step": 691 |
| }, |
| { |
| "epoch": 4.0469208211143695, |
| "grad_norm": 0.6997071585836834, |
| "learning_rate": 2.8165312995211596e-05, |
| "loss": 0.0805, |
| "mean_token_accuracy": 0.9769442081451416, |
| "step": 692 |
| }, |
| { |
| "epoch": 4.052785923753666, |
| "grad_norm": 0.6214295435479037, |
| "learning_rate": 2.813308343714156e-05, |
| "loss": 0.0696, |
| "mean_token_accuracy": 0.9754916131496429, |
| "step": 693 |
| }, |
| { |
| "epoch": 4.058651026392962, |
| "grad_norm": 0.9160480861099328, |
| "learning_rate": 2.810083161845564e-05, |
| "loss": 0.0843, |
| "mean_token_accuracy": 0.9728389903903008, |
| "step": 694 |
| }, |
| { |
| "epoch": 4.064516129032258, |
| "grad_norm": 0.8228292525646084, |
| "learning_rate": 2.8068557656214913e-05, |
| "loss": 0.0877, |
| "mean_token_accuracy": 0.975266806781292, |
| "step": 695 |
| }, |
| { |
| "epoch": 4.070381231671554, |
| "grad_norm": 0.7567610887777896, |
| "learning_rate": 2.8036261667560826e-05, |
| "loss": 0.0857, |
| "mean_token_accuracy": 0.9754011780023575, |
| "step": 696 |
| }, |
| { |
| "epoch": 4.07624633431085, |
| "grad_norm": 0.8298182774230494, |
| "learning_rate": 2.8003943769714776e-05, |
| "loss": 0.0987, |
| "mean_token_accuracy": 0.9720055907964706, |
| "step": 697 |
| }, |
| { |
| "epoch": 4.0821114369501466, |
| "grad_norm": 0.8355014577188172, |
| "learning_rate": 2.7971604079977673e-05, |
| "loss": 0.103, |
| "mean_token_accuracy": 0.969631053507328, |
| "step": 698 |
| }, |
| { |
| "epoch": 4.087976539589443, |
| "grad_norm": 0.7652439863283277, |
| "learning_rate": 2.793924271572954e-05, |
| "loss": 0.0877, |
| "mean_token_accuracy": 0.9737903922796249, |
| "step": 699 |
| }, |
| { |
| "epoch": 4.093841642228739, |
| "grad_norm": 0.8251456929986012, |
| "learning_rate": 2.7906859794429047e-05, |
| "loss": 0.0907, |
| "mean_token_accuracy": 0.9713805019855499, |
| "step": 700 |
| }, |
| { |
| "epoch": 4.099706744868035, |
| "grad_norm": 0.8578244497152002, |
| "learning_rate": 2.787445543361313e-05, |
| "loss": 0.0817, |
| "mean_token_accuracy": 0.9748812690377235, |
| "step": 701 |
| }, |
| { |
| "epoch": 4.105571847507331, |
| "grad_norm": 2.0012386249383654, |
| "learning_rate": 2.7842029750896525e-05, |
| "loss": 0.1236, |
| "mean_token_accuracy": 0.9688002988696098, |
| "step": 702 |
| }, |
| { |
| "epoch": 4.1114369501466275, |
| "grad_norm": 0.8169472384017665, |
| "learning_rate": 2.7809582863971373e-05, |
| "loss": 0.1007, |
| "mean_token_accuracy": 0.9726080745458603, |
| "step": 703 |
| }, |
| { |
| "epoch": 4.117302052785924, |
| "grad_norm": 0.7344538146094689, |
| "learning_rate": 2.777711489060676e-05, |
| "loss": 0.0952, |
| "mean_token_accuracy": 0.9706440791487694, |
| "step": 704 |
| }, |
| { |
| "epoch": 4.12316715542522, |
| "grad_norm": 0.6827415837619415, |
| "learning_rate": 2.7744625948648316e-05, |
| "loss": 0.0814, |
| "mean_token_accuracy": 0.9768778160214424, |
| "step": 705 |
| }, |
| { |
| "epoch": 4.129032258064516, |
| "grad_norm": 0.6892663949268744, |
| "learning_rate": 2.7712116156017783e-05, |
| "loss": 0.083, |
| "mean_token_accuracy": 0.976724274456501, |
| "step": 706 |
| }, |
| { |
| "epoch": 4.134897360703812, |
| "grad_norm": 0.8833845705107489, |
| "learning_rate": 2.7679585630712585e-05, |
| "loss": 0.1002, |
| "mean_token_accuracy": 0.9703218340873718, |
| "step": 707 |
| }, |
| { |
| "epoch": 4.140762463343108, |
| "grad_norm": 0.6951848212640516, |
| "learning_rate": 2.764703449080538e-05, |
| "loss": 0.0852, |
| "mean_token_accuracy": 0.9751351922750473, |
| "step": 708 |
| }, |
| { |
| "epoch": 4.146627565982405, |
| "grad_norm": 0.7844537288917677, |
| "learning_rate": 2.761446285444366e-05, |
| "loss": 0.094, |
| "mean_token_accuracy": 0.9713953137397766, |
| "step": 709 |
| }, |
| { |
| "epoch": 4.152492668621701, |
| "grad_norm": 0.6073561410934927, |
| "learning_rate": 2.758187083984931e-05, |
| "loss": 0.0742, |
| "mean_token_accuracy": 0.979846678674221, |
| "step": 710 |
| }, |
| { |
| "epoch": 4.158357771260997, |
| "grad_norm": 1.02646903244523, |
| "learning_rate": 2.754925856531819e-05, |
| "loss": 0.1017, |
| "mean_token_accuracy": 0.9713460206985474, |
| "step": 711 |
| }, |
| { |
| "epoch": 4.164222873900293, |
| "grad_norm": 0.791224278335533, |
| "learning_rate": 2.7516626149219678e-05, |
| "loss": 0.0822, |
| "mean_token_accuracy": 0.9769997522234917, |
| "step": 712 |
| }, |
| { |
| "epoch": 4.170087976539589, |
| "grad_norm": 0.6766217855079016, |
| "learning_rate": 2.7483973709996267e-05, |
| "loss": 0.0882, |
| "mean_token_accuracy": 0.9750803634524345, |
| "step": 713 |
| }, |
| { |
| "epoch": 4.1759530791788855, |
| "grad_norm": 0.8810581764225817, |
| "learning_rate": 2.7451301366163116e-05, |
| "loss": 0.103, |
| "mean_token_accuracy": 0.9694948419928551, |
| "step": 714 |
| }, |
| { |
| "epoch": 4.181818181818182, |
| "grad_norm": 0.6091010162338775, |
| "learning_rate": 2.741860923630765e-05, |
| "loss": 0.0722, |
| "mean_token_accuracy": 0.9799239709973335, |
| "step": 715 |
| }, |
| { |
| "epoch": 4.187683284457478, |
| "grad_norm": 0.9397306887291648, |
| "learning_rate": 2.7385897439089086e-05, |
| "loss": 0.0897, |
| "mean_token_accuracy": 0.9735899195075035, |
| "step": 716 |
| }, |
| { |
| "epoch": 4.193548387096774, |
| "grad_norm": 0.9305247718186483, |
| "learning_rate": 2.735316609323804e-05, |
| "loss": 0.105, |
| "mean_token_accuracy": 0.9696411564946175, |
| "step": 717 |
| }, |
| { |
| "epoch": 4.19941348973607, |
| "grad_norm": 0.839558099374855, |
| "learning_rate": 2.7320415317556085e-05, |
| "loss": 0.0926, |
| "mean_token_accuracy": 0.9743531122803688, |
| "step": 718 |
| }, |
| { |
| "epoch": 4.205278592375366, |
| "grad_norm": 0.8015165041637531, |
| "learning_rate": 2.72876452309153e-05, |
| "loss": 0.0769, |
| "mean_token_accuracy": 0.9769142642617226, |
| "step": 719 |
| }, |
| { |
| "epoch": 4.211143695014663, |
| "grad_norm": 0.904863126847494, |
| "learning_rate": 2.7254855952257867e-05, |
| "loss": 0.0965, |
| "mean_token_accuracy": 0.9713497161865234, |
| "step": 720 |
| }, |
| { |
| "epoch": 4.217008797653959, |
| "grad_norm": 1.1447287147619216, |
| "learning_rate": 2.7222047600595626e-05, |
| "loss": 0.1125, |
| "mean_token_accuracy": 0.9678602889180183, |
| "step": 721 |
| }, |
| { |
| "epoch": 4.222873900293255, |
| "grad_norm": 0.6811363601209449, |
| "learning_rate": 2.718922029500965e-05, |
| "loss": 0.082, |
| "mean_token_accuracy": 0.9760172292590141, |
| "step": 722 |
| }, |
| { |
| "epoch": 4.228739002932551, |
| "grad_norm": 0.8682321737802231, |
| "learning_rate": 2.7156374154649787e-05, |
| "loss": 0.0895, |
| "mean_token_accuracy": 0.972284585237503, |
| "step": 723 |
| }, |
| { |
| "epoch": 4.234604105571847, |
| "grad_norm": 0.7858842014740195, |
| "learning_rate": 2.7123509298734267e-05, |
| "loss": 0.0896, |
| "mean_token_accuracy": 0.9748860970139503, |
| "step": 724 |
| }, |
| { |
| "epoch": 4.2404692082111435, |
| "grad_norm": 0.7803207391492687, |
| "learning_rate": 2.7090625846549247e-05, |
| "loss": 0.0925, |
| "mean_token_accuracy": 0.9706885814666748, |
| "step": 725 |
| }, |
| { |
| "epoch": 4.24633431085044, |
| "grad_norm": 1.1677543957359848, |
| "learning_rate": 2.705772391744837e-05, |
| "loss": 0.1145, |
| "mean_token_accuracy": 0.9681753516197205, |
| "step": 726 |
| }, |
| { |
| "epoch": 4.252199413489736, |
| "grad_norm": 0.9170706318759467, |
| "learning_rate": 2.7024803630852362e-05, |
| "loss": 0.0921, |
| "mean_token_accuracy": 0.9747585207223892, |
| "step": 727 |
| }, |
| { |
| "epoch": 4.258064516129032, |
| "grad_norm": 0.7132222699945785, |
| "learning_rate": 2.699186510624856e-05, |
| "loss": 0.0989, |
| "mean_token_accuracy": 0.9715269804000854, |
| "step": 728 |
| }, |
| { |
| "epoch": 4.263929618768328, |
| "grad_norm": 0.7219852764632368, |
| "learning_rate": 2.6958908463190506e-05, |
| "loss": 0.092, |
| "mean_token_accuracy": 0.9742382988333702, |
| "step": 729 |
| }, |
| { |
| "epoch": 4.269794721407624, |
| "grad_norm": 0.7543221985745602, |
| "learning_rate": 2.6925933821297497e-05, |
| "loss": 0.091, |
| "mean_token_accuracy": 0.9712286666035652, |
| "step": 730 |
| }, |
| { |
| "epoch": 4.275659824046921, |
| "grad_norm": 0.8374221740590484, |
| "learning_rate": 2.6892941300254176e-05, |
| "loss": 0.1058, |
| "mean_token_accuracy": 0.9711539074778557, |
| "step": 731 |
| }, |
| { |
| "epoch": 4.281524926686217, |
| "grad_norm": 0.753573683888248, |
| "learning_rate": 2.685993101981007e-05, |
| "loss": 0.0914, |
| "mean_token_accuracy": 0.9735663160681725, |
| "step": 732 |
| }, |
| { |
| "epoch": 4.287390029325513, |
| "grad_norm": 0.8643191548607165, |
| "learning_rate": 2.6826903099779157e-05, |
| "loss": 0.0925, |
| "mean_token_accuracy": 0.976229302585125, |
| "step": 733 |
| }, |
| { |
| "epoch": 4.293255131964809, |
| "grad_norm": 0.8183124471156848, |
| "learning_rate": 2.679385766003945e-05, |
| "loss": 0.0961, |
| "mean_token_accuracy": 0.971428208053112, |
| "step": 734 |
| }, |
| { |
| "epoch": 4.299120234604105, |
| "grad_norm": 0.7393638741111308, |
| "learning_rate": 2.676079482053255e-05, |
| "loss": 0.1018, |
| "mean_token_accuracy": 0.9702118262648582, |
| "step": 735 |
| }, |
| { |
| "epoch": 4.3049853372434015, |
| "grad_norm": 0.8476429324489293, |
| "learning_rate": 2.6727714701263212e-05, |
| "loss": 0.0952, |
| "mean_token_accuracy": 0.973472535610199, |
| "step": 736 |
| }, |
| { |
| "epoch": 4.310850439882698, |
| "grad_norm": 0.8099782154425992, |
| "learning_rate": 2.669461742229891e-05, |
| "loss": 0.1012, |
| "mean_token_accuracy": 0.9737088829278946, |
| "step": 737 |
| }, |
| { |
| "epoch": 4.316715542521994, |
| "grad_norm": 0.6707361657569837, |
| "learning_rate": 2.6661503103769404e-05, |
| "loss": 0.0792, |
| "mean_token_accuracy": 0.9772538915276527, |
| "step": 738 |
| }, |
| { |
| "epoch": 4.32258064516129, |
| "grad_norm": 0.8535587162942073, |
| "learning_rate": 2.6628371865866286e-05, |
| "loss": 0.1011, |
| "mean_token_accuracy": 0.9715052172541618, |
| "step": 739 |
| }, |
| { |
| "epoch": 4.328445747800586, |
| "grad_norm": 0.7764991300467, |
| "learning_rate": 2.6595223828842578e-05, |
| "loss": 0.0966, |
| "mean_token_accuracy": 0.9695071950554848, |
| "step": 740 |
| }, |
| { |
| "epoch": 4.334310850439882, |
| "grad_norm": 0.7804651105373259, |
| "learning_rate": 2.6562059113012253e-05, |
| "loss": 0.0933, |
| "mean_token_accuracy": 0.9718307480216026, |
| "step": 741 |
| }, |
| { |
| "epoch": 4.340175953079179, |
| "grad_norm": 0.8407216614420148, |
| "learning_rate": 2.6528877838749853e-05, |
| "loss": 0.0867, |
| "mean_token_accuracy": 0.9775464683771133, |
| "step": 742 |
| }, |
| { |
| "epoch": 4.346041055718475, |
| "grad_norm": 0.8618094586938339, |
| "learning_rate": 2.6495680126489984e-05, |
| "loss": 0.0919, |
| "mean_token_accuracy": 0.971205361187458, |
| "step": 743 |
| }, |
| { |
| "epoch": 4.351906158357771, |
| "grad_norm": 0.8163478228495167, |
| "learning_rate": 2.6462466096726954e-05, |
| "loss": 0.1073, |
| "mean_token_accuracy": 0.9718838185071945, |
| "step": 744 |
| }, |
| { |
| "epoch": 4.357771260997067, |
| "grad_norm": 0.8594960287919026, |
| "learning_rate": 2.6429235870014256e-05, |
| "loss": 0.0949, |
| "mean_token_accuracy": 0.9723696932196617, |
| "step": 745 |
| }, |
| { |
| "epoch": 4.363636363636363, |
| "grad_norm": 1.1525397696475228, |
| "learning_rate": 2.639598956696421e-05, |
| "loss": 0.1052, |
| "mean_token_accuracy": 0.9725246876478195, |
| "step": 746 |
| }, |
| { |
| "epoch": 4.3695014662756595, |
| "grad_norm": 0.6454962182852607, |
| "learning_rate": 2.6362727308247458e-05, |
| "loss": 0.08, |
| "mean_token_accuracy": 0.9751030281186104, |
| "step": 747 |
| }, |
| { |
| "epoch": 4.375366568914956, |
| "grad_norm": 0.7198413708470565, |
| "learning_rate": 2.6329449214592568e-05, |
| "loss": 0.0947, |
| "mean_token_accuracy": 0.9728525876998901, |
| "step": 748 |
| }, |
| { |
| "epoch": 4.381231671554252, |
| "grad_norm": 0.8073069554708537, |
| "learning_rate": 2.6296155406785578e-05, |
| "loss": 0.0943, |
| "mean_token_accuracy": 0.9722790792584419, |
| "step": 749 |
| }, |
| { |
| "epoch": 4.387096774193548, |
| "grad_norm": 0.7273915769534642, |
| "learning_rate": 2.6262846005669572e-05, |
| "loss": 0.0872, |
| "mean_token_accuracy": 0.9755823463201523, |
| "step": 750 |
| }, |
| { |
| "epoch": 4.392961876832844, |
| "grad_norm": 0.6222972696609765, |
| "learning_rate": 2.6229521132144212e-05, |
| "loss": 0.0795, |
| "mean_token_accuracy": 0.9756253361701965, |
| "step": 751 |
| }, |
| { |
| "epoch": 4.39882697947214, |
| "grad_norm": 0.6886258769301212, |
| "learning_rate": 2.619618090716534e-05, |
| "loss": 0.0855, |
| "mean_token_accuracy": 0.973938450217247, |
| "step": 752 |
| }, |
| { |
| "epoch": 4.404692082111437, |
| "grad_norm": 0.8210958542755064, |
| "learning_rate": 2.61628254517445e-05, |
| "loss": 0.0831, |
| "mean_token_accuracy": 0.9736155867576599, |
| "step": 753 |
| }, |
| { |
| "epoch": 4.410557184750733, |
| "grad_norm": 0.804804559262862, |
| "learning_rate": 2.612945488694853e-05, |
| "loss": 0.0997, |
| "mean_token_accuracy": 0.9714327901601791, |
| "step": 754 |
| }, |
| { |
| "epoch": 4.416422287390029, |
| "grad_norm": 1.007434669319931, |
| "learning_rate": 2.6096069333899094e-05, |
| "loss": 0.0922, |
| "mean_token_accuracy": 0.9747961461544037, |
| "step": 755 |
| }, |
| { |
| "epoch": 4.422287390029325, |
| "grad_norm": 0.9735266563411731, |
| "learning_rate": 2.6062668913772275e-05, |
| "loss": 0.1074, |
| "mean_token_accuracy": 0.9690496772527695, |
| "step": 756 |
| }, |
| { |
| "epoch": 4.428152492668621, |
| "grad_norm": 0.7776668124323017, |
| "learning_rate": 2.60292537477981e-05, |
| "loss": 0.0912, |
| "mean_token_accuracy": 0.9735496193170547, |
| "step": 757 |
| }, |
| { |
| "epoch": 4.4340175953079175, |
| "grad_norm": 0.9820708255779215, |
| "learning_rate": 2.5995823957260132e-05, |
| "loss": 0.1184, |
| "mean_token_accuracy": 0.9666420146822929, |
| "step": 758 |
| }, |
| { |
| "epoch": 4.439882697947214, |
| "grad_norm": 0.6577310837958226, |
| "learning_rate": 2.596237966349501e-05, |
| "loss": 0.09, |
| "mean_token_accuracy": 0.9744406044483185, |
| "step": 759 |
| }, |
| { |
| "epoch": 4.44574780058651, |
| "grad_norm": 0.7130928227326236, |
| "learning_rate": 2.592892098789201e-05, |
| "loss": 0.0724, |
| "mean_token_accuracy": 0.9780396446585655, |
| "step": 760 |
| }, |
| { |
| "epoch": 4.451612903225806, |
| "grad_norm": 0.7194850985370883, |
| "learning_rate": 2.589544805189261e-05, |
| "loss": 0.0873, |
| "mean_token_accuracy": 0.9740453436970711, |
| "step": 761 |
| }, |
| { |
| "epoch": 4.457478005865102, |
| "grad_norm": 0.7484956451034829, |
| "learning_rate": 2.5861960976990056e-05, |
| "loss": 0.0887, |
| "mean_token_accuracy": 0.9758842661976814, |
| "step": 762 |
| }, |
| { |
| "epoch": 4.463343108504398, |
| "grad_norm": 0.8637894057449226, |
| "learning_rate": 2.5828459884728898e-05, |
| "loss": 0.1057, |
| "mean_token_accuracy": 0.9708142057061195, |
| "step": 763 |
| }, |
| { |
| "epoch": 4.469208211143695, |
| "grad_norm": 0.6269525817460034, |
| "learning_rate": 2.5794944896704572e-05, |
| "loss": 0.0769, |
| "mean_token_accuracy": 0.9770293310284615, |
| "step": 764 |
| }, |
| { |
| "epoch": 4.475073313782991, |
| "grad_norm": 0.7346587688130491, |
| "learning_rate": 2.5761416134562955e-05, |
| "loss": 0.088, |
| "mean_token_accuracy": 0.9742003232240677, |
| "step": 765 |
| }, |
| { |
| "epoch": 4.480938416422287, |
| "grad_norm": 0.7913759302559801, |
| "learning_rate": 2.5727873719999904e-05, |
| "loss": 0.0835, |
| "mean_token_accuracy": 0.9742173254489899, |
| "step": 766 |
| }, |
| { |
| "epoch": 4.486803519061583, |
| "grad_norm": 0.937686464289818, |
| "learning_rate": 2.569431777476084e-05, |
| "loss": 0.1006, |
| "mean_token_accuracy": 0.9709660932421684, |
| "step": 767 |
| }, |
| { |
| "epoch": 4.492668621700879, |
| "grad_norm": 0.5744331833304884, |
| "learning_rate": 2.566074842064029e-05, |
| "loss": 0.0745, |
| "mean_token_accuracy": 0.9800982251763344, |
| "step": 768 |
| }, |
| { |
| "epoch": 4.4985337243401755, |
| "grad_norm": 0.5713487078602227, |
| "learning_rate": 2.562716577948145e-05, |
| "loss": 0.0816, |
| "mean_token_accuracy": 0.9764345660805702, |
| "step": 769 |
| }, |
| { |
| "epoch": 4.504398826979472, |
| "grad_norm": 0.6901009094958664, |
| "learning_rate": 2.5593569973175757e-05, |
| "loss": 0.0818, |
| "mean_token_accuracy": 0.9730259105563164, |
| "step": 770 |
| }, |
| { |
| "epoch": 4.510263929618768, |
| "grad_norm": 0.6757180129841208, |
| "learning_rate": 2.5559961123662405e-05, |
| "loss": 0.0834, |
| "mean_token_accuracy": 0.976299561560154, |
| "step": 771 |
| }, |
| { |
| "epoch": 4.516129032258064, |
| "grad_norm": 0.802104682961351, |
| "learning_rate": 2.5526339352927956e-05, |
| "loss": 0.0972, |
| "mean_token_accuracy": 0.9707585051655769, |
| "step": 772 |
| }, |
| { |
| "epoch": 4.52199413489736, |
| "grad_norm": 0.5581852249169775, |
| "learning_rate": 2.5492704783005847e-05, |
| "loss": 0.0856, |
| "mean_token_accuracy": 0.9735557809472084, |
| "step": 773 |
| }, |
| { |
| "epoch": 4.527859237536656, |
| "grad_norm": 0.9420509929703049, |
| "learning_rate": 2.5459057535975985e-05, |
| "loss": 0.1087, |
| "mean_token_accuracy": 0.9727348163723946, |
| "step": 774 |
| }, |
| { |
| "epoch": 4.533724340175953, |
| "grad_norm": 0.8421175681685341, |
| "learning_rate": 2.542539773396429e-05, |
| "loss": 0.0951, |
| "mean_token_accuracy": 0.9689114019274712, |
| "step": 775 |
| }, |
| { |
| "epoch": 4.539589442815249, |
| "grad_norm": 0.822523743674553, |
| "learning_rate": 2.5391725499142253e-05, |
| "loss": 0.1019, |
| "mean_token_accuracy": 0.9720019325613976, |
| "step": 776 |
| }, |
| { |
| "epoch": 4.545454545454545, |
| "grad_norm": 0.7865828546712166, |
| "learning_rate": 2.535804095372648e-05, |
| "loss": 0.0888, |
| "mean_token_accuracy": 0.9751103669404984, |
| "step": 777 |
| }, |
| { |
| "epoch": 4.551319648093841, |
| "grad_norm": 0.8382216485189787, |
| "learning_rate": 2.5324344219978273e-05, |
| "loss": 0.0917, |
| "mean_token_accuracy": 0.9712260961532593, |
| "step": 778 |
| }, |
| { |
| "epoch": 4.557184750733137, |
| "grad_norm": 0.8165510195730435, |
| "learning_rate": 2.5290635420203162e-05, |
| "loss": 0.0929, |
| "mean_token_accuracy": 0.973741427063942, |
| "step": 779 |
| }, |
| { |
| "epoch": 4.563049853372434, |
| "grad_norm": 0.6822046725758385, |
| "learning_rate": 2.525691467675048e-05, |
| "loss": 0.0922, |
| "mean_token_accuracy": 0.9758124351501465, |
| "step": 780 |
| }, |
| { |
| "epoch": 4.568914956011731, |
| "grad_norm": 0.7259563170378975, |
| "learning_rate": 2.5223182112012897e-05, |
| "loss": 0.082, |
| "mean_token_accuracy": 0.9766591638326645, |
| "step": 781 |
| }, |
| { |
| "epoch": 4.574780058651027, |
| "grad_norm": 0.5910130365914025, |
| "learning_rate": 2.5189437848426016e-05, |
| "loss": 0.0731, |
| "mean_token_accuracy": 0.9782171174883842, |
| "step": 782 |
| }, |
| { |
| "epoch": 4.580645161290323, |
| "grad_norm": 1.024807120825259, |
| "learning_rate": 2.515568200846787e-05, |
| "loss": 0.1114, |
| "mean_token_accuracy": 0.9679220989346504, |
| "step": 783 |
| }, |
| { |
| "epoch": 4.586510263929619, |
| "grad_norm": 0.8080385542671041, |
| "learning_rate": 2.5121914714658526e-05, |
| "loss": 0.0928, |
| "mean_token_accuracy": 0.9725649207830429, |
| "step": 784 |
| }, |
| { |
| "epoch": 4.592375366568915, |
| "grad_norm": 0.6671413109766742, |
| "learning_rate": 2.5088136089559636e-05, |
| "loss": 0.0768, |
| "mean_token_accuracy": 0.977656364440918, |
| "step": 785 |
| }, |
| { |
| "epoch": 4.5982404692082115, |
| "grad_norm": 0.6696595768279495, |
| "learning_rate": 2.5054346255773952e-05, |
| "loss": 0.0743, |
| "mean_token_accuracy": 0.977767638862133, |
| "step": 786 |
| }, |
| { |
| "epoch": 4.604105571847508, |
| "grad_norm": 0.8235186961278428, |
| "learning_rate": 2.502054533594493e-05, |
| "loss": 0.0919, |
| "mean_token_accuracy": 0.9731400832533836, |
| "step": 787 |
| }, |
| { |
| "epoch": 4.609970674486804, |
| "grad_norm": 0.8741694871387966, |
| "learning_rate": 2.4986733452756264e-05, |
| "loss": 0.0935, |
| "mean_token_accuracy": 0.975216455757618, |
| "step": 788 |
| }, |
| { |
| "epoch": 4.6158357771261, |
| "grad_norm": 0.6077795411761349, |
| "learning_rate": 2.495291072893142e-05, |
| "loss": 0.0945, |
| "mean_token_accuracy": 0.9746409058570862, |
| "step": 789 |
| }, |
| { |
| "epoch": 4.621700879765396, |
| "grad_norm": 0.9026723260115013, |
| "learning_rate": 2.4919077287233237e-05, |
| "loss": 0.0936, |
| "mean_token_accuracy": 0.9729236662387848, |
| "step": 790 |
| }, |
| { |
| "epoch": 4.627565982404692, |
| "grad_norm": 0.8316840710889603, |
| "learning_rate": 2.4885233250463445e-05, |
| "loss": 0.0924, |
| "mean_token_accuracy": 0.9731330275535583, |
| "step": 791 |
| }, |
| { |
| "epoch": 4.633431085043989, |
| "grad_norm": 0.8262082417744588, |
| "learning_rate": 2.485137874146222e-05, |
| "loss": 0.0927, |
| "mean_token_accuracy": 0.9719960913062096, |
| "step": 792 |
| }, |
| { |
| "epoch": 4.639296187683285, |
| "grad_norm": 0.7938102499987799, |
| "learning_rate": 2.4817513883107762e-05, |
| "loss": 0.1038, |
| "mean_token_accuracy": 0.9677957743406296, |
| "step": 793 |
| }, |
| { |
| "epoch": 4.645161290322581, |
| "grad_norm": 0.6991244736753061, |
| "learning_rate": 2.4783638798315822e-05, |
| "loss": 0.0836, |
| "mean_token_accuracy": 0.9754368960857391, |
| "step": 794 |
| }, |
| { |
| "epoch": 4.651026392961877, |
| "grad_norm": 0.7542382340948242, |
| "learning_rate": 2.4749753610039288e-05, |
| "loss": 0.0806, |
| "mean_token_accuracy": 0.9750531688332558, |
| "step": 795 |
| }, |
| { |
| "epoch": 4.656891495601173, |
| "grad_norm": 0.7190292471649612, |
| "learning_rate": 2.4715858441267706e-05, |
| "loss": 0.0862, |
| "mean_token_accuracy": 0.9736650809645653, |
| "step": 796 |
| }, |
| { |
| "epoch": 4.6627565982404695, |
| "grad_norm": 0.9829058369454252, |
| "learning_rate": 2.4681953415026845e-05, |
| "loss": 0.1087, |
| "mean_token_accuracy": 0.9707975834608078, |
| "step": 797 |
| }, |
| { |
| "epoch": 4.668621700879766, |
| "grad_norm": 0.6830295915194216, |
| "learning_rate": 2.464803865437826e-05, |
| "loss": 0.0882, |
| "mean_token_accuracy": 0.9731217548251152, |
| "step": 798 |
| }, |
| { |
| "epoch": 4.674486803519062, |
| "grad_norm": 0.8978252666950851, |
| "learning_rate": 2.461411428241883e-05, |
| "loss": 0.1053, |
| "mean_token_accuracy": 0.9693214297294617, |
| "step": 799 |
| }, |
| { |
| "epoch": 4.680351906158358, |
| "grad_norm": 0.5435088680199814, |
| "learning_rate": 2.4580180422280325e-05, |
| "loss": 0.0811, |
| "mean_token_accuracy": 0.9754936322569847, |
| "step": 800 |
| }, |
| { |
| "epoch": 4.686217008797654, |
| "grad_norm": 0.7490474220611864, |
| "learning_rate": 2.4546237197128955e-05, |
| "loss": 0.096, |
| "mean_token_accuracy": 0.973475269973278, |
| "step": 801 |
| }, |
| { |
| "epoch": 4.69208211143695, |
| "grad_norm": 0.7093663497421644, |
| "learning_rate": 2.451228473016492e-05, |
| "loss": 0.0856, |
| "mean_token_accuracy": 0.9768622368574142, |
| "step": 802 |
| }, |
| { |
| "epoch": 4.697947214076247, |
| "grad_norm": 0.6479956911087104, |
| "learning_rate": 2.447832314462196e-05, |
| "loss": 0.0902, |
| "mean_token_accuracy": 0.9753652885556221, |
| "step": 803 |
| }, |
| { |
| "epoch": 4.703812316715543, |
| "grad_norm": 0.6097972135855906, |
| "learning_rate": 2.444435256376692e-05, |
| "loss": 0.0799, |
| "mean_token_accuracy": 0.9760509207844734, |
| "step": 804 |
| }, |
| { |
| "epoch": 4.709677419354839, |
| "grad_norm": 0.7427447154179425, |
| "learning_rate": 2.4410373110899278e-05, |
| "loss": 0.0771, |
| "mean_token_accuracy": 0.978294849395752, |
| "step": 805 |
| }, |
| { |
| "epoch": 4.715542521994135, |
| "grad_norm": 0.6884469910478106, |
| "learning_rate": 2.4376384909350735e-05, |
| "loss": 0.0932, |
| "mean_token_accuracy": 0.9721456244587898, |
| "step": 806 |
| }, |
| { |
| "epoch": 4.721407624633431, |
| "grad_norm": 0.7936450834045352, |
| "learning_rate": 2.434238808248472e-05, |
| "loss": 0.0833, |
| "mean_token_accuracy": 0.974332258105278, |
| "step": 807 |
| }, |
| { |
| "epoch": 4.7272727272727275, |
| "grad_norm": 0.8518884554725347, |
| "learning_rate": 2.4308382753696e-05, |
| "loss": 0.0917, |
| "mean_token_accuracy": 0.973288893699646, |
| "step": 808 |
| }, |
| { |
| "epoch": 4.733137829912024, |
| "grad_norm": 0.7828384801271718, |
| "learning_rate": 2.4274369046410183e-05, |
| "loss": 0.098, |
| "mean_token_accuracy": 0.9744915068149567, |
| "step": 809 |
| }, |
| { |
| "epoch": 4.73900293255132, |
| "grad_norm": 0.615178927181312, |
| "learning_rate": 2.4240347084083284e-05, |
| "loss": 0.08, |
| "mean_token_accuracy": 0.974980354309082, |
| "step": 810 |
| }, |
| { |
| "epoch": 4.744868035190616, |
| "grad_norm": 0.8838518898607127, |
| "learning_rate": 2.4206316990201288e-05, |
| "loss": 0.0936, |
| "mean_token_accuracy": 0.9703791290521622, |
| "step": 811 |
| }, |
| { |
| "epoch": 4.750733137829912, |
| "grad_norm": 0.6907232787969249, |
| "learning_rate": 2.4172278888279686e-05, |
| "loss": 0.0984, |
| "mean_token_accuracy": 0.9722641780972481, |
| "step": 812 |
| }, |
| { |
| "epoch": 4.756598240469208, |
| "grad_norm": 1.029666605767164, |
| "learning_rate": 2.4138232901863053e-05, |
| "loss": 0.0943, |
| "mean_token_accuracy": 0.971537858247757, |
| "step": 813 |
| }, |
| { |
| "epoch": 4.762463343108505, |
| "grad_norm": 0.7159086498080418, |
| "learning_rate": 2.4104179154524557e-05, |
| "loss": 0.082, |
| "mean_token_accuracy": 0.9783857464790344, |
| "step": 814 |
| }, |
| { |
| "epoch": 4.768328445747801, |
| "grad_norm": 0.649220942218314, |
| "learning_rate": 2.4070117769865554e-05, |
| "loss": 0.0831, |
| "mean_token_accuracy": 0.9754119515419006, |
| "step": 815 |
| }, |
| { |
| "epoch": 4.774193548387097, |
| "grad_norm": 0.7457451847390401, |
| "learning_rate": 2.403604887151512e-05, |
| "loss": 0.0912, |
| "mean_token_accuracy": 0.9736931174993515, |
| "step": 816 |
| }, |
| { |
| "epoch": 4.780058651026393, |
| "grad_norm": 0.8083203917249773, |
| "learning_rate": 2.400197258312959e-05, |
| "loss": 0.0766, |
| "mean_token_accuracy": 0.9776452630758286, |
| "step": 817 |
| }, |
| { |
| "epoch": 4.785923753665689, |
| "grad_norm": 0.5884376674496129, |
| "learning_rate": 2.3967889028392115e-05, |
| "loss": 0.0779, |
| "mean_token_accuracy": 0.9779343828558922, |
| "step": 818 |
| }, |
| { |
| "epoch": 4.7917888563049855, |
| "grad_norm": 0.71170792279826, |
| "learning_rate": 2.3933798331012255e-05, |
| "loss": 0.086, |
| "mean_token_accuracy": 0.9734879434108734, |
| "step": 819 |
| }, |
| { |
| "epoch": 4.797653958944282, |
| "grad_norm": 0.7493548129924873, |
| "learning_rate": 2.3899700614725458e-05, |
| "loss": 0.0921, |
| "mean_token_accuracy": 0.9694371744990349, |
| "step": 820 |
| }, |
| { |
| "epoch": 4.803519061583578, |
| "grad_norm": 0.8035228450448255, |
| "learning_rate": 2.3865596003292674e-05, |
| "loss": 0.0914, |
| "mean_token_accuracy": 0.9717112332582474, |
| "step": 821 |
| }, |
| { |
| "epoch": 4.809384164222874, |
| "grad_norm": 0.7789660984026828, |
| "learning_rate": 2.3831484620499867e-05, |
| "loss": 0.0859, |
| "mean_token_accuracy": 0.9748634770512581, |
| "step": 822 |
| }, |
| { |
| "epoch": 4.81524926686217, |
| "grad_norm": 0.712380771905728, |
| "learning_rate": 2.3797366590157565e-05, |
| "loss": 0.1038, |
| "mean_token_accuracy": 0.9669318273663521, |
| "step": 823 |
| }, |
| { |
| "epoch": 4.821114369501466, |
| "grad_norm": 0.6611721434012169, |
| "learning_rate": 2.3763242036100457e-05, |
| "loss": 0.0814, |
| "mean_token_accuracy": 0.9744805321097374, |
| "step": 824 |
| }, |
| { |
| "epoch": 4.826979472140763, |
| "grad_norm": 0.6735485939113598, |
| "learning_rate": 2.372911108218688e-05, |
| "loss": 0.0835, |
| "mean_token_accuracy": 0.9754609763622284, |
| "step": 825 |
| }, |
| { |
| "epoch": 4.832844574780059, |
| "grad_norm": 0.7840099401445052, |
| "learning_rate": 2.3694973852298425e-05, |
| "loss": 0.0952, |
| "mean_token_accuracy": 0.9717969074845314, |
| "step": 826 |
| }, |
| { |
| "epoch": 4.838709677419355, |
| "grad_norm": 0.7131184393140502, |
| "learning_rate": 2.3660830470339436e-05, |
| "loss": 0.0806, |
| "mean_token_accuracy": 0.9741077572107315, |
| "step": 827 |
| }, |
| { |
| "epoch": 4.844574780058651, |
| "grad_norm": 0.6852088395751421, |
| "learning_rate": 2.362668106023661e-05, |
| "loss": 0.0905, |
| "mean_token_accuracy": 0.9730967953801155, |
| "step": 828 |
| }, |
| { |
| "epoch": 4.850439882697947, |
| "grad_norm": 0.9163240926554376, |
| "learning_rate": 2.3592525745938515e-05, |
| "loss": 0.094, |
| "mean_token_accuracy": 0.9740098342299461, |
| "step": 829 |
| }, |
| { |
| "epoch": 4.8563049853372435, |
| "grad_norm": 0.7099935602934261, |
| "learning_rate": 2.355836465141513e-05, |
| "loss": 0.0752, |
| "mean_token_accuracy": 0.9769460931420326, |
| "step": 830 |
| }, |
| { |
| "epoch": 4.86217008797654, |
| "grad_norm": 1.0067753814550802, |
| "learning_rate": 2.3524197900657447e-05, |
| "loss": 0.1104, |
| "mean_token_accuracy": 0.9696153551340103, |
| "step": 831 |
| }, |
| { |
| "epoch": 4.868035190615836, |
| "grad_norm": 0.6432755158012772, |
| "learning_rate": 2.3490025617676966e-05, |
| "loss": 0.077, |
| "mean_token_accuracy": 0.9786104187369347, |
| "step": 832 |
| }, |
| { |
| "epoch": 4.873900293255132, |
| "grad_norm": 0.804250963741737, |
| "learning_rate": 2.3455847926505283e-05, |
| "loss": 0.0955, |
| "mean_token_accuracy": 0.9707959890365601, |
| "step": 833 |
| }, |
| { |
| "epoch": 4.879765395894428, |
| "grad_norm": 0.6226123101954701, |
| "learning_rate": 2.3421664951193596e-05, |
| "loss": 0.0913, |
| "mean_token_accuracy": 0.9721181318163872, |
| "step": 834 |
| }, |
| { |
| "epoch": 4.885630498533724, |
| "grad_norm": 0.6065233416312935, |
| "learning_rate": 2.3387476815812313e-05, |
| "loss": 0.0852, |
| "mean_token_accuracy": 0.9747011289000511, |
| "step": 835 |
| }, |
| { |
| "epoch": 4.891495601173021, |
| "grad_norm": 0.8683808500129969, |
| "learning_rate": 2.3353283644450556e-05, |
| "loss": 0.0979, |
| "mean_token_accuracy": 0.9719295874238014, |
| "step": 836 |
| }, |
| { |
| "epoch": 4.897360703812317, |
| "grad_norm": 0.6831530034869415, |
| "learning_rate": 2.3319085561215724e-05, |
| "loss": 0.0878, |
| "mean_token_accuracy": 0.9732778072357178, |
| "step": 837 |
| }, |
| { |
| "epoch": 4.903225806451613, |
| "grad_norm": 0.8048778653317876, |
| "learning_rate": 2.328488269023305e-05, |
| "loss": 0.0865, |
| "mean_token_accuracy": 0.9767483249306679, |
| "step": 838 |
| }, |
| { |
| "epoch": 4.909090909090909, |
| "grad_norm": 0.8918128316293171, |
| "learning_rate": 2.3250675155645136e-05, |
| "loss": 0.0925, |
| "mean_token_accuracy": 0.9727633222937584, |
| "step": 839 |
| }, |
| { |
| "epoch": 4.914956011730205, |
| "grad_norm": 0.6235830647708027, |
| "learning_rate": 2.3216463081611525e-05, |
| "loss": 0.0764, |
| "mean_token_accuracy": 0.9749378114938736, |
| "step": 840 |
| }, |
| { |
| "epoch": 4.9208211143695015, |
| "grad_norm": 1.0727573864438122, |
| "learning_rate": 2.3182246592308235e-05, |
| "loss": 0.1065, |
| "mean_token_accuracy": 0.971137098968029, |
| "step": 841 |
| }, |
| { |
| "epoch": 4.926686217008798, |
| "grad_norm": 0.6587157219709209, |
| "learning_rate": 2.314802581192728e-05, |
| "loss": 0.0892, |
| "mean_token_accuracy": 0.9734735786914825, |
| "step": 842 |
| }, |
| { |
| "epoch": 4.932551319648094, |
| "grad_norm": 0.9278686915137605, |
| "learning_rate": 2.311380086467629e-05, |
| "loss": 0.1097, |
| "mean_token_accuracy": 0.9702532961964607, |
| "step": 843 |
| }, |
| { |
| "epoch": 4.93841642228739, |
| "grad_norm": 0.6510783115585961, |
| "learning_rate": 2.3079571874778e-05, |
| "loss": 0.0923, |
| "mean_token_accuracy": 0.972200870513916, |
| "step": 844 |
| }, |
| { |
| "epoch": 4.944281524926686, |
| "grad_norm": 0.6796666479114434, |
| "learning_rate": 2.304533896646981e-05, |
| "loss": 0.0896, |
| "mean_token_accuracy": 0.9741808176040649, |
| "step": 845 |
| }, |
| { |
| "epoch": 4.9501466275659824, |
| "grad_norm": 0.5588006016435534, |
| "learning_rate": 2.3011102264003354e-05, |
| "loss": 0.0866, |
| "mean_token_accuracy": 0.9756291657686234, |
| "step": 846 |
| }, |
| { |
| "epoch": 4.956011730205279, |
| "grad_norm": 0.6515199213439168, |
| "learning_rate": 2.2976861891644045e-05, |
| "loss": 0.0862, |
| "mean_token_accuracy": 0.9755071625113487, |
| "step": 847 |
| }, |
| { |
| "epoch": 4.961876832844575, |
| "grad_norm": 0.6597011754000468, |
| "learning_rate": 2.2942617973670596e-05, |
| "loss": 0.0841, |
| "mean_token_accuracy": 0.9742411524057388, |
| "step": 848 |
| }, |
| { |
| "epoch": 4.967741935483871, |
| "grad_norm": 0.8595960189097062, |
| "learning_rate": 2.2908370634374603e-05, |
| "loss": 0.1119, |
| "mean_token_accuracy": 0.9660947695374489, |
| "step": 849 |
| }, |
| { |
| "epoch": 4.973607038123167, |
| "grad_norm": 0.6326753578882204, |
| "learning_rate": 2.287411999806007e-05, |
| "loss": 0.0803, |
| "mean_token_accuracy": 0.9757585823535919, |
| "step": 850 |
| }, |
| { |
| "epoch": 4.979472140762463, |
| "grad_norm": 0.8954416714362815, |
| "learning_rate": 2.2839866189042983e-05, |
| "loss": 0.0928, |
| "mean_token_accuracy": 0.9719807282090187, |
| "step": 851 |
| }, |
| { |
| "epoch": 4.9853372434017595, |
| "grad_norm": 0.7040679174576174, |
| "learning_rate": 2.2805609331650826e-05, |
| "loss": 0.0987, |
| "mean_token_accuracy": 0.9714400470256805, |
| "step": 852 |
| }, |
| { |
| "epoch": 4.991202346041056, |
| "grad_norm": 0.7406739814087293, |
| "learning_rate": 2.2771349550222158e-05, |
| "loss": 0.0817, |
| "mean_token_accuracy": 0.9749223962426186, |
| "step": 853 |
| }, |
| { |
| "epoch": 4.997067448680352, |
| "grad_norm": 0.5768671268589982, |
| "learning_rate": 2.273708696910616e-05, |
| "loss": 0.0804, |
| "mean_token_accuracy": 0.9751258715987206, |
| "step": 854 |
| }, |
| { |
| "epoch": 5.0, |
| "grad_norm": 0.5768671268589982, |
| "learning_rate": 2.2702821712662147e-05, |
| "loss": 0.0683, |
| "mean_token_accuracy": 0.9784054607152939, |
| "step": 855 |
| }, |
| { |
| "epoch": 5.005865102639296, |
| "grad_norm": 0.8099033611603849, |
| "learning_rate": 2.2668553905259168e-05, |
| "loss": 0.0681, |
| "mean_token_accuracy": 0.978220023214817, |
| "step": 856 |
| }, |
| { |
| "epoch": 5.011730205278592, |
| "grad_norm": 0.4450190361943267, |
| "learning_rate": 2.2634283671275523e-05, |
| "loss": 0.06, |
| "mean_token_accuracy": 0.9821461737155914, |
| "step": 857 |
| }, |
| { |
| "epoch": 5.0175953079178885, |
| "grad_norm": 0.5790492440675818, |
| "learning_rate": 2.2600011135098323e-05, |
| "loss": 0.0715, |
| "mean_token_accuracy": 0.9782145693898201, |
| "step": 858 |
| }, |
| { |
| "epoch": 5.023460410557185, |
| "grad_norm": 0.369951752998347, |
| "learning_rate": 2.2565736421123035e-05, |
| "loss": 0.0697, |
| "mean_token_accuracy": 0.9796851649880409, |
| "step": 859 |
| }, |
| { |
| "epoch": 5.029325513196481, |
| "grad_norm": 0.6060126099707575, |
| "learning_rate": 2.253145965375302e-05, |
| "loss": 0.0875, |
| "mean_token_accuracy": 0.9720205143094063, |
| "step": 860 |
| }, |
| { |
| "epoch": 5.035190615835777, |
| "grad_norm": 0.6165958564660802, |
| "learning_rate": 2.2497180957399108e-05, |
| "loss": 0.0866, |
| "mean_token_accuracy": 0.9744477048516273, |
| "step": 861 |
| }, |
| { |
| "epoch": 5.041055718475073, |
| "grad_norm": 0.6771859544459322, |
| "learning_rate": 2.246290045647912e-05, |
| "loss": 0.0723, |
| "mean_token_accuracy": 0.9792094677686691, |
| "step": 862 |
| }, |
| { |
| "epoch": 5.0469208211143695, |
| "grad_norm": 0.7193259034964399, |
| "learning_rate": 2.242861827541742e-05, |
| "loss": 0.0634, |
| "mean_token_accuracy": 0.9807204157114029, |
| "step": 863 |
| }, |
| { |
| "epoch": 5.052785923753666, |
| "grad_norm": 0.5659196503147593, |
| "learning_rate": 2.2394334538644494e-05, |
| "loss": 0.0772, |
| "mean_token_accuracy": 0.976197637617588, |
| "step": 864 |
| }, |
| { |
| "epoch": 5.058651026392962, |
| "grad_norm": 0.7669216428482878, |
| "learning_rate": 2.2360049370596454e-05, |
| "loss": 0.0726, |
| "mean_token_accuracy": 0.9803265184164047, |
| "step": 865 |
| }, |
| { |
| "epoch": 5.064516129032258, |
| "grad_norm": 0.6675976013272769, |
| "learning_rate": 2.2325762895714616e-05, |
| "loss": 0.0763, |
| "mean_token_accuracy": 0.9768341109156609, |
| "step": 866 |
| }, |
| { |
| "epoch": 5.070381231671554, |
| "grad_norm": 0.6310094477428734, |
| "learning_rate": 2.2291475238445033e-05, |
| "loss": 0.0768, |
| "mean_token_accuracy": 0.9780902415513992, |
| "step": 867 |
| }, |
| { |
| "epoch": 5.07624633431085, |
| "grad_norm": 0.551208157538957, |
| "learning_rate": 2.225718652323805e-05, |
| "loss": 0.0774, |
| "mean_token_accuracy": 0.9757518768310547, |
| "step": 868 |
| }, |
| { |
| "epoch": 5.0821114369501466, |
| "grad_norm": 0.7407751441472306, |
| "learning_rate": 2.2222896874547856e-05, |
| "loss": 0.096, |
| "mean_token_accuracy": 0.9750194400548935, |
| "step": 869 |
| }, |
| { |
| "epoch": 5.087976539589443, |
| "grad_norm": 0.6068040244873181, |
| "learning_rate": 2.2188606416832035e-05, |
| "loss": 0.0636, |
| "mean_token_accuracy": 0.9805742874741554, |
| "step": 870 |
| }, |
| { |
| "epoch": 5.093841642228739, |
| "grad_norm": 0.6185459789558916, |
| "learning_rate": 2.2154315274551093e-05, |
| "loss": 0.0812, |
| "mean_token_accuracy": 0.9773125946521759, |
| "step": 871 |
| }, |
| { |
| "epoch": 5.099706744868035, |
| "grad_norm": 0.5449089650374084, |
| "learning_rate": 2.2120023572168026e-05, |
| "loss": 0.0681, |
| "mean_token_accuracy": 0.9807572066783905, |
| "step": 872 |
| }, |
| { |
| "epoch": 5.105571847507331, |
| "grad_norm": 0.5466347088828135, |
| "learning_rate": 2.208573143414787e-05, |
| "loss": 0.0653, |
| "mean_token_accuracy": 0.9815317243337631, |
| "step": 873 |
| }, |
| { |
| "epoch": 5.1114369501466275, |
| "grad_norm": 0.6933178932755342, |
| "learning_rate": 2.2051438984957234e-05, |
| "loss": 0.0758, |
| "mean_token_accuracy": 0.9780973717570305, |
| "step": 874 |
| }, |
| { |
| "epoch": 5.117302052785924, |
| "grad_norm": 0.5794805869329679, |
| "learning_rate": 2.2017146349063855e-05, |
| "loss": 0.0703, |
| "mean_token_accuracy": 0.9793791621923447, |
| "step": 875 |
| }, |
| { |
| "epoch": 5.12316715542522, |
| "grad_norm": 0.49280867315149984, |
| "learning_rate": 2.1982853650936154e-05, |
| "loss": 0.0778, |
| "mean_token_accuracy": 0.9783745110034943, |
| "step": 876 |
| }, |
| { |
| "epoch": 5.129032258064516, |
| "grad_norm": 0.6399855244458721, |
| "learning_rate": 2.1948561015042772e-05, |
| "loss": 0.0769, |
| "mean_token_accuracy": 0.9801036417484283, |
| "step": 877 |
| }, |
| { |
| "epoch": 5.134897360703812, |
| "grad_norm": 0.658746744986044, |
| "learning_rate": 2.1914268565852134e-05, |
| "loss": 0.0792, |
| "mean_token_accuracy": 0.9752889424562454, |
| "step": 878 |
| }, |
| { |
| "epoch": 5.140762463343108, |
| "grad_norm": 0.6889876053257266, |
| "learning_rate": 2.1879976427831983e-05, |
| "loss": 0.0791, |
| "mean_token_accuracy": 0.9774133116006851, |
| "step": 879 |
| }, |
| { |
| "epoch": 5.146627565982405, |
| "grad_norm": 0.6564951399065133, |
| "learning_rate": 2.1845684725448916e-05, |
| "loss": 0.0853, |
| "mean_token_accuracy": 0.9751299694180489, |
| "step": 880 |
| }, |
| { |
| "epoch": 5.152492668621701, |
| "grad_norm": 0.6990710395104928, |
| "learning_rate": 2.181139358316797e-05, |
| "loss": 0.0802, |
| "mean_token_accuracy": 0.9749646335840225, |
| "step": 881 |
| }, |
| { |
| "epoch": 5.158357771260997, |
| "grad_norm": 0.7796329399858077, |
| "learning_rate": 2.1777103125452146e-05, |
| "loss": 0.0746, |
| "mean_token_accuracy": 0.9780853018164635, |
| "step": 882 |
| }, |
| { |
| "epoch": 5.164222873900293, |
| "grad_norm": 0.7991341320122649, |
| "learning_rate": 2.1742813476761958e-05, |
| "loss": 0.0923, |
| "mean_token_accuracy": 0.973864234983921, |
| "step": 883 |
| }, |
| { |
| "epoch": 5.170087976539589, |
| "grad_norm": 0.5346267401371, |
| "learning_rate": 2.1708524761554973e-05, |
| "loss": 0.084, |
| "mean_token_accuracy": 0.9747622609138489, |
| "step": 884 |
| }, |
| { |
| "epoch": 5.1759530791788855, |
| "grad_norm": 0.7536037260952937, |
| "learning_rate": 2.1674237104285393e-05, |
| "loss": 0.0718, |
| "mean_token_accuracy": 0.9780940935015678, |
| "step": 885 |
| }, |
| { |
| "epoch": 5.181818181818182, |
| "grad_norm": 0.4613117403210394, |
| "learning_rate": 2.1639950629403552e-05, |
| "loss": 0.0623, |
| "mean_token_accuracy": 0.9808356538414955, |
| "step": 886 |
| }, |
| { |
| "epoch": 5.187683284457478, |
| "grad_norm": 0.5208424966805913, |
| "learning_rate": 2.1605665461355515e-05, |
| "loss": 0.076, |
| "mean_token_accuracy": 0.9781753346323967, |
| "step": 887 |
| }, |
| { |
| "epoch": 5.193548387096774, |
| "grad_norm": 0.6828043686906896, |
| "learning_rate": 2.1571381724582588e-05, |
| "loss": 0.0966, |
| "mean_token_accuracy": 0.9742318615317345, |
| "step": 888 |
| }, |
| { |
| "epoch": 5.19941348973607, |
| "grad_norm": 0.6401984996207497, |
| "learning_rate": 2.153709954352089e-05, |
| "loss": 0.0688, |
| "mean_token_accuracy": 0.978904701769352, |
| "step": 889 |
| }, |
| { |
| "epoch": 5.205278592375366, |
| "grad_norm": 0.6584127670692117, |
| "learning_rate": 2.15028190426009e-05, |
| "loss": 0.0795, |
| "mean_token_accuracy": 0.9756882935762405, |
| "step": 890 |
| }, |
| { |
| "epoch": 5.211143695014663, |
| "grad_norm": 0.5242045901075086, |
| "learning_rate": 2.1468540346246986e-05, |
| "loss": 0.0732, |
| "mean_token_accuracy": 0.9772383645176888, |
| "step": 891 |
| }, |
| { |
| "epoch": 5.217008797653959, |
| "grad_norm": 0.7677673529791075, |
| "learning_rate": 2.143426357887697e-05, |
| "loss": 0.0838, |
| "mean_token_accuracy": 0.9748184457421303, |
| "step": 892 |
| }, |
| { |
| "epoch": 5.222873900293255, |
| "grad_norm": 0.6457074194873286, |
| "learning_rate": 2.139998886490169e-05, |
| "loss": 0.0644, |
| "mean_token_accuracy": 0.9803335294127464, |
| "step": 893 |
| }, |
| { |
| "epoch": 5.228739002932551, |
| "grad_norm": 0.5107497247898192, |
| "learning_rate": 2.136571632872449e-05, |
| "loss": 0.0784, |
| "mean_token_accuracy": 0.9764648675918579, |
| "step": 894 |
| }, |
| { |
| "epoch": 5.234604105571847, |
| "grad_norm": 0.6904728447258073, |
| "learning_rate": 2.1331446094740845e-05, |
| "loss": 0.0885, |
| "mean_token_accuracy": 0.974873885512352, |
| "step": 895 |
| }, |
| { |
| "epoch": 5.2404692082111435, |
| "grad_norm": 0.7503481221592241, |
| "learning_rate": 2.1297178287337865e-05, |
| "loss": 0.0799, |
| "mean_token_accuracy": 0.9755254238843918, |
| "step": 896 |
| }, |
| { |
| "epoch": 5.24633431085044, |
| "grad_norm": 0.6840723971970181, |
| "learning_rate": 2.1262913030893855e-05, |
| "loss": 0.0876, |
| "mean_token_accuracy": 0.9740219637751579, |
| "step": 897 |
| }, |
| { |
| "epoch": 5.252199413489736, |
| "grad_norm": 0.8127484480176936, |
| "learning_rate": 2.1228650449777848e-05, |
| "loss": 0.0853, |
| "mean_token_accuracy": 0.9751054421067238, |
| "step": 898 |
| }, |
| { |
| "epoch": 5.258064516129032, |
| "grad_norm": 0.6498239243812226, |
| "learning_rate": 2.1194390668349186e-05, |
| "loss": 0.0796, |
| "mean_token_accuracy": 0.9772773683071136, |
| "step": 899 |
| }, |
| { |
| "epoch": 5.263929618768328, |
| "grad_norm": 1.1008053864242204, |
| "learning_rate": 2.116013381095703e-05, |
| "loss": 0.07, |
| "mean_token_accuracy": 0.9801924675703049, |
| "step": 900 |
| }, |
| { |
| "epoch": 5.269794721407624, |
| "grad_norm": 0.547889815369571, |
| "learning_rate": 2.112588000193994e-05, |
| "loss": 0.0771, |
| "mean_token_accuracy": 0.9764879941940308, |
| "step": 901 |
| }, |
| { |
| "epoch": 5.275659824046921, |
| "grad_norm": 0.8521673135262312, |
| "learning_rate": 2.1091629365625403e-05, |
| "loss": 0.078, |
| "mean_token_accuracy": 0.976124718785286, |
| "step": 902 |
| }, |
| { |
| "epoch": 5.281524926686217, |
| "grad_norm": 0.6082701446387903, |
| "learning_rate": 2.105738202632941e-05, |
| "loss": 0.0874, |
| "mean_token_accuracy": 0.9764643460512161, |
| "step": 903 |
| }, |
| { |
| "epoch": 5.287390029325513, |
| "grad_norm": 0.6600651650672481, |
| "learning_rate": 2.1023138108355957e-05, |
| "loss": 0.0713, |
| "mean_token_accuracy": 0.9807606041431427, |
| "step": 904 |
| }, |
| { |
| "epoch": 5.293255131964809, |
| "grad_norm": 0.49312738828651276, |
| "learning_rate": 2.098889773599665e-05, |
| "loss": 0.0859, |
| "mean_token_accuracy": 0.9751582518219948, |
| "step": 905 |
| }, |
| { |
| "epoch": 5.299120234604105, |
| "grad_norm": 0.6702665428374299, |
| "learning_rate": 2.0954661033530193e-05, |
| "loss": 0.0695, |
| "mean_token_accuracy": 0.9784847497940063, |
| "step": 906 |
| }, |
| { |
| "epoch": 5.3049853372434015, |
| "grad_norm": 0.45413216504967313, |
| "learning_rate": 2.0920428125222004e-05, |
| "loss": 0.0733, |
| "mean_token_accuracy": 0.9797236323356628, |
| "step": 907 |
| }, |
| { |
| "epoch": 5.310850439882698, |
| "grad_norm": 0.5443492720347446, |
| "learning_rate": 2.0886199135323712e-05, |
| "loss": 0.0874, |
| "mean_token_accuracy": 0.9746130779385567, |
| "step": 908 |
| }, |
| { |
| "epoch": 5.316715542521994, |
| "grad_norm": 0.6727309078114576, |
| "learning_rate": 2.085197418807272e-05, |
| "loss": 0.0735, |
| "mean_token_accuracy": 0.9795581921935081, |
| "step": 909 |
| }, |
| { |
| "epoch": 5.32258064516129, |
| "grad_norm": 0.48912171922210684, |
| "learning_rate": 2.0817753407691774e-05, |
| "loss": 0.0766, |
| "mean_token_accuracy": 0.9777567386627197, |
| "step": 910 |
| }, |
| { |
| "epoch": 5.328445747800586, |
| "grad_norm": 0.5828476592220785, |
| "learning_rate": 2.0783536918388477e-05, |
| "loss": 0.0911, |
| "mean_token_accuracy": 0.9743940532207489, |
| "step": 911 |
| }, |
| { |
| "epoch": 5.334310850439882, |
| "grad_norm": 0.6715410606054701, |
| "learning_rate": 2.0749324844354867e-05, |
| "loss": 0.0719, |
| "mean_token_accuracy": 0.9782103151082993, |
| "step": 912 |
| }, |
| { |
| "epoch": 5.340175953079179, |
| "grad_norm": 0.672571913081858, |
| "learning_rate": 2.0715117309766953e-05, |
| "loss": 0.0692, |
| "mean_token_accuracy": 0.9785708412528038, |
| "step": 913 |
| }, |
| { |
| "epoch": 5.346041055718475, |
| "grad_norm": 0.4654116633126373, |
| "learning_rate": 2.068091443878428e-05, |
| "loss": 0.0776, |
| "mean_token_accuracy": 0.9766899198293686, |
| "step": 914 |
| }, |
| { |
| "epoch": 5.351906158357771, |
| "grad_norm": 0.7860851552775493, |
| "learning_rate": 2.064671635554945e-05, |
| "loss": 0.0908, |
| "mean_token_accuracy": 0.9766247346997261, |
| "step": 915 |
| }, |
| { |
| "epoch": 5.357771260997067, |
| "grad_norm": 0.670661561387845, |
| "learning_rate": 2.0612523184187693e-05, |
| "loss": 0.0747, |
| "mean_token_accuracy": 0.9768082797527313, |
| "step": 916 |
| }, |
| { |
| "epoch": 5.363636363636363, |
| "grad_norm": 0.5827806964669583, |
| "learning_rate": 2.057833504880641e-05, |
| "loss": 0.0793, |
| "mean_token_accuracy": 0.974205270409584, |
| "step": 917 |
| }, |
| { |
| "epoch": 5.3695014662756595, |
| "grad_norm": 0.6679178730365597, |
| "learning_rate": 2.054415207349473e-05, |
| "loss": 0.0842, |
| "mean_token_accuracy": 0.9742937907576561, |
| "step": 918 |
| }, |
| { |
| "epoch": 5.375366568914956, |
| "grad_norm": 0.9882368279810648, |
| "learning_rate": 2.0509974382323043e-05, |
| "loss": 0.0726, |
| "mean_token_accuracy": 0.9780319705605507, |
| "step": 919 |
| }, |
| { |
| "epoch": 5.381231671554252, |
| "grad_norm": 0.471815730617989, |
| "learning_rate": 2.047580209934256e-05, |
| "loss": 0.0701, |
| "mean_token_accuracy": 0.9799467623233795, |
| "step": 920 |
| }, |
| { |
| "epoch": 5.387096774193548, |
| "grad_norm": 0.47451791208039407, |
| "learning_rate": 2.0441635348584876e-05, |
| "loss": 0.076, |
| "mean_token_accuracy": 0.9799469783902168, |
| "step": 921 |
| }, |
| { |
| "epoch": 5.392961876832844, |
| "grad_norm": 0.5023809611511383, |
| "learning_rate": 2.0407474254061498e-05, |
| "loss": 0.0826, |
| "mean_token_accuracy": 0.9753458574414253, |
| "step": 922 |
| }, |
| { |
| "epoch": 5.39882697947214, |
| "grad_norm": 0.5075686409018196, |
| "learning_rate": 2.0373318939763397e-05, |
| "loss": 0.0765, |
| "mean_token_accuracy": 0.9750477820634842, |
| "step": 923 |
| }, |
| { |
| "epoch": 5.404692082111437, |
| "grad_norm": 0.6435726318443664, |
| "learning_rate": 2.033916952966057e-05, |
| "loss": 0.0712, |
| "mean_token_accuracy": 0.9771361127495766, |
| "step": 924 |
| }, |
| { |
| "epoch": 5.410557184750733, |
| "grad_norm": 0.5962098923490655, |
| "learning_rate": 2.0305026147701584e-05, |
| "loss": 0.0816, |
| "mean_token_accuracy": 0.9740441292524338, |
| "step": 925 |
| }, |
| { |
| "epoch": 5.416422287390029, |
| "grad_norm": 0.5837016205213843, |
| "learning_rate": 2.0270888917813124e-05, |
| "loss": 0.0655, |
| "mean_token_accuracy": 0.9783652052283287, |
| "step": 926 |
| }, |
| { |
| "epoch": 5.422287390029325, |
| "grad_norm": 0.5544663430780863, |
| "learning_rate": 2.0236757963899548e-05, |
| "loss": 0.0791, |
| "mean_token_accuracy": 0.9762725159525871, |
| "step": 927 |
| }, |
| { |
| "epoch": 5.428152492668621, |
| "grad_norm": 0.5937736275356819, |
| "learning_rate": 2.020263340984244e-05, |
| "loss": 0.0814, |
| "mean_token_accuracy": 0.9787080064415932, |
| "step": 928 |
| }, |
| { |
| "epoch": 5.4340175953079175, |
| "grad_norm": 0.5482338781621862, |
| "learning_rate": 2.0168515379500145e-05, |
| "loss": 0.0664, |
| "mean_token_accuracy": 0.9771486297249794, |
| "step": 929 |
| }, |
| { |
| "epoch": 5.439882697947214, |
| "grad_norm": 0.6214123829163545, |
| "learning_rate": 2.0134403996707338e-05, |
| "loss": 0.0691, |
| "mean_token_accuracy": 0.9789487943053246, |
| "step": 930 |
| }, |
| { |
| "epoch": 5.44574780058651, |
| "grad_norm": 0.39382140581253744, |
| "learning_rate": 2.0100299385274547e-05, |
| "loss": 0.0688, |
| "mean_token_accuracy": 0.9780780300498009, |
| "step": 931 |
| }, |
| { |
| "epoch": 5.451612903225806, |
| "grad_norm": 0.7154256082721208, |
| "learning_rate": 2.0066201668987757e-05, |
| "loss": 0.0936, |
| "mean_token_accuracy": 0.973826490342617, |
| "step": 932 |
| }, |
| { |
| "epoch": 5.457478005865102, |
| "grad_norm": 0.5851811926501702, |
| "learning_rate": 2.0032110971607894e-05, |
| "loss": 0.0715, |
| "mean_token_accuracy": 0.9797235950827599, |
| "step": 933 |
| }, |
| { |
| "epoch": 5.463343108504398, |
| "grad_norm": 0.5534379033832495, |
| "learning_rate": 1.999802741687042e-05, |
| "loss": 0.0838, |
| "mean_token_accuracy": 0.9770290404558182, |
| "step": 934 |
| }, |
| { |
| "epoch": 5.469208211143695, |
| "grad_norm": 0.7164411676483846, |
| "learning_rate": 1.9963951128484886e-05, |
| "loss": 0.0649, |
| "mean_token_accuracy": 0.9806244075298309, |
| "step": 935 |
| }, |
| { |
| "epoch": 5.475073313782991, |
| "grad_norm": 0.47696779969791275, |
| "learning_rate": 1.9929882230134452e-05, |
| "loss": 0.0748, |
| "mean_token_accuracy": 0.9765933528542519, |
| "step": 936 |
| }, |
| { |
| "epoch": 5.480938416422287, |
| "grad_norm": 0.5470776765030727, |
| "learning_rate": 1.9895820845475445e-05, |
| "loss": 0.0878, |
| "mean_token_accuracy": 0.9753799438476562, |
| "step": 937 |
| }, |
| { |
| "epoch": 5.486803519061583, |
| "grad_norm": 0.7100920429755581, |
| "learning_rate": 1.9861767098136956e-05, |
| "loss": 0.0665, |
| "mean_token_accuracy": 0.9792315140366554, |
| "step": 938 |
| }, |
| { |
| "epoch": 5.492668621700879, |
| "grad_norm": 0.4029396388053985, |
| "learning_rate": 1.982772111172032e-05, |
| "loss": 0.0722, |
| "mean_token_accuracy": 0.9785656332969666, |
| "step": 939 |
| }, |
| { |
| "epoch": 5.4985337243401755, |
| "grad_norm": 0.5709639222922572, |
| "learning_rate": 1.9793683009798718e-05, |
| "loss": 0.0647, |
| "mean_token_accuracy": 0.9799299314618111, |
| "step": 940 |
| }, |
| { |
| "epoch": 5.504398826979472, |
| "grad_norm": 0.4227698091411673, |
| "learning_rate": 1.975965291591672e-05, |
| "loss": 0.0838, |
| "mean_token_accuracy": 0.9743452370166779, |
| "step": 941 |
| }, |
| { |
| "epoch": 5.510263929618768, |
| "grad_norm": 0.5747683090929688, |
| "learning_rate": 1.9725630953589823e-05, |
| "loss": 0.0749, |
| "mean_token_accuracy": 0.9801840931177139, |
| "step": 942 |
| }, |
| { |
| "epoch": 5.516129032258064, |
| "grad_norm": 0.5511712501852833, |
| "learning_rate": 1.9691617246304007e-05, |
| "loss": 0.0699, |
| "mean_token_accuracy": 0.9766572862863541, |
| "step": 943 |
| }, |
| { |
| "epoch": 5.52199413489736, |
| "grad_norm": 0.48550957447325593, |
| "learning_rate": 1.9657611917515287e-05, |
| "loss": 0.0802, |
| "mean_token_accuracy": 0.977307416498661, |
| "step": 944 |
| }, |
| { |
| "epoch": 5.527859237536656, |
| "grad_norm": 0.4962656544581569, |
| "learning_rate": 1.962361509064928e-05, |
| "loss": 0.067, |
| "mean_token_accuracy": 0.9810660406947136, |
| "step": 945 |
| }, |
| { |
| "epoch": 5.533724340175953, |
| "grad_norm": 0.4585981984962692, |
| "learning_rate": 1.958962688910073e-05, |
| "loss": 0.0664, |
| "mean_token_accuracy": 0.9795481562614441, |
| "step": 946 |
| }, |
| { |
| "epoch": 5.539589442815249, |
| "grad_norm": 0.8789699963455241, |
| "learning_rate": 1.9555647436233093e-05, |
| "loss": 0.0811, |
| "mean_token_accuracy": 0.9794306084513664, |
| "step": 947 |
| }, |
| { |
| "epoch": 5.545454545454545, |
| "grad_norm": 0.6589501732448013, |
| "learning_rate": 1.9521676855378045e-05, |
| "loss": 0.0756, |
| "mean_token_accuracy": 0.9795940294861794, |
| "step": 948 |
| }, |
| { |
| "epoch": 5.551319648093841, |
| "grad_norm": 0.47109469222419814, |
| "learning_rate": 1.9487715269835082e-05, |
| "loss": 0.0673, |
| "mean_token_accuracy": 0.9784109368920326, |
| "step": 949 |
| }, |
| { |
| "epoch": 5.557184750733137, |
| "grad_norm": 0.6780584444910192, |
| "learning_rate": 1.945376280287105e-05, |
| "loss": 0.0789, |
| "mean_token_accuracy": 0.9758977070450783, |
| "step": 950 |
| }, |
| { |
| "epoch": 5.563049853372434, |
| "grad_norm": 0.547538371775988, |
| "learning_rate": 1.9419819577719684e-05, |
| "loss": 0.075, |
| "mean_token_accuracy": 0.9771006405353546, |
| "step": 951 |
| }, |
| { |
| "epoch": 5.568914956011731, |
| "grad_norm": 0.7026091797815018, |
| "learning_rate": 1.9385885717581182e-05, |
| "loss": 0.0831, |
| "mean_token_accuracy": 0.9737556874752045, |
| "step": 952 |
| }, |
| { |
| "epoch": 5.574780058651027, |
| "grad_norm": 0.6594999054981713, |
| "learning_rate": 1.935196134562175e-05, |
| "loss": 0.0659, |
| "mean_token_accuracy": 0.9800437390804291, |
| "step": 953 |
| }, |
| { |
| "epoch": 5.580645161290323, |
| "grad_norm": 0.5616998292882237, |
| "learning_rate": 1.931804658497316e-05, |
| "loss": 0.0795, |
| "mean_token_accuracy": 0.9787877053022385, |
| "step": 954 |
| }, |
| { |
| "epoch": 5.586510263929619, |
| "grad_norm": 0.7521827670887291, |
| "learning_rate": 1.9284141558732296e-05, |
| "loss": 0.0814, |
| "mean_token_accuracy": 0.9771803990006447, |
| "step": 955 |
| }, |
| { |
| "epoch": 5.592375366568915, |
| "grad_norm": 0.780497739247058, |
| "learning_rate": 1.925024638996071e-05, |
| "loss": 0.0801, |
| "mean_token_accuracy": 0.976881816983223, |
| "step": 956 |
| }, |
| { |
| "epoch": 5.5982404692082115, |
| "grad_norm": 0.4162052339210939, |
| "learning_rate": 1.9216361201684174e-05, |
| "loss": 0.0726, |
| "mean_token_accuracy": 0.9800549224019051, |
| "step": 957 |
| }, |
| { |
| "epoch": 5.604105571847508, |
| "grad_norm": 0.6287866231807394, |
| "learning_rate": 1.918248611689224e-05, |
| "loss": 0.076, |
| "mean_token_accuracy": 0.9785019308328629, |
| "step": 958 |
| }, |
| { |
| "epoch": 5.609970674486804, |
| "grad_norm": 0.49146726443913197, |
| "learning_rate": 1.9148621258537782e-05, |
| "loss": 0.0759, |
| "mean_token_accuracy": 0.9774388298392296, |
| "step": 959 |
| }, |
| { |
| "epoch": 5.6158357771261, |
| "grad_norm": 0.6072290541914621, |
| "learning_rate": 1.911476674953656e-05, |
| "loss": 0.0683, |
| "mean_token_accuracy": 0.9797725901007652, |
| "step": 960 |
| }, |
| { |
| "epoch": 5.621700879765396, |
| "grad_norm": 0.5459267155440238, |
| "learning_rate": 1.9080922712766762e-05, |
| "loss": 0.0767, |
| "mean_token_accuracy": 0.9748610332608223, |
| "step": 961 |
| }, |
| { |
| "epoch": 5.627565982404692, |
| "grad_norm": 0.46593356248507284, |
| "learning_rate": 1.904708927106858e-05, |
| "loss": 0.0821, |
| "mean_token_accuracy": 0.9751980304718018, |
| "step": 962 |
| }, |
| { |
| "epoch": 5.633431085043989, |
| "grad_norm": 0.6913652665852186, |
| "learning_rate": 1.9013266547243742e-05, |
| "loss": 0.068, |
| "mean_token_accuracy": 0.9801571518182755, |
| "step": 963 |
| }, |
| { |
| "epoch": 5.639296187683285, |
| "grad_norm": 0.5509304382779889, |
| "learning_rate": 1.8979454664055068e-05, |
| "loss": 0.073, |
| "mean_token_accuracy": 0.9766935929656029, |
| "step": 964 |
| }, |
| { |
| "epoch": 5.645161290322581, |
| "grad_norm": 0.635061720229963, |
| "learning_rate": 1.894565374422605e-05, |
| "loss": 0.067, |
| "mean_token_accuracy": 0.9784405454993248, |
| "step": 965 |
| }, |
| { |
| "epoch": 5.651026392961877, |
| "grad_norm": 0.39936389348973156, |
| "learning_rate": 1.891186391044037e-05, |
| "loss": 0.0803, |
| "mean_token_accuracy": 0.9737694561481476, |
| "step": 966 |
| }, |
| { |
| "epoch": 5.656891495601173, |
| "grad_norm": 0.6400412396273522, |
| "learning_rate": 1.887808528534148e-05, |
| "loss": 0.0714, |
| "mean_token_accuracy": 0.9779755920171738, |
| "step": 967 |
| }, |
| { |
| "epoch": 5.6627565982404695, |
| "grad_norm": 0.7067667447837913, |
| "learning_rate": 1.884431799153214e-05, |
| "loss": 0.0772, |
| "mean_token_accuracy": 0.9778576120734215, |
| "step": 968 |
| }, |
| { |
| "epoch": 5.668621700879766, |
| "grad_norm": 1.012390712709044, |
| "learning_rate": 1.8810562151573993e-05, |
| "loss": 0.089, |
| "mean_token_accuracy": 0.9746776595711708, |
| "step": 969 |
| }, |
| { |
| "epoch": 5.674486803519062, |
| "grad_norm": 0.7423043220181863, |
| "learning_rate": 1.8776817887987105e-05, |
| "loss": 0.0877, |
| "mean_token_accuracy": 0.9754098355770111, |
| "step": 970 |
| }, |
| { |
| "epoch": 5.680351906158358, |
| "grad_norm": 0.6077907639730374, |
| "learning_rate": 1.8743085323249527e-05, |
| "loss": 0.0774, |
| "mean_token_accuracy": 0.9754339978098869, |
| "step": 971 |
| }, |
| { |
| "epoch": 5.686217008797654, |
| "grad_norm": 0.49881643744105175, |
| "learning_rate": 1.870936457979684e-05, |
| "loss": 0.0797, |
| "mean_token_accuracy": 0.9773345366120338, |
| "step": 972 |
| }, |
| { |
| "epoch": 5.69208211143695, |
| "grad_norm": 0.4582361113723667, |
| "learning_rate": 1.8675655780021733e-05, |
| "loss": 0.0684, |
| "mean_token_accuracy": 0.9787016063928604, |
| "step": 973 |
| }, |
| { |
| "epoch": 5.697947214076247, |
| "grad_norm": 0.568024453102634, |
| "learning_rate": 1.8641959046273525e-05, |
| "loss": 0.0851, |
| "mean_token_accuracy": 0.9769276455044746, |
| "step": 974 |
| }, |
| { |
| "epoch": 5.703812316715543, |
| "grad_norm": 0.4968249690754107, |
| "learning_rate": 1.8608274500857756e-05, |
| "loss": 0.071, |
| "mean_token_accuracy": 0.9795166626572609, |
| "step": 975 |
| }, |
| { |
| "epoch": 5.709677419354839, |
| "grad_norm": 0.4002229392999077, |
| "learning_rate": 1.8574602266035714e-05, |
| "loss": 0.0681, |
| "mean_token_accuracy": 0.9806966185569763, |
| "step": 976 |
| }, |
| { |
| "epoch": 5.715542521994135, |
| "grad_norm": 0.4984740210286059, |
| "learning_rate": 1.854094246402402e-05, |
| "loss": 0.0872, |
| "mean_token_accuracy": 0.974516287446022, |
| "step": 977 |
| }, |
| { |
| "epoch": 5.721407624633431, |
| "grad_norm": 0.5848984981840332, |
| "learning_rate": 1.8507295216994162e-05, |
| "loss": 0.0715, |
| "mean_token_accuracy": 0.9809279665350914, |
| "step": 978 |
| }, |
| { |
| "epoch": 5.7272727272727275, |
| "grad_norm": 0.4250499033716092, |
| "learning_rate": 1.8473660647072053e-05, |
| "loss": 0.0715, |
| "mean_token_accuracy": 0.9773638993501663, |
| "step": 979 |
| }, |
| { |
| "epoch": 5.733137829912024, |
| "grad_norm": 0.46841773113513163, |
| "learning_rate": 1.8440038876337597e-05, |
| "loss": 0.0624, |
| "mean_token_accuracy": 0.9801914915442467, |
| "step": 980 |
| }, |
| { |
| "epoch": 5.73900293255132, |
| "grad_norm": 0.5038261427174479, |
| "learning_rate": 1.8406430026824252e-05, |
| "loss": 0.075, |
| "mean_token_accuracy": 0.9773709028959274, |
| "step": 981 |
| }, |
| { |
| "epoch": 5.744868035190616, |
| "grad_norm": 0.47075990803551643, |
| "learning_rate": 1.837283422051855e-05, |
| "loss": 0.0743, |
| "mean_token_accuracy": 0.9782584458589554, |
| "step": 982 |
| }, |
| { |
| "epoch": 5.750733137829912, |
| "grad_norm": 0.567572930616802, |
| "learning_rate": 1.8339251579359713e-05, |
| "loss": 0.0778, |
| "mean_token_accuracy": 0.9760931208729744, |
| "step": 983 |
| }, |
| { |
| "epoch": 5.756598240469208, |
| "grad_norm": 0.3936380859190155, |
| "learning_rate": 1.8305682225239167e-05, |
| "loss": 0.0713, |
| "mean_token_accuracy": 0.9801273196935654, |
| "step": 984 |
| }, |
| { |
| "epoch": 5.762463343108505, |
| "grad_norm": 0.7903767668109325, |
| "learning_rate": 1.8272126280000102e-05, |
| "loss": 0.0884, |
| "mean_token_accuracy": 0.9739851281046867, |
| "step": 985 |
| }, |
| { |
| "epoch": 5.768328445747801, |
| "grad_norm": 0.6608741086050125, |
| "learning_rate": 1.823858386543705e-05, |
| "loss": 0.0652, |
| "mean_token_accuracy": 0.9803629368543625, |
| "step": 986 |
| }, |
| { |
| "epoch": 5.774193548387097, |
| "grad_norm": 0.4998320602993573, |
| "learning_rate": 1.8205055103295434e-05, |
| "loss": 0.0768, |
| "mean_token_accuracy": 0.9743634089827538, |
| "step": 987 |
| }, |
| { |
| "epoch": 5.780058651026393, |
| "grad_norm": 0.4671426923936314, |
| "learning_rate": 1.8171540115271108e-05, |
| "loss": 0.0841, |
| "mean_token_accuracy": 0.9734274372458458, |
| "step": 988 |
| }, |
| { |
| "epoch": 5.785923753665689, |
| "grad_norm": 0.593095309506939, |
| "learning_rate": 1.813803902300995e-05, |
| "loss": 0.0737, |
| "mean_token_accuracy": 0.9768568873405457, |
| "step": 989 |
| }, |
| { |
| "epoch": 5.7917888563049855, |
| "grad_norm": 0.5184984999658933, |
| "learning_rate": 1.8104551948107395e-05, |
| "loss": 0.0856, |
| "mean_token_accuracy": 0.97777359187603, |
| "step": 990 |
| }, |
| { |
| "epoch": 5.797653958944282, |
| "grad_norm": 0.5641853565258578, |
| "learning_rate": 1.8071079012107997e-05, |
| "loss": 0.0633, |
| "mean_token_accuracy": 0.9801298975944519, |
| "step": 991 |
| }, |
| { |
| "epoch": 5.803519061583578, |
| "grad_norm": 0.4631484693838226, |
| "learning_rate": 1.8037620336504993e-05, |
| "loss": 0.0706, |
| "mean_token_accuracy": 0.9805011823773384, |
| "step": 992 |
| }, |
| { |
| "epoch": 5.809384164222874, |
| "grad_norm": 0.44416688250468606, |
| "learning_rate": 1.8004176042739877e-05, |
| "loss": 0.071, |
| "mean_token_accuracy": 0.9795691072940826, |
| "step": 993 |
| }, |
| { |
| "epoch": 5.81524926686217, |
| "grad_norm": 0.5965136059432004, |
| "learning_rate": 1.797074625220191e-05, |
| "loss": 0.0748, |
| "mean_token_accuracy": 0.9784457981586456, |
| "step": 994 |
| }, |
| { |
| "epoch": 5.821114369501466, |
| "grad_norm": 0.5438818438785552, |
| "learning_rate": 1.7937331086227737e-05, |
| "loss": 0.0763, |
| "mean_token_accuracy": 0.9762759432196617, |
| "step": 995 |
| }, |
| { |
| "epoch": 5.826979472140763, |
| "grad_norm": 0.4977872314812647, |
| "learning_rate": 1.790393066610091e-05, |
| "loss": 0.0826, |
| "mean_token_accuracy": 0.9762104973196983, |
| "step": 996 |
| }, |
| { |
| "epoch": 5.832844574780059, |
| "grad_norm": 0.6131847389744154, |
| "learning_rate": 1.787054511305148e-05, |
| "loss": 0.0815, |
| "mean_token_accuracy": 0.9775402843952179, |
| "step": 997 |
| }, |
| { |
| "epoch": 5.838709677419355, |
| "grad_norm": 0.5577275741311593, |
| "learning_rate": 1.7837174548255504e-05, |
| "loss": 0.0814, |
| "mean_token_accuracy": 0.9762129485607147, |
| "step": 998 |
| }, |
| { |
| "epoch": 5.844574780058651, |
| "grad_norm": 0.5592068604336378, |
| "learning_rate": 1.7803819092834668e-05, |
| "loss": 0.0645, |
| "mean_token_accuracy": 0.9782524555921555, |
| "step": 999 |
| }, |
| { |
| "epoch": 5.850439882697947, |
| "grad_norm": 0.6354990519774383, |
| "learning_rate": 1.7770478867855797e-05, |
| "loss": 0.0839, |
| "mean_token_accuracy": 0.9766361862421036, |
| "step": 1000 |
| }, |
| { |
| "epoch": 5.8563049853372435, |
| "grad_norm": 0.6256455849819228, |
| "learning_rate": 1.7737153994330437e-05, |
| "loss": 0.0896, |
| "mean_token_accuracy": 0.9751609116792679, |
| "step": 1001 |
| }, |
| { |
| "epoch": 5.86217008797654, |
| "grad_norm": 0.5452759134932382, |
| "learning_rate": 1.7703844593214427e-05, |
| "loss": 0.075, |
| "mean_token_accuracy": 0.9791750013828278, |
| "step": 1002 |
| }, |
| { |
| "epoch": 5.868035190615836, |
| "grad_norm": 0.5075678241957828, |
| "learning_rate": 1.7670550785407444e-05, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.9794988706707954, |
| "step": 1003 |
| }, |
| { |
| "epoch": 5.873900293255132, |
| "grad_norm": 0.6731979059855191, |
| "learning_rate": 1.7637272691752548e-05, |
| "loss": 0.0794, |
| "mean_token_accuracy": 0.974234364926815, |
| "step": 1004 |
| }, |
| { |
| "epoch": 5.879765395894428, |
| "grad_norm": 0.4480038296462438, |
| "learning_rate": 1.7604010433035793e-05, |
| "loss": 0.0869, |
| "mean_token_accuracy": 0.9753069505095482, |
| "step": 1005 |
| }, |
| { |
| "epoch": 5.885630498533724, |
| "grad_norm": 0.5462367128398795, |
| "learning_rate": 1.7570764129985747e-05, |
| "loss": 0.0824, |
| "mean_token_accuracy": 0.9754479303956032, |
| "step": 1006 |
| }, |
| { |
| "epoch": 5.891495601173021, |
| "grad_norm": 0.5481811313348861, |
| "learning_rate": 1.7537533903273055e-05, |
| "loss": 0.079, |
| "mean_token_accuracy": 0.9769573882222176, |
| "step": 1007 |
| }, |
| { |
| "epoch": 5.897360703812317, |
| "grad_norm": 0.8764032211615499, |
| "learning_rate": 1.7504319873510014e-05, |
| "loss": 0.0921, |
| "mean_token_accuracy": 0.9756467416882515, |
| "step": 1008 |
| }, |
| { |
| "epoch": 5.903225806451613, |
| "grad_norm": 0.5742525162178889, |
| "learning_rate": 1.7471122161250153e-05, |
| "loss": 0.0796, |
| "mean_token_accuracy": 0.9754255339503288, |
| "step": 1009 |
| }, |
| { |
| "epoch": 5.909090909090909, |
| "grad_norm": 0.7279542813059033, |
| "learning_rate": 1.743794088698775e-05, |
| "loss": 0.0754, |
| "mean_token_accuracy": 0.9784489199519157, |
| "step": 1010 |
| }, |
| { |
| "epoch": 5.914956011730205, |
| "grad_norm": 0.4522109182504477, |
| "learning_rate": 1.7404776171157428e-05, |
| "loss": 0.0823, |
| "mean_token_accuracy": 0.9760701656341553, |
| "step": 1011 |
| }, |
| { |
| "epoch": 5.9208211143695015, |
| "grad_norm": 0.5006876106993897, |
| "learning_rate": 1.7371628134133716e-05, |
| "loss": 0.0814, |
| "mean_token_accuracy": 0.9751926735043526, |
| "step": 1012 |
| }, |
| { |
| "epoch": 5.926686217008798, |
| "grad_norm": 0.4417156692330552, |
| "learning_rate": 1.73384968962306e-05, |
| "loss": 0.0756, |
| "mean_token_accuracy": 0.975707083940506, |
| "step": 1013 |
| }, |
| { |
| "epoch": 5.932551319648094, |
| "grad_norm": 0.6094248911195603, |
| "learning_rate": 1.7305382577701088e-05, |
| "loss": 0.0808, |
| "mean_token_accuracy": 0.9764841720461845, |
| "step": 1014 |
| }, |
| { |
| "epoch": 5.93841642228739, |
| "grad_norm": 0.551520586810897, |
| "learning_rate": 1.7272285298736787e-05, |
| "loss": 0.0782, |
| "mean_token_accuracy": 0.9761537089943886, |
| "step": 1015 |
| }, |
| { |
| "epoch": 5.944281524926686, |
| "grad_norm": 0.6403501488586054, |
| "learning_rate": 1.7239205179467453e-05, |
| "loss": 0.0844, |
| "mean_token_accuracy": 0.974406361579895, |
| "step": 1016 |
| }, |
| { |
| "epoch": 5.9501466275659824, |
| "grad_norm": 0.5514850408949352, |
| "learning_rate": 1.720614233996056e-05, |
| "loss": 0.083, |
| "mean_token_accuracy": 0.9733666777610779, |
| "step": 1017 |
| }, |
| { |
| "epoch": 5.956011730205279, |
| "grad_norm": 0.5165899623290655, |
| "learning_rate": 1.7173096900220852e-05, |
| "loss": 0.0789, |
| "mean_token_accuracy": 0.9754836708307266, |
| "step": 1018 |
| }, |
| { |
| "epoch": 5.961876832844575, |
| "grad_norm": 0.49632223872221254, |
| "learning_rate": 1.7140068980189943e-05, |
| "loss": 0.0811, |
| "mean_token_accuracy": 0.974688708782196, |
| "step": 1019 |
| }, |
| { |
| "epoch": 5.967741935483871, |
| "grad_norm": 0.5819762705527881, |
| "learning_rate": 1.710705869974583e-05, |
| "loss": 0.0771, |
| "mean_token_accuracy": 0.9771495833992958, |
| "step": 1020 |
| }, |
| { |
| "epoch": 5.973607038123167, |
| "grad_norm": 0.6180454944945127, |
| "learning_rate": 1.7074066178702512e-05, |
| "loss": 0.0661, |
| "mean_token_accuracy": 0.9801411479711533, |
| "step": 1021 |
| }, |
| { |
| "epoch": 5.979472140762463, |
| "grad_norm": 0.4411679881699406, |
| "learning_rate": 1.7041091536809506e-05, |
| "loss": 0.0715, |
| "mean_token_accuracy": 0.9799164235591888, |
| "step": 1022 |
| }, |
| { |
| "epoch": 5.9853372434017595, |
| "grad_norm": 0.5065972988067083, |
| "learning_rate": 1.7008134893751446e-05, |
| "loss": 0.0688, |
| "mean_token_accuracy": 0.979424737393856, |
| "step": 1023 |
| }, |
| { |
| "epoch": 5.991202346041056, |
| "grad_norm": 0.4240940682692869, |
| "learning_rate": 1.697519636914765e-05, |
| "loss": 0.071, |
| "mean_token_accuracy": 0.9785429760813713, |
| "step": 1024 |
| }, |
| { |
| "epoch": 5.997067448680352, |
| "grad_norm": 0.611593671142202, |
| "learning_rate": 1.6942276082551634e-05, |
| "loss": 0.0876, |
| "mean_token_accuracy": 0.973278783261776, |
| "step": 1025 |
| }, |
| { |
| "epoch": 6.0, |
| "grad_norm": 0.989390280244205, |
| "learning_rate": 1.6909374153450762e-05, |
| "loss": 0.081, |
| "mean_token_accuracy": 0.9779550731182098, |
| "step": 1026 |
| }, |
| { |
| "epoch": 6.005865102639296, |
| "grad_norm": 0.4230070349459214, |
| "learning_rate": 1.6876490701265736e-05, |
| "loss": 0.0602, |
| "mean_token_accuracy": 0.9809990078210831, |
| "step": 1027 |
| }, |
| { |
| "epoch": 6.011730205278592, |
| "grad_norm": 0.4809667816759392, |
| "learning_rate": 1.684362584535022e-05, |
| "loss": 0.0686, |
| "mean_token_accuracy": 0.9796543195843697, |
| "step": 1028 |
| }, |
| { |
| "epoch": 6.0175953079178885, |
| "grad_norm": 0.9016883836801177, |
| "learning_rate": 1.6810779704990358e-05, |
| "loss": 0.064, |
| "mean_token_accuracy": 0.9786367863416672, |
| "step": 1029 |
| }, |
| { |
| "epoch": 6.023460410557185, |
| "grad_norm": 0.5120683418670421, |
| "learning_rate": 1.677795239940438e-05, |
| "loss": 0.0589, |
| "mean_token_accuracy": 0.9816581308841705, |
| "step": 1030 |
| }, |
| { |
| "epoch": 6.029325513196481, |
| "grad_norm": 0.48081169024458126, |
| "learning_rate": 1.674514404774214e-05, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9813550114631653, |
| "step": 1031 |
| }, |
| { |
| "epoch": 6.035190615835777, |
| "grad_norm": 0.5765323121918493, |
| "learning_rate": 1.671235476908471e-05, |
| "loss": 0.0659, |
| "mean_token_accuracy": 0.9793925806879997, |
| "step": 1032 |
| }, |
| { |
| "epoch": 6.041055718475073, |
| "grad_norm": 0.4326327601941797, |
| "learning_rate": 1.6679584682443924e-05, |
| "loss": 0.0591, |
| "mean_token_accuracy": 0.9802664965391159, |
| "step": 1033 |
| }, |
| { |
| "epoch": 6.0469208211143695, |
| "grad_norm": 0.5269803365906425, |
| "learning_rate": 1.6646833906761965e-05, |
| "loss": 0.0653, |
| "mean_token_accuracy": 0.9782321378588676, |
| "step": 1034 |
| }, |
| { |
| "epoch": 6.052785923753666, |
| "grad_norm": 0.4138760129091301, |
| "learning_rate": 1.661410256091092e-05, |
| "loss": 0.0641, |
| "mean_token_accuracy": 0.9822335913777351, |
| "step": 1035 |
| }, |
| { |
| "epoch": 6.058651026392962, |
| "grad_norm": 0.3503802526401633, |
| "learning_rate": 1.658139076369236e-05, |
| "loss": 0.0664, |
| "mean_token_accuracy": 0.9802732914686203, |
| "step": 1036 |
| }, |
| { |
| "epoch": 6.064516129032258, |
| "grad_norm": 0.5238336475389761, |
| "learning_rate": 1.6548698633836893e-05, |
| "loss": 0.0654, |
| "mean_token_accuracy": 0.9764923080801964, |
| "step": 1037 |
| }, |
| { |
| "epoch": 6.070381231671554, |
| "grad_norm": 0.6481246518288559, |
| "learning_rate": 1.6516026290003746e-05, |
| "loss": 0.0655, |
| "mean_token_accuracy": 0.9822241738438606, |
| "step": 1038 |
| }, |
| { |
| "epoch": 6.07624633431085, |
| "grad_norm": 0.4818098827810952, |
| "learning_rate": 1.6483373850780328e-05, |
| "loss": 0.0671, |
| "mean_token_accuracy": 0.9789280816912651, |
| "step": 1039 |
| }, |
| { |
| "epoch": 6.0821114369501466, |
| "grad_norm": 0.3031875450319505, |
| "learning_rate": 1.645074143468181e-05, |
| "loss": 0.0523, |
| "mean_token_accuracy": 0.9837686270475388, |
| "step": 1040 |
| }, |
| { |
| "epoch": 6.087976539589443, |
| "grad_norm": 0.5254248298346764, |
| "learning_rate": 1.6418129160150692e-05, |
| "loss": 0.0642, |
| "mean_token_accuracy": 0.9779577627778053, |
| "step": 1041 |
| }, |
| { |
| "epoch": 6.093841642228739, |
| "grad_norm": 0.4566878185169901, |
| "learning_rate": 1.6385537145556346e-05, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.9836693927645683, |
| "step": 1042 |
| }, |
| { |
| "epoch": 6.099706744868035, |
| "grad_norm": 0.41107292338776835, |
| "learning_rate": 1.6352965509194634e-05, |
| "loss": 0.0577, |
| "mean_token_accuracy": 0.9834092557430267, |
| "step": 1043 |
| }, |
| { |
| "epoch": 6.105571847507331, |
| "grad_norm": 0.46469592304351814, |
| "learning_rate": 1.6320414369287427e-05, |
| "loss": 0.0549, |
| "mean_token_accuracy": 0.9818287864327431, |
| "step": 1044 |
| }, |
| { |
| "epoch": 6.1114369501466275, |
| "grad_norm": 0.3758735824688024, |
| "learning_rate": 1.6287883843982223e-05, |
| "loss": 0.064, |
| "mean_token_accuracy": 0.9818753302097321, |
| "step": 1045 |
| }, |
| { |
| "epoch": 6.117302052785924, |
| "grad_norm": 0.5436745352949359, |
| "learning_rate": 1.625537405135169e-05, |
| "loss": 0.081, |
| "mean_token_accuracy": 0.9740028008818626, |
| "step": 1046 |
| }, |
| { |
| "epoch": 6.12316715542522, |
| "grad_norm": 0.4545248918295238, |
| "learning_rate": 1.622288510939325e-05, |
| "loss": 0.0656, |
| "mean_token_accuracy": 0.9772230237722397, |
| "step": 1047 |
| }, |
| { |
| "epoch": 6.129032258064516, |
| "grad_norm": 0.45739493592200814, |
| "learning_rate": 1.619041713602864e-05, |
| "loss": 0.0728, |
| "mean_token_accuracy": 0.9779245927929878, |
| "step": 1048 |
| }, |
| { |
| "epoch": 6.134897360703812, |
| "grad_norm": 0.51162293891879, |
| "learning_rate": 1.6157970249103484e-05, |
| "loss": 0.0743, |
| "mean_token_accuracy": 0.9762742295861244, |
| "step": 1049 |
| }, |
| { |
| "epoch": 6.140762463343108, |
| "grad_norm": 0.5507465476783818, |
| "learning_rate": 1.612554456638688e-05, |
| "loss": 0.0721, |
| "mean_token_accuracy": 0.9776153936982155, |
| "step": 1050 |
| }, |
| { |
| "epoch": 6.146627565982405, |
| "grad_norm": 0.5145632814275362, |
| "learning_rate": 1.6093140205570962e-05, |
| "loss": 0.0791, |
| "mean_token_accuracy": 0.976268582046032, |
| "step": 1051 |
| }, |
| { |
| "epoch": 6.152492668621701, |
| "grad_norm": 0.9051351509370605, |
| "learning_rate": 1.6060757284270474e-05, |
| "loss": 0.0805, |
| "mean_token_accuracy": 0.9752627164125443, |
| "step": 1052 |
| }, |
| { |
| "epoch": 6.158357771260997, |
| "grad_norm": 0.4403044486083453, |
| "learning_rate": 1.6028395920022336e-05, |
| "loss": 0.0574, |
| "mean_token_accuracy": 0.9793043285608292, |
| "step": 1053 |
| }, |
| { |
| "epoch": 6.164222873900293, |
| "grad_norm": 0.3794117905310881, |
| "learning_rate": 1.5996056230285237e-05, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9801375046372414, |
| "step": 1054 |
| }, |
| { |
| "epoch": 6.170087976539589, |
| "grad_norm": 0.4175007624888782, |
| "learning_rate": 1.596373833243918e-05, |
| "loss": 0.0643, |
| "mean_token_accuracy": 0.978547640144825, |
| "step": 1055 |
| }, |
| { |
| "epoch": 6.1759530791788855, |
| "grad_norm": 0.45255458686021044, |
| "learning_rate": 1.593144234378509e-05, |
| "loss": 0.0656, |
| "mean_token_accuracy": 0.9782090336084366, |
| "step": 1056 |
| }, |
| { |
| "epoch": 6.181818181818182, |
| "grad_norm": 0.49640241962018194, |
| "learning_rate": 1.5899168381544362e-05, |
| "loss": 0.0651, |
| "mean_token_accuracy": 0.9813453853130341, |
| "step": 1057 |
| }, |
| { |
| "epoch": 6.187683284457478, |
| "grad_norm": 0.4012097342615111, |
| "learning_rate": 1.5866916562858444e-05, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.9798336252570152, |
| "step": 1058 |
| }, |
| { |
| "epoch": 6.193548387096774, |
| "grad_norm": 0.3832795337648082, |
| "learning_rate": 1.5834687004788406e-05, |
| "loss": 0.061, |
| "mean_token_accuracy": 0.9790323451161385, |
| "step": 1059 |
| }, |
| { |
| "epoch": 6.19941348973607, |
| "grad_norm": 0.45921292178284495, |
| "learning_rate": 1.5802479824314537e-05, |
| "loss": 0.0713, |
| "mean_token_accuracy": 0.9753189608454704, |
| "step": 1060 |
| }, |
| { |
| "epoch": 6.205278592375366, |
| "grad_norm": 0.37110042750500344, |
| "learning_rate": 1.5770295138335896e-05, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9829725921154022, |
| "step": 1061 |
| }, |
| { |
| "epoch": 6.211143695014663, |
| "grad_norm": 0.5292919165677671, |
| "learning_rate": 1.573813306366988e-05, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9827964678406715, |
| "step": 1062 |
| }, |
| { |
| "epoch": 6.217008797653959, |
| "grad_norm": 0.5901800906736643, |
| "learning_rate": 1.5705993717051838e-05, |
| "loss": 0.0803, |
| "mean_token_accuracy": 0.9757646322250366, |
| "step": 1063 |
| }, |
| { |
| "epoch": 6.222873900293255, |
| "grad_norm": 0.5673704851630527, |
| "learning_rate": 1.567387721513462e-05, |
| "loss": 0.0742, |
| "mean_token_accuracy": 0.9788571149110794, |
| "step": 1064 |
| }, |
| { |
| "epoch": 6.228739002932551, |
| "grad_norm": 0.517815339963219, |
| "learning_rate": 1.5641783674488155e-05, |
| "loss": 0.068, |
| "mean_token_accuracy": 0.9804918318986893, |
| "step": 1065 |
| }, |
| { |
| "epoch": 6.234604105571847, |
| "grad_norm": 0.6981822028647853, |
| "learning_rate": 1.5609713211599035e-05, |
| "loss": 0.0771, |
| "mean_token_accuracy": 0.9772537648677826, |
| "step": 1066 |
| }, |
| { |
| "epoch": 6.2404692082111435, |
| "grad_norm": 0.5645231236916332, |
| "learning_rate": 1.557766594287009e-05, |
| "loss": 0.0783, |
| "mean_token_accuracy": 0.9776250943541527, |
| "step": 1067 |
| }, |
| { |
| "epoch": 6.24633431085044, |
| "grad_norm": 0.425211654077209, |
| "learning_rate": 1.554564198461996e-05, |
| "loss": 0.0772, |
| "mean_token_accuracy": 0.9736573025584221, |
| "step": 1068 |
| }, |
| { |
| "epoch": 6.252199413489736, |
| "grad_norm": 0.6755364232320741, |
| "learning_rate": 1.5513641453082672e-05, |
| "loss": 0.0715, |
| "mean_token_accuracy": 0.9788224399089813, |
| "step": 1069 |
| }, |
| { |
| "epoch": 6.258064516129032, |
| "grad_norm": 0.4802248171400769, |
| "learning_rate": 1.5481664464407246e-05, |
| "loss": 0.0638, |
| "mean_token_accuracy": 0.9831561893224716, |
| "step": 1070 |
| }, |
| { |
| "epoch": 6.263929618768328, |
| "grad_norm": 1.7321569882434473, |
| "learning_rate": 1.5449711134657224e-05, |
| "loss": 0.0757, |
| "mean_token_accuracy": 0.9757629260420799, |
| "step": 1071 |
| }, |
| { |
| "epoch": 6.269794721407624, |
| "grad_norm": 0.44523777582660745, |
| "learning_rate": 1.5417781579810296e-05, |
| "loss": 0.0691, |
| "mean_token_accuracy": 0.9794281423091888, |
| "step": 1072 |
| }, |
| { |
| "epoch": 6.275659824046921, |
| "grad_norm": 0.5126014904862785, |
| "learning_rate": 1.5385875915757846e-05, |
| "loss": 0.0624, |
| "mean_token_accuracy": 0.9795156866312027, |
| "step": 1073 |
| }, |
| { |
| "epoch": 6.281524926686217, |
| "grad_norm": 0.3975436578422233, |
| "learning_rate": 1.535399425830456e-05, |
| "loss": 0.0642, |
| "mean_token_accuracy": 0.9801967516541481, |
| "step": 1074 |
| }, |
| { |
| "epoch": 6.287390029325513, |
| "grad_norm": 0.5115367202459034, |
| "learning_rate": 1.5322136723167957e-05, |
| "loss": 0.0669, |
| "mean_token_accuracy": 0.9776618257164955, |
| "step": 1075 |
| }, |
| { |
| "epoch": 6.293255131964809, |
| "grad_norm": 0.4162534346021217, |
| "learning_rate": 1.5290303425978036e-05, |
| "loss": 0.0636, |
| "mean_token_accuracy": 0.9809231907129288, |
| "step": 1076 |
| }, |
| { |
| "epoch": 6.299120234604105, |
| "grad_norm": 0.5679322341771472, |
| "learning_rate": 1.525849448227681e-05, |
| "loss": 0.0721, |
| "mean_token_accuracy": 0.9788202419877052, |
| "step": 1077 |
| }, |
| { |
| "epoch": 6.3049853372434015, |
| "grad_norm": 0.33264597776146443, |
| "learning_rate": 1.5226710007517894e-05, |
| "loss": 0.0728, |
| "mean_token_accuracy": 0.9753846675157547, |
| "step": 1078 |
| }, |
| { |
| "epoch": 6.310850439882698, |
| "grad_norm": 0.3700642741877526, |
| "learning_rate": 1.5194950117066097e-05, |
| "loss": 0.0602, |
| "mean_token_accuracy": 0.9789994210004807, |
| "step": 1079 |
| }, |
| { |
| "epoch": 6.316715542521994, |
| "grad_norm": 0.4538963744798111, |
| "learning_rate": 1.5163214926196995e-05, |
| "loss": 0.0795, |
| "mean_token_accuracy": 0.9746260717511177, |
| "step": 1080 |
| }, |
| { |
| "epoch": 6.32258064516129, |
| "grad_norm": 0.41619435583306597, |
| "learning_rate": 1.5131504550096515e-05, |
| "loss": 0.0677, |
| "mean_token_accuracy": 0.9778345227241516, |
| "step": 1081 |
| }, |
| { |
| "epoch": 6.328445747800586, |
| "grad_norm": 0.2562840436018545, |
| "learning_rate": 1.5099819103860504e-05, |
| "loss": 0.0603, |
| "mean_token_accuracy": 0.9805175438523293, |
| "step": 1082 |
| }, |
| { |
| "epoch": 6.334310850439882, |
| "grad_norm": 0.48366360471108993, |
| "learning_rate": 1.5068158702494348e-05, |
| "loss": 0.0588, |
| "mean_token_accuracy": 0.9807134121656418, |
| "step": 1083 |
| }, |
| { |
| "epoch": 6.340175953079179, |
| "grad_norm": 0.43233510759403737, |
| "learning_rate": 1.5036523460912511e-05, |
| "loss": 0.0589, |
| "mean_token_accuracy": 0.982612282037735, |
| "step": 1084 |
| }, |
| { |
| "epoch": 6.346041055718475, |
| "grad_norm": 0.41436575580785434, |
| "learning_rate": 1.5004913493938147e-05, |
| "loss": 0.0672, |
| "mean_token_accuracy": 0.9788793921470642, |
| "step": 1085 |
| }, |
| { |
| "epoch": 6.351906158357771, |
| "grad_norm": 0.5154873539617718, |
| "learning_rate": 1.4973328916302667e-05, |
| "loss": 0.0746, |
| "mean_token_accuracy": 0.9756126180291176, |
| "step": 1086 |
| }, |
| { |
| "epoch": 6.357771260997067, |
| "grad_norm": 0.40160039748906046, |
| "learning_rate": 1.4941769842645335e-05, |
| "loss": 0.0694, |
| "mean_token_accuracy": 0.9775484576821327, |
| "step": 1087 |
| }, |
| { |
| "epoch": 6.363636363636363, |
| "grad_norm": 0.3751129300388227, |
| "learning_rate": 1.4910236387512837e-05, |
| "loss": 0.06, |
| "mean_token_accuracy": 0.9810876697301865, |
| "step": 1088 |
| }, |
| { |
| "epoch": 6.3695014662756595, |
| "grad_norm": 0.38549860564235966, |
| "learning_rate": 1.487872866535888e-05, |
| "loss": 0.0633, |
| "mean_token_accuracy": 0.981402188539505, |
| "step": 1089 |
| }, |
| { |
| "epoch": 6.375366568914956, |
| "grad_norm": 0.4941639857655589, |
| "learning_rate": 1.4847246790543773e-05, |
| "loss": 0.067, |
| "mean_token_accuracy": 0.9788068756461143, |
| "step": 1090 |
| }, |
| { |
| "epoch": 6.381231671554252, |
| "grad_norm": 0.4267367405789239, |
| "learning_rate": 1.4815790877334007e-05, |
| "loss": 0.0585, |
| "mean_token_accuracy": 0.9816467389464378, |
| "step": 1091 |
| }, |
| { |
| "epoch": 6.387096774193548, |
| "grad_norm": 0.4632733601898166, |
| "learning_rate": 1.4784361039901844e-05, |
| "loss": 0.0699, |
| "mean_token_accuracy": 0.9788152202963829, |
| "step": 1092 |
| }, |
| { |
| "epoch": 6.392961876832844, |
| "grad_norm": 0.4401889419648337, |
| "learning_rate": 1.47529573923249e-05, |
| "loss": 0.0603, |
| "mean_token_accuracy": 0.98129902780056, |
| "step": 1093 |
| }, |
| { |
| "epoch": 6.39882697947214, |
| "grad_norm": 0.4408537773426437, |
| "learning_rate": 1.472158004858573e-05, |
| "loss": 0.0672, |
| "mean_token_accuracy": 0.979188434779644, |
| "step": 1094 |
| }, |
| { |
| "epoch": 6.404692082111437, |
| "grad_norm": 0.40532565045994134, |
| "learning_rate": 1.4690229122571419e-05, |
| "loss": 0.0748, |
| "mean_token_accuracy": 0.9763947352766991, |
| "step": 1095 |
| }, |
| { |
| "epoch": 6.410557184750733, |
| "grad_norm": 0.467733449302367, |
| "learning_rate": 1.4658904728073169e-05, |
| "loss": 0.0619, |
| "mean_token_accuracy": 0.9803221970796585, |
| "step": 1096 |
| }, |
| { |
| "epoch": 6.416422287390029, |
| "grad_norm": 0.4423734507777753, |
| "learning_rate": 1.4627606978785878e-05, |
| "loss": 0.07, |
| "mean_token_accuracy": 0.9782881215214729, |
| "step": 1097 |
| }, |
| { |
| "epoch": 6.422287390029325, |
| "grad_norm": 0.5813032813305795, |
| "learning_rate": 1.4596335988307736e-05, |
| "loss": 0.075, |
| "mean_token_accuracy": 0.9799735173583031, |
| "step": 1098 |
| }, |
| { |
| "epoch": 6.428152492668621, |
| "grad_norm": 0.3990593770762677, |
| "learning_rate": 1.4565091870139814e-05, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.9816461279988289, |
| "step": 1099 |
| }, |
| { |
| "epoch": 6.4340175953079175, |
| "grad_norm": 0.5096360075436533, |
| "learning_rate": 1.4533874737685638e-05, |
| "loss": 0.0827, |
| "mean_token_accuracy": 0.9770070910453796, |
| "step": 1100 |
| }, |
| { |
| "epoch": 6.439882697947214, |
| "grad_norm": 0.4034576006966357, |
| "learning_rate": 1.450268470425079e-05, |
| "loss": 0.0623, |
| "mean_token_accuracy": 0.9812736809253693, |
| "step": 1101 |
| }, |
| { |
| "epoch": 6.44574780058651, |
| "grad_norm": 0.5083541291281424, |
| "learning_rate": 1.4471521883042492e-05, |
| "loss": 0.0656, |
| "mean_token_accuracy": 0.9808938726782799, |
| "step": 1102 |
| }, |
| { |
| "epoch": 6.451612903225806, |
| "grad_norm": 0.547718663444142, |
| "learning_rate": 1.4440386387169207e-05, |
| "loss": 0.0721, |
| "mean_token_accuracy": 0.9780811071395874, |
| "step": 1103 |
| }, |
| { |
| "epoch": 6.457478005865102, |
| "grad_norm": 0.471186574564861, |
| "learning_rate": 1.4409278329640218e-05, |
| "loss": 0.069, |
| "mean_token_accuracy": 0.9777532294392586, |
| "step": 1104 |
| }, |
| { |
| "epoch": 6.463343108504398, |
| "grad_norm": 0.39531628982526346, |
| "learning_rate": 1.4378197823365186e-05, |
| "loss": 0.067, |
| "mean_token_accuracy": 0.9800560027360916, |
| "step": 1105 |
| }, |
| { |
| "epoch": 6.469208211143695, |
| "grad_norm": 0.5769580026963542, |
| "learning_rate": 1.4347144981153807e-05, |
| "loss": 0.0824, |
| "mean_token_accuracy": 0.9750961661338806, |
| "step": 1106 |
| }, |
| { |
| "epoch": 6.475073313782991, |
| "grad_norm": 0.41834706105462965, |
| "learning_rate": 1.4316119915715363e-05, |
| "loss": 0.0598, |
| "mean_token_accuracy": 0.9810346961021423, |
| "step": 1107 |
| }, |
| { |
| "epoch": 6.480938416422287, |
| "grad_norm": 0.5247956654805205, |
| "learning_rate": 1.42851227396583e-05, |
| "loss": 0.076, |
| "mean_token_accuracy": 0.9773802384734154, |
| "step": 1108 |
| }, |
| { |
| "epoch": 6.486803519061583, |
| "grad_norm": 0.5182710062953582, |
| "learning_rate": 1.4254153565489861e-05, |
| "loss": 0.074, |
| "mean_token_accuracy": 0.9766635000705719, |
| "step": 1109 |
| }, |
| { |
| "epoch": 6.492668621700879, |
| "grad_norm": 0.4548167468262035, |
| "learning_rate": 1.4223212505615634e-05, |
| "loss": 0.0656, |
| "mean_token_accuracy": 0.9804381132125854, |
| "step": 1110 |
| }, |
| { |
| "epoch": 6.4985337243401755, |
| "grad_norm": 0.40430833242136927, |
| "learning_rate": 1.4192299672339167e-05, |
| "loss": 0.0578, |
| "mean_token_accuracy": 0.9801406562328339, |
| "step": 1111 |
| }, |
| { |
| "epoch": 6.504398826979472, |
| "grad_norm": 0.5370970451033729, |
| "learning_rate": 1.4161415177861568e-05, |
| "loss": 0.0713, |
| "mean_token_accuracy": 0.9772634580731392, |
| "step": 1112 |
| }, |
| { |
| "epoch": 6.510263929618768, |
| "grad_norm": 0.3364637357817881, |
| "learning_rate": 1.4130559134281074e-05, |
| "loss": 0.0592, |
| "mean_token_accuracy": 0.9810837209224701, |
| "step": 1113 |
| }, |
| { |
| "epoch": 6.516129032258064, |
| "grad_norm": 0.43331710088554903, |
| "learning_rate": 1.4099731653592668e-05, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9798248186707497, |
| "step": 1114 |
| }, |
| { |
| "epoch": 6.52199413489736, |
| "grad_norm": 0.4495256260222478, |
| "learning_rate": 1.406893284768764e-05, |
| "loss": 0.0781, |
| "mean_token_accuracy": 0.9766861349344254, |
| "step": 1115 |
| }, |
| { |
| "epoch": 6.527859237536656, |
| "grad_norm": 0.5395741783044383, |
| "learning_rate": 1.4038162828353223e-05, |
| "loss": 0.0753, |
| "mean_token_accuracy": 0.9756533950567245, |
| "step": 1116 |
| }, |
| { |
| "epoch": 6.533724340175953, |
| "grad_norm": 0.5422962438171246, |
| "learning_rate": 1.4007421707272167e-05, |
| "loss": 0.0716, |
| "mean_token_accuracy": 0.9782907888293266, |
| "step": 1117 |
| }, |
| { |
| "epoch": 6.539589442815249, |
| "grad_norm": 0.5546002790540274, |
| "learning_rate": 1.3976709596022313e-05, |
| "loss": 0.0709, |
| "mean_token_accuracy": 0.9770197793841362, |
| "step": 1118 |
| }, |
| { |
| "epoch": 6.545454545454545, |
| "grad_norm": 0.518015113413407, |
| "learning_rate": 1.3946026606076232e-05, |
| "loss": 0.0716, |
| "mean_token_accuracy": 0.9807683080434799, |
| "step": 1119 |
| }, |
| { |
| "epoch": 6.551319648093841, |
| "grad_norm": 0.6932508207570297, |
| "learning_rate": 1.3915372848800784e-05, |
| "loss": 0.0776, |
| "mean_token_accuracy": 0.9786146953701973, |
| "step": 1120 |
| }, |
| { |
| "epoch": 6.557184750733137, |
| "grad_norm": 0.46596073614841477, |
| "learning_rate": 1.388474843545672e-05, |
| "loss": 0.0615, |
| "mean_token_accuracy": 0.979241244494915, |
| "step": 1121 |
| }, |
| { |
| "epoch": 6.563049853372434, |
| "grad_norm": 0.48023768969255687, |
| "learning_rate": 1.3854153477198305e-05, |
| "loss": 0.083, |
| "mean_token_accuracy": 0.9719856157898903, |
| "step": 1122 |
| }, |
| { |
| "epoch": 6.568914956011731, |
| "grad_norm": 0.4138687687316157, |
| "learning_rate": 1.3823588085072865e-05, |
| "loss": 0.0661, |
| "mean_token_accuracy": 0.9797427132725716, |
| "step": 1123 |
| }, |
| { |
| "epoch": 6.574780058651027, |
| "grad_norm": 0.47858914117559365, |
| "learning_rate": 1.3793052370020441e-05, |
| "loss": 0.0718, |
| "mean_token_accuracy": 0.9773967415094376, |
| "step": 1124 |
| }, |
| { |
| "epoch": 6.580645161290323, |
| "grad_norm": 0.6243697871259365, |
| "learning_rate": 1.3762546442873343e-05, |
| "loss": 0.0692, |
| "mean_token_accuracy": 0.9803427085280418, |
| "step": 1125 |
| }, |
| { |
| "epoch": 6.586510263929619, |
| "grad_norm": 0.4875492799742511, |
| "learning_rate": 1.3732070414355766e-05, |
| "loss": 0.0705, |
| "mean_token_accuracy": 0.9797642901539803, |
| "step": 1126 |
| }, |
| { |
| "epoch": 6.592375366568915, |
| "grad_norm": 0.3718015452532362, |
| "learning_rate": 1.370162439508339e-05, |
| "loss": 0.0606, |
| "mean_token_accuracy": 0.9801923632621765, |
| "step": 1127 |
| }, |
| { |
| "epoch": 6.5982404692082115, |
| "grad_norm": 0.5704303577432631, |
| "learning_rate": 1.367120849556296e-05, |
| "loss": 0.0724, |
| "mean_token_accuracy": 0.9793426245450974, |
| "step": 1128 |
| }, |
| { |
| "epoch": 6.604105571847508, |
| "grad_norm": 0.5146825324740882, |
| "learning_rate": 1.3640822826191907e-05, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.9816078171133995, |
| "step": 1129 |
| }, |
| { |
| "epoch": 6.609970674486804, |
| "grad_norm": 0.5643347398770314, |
| "learning_rate": 1.361046749725794e-05, |
| "loss": 0.0727, |
| "mean_token_accuracy": 0.9767194986343384, |
| "step": 1130 |
| }, |
| { |
| "epoch": 6.6158357771261, |
| "grad_norm": 0.38975674311350267, |
| "learning_rate": 1.3580142618938647e-05, |
| "loss": 0.0566, |
| "mean_token_accuracy": 0.9839957654476166, |
| "step": 1131 |
| }, |
| { |
| "epoch": 6.621700879765396, |
| "grad_norm": 0.34822313778323327, |
| "learning_rate": 1.354984830130109e-05, |
| "loss": 0.0696, |
| "mean_token_accuracy": 0.9769606366753578, |
| "step": 1132 |
| }, |
| { |
| "epoch": 6.627565982404692, |
| "grad_norm": 0.4365409164065618, |
| "learning_rate": 1.3519584654301401e-05, |
| "loss": 0.0655, |
| "mean_token_accuracy": 0.9780000522732735, |
| "step": 1133 |
| }, |
| { |
| "epoch": 6.633431085043989, |
| "grad_norm": 0.4528538426658204, |
| "learning_rate": 1.3489351787784398e-05, |
| "loss": 0.0673, |
| "mean_token_accuracy": 0.9787932485342026, |
| "step": 1134 |
| }, |
| { |
| "epoch": 6.639296187683285, |
| "grad_norm": 0.48020115114867207, |
| "learning_rate": 1.3459149811483178e-05, |
| "loss": 0.0779, |
| "mean_token_accuracy": 0.9763984754681587, |
| "step": 1135 |
| }, |
| { |
| "epoch": 6.645161290322581, |
| "grad_norm": 0.5851000334081872, |
| "learning_rate": 1.342897883501872e-05, |
| "loss": 0.0796, |
| "mean_token_accuracy": 0.9779474139213562, |
| "step": 1136 |
| }, |
| { |
| "epoch": 6.651026392961877, |
| "grad_norm": 0.3951030203418182, |
| "learning_rate": 1.3398838967899477e-05, |
| "loss": 0.0641, |
| "mean_token_accuracy": 0.9799654707312584, |
| "step": 1137 |
| }, |
| { |
| "epoch": 6.656891495601173, |
| "grad_norm": 0.41805758317928976, |
| "learning_rate": 1.3368730319520992e-05, |
| "loss": 0.0638, |
| "mean_token_accuracy": 0.9813594818115234, |
| "step": 1138 |
| }, |
| { |
| "epoch": 6.6627565982404695, |
| "grad_norm": 0.43689086975785124, |
| "learning_rate": 1.3338652999165511e-05, |
| "loss": 0.0725, |
| "mean_token_accuracy": 0.9788738563656807, |
| "step": 1139 |
| }, |
| { |
| "epoch": 6.668621700879766, |
| "grad_norm": 0.31790770823484493, |
| "learning_rate": 1.3308607116001549e-05, |
| "loss": 0.0588, |
| "mean_token_accuracy": 0.9820768386125565, |
| "step": 1140 |
| }, |
| { |
| "epoch": 6.674486803519062, |
| "grad_norm": 0.36071681861745586, |
| "learning_rate": 1.3278592779083534e-05, |
| "loss": 0.059, |
| "mean_token_accuracy": 0.9846365228295326, |
| "step": 1141 |
| }, |
| { |
| "epoch": 6.680351906158358, |
| "grad_norm": 0.406874459719353, |
| "learning_rate": 1.324861009735138e-05, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.9802506789565086, |
| "step": 1142 |
| }, |
| { |
| "epoch": 6.686217008797654, |
| "grad_norm": 0.4026037779692382, |
| "learning_rate": 1.3218659179630112e-05, |
| "loss": 0.0689, |
| "mean_token_accuracy": 0.9794812649488449, |
| "step": 1143 |
| }, |
| { |
| "epoch": 6.69208211143695, |
| "grad_norm": 0.3609274332773618, |
| "learning_rate": 1.3188740134629469e-05, |
| "loss": 0.0651, |
| "mean_token_accuracy": 0.9809269681572914, |
| "step": 1144 |
| }, |
| { |
| "epoch": 6.697947214076247, |
| "grad_norm": 0.43413406807039673, |
| "learning_rate": 1.3158853070943499e-05, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.981363870203495, |
| "step": 1145 |
| }, |
| { |
| "epoch": 6.703812316715543, |
| "grad_norm": 0.3905644328801645, |
| "learning_rate": 1.3128998097050174e-05, |
| "loss": 0.0639, |
| "mean_token_accuracy": 0.9799892753362656, |
| "step": 1146 |
| }, |
| { |
| "epoch": 6.709677419354839, |
| "grad_norm": 0.4415899012250326, |
| "learning_rate": 1.3099175321310993e-05, |
| "loss": 0.0663, |
| "mean_token_accuracy": 0.9794251173734665, |
| "step": 1147 |
| }, |
| { |
| "epoch": 6.715542521994135, |
| "grad_norm": 0.3303445901009437, |
| "learning_rate": 1.3069384851970584e-05, |
| "loss": 0.0577, |
| "mean_token_accuracy": 0.9799608886241913, |
| "step": 1148 |
| }, |
| { |
| "epoch": 6.721407624633431, |
| "grad_norm": 0.542470612619514, |
| "learning_rate": 1.3039626797156321e-05, |
| "loss": 0.0684, |
| "mean_token_accuracy": 0.978044830262661, |
| "step": 1149 |
| }, |
| { |
| "epoch": 6.7272727272727275, |
| "grad_norm": 0.4478625244312105, |
| "learning_rate": 1.3009901264877924e-05, |
| "loss": 0.0635, |
| "mean_token_accuracy": 0.9832303300499916, |
| "step": 1150 |
| }, |
| { |
| "epoch": 6.733137829912024, |
| "grad_norm": 0.3070246305139214, |
| "learning_rate": 1.298020836302707e-05, |
| "loss": 0.0634, |
| "mean_token_accuracy": 0.9798863604664803, |
| "step": 1151 |
| }, |
| { |
| "epoch": 6.73900293255132, |
| "grad_norm": 0.3787118140466253, |
| "learning_rate": 1.2950548199376999e-05, |
| "loss": 0.0619, |
| "mean_token_accuracy": 0.9830320551991463, |
| "step": 1152 |
| }, |
| { |
| "epoch": 6.744868035190616, |
| "grad_norm": 0.6262382974166212, |
| "learning_rate": 1.292092088158213e-05, |
| "loss": 0.0724, |
| "mean_token_accuracy": 0.9787451773881912, |
| "step": 1153 |
| }, |
| { |
| "epoch": 6.750733137829912, |
| "grad_norm": 0.4031409936415585, |
| "learning_rate": 1.2891326517177663e-05, |
| "loss": 0.057, |
| "mean_token_accuracy": 0.9842765405774117, |
| "step": 1154 |
| }, |
| { |
| "epoch": 6.756598240469208, |
| "grad_norm": 0.370569744572269, |
| "learning_rate": 1.2861765213579177e-05, |
| "loss": 0.0673, |
| "mean_token_accuracy": 0.9774162173271179, |
| "step": 1155 |
| }, |
| { |
| "epoch": 6.762463343108505, |
| "grad_norm": 0.4504539339758509, |
| "learning_rate": 1.2832237078082272e-05, |
| "loss": 0.0646, |
| "mean_token_accuracy": 0.9795903638005257, |
| "step": 1156 |
| }, |
| { |
| "epoch": 6.768328445747801, |
| "grad_norm": 0.3525672565690468, |
| "learning_rate": 1.2802742217862156e-05, |
| "loss": 0.068, |
| "mean_token_accuracy": 0.9798642173409462, |
| "step": 1157 |
| }, |
| { |
| "epoch": 6.774193548387097, |
| "grad_norm": 0.4219177264271062, |
| "learning_rate": 1.2773280739973255e-05, |
| "loss": 0.0664, |
| "mean_token_accuracy": 0.978237122297287, |
| "step": 1158 |
| }, |
| { |
| "epoch": 6.780058651026393, |
| "grad_norm": 0.3757554934232093, |
| "learning_rate": 1.2743852751348833e-05, |
| "loss": 0.0558, |
| "mean_token_accuracy": 0.9824602827429771, |
| "step": 1159 |
| }, |
| { |
| "epoch": 6.785923753665689, |
| "grad_norm": 0.44869090627023644, |
| "learning_rate": 1.2714458358800612e-05, |
| "loss": 0.0508, |
| "mean_token_accuracy": 0.9844018071889877, |
| "step": 1160 |
| }, |
| { |
| "epoch": 6.7917888563049855, |
| "grad_norm": 0.599932829838675, |
| "learning_rate": 1.2685097669018362e-05, |
| "loss": 0.0835, |
| "mean_token_accuracy": 0.976402185857296, |
| "step": 1161 |
| }, |
| { |
| "epoch": 6.797653958944282, |
| "grad_norm": 0.35639663652954295, |
| "learning_rate": 1.265577078856953e-05, |
| "loss": 0.0708, |
| "mean_token_accuracy": 0.9760590195655823, |
| "step": 1162 |
| }, |
| { |
| "epoch": 6.803519061583578, |
| "grad_norm": 0.4358245772006115, |
| "learning_rate": 1.2626477823898843e-05, |
| "loss": 0.0737, |
| "mean_token_accuracy": 0.979936808347702, |
| "step": 1163 |
| }, |
| { |
| "epoch": 6.809384164222874, |
| "grad_norm": 0.4794803687851331, |
| "learning_rate": 1.2597218881327944e-05, |
| "loss": 0.0706, |
| "mean_token_accuracy": 0.9768901541829109, |
| "step": 1164 |
| }, |
| { |
| "epoch": 6.81524926686217, |
| "grad_norm": 0.32937163939726377, |
| "learning_rate": 1.2567994067054961e-05, |
| "loss": 0.063, |
| "mean_token_accuracy": 0.9787830784916878, |
| "step": 1165 |
| }, |
| { |
| "epoch": 6.821114369501466, |
| "grad_norm": 0.39110647767955126, |
| "learning_rate": 1.2538803487154177e-05, |
| "loss": 0.0643, |
| "mean_token_accuracy": 0.979418084025383, |
| "step": 1166 |
| }, |
| { |
| "epoch": 6.826979472140763, |
| "grad_norm": 0.33247603921786206, |
| "learning_rate": 1.25096472475756e-05, |
| "loss": 0.0644, |
| "mean_token_accuracy": 0.9782299101352692, |
| "step": 1167 |
| }, |
| { |
| "epoch": 6.832844574780059, |
| "grad_norm": 0.35810789676260385, |
| "learning_rate": 1.248052545414461e-05, |
| "loss": 0.0666, |
| "mean_token_accuracy": 0.9819423481822014, |
| "step": 1168 |
| }, |
| { |
| "epoch": 6.838709677419355, |
| "grad_norm": 0.4906003508933705, |
| "learning_rate": 1.2451438212561556e-05, |
| "loss": 0.0734, |
| "mean_token_accuracy": 0.9736126214265823, |
| "step": 1169 |
| }, |
| { |
| "epoch": 6.844574780058651, |
| "grad_norm": 0.37903277572822597, |
| "learning_rate": 1.2422385628401377e-05, |
| "loss": 0.0676, |
| "mean_token_accuracy": 0.9789053797721863, |
| "step": 1170 |
| }, |
| { |
| "epoch": 6.850439882697947, |
| "grad_norm": 0.7759463426777434, |
| "learning_rate": 1.2393367807113217e-05, |
| "loss": 0.0752, |
| "mean_token_accuracy": 0.9790110364556313, |
| "step": 1171 |
| }, |
| { |
| "epoch": 6.8563049853372435, |
| "grad_norm": 0.43252889379637655, |
| "learning_rate": 1.236438485402005e-05, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9801287278532982, |
| "step": 1172 |
| }, |
| { |
| "epoch": 6.86217008797654, |
| "grad_norm": 0.5288479160944122, |
| "learning_rate": 1.2335436874318293e-05, |
| "loss": 0.0623, |
| "mean_token_accuracy": 0.9801551327109337, |
| "step": 1173 |
| }, |
| { |
| "epoch": 6.868035190615836, |
| "grad_norm": 0.35953238759821077, |
| "learning_rate": 1.2306523973077416e-05, |
| "loss": 0.0751, |
| "mean_token_accuracy": 0.9780450016260147, |
| "step": 1174 |
| }, |
| { |
| "epoch": 6.873900293255132, |
| "grad_norm": 0.44824241707674634, |
| "learning_rate": 1.2277646255239572e-05, |
| "loss": 0.0742, |
| "mean_token_accuracy": 0.9785097539424896, |
| "step": 1175 |
| }, |
| { |
| "epoch": 6.879765395894428, |
| "grad_norm": 0.3386479051039518, |
| "learning_rate": 1.2248803825619224e-05, |
| "loss": 0.0652, |
| "mean_token_accuracy": 0.9789741039276123, |
| "step": 1176 |
| }, |
| { |
| "epoch": 6.885630498533724, |
| "grad_norm": 0.3734375985346956, |
| "learning_rate": 1.2219996788902734e-05, |
| "loss": 0.0643, |
| "mean_token_accuracy": 0.980387419462204, |
| "step": 1177 |
| }, |
| { |
| "epoch": 6.891495601173021, |
| "grad_norm": 0.40272307561699655, |
| "learning_rate": 1.2191225249648016e-05, |
| "loss": 0.0616, |
| "mean_token_accuracy": 0.9799608364701271, |
| "step": 1178 |
| }, |
| { |
| "epoch": 6.897360703812317, |
| "grad_norm": 0.4925163928492032, |
| "learning_rate": 1.216248931228413e-05, |
| "loss": 0.0707, |
| "mean_token_accuracy": 0.9777872562408447, |
| "step": 1179 |
| }, |
| { |
| "epoch": 6.903225806451613, |
| "grad_norm": 0.3894825168802102, |
| "learning_rate": 1.2133789081110927e-05, |
| "loss": 0.062, |
| "mean_token_accuracy": 0.981035090982914, |
| "step": 1180 |
| }, |
| { |
| "epoch": 6.909090909090909, |
| "grad_norm": 0.5362801208592477, |
| "learning_rate": 1.2105124660298655e-05, |
| "loss": 0.0669, |
| "mean_token_accuracy": 0.9792104065418243, |
| "step": 1181 |
| }, |
| { |
| "epoch": 6.914956011730205, |
| "grad_norm": 0.44854169792906545, |
| "learning_rate": 1.2076496153887587e-05, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9807733446359634, |
| "step": 1182 |
| }, |
| { |
| "epoch": 6.9208211143695015, |
| "grad_norm": 0.3430754024750591, |
| "learning_rate": 1.2047903665787633e-05, |
| "loss": 0.0623, |
| "mean_token_accuracy": 0.9828178733587265, |
| "step": 1183 |
| }, |
| { |
| "epoch": 6.926686217008798, |
| "grad_norm": 0.4263487835060375, |
| "learning_rate": 1.2019347299777981e-05, |
| "loss": 0.0564, |
| "mean_token_accuracy": 0.9828721657395363, |
| "step": 1184 |
| }, |
| { |
| "epoch": 6.932551319648094, |
| "grad_norm": 0.4364783671104784, |
| "learning_rate": 1.199082715950671e-05, |
| "loss": 0.074, |
| "mean_token_accuracy": 0.9775600358843803, |
| "step": 1185 |
| }, |
| { |
| "epoch": 6.93841642228739, |
| "grad_norm": 0.3615151589709061, |
| "learning_rate": 1.1962343348490407e-05, |
| "loss": 0.0591, |
| "mean_token_accuracy": 0.9815037250518799, |
| "step": 1186 |
| }, |
| { |
| "epoch": 6.944281524926686, |
| "grad_norm": 0.34842137870991524, |
| "learning_rate": 1.1933895970113798e-05, |
| "loss": 0.07, |
| "mean_token_accuracy": 0.9812806695699692, |
| "step": 1187 |
| }, |
| { |
| "epoch": 6.9501466275659824, |
| "grad_norm": 0.39779087229671267, |
| "learning_rate": 1.1905485127629387e-05, |
| "loss": 0.0687, |
| "mean_token_accuracy": 0.9787686914205551, |
| "step": 1188 |
| }, |
| { |
| "epoch": 6.956011730205279, |
| "grad_norm": 0.37156810873265006, |
| "learning_rate": 1.1877110924157046e-05, |
| "loss": 0.064, |
| "mean_token_accuracy": 0.9793610125780106, |
| "step": 1189 |
| }, |
| { |
| "epoch": 6.961876832844575, |
| "grad_norm": 0.36891675930420137, |
| "learning_rate": 1.1848773462683684e-05, |
| "loss": 0.0691, |
| "mean_token_accuracy": 0.9793200343847275, |
| "step": 1190 |
| }, |
| { |
| "epoch": 6.967741935483871, |
| "grad_norm": 0.3973752929987383, |
| "learning_rate": 1.1820472846062842e-05, |
| "loss": 0.0612, |
| "mean_token_accuracy": 0.980794683098793, |
| "step": 1191 |
| }, |
| { |
| "epoch": 6.973607038123167, |
| "grad_norm": 0.334569020236037, |
| "learning_rate": 1.1792209177014317e-05, |
| "loss": 0.0626, |
| "mean_token_accuracy": 0.9811923578381538, |
| "step": 1192 |
| }, |
| { |
| "epoch": 6.979472140762463, |
| "grad_norm": 0.349284009378184, |
| "learning_rate": 1.1763982558123823e-05, |
| "loss": 0.0673, |
| "mean_token_accuracy": 0.9803842082619667, |
| "step": 1193 |
| }, |
| { |
| "epoch": 6.9853372434017595, |
| "grad_norm": 0.48509516426421756, |
| "learning_rate": 1.1735793091842583e-05, |
| "loss": 0.0661, |
| "mean_token_accuracy": 0.9790410473942757, |
| "step": 1194 |
| }, |
| { |
| "epoch": 6.991202346041056, |
| "grad_norm": 0.6182624878074343, |
| "learning_rate": 1.1707640880486975e-05, |
| "loss": 0.083, |
| "mean_token_accuracy": 0.9752562269568443, |
| "step": 1195 |
| }, |
| { |
| "epoch": 6.997067448680352, |
| "grad_norm": 0.26860092970951027, |
| "learning_rate": 1.1679526026238155e-05, |
| "loss": 0.0506, |
| "mean_token_accuracy": 0.9840497225522995, |
| "step": 1196 |
| }, |
| { |
| "epoch": 7.0, |
| "grad_norm": 0.26860092970951027, |
| "learning_rate": 1.165144863114169e-05, |
| "loss": 0.0556, |
| "mean_token_accuracy": 0.9838097840547562, |
| "step": 1197 |
| }, |
| { |
| "epoch": 7.005865102639296, |
| "grad_norm": 0.543930531637957, |
| "learning_rate": 1.1623408797107185e-05, |
| "loss": 0.068, |
| "mean_token_accuracy": 0.9765876084566116, |
| "step": 1198 |
| }, |
| { |
| "epoch": 7.011730205278592, |
| "grad_norm": 0.3599707466085984, |
| "learning_rate": 1.1595406625907914e-05, |
| "loss": 0.0596, |
| "mean_token_accuracy": 0.9841873943805695, |
| "step": 1199 |
| }, |
| { |
| "epoch": 7.0175953079178885, |
| "grad_norm": 0.7986070629261153, |
| "learning_rate": 1.1567442219180446e-05, |
| "loss": 0.0552, |
| "mean_token_accuracy": 0.9836561754345894, |
| "step": 1200 |
| }, |
| { |
| "epoch": 7.023460410557185, |
| "grad_norm": 0.2858257280488765, |
| "learning_rate": 1.153951567842429e-05, |
| "loss": 0.0511, |
| "mean_token_accuracy": 0.9851352721452713, |
| "step": 1201 |
| }, |
| { |
| "epoch": 7.029325513196481, |
| "grad_norm": 0.43882380033807117, |
| "learning_rate": 1.1511627105001501e-05, |
| "loss": 0.062, |
| "mean_token_accuracy": 0.9812534153461456, |
| "step": 1202 |
| }, |
| { |
| "epoch": 7.035190615835777, |
| "grad_norm": 0.32376660322769785, |
| "learning_rate": 1.1483776600136344e-05, |
| "loss": 0.0642, |
| "mean_token_accuracy": 0.9787701517343521, |
| "step": 1203 |
| }, |
| { |
| "epoch": 7.041055718475073, |
| "grad_norm": 0.2845445707837671, |
| "learning_rate": 1.1455964264914906e-05, |
| "loss": 0.0529, |
| "mean_token_accuracy": 0.9829073548316956, |
| "step": 1204 |
| }, |
| { |
| "epoch": 7.0469208211143695, |
| "grad_norm": 0.3581481876523457, |
| "learning_rate": 1.142819020028472e-05, |
| "loss": 0.0659, |
| "mean_token_accuracy": 0.9776208847761154, |
| "step": 1205 |
| }, |
| { |
| "epoch": 7.052785923753666, |
| "grad_norm": 0.31359656987227214, |
| "learning_rate": 1.140045450705443e-05, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9799343273043633, |
| "step": 1206 |
| }, |
| { |
| "epoch": 7.058651026392962, |
| "grad_norm": 0.34541167440285503, |
| "learning_rate": 1.13727572858934e-05, |
| "loss": 0.055, |
| "mean_token_accuracy": 0.9838607162237167, |
| "step": 1207 |
| }, |
| { |
| "epoch": 7.064516129032258, |
| "grad_norm": 0.2656366030140541, |
| "learning_rate": 1.1345098637331356e-05, |
| "loss": 0.0515, |
| "mean_token_accuracy": 0.9840966165065765, |
| "step": 1208 |
| }, |
| { |
| "epoch": 7.070381231671554, |
| "grad_norm": 0.3732026940010526, |
| "learning_rate": 1.1317478661758022e-05, |
| "loss": 0.0738, |
| "mean_token_accuracy": 0.9770562797784805, |
| "step": 1209 |
| }, |
| { |
| "epoch": 7.07624633431085, |
| "grad_norm": 0.3620841580037238, |
| "learning_rate": 1.1289897459422756e-05, |
| "loss": 0.053, |
| "mean_token_accuracy": 0.9833652973175049, |
| "step": 1210 |
| }, |
| { |
| "epoch": 7.0821114369501466, |
| "grad_norm": 0.3890273971843419, |
| "learning_rate": 1.126235513043418e-05, |
| "loss": 0.064, |
| "mean_token_accuracy": 0.9798462018370628, |
| "step": 1211 |
| }, |
| { |
| "epoch": 7.087976539589443, |
| "grad_norm": 0.40304516205749985, |
| "learning_rate": 1.1234851774759828e-05, |
| "loss": 0.0535, |
| "mean_token_accuracy": 0.9842343777418137, |
| "step": 1212 |
| }, |
| { |
| "epoch": 7.093841642228739, |
| "grad_norm": 0.2898298813640276, |
| "learning_rate": 1.1207387492225772e-05, |
| "loss": 0.0577, |
| "mean_token_accuracy": 0.9817237481474876, |
| "step": 1213 |
| }, |
| { |
| "epoch": 7.099706744868035, |
| "grad_norm": 0.346760418469883, |
| "learning_rate": 1.1179962382516268e-05, |
| "loss": 0.0677, |
| "mean_token_accuracy": 0.9793826043605804, |
| "step": 1214 |
| }, |
| { |
| "epoch": 7.105571847507331, |
| "grad_norm": 0.32802116910426204, |
| "learning_rate": 1.1152576545173388e-05, |
| "loss": 0.0571, |
| "mean_token_accuracy": 0.9839992597699165, |
| "step": 1215 |
| }, |
| { |
| "epoch": 7.1114369501466275, |
| "grad_norm": 0.33448701048483737, |
| "learning_rate": 1.1125230079596654e-05, |
| "loss": 0.0515, |
| "mean_token_accuracy": 0.9829333648085594, |
| "step": 1216 |
| }, |
| { |
| "epoch": 7.117302052785924, |
| "grad_norm": 0.47043879663050175, |
| "learning_rate": 1.10979230850427e-05, |
| "loss": 0.0567, |
| "mean_token_accuracy": 0.9834040552377701, |
| "step": 1217 |
| }, |
| { |
| "epoch": 7.12316715542522, |
| "grad_norm": 0.3169648164702154, |
| "learning_rate": 1.1070655660624876e-05, |
| "loss": 0.0677, |
| "mean_token_accuracy": 0.9791783094406128, |
| "step": 1218 |
| }, |
| { |
| "epoch": 7.129032258064516, |
| "grad_norm": 0.42639076528279224, |
| "learning_rate": 1.1043427905312933e-05, |
| "loss": 0.0678, |
| "mean_token_accuracy": 0.9799103289842606, |
| "step": 1219 |
| }, |
| { |
| "epoch": 7.134897360703812, |
| "grad_norm": 0.41740113237596277, |
| "learning_rate": 1.1016239917932618e-05, |
| "loss": 0.0577, |
| "mean_token_accuracy": 0.9818514063954353, |
| "step": 1220 |
| }, |
| { |
| "epoch": 7.140762463343108, |
| "grad_norm": 0.2721497498601549, |
| "learning_rate": 1.098909179716535e-05, |
| "loss": 0.063, |
| "mean_token_accuracy": 0.979342058300972, |
| "step": 1221 |
| }, |
| { |
| "epoch": 7.146627565982405, |
| "grad_norm": 0.37368651106908646, |
| "learning_rate": 1.096198364154784e-05, |
| "loss": 0.0566, |
| "mean_token_accuracy": 0.9820699691772461, |
| "step": 1222 |
| }, |
| { |
| "epoch": 7.152492668621701, |
| "grad_norm": 0.46464039008643165, |
| "learning_rate": 1.0934915549471747e-05, |
| "loss": 0.0549, |
| "mean_token_accuracy": 0.9828799217939377, |
| "step": 1223 |
| }, |
| { |
| "epoch": 7.158357771260997, |
| "grad_norm": 0.24275403590533381, |
| "learning_rate": 1.0907887619183308e-05, |
| "loss": 0.0531, |
| "mean_token_accuracy": 0.9846633151173592, |
| "step": 1224 |
| }, |
| { |
| "epoch": 7.164222873900293, |
| "grad_norm": 0.24404744608544118, |
| "learning_rate": 1.0880899948783002e-05, |
| "loss": 0.0593, |
| "mean_token_accuracy": 0.9814930409193039, |
| "step": 1225 |
| }, |
| { |
| "epoch": 7.170087976539589, |
| "grad_norm": 0.4054052415960616, |
| "learning_rate": 1.0853952636225165e-05, |
| "loss": 0.0665, |
| "mean_token_accuracy": 0.9808385893702507, |
| "step": 1226 |
| }, |
| { |
| "epoch": 7.1759530791788855, |
| "grad_norm": 0.4408475594615136, |
| "learning_rate": 1.0827045779317662e-05, |
| "loss": 0.0611, |
| "mean_token_accuracy": 0.9818901941180229, |
| "step": 1227 |
| }, |
| { |
| "epoch": 7.181818181818182, |
| "grad_norm": 0.3809276180859335, |
| "learning_rate": 1.080017947572152e-05, |
| "loss": 0.0563, |
| "mean_token_accuracy": 0.9834899082779884, |
| "step": 1228 |
| }, |
| { |
| "epoch": 7.187683284457478, |
| "grad_norm": 0.23664871794200695, |
| "learning_rate": 1.0773353822950563e-05, |
| "loss": 0.0651, |
| "mean_token_accuracy": 0.9821924492716789, |
| "step": 1229 |
| }, |
| { |
| "epoch": 7.193548387096774, |
| "grad_norm": 0.39673119822118297, |
| "learning_rate": 1.074656891837108e-05, |
| "loss": 0.0547, |
| "mean_token_accuracy": 0.9831197336316109, |
| "step": 1230 |
| }, |
| { |
| "epoch": 7.19941348973607, |
| "grad_norm": 0.23952062843645364, |
| "learning_rate": 1.0719824859201457e-05, |
| "loss": 0.0595, |
| "mean_token_accuracy": 0.9816852286458015, |
| "step": 1231 |
| }, |
| { |
| "epoch": 7.205278592375366, |
| "grad_norm": 0.4291529890704876, |
| "learning_rate": 1.0693121742511828e-05, |
| "loss": 0.0699, |
| "mean_token_accuracy": 0.9776555746793747, |
| "step": 1232 |
| }, |
| { |
| "epoch": 7.211143695014663, |
| "grad_norm": 0.3259261714222968, |
| "learning_rate": 1.0666459665223718e-05, |
| "loss": 0.0615, |
| "mean_token_accuracy": 0.9814717844128609, |
| "step": 1233 |
| }, |
| { |
| "epoch": 7.217008797653959, |
| "grad_norm": 0.3219563587981844, |
| "learning_rate": 1.0639838724109708e-05, |
| "loss": 0.0606, |
| "mean_token_accuracy": 0.9811657071113586, |
| "step": 1234 |
| }, |
| { |
| "epoch": 7.222873900293255, |
| "grad_norm": 0.2887441757620735, |
| "learning_rate": 1.0613259015793056e-05, |
| "loss": 0.0526, |
| "mean_token_accuracy": 0.9813622236251831, |
| "step": 1235 |
| }, |
| { |
| "epoch": 7.228739002932551, |
| "grad_norm": 0.5016128124855813, |
| "learning_rate": 1.0586720636747368e-05, |
| "loss": 0.0614, |
| "mean_token_accuracy": 0.980540856719017, |
| "step": 1236 |
| }, |
| { |
| "epoch": 7.234604105571847, |
| "grad_norm": 0.32704366790322426, |
| "learning_rate": 1.0560223683296244e-05, |
| "loss": 0.0615, |
| "mean_token_accuracy": 0.979736678302288, |
| "step": 1237 |
| }, |
| { |
| "epoch": 7.2404692082111435, |
| "grad_norm": 0.24588497441247914, |
| "learning_rate": 1.0533768251612924e-05, |
| "loss": 0.0606, |
| "mean_token_accuracy": 0.9808222204446793, |
| "step": 1238 |
| }, |
| { |
| "epoch": 7.24633431085044, |
| "grad_norm": 0.3175117728124407, |
| "learning_rate": 1.0507354437719938e-05, |
| "loss": 0.0527, |
| "mean_token_accuracy": 0.9847884327173233, |
| "step": 1239 |
| }, |
| { |
| "epoch": 7.252199413489736, |
| "grad_norm": 0.3383051888288448, |
| "learning_rate": 1.0480982337488768e-05, |
| "loss": 0.057, |
| "mean_token_accuracy": 0.9824387729167938, |
| "step": 1240 |
| }, |
| { |
| "epoch": 7.258064516129032, |
| "grad_norm": 0.2760561608413442, |
| "learning_rate": 1.0454652046639486e-05, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9802872315049171, |
| "step": 1241 |
| }, |
| { |
| "epoch": 7.263929618768328, |
| "grad_norm": 0.34101044843139294, |
| "learning_rate": 1.0428363660740407e-05, |
| "loss": 0.0621, |
| "mean_token_accuracy": 0.9803706407546997, |
| "step": 1242 |
| }, |
| { |
| "epoch": 7.269794721407624, |
| "grad_norm": 0.3854063802655829, |
| "learning_rate": 1.0402117275207757e-05, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.9794178232550621, |
| "step": 1243 |
| }, |
| { |
| "epoch": 7.275659824046921, |
| "grad_norm": 0.3362556785057891, |
| "learning_rate": 1.0375912985305319e-05, |
| "loss": 0.059, |
| "mean_token_accuracy": 0.9811040312051773, |
| "step": 1244 |
| }, |
| { |
| "epoch": 7.281524926686217, |
| "grad_norm": 0.24692741649753694, |
| "learning_rate": 1.0349750886144077e-05, |
| "loss": 0.0587, |
| "mean_token_accuracy": 0.980044037103653, |
| "step": 1245 |
| }, |
| { |
| "epoch": 7.287390029325513, |
| "grad_norm": 0.2366994852389697, |
| "learning_rate": 1.0323631072681888e-05, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.982071615755558, |
| "step": 1246 |
| }, |
| { |
| "epoch": 7.293255131964809, |
| "grad_norm": 0.31542740583531625, |
| "learning_rate": 1.0297553639723123e-05, |
| "loss": 0.0533, |
| "mean_token_accuracy": 0.9839030206203461, |
| "step": 1247 |
| }, |
| { |
| "epoch": 7.299120234604105, |
| "grad_norm": 0.3706887349147297, |
| "learning_rate": 1.027151868191834e-05, |
| "loss": 0.0634, |
| "mean_token_accuracy": 0.9778928458690643, |
| "step": 1248 |
| }, |
| { |
| "epoch": 7.3049853372434015, |
| "grad_norm": 0.4809721901376831, |
| "learning_rate": 1.0245526293763908e-05, |
| "loss": 0.0692, |
| "mean_token_accuracy": 0.9787572473287582, |
| "step": 1249 |
| }, |
| { |
| "epoch": 7.310850439882698, |
| "grad_norm": 0.31650509706650065, |
| "learning_rate": 1.0219576569601707e-05, |
| "loss": 0.0714, |
| "mean_token_accuracy": 0.9798088297247887, |
| "step": 1250 |
| }, |
| { |
| "epoch": 7.316715542521994, |
| "grad_norm": 0.5798554299170097, |
| "learning_rate": 1.0193669603618757e-05, |
| "loss": 0.065, |
| "mean_token_accuracy": 0.9797441512346268, |
| "step": 1251 |
| }, |
| { |
| "epoch": 7.32258064516129, |
| "grad_norm": 0.23068366144962413, |
| "learning_rate": 1.0167805489846873e-05, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.9825217947363853, |
| "step": 1252 |
| }, |
| { |
| "epoch": 7.328445747800586, |
| "grad_norm": 0.38274632853117607, |
| "learning_rate": 1.0141984322162353e-05, |
| "loss": 0.0563, |
| "mean_token_accuracy": 0.98308215290308, |
| "step": 1253 |
| }, |
| { |
| "epoch": 7.334310850439882, |
| "grad_norm": 0.2780363898982002, |
| "learning_rate": 1.0116206194285598e-05, |
| "loss": 0.0612, |
| "mean_token_accuracy": 0.9808923453092575, |
| "step": 1254 |
| }, |
| { |
| "epoch": 7.340175953079179, |
| "grad_norm": 0.43432483337721645, |
| "learning_rate": 1.0090471199780812e-05, |
| "loss": 0.0704, |
| "mean_token_accuracy": 0.9796313270926476, |
| "step": 1255 |
| }, |
| { |
| "epoch": 7.346041055718475, |
| "grad_norm": 0.44244848233473943, |
| "learning_rate": 1.0064779432055616e-05, |
| "loss": 0.0593, |
| "mean_token_accuracy": 0.9802607670426369, |
| "step": 1256 |
| }, |
| { |
| "epoch": 7.351906158357771, |
| "grad_norm": 0.25207004596265176, |
| "learning_rate": 1.0039130984360761e-05, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9812619239091873, |
| "step": 1257 |
| }, |
| { |
| "epoch": 7.357771260997067, |
| "grad_norm": 0.2515940949933918, |
| "learning_rate": 1.0013525949789745e-05, |
| "loss": 0.0716, |
| "mean_token_accuracy": 0.9782749563455582, |
| "step": 1258 |
| }, |
| { |
| "epoch": 7.363636363636363, |
| "grad_norm": 0.46435768646393183, |
| "learning_rate": 9.987964421278512e-06, |
| "loss": 0.0551, |
| "mean_token_accuracy": 0.9833088368177414, |
| "step": 1259 |
| }, |
| { |
| "epoch": 7.3695014662756595, |
| "grad_norm": 0.26816012997514577, |
| "learning_rate": 9.962446491605084e-06, |
| "loss": 0.0638, |
| "mean_token_accuracy": 0.9795294478535652, |
| "step": 1260 |
| }, |
| { |
| "epoch": 7.375366568914956, |
| "grad_norm": 0.3559008264487101, |
| "learning_rate": 9.936972253389235e-06, |
| "loss": 0.0581, |
| "mean_token_accuracy": 0.9806554466485977, |
| "step": 1261 |
| }, |
| { |
| "epoch": 7.381231671554252, |
| "grad_norm": 0.39486851602267986, |
| "learning_rate": 9.911541799092162e-06, |
| "loss": 0.0659, |
| "mean_token_accuracy": 0.9786085188388824, |
| "step": 1262 |
| }, |
| { |
| "epoch": 7.387096774193548, |
| "grad_norm": 0.335786358952341, |
| "learning_rate": 9.88615522101615e-06, |
| "loss": 0.0565, |
| "mean_token_accuracy": 0.9813254401087761, |
| "step": 1263 |
| }, |
| { |
| "epoch": 7.392961876832844, |
| "grad_norm": 0.2878142458194373, |
| "learning_rate": 9.860812611304225e-06, |
| "loss": 0.0571, |
| "mean_token_accuracy": 0.9820192754268646, |
| "step": 1264 |
| }, |
| { |
| "epoch": 7.39882697947214, |
| "grad_norm": 0.3408757371760065, |
| "learning_rate": 9.835514061939822e-06, |
| "loss": 0.0545, |
| "mean_token_accuracy": 0.9838089644908905, |
| "step": 1265 |
| }, |
| { |
| "epoch": 7.404692082111437, |
| "grad_norm": 0.24216134788014795, |
| "learning_rate": 9.810259664746454e-06, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9823042750358582, |
| "step": 1266 |
| }, |
| { |
| "epoch": 7.410557184750733, |
| "grad_norm": 0.43774220429405847, |
| "learning_rate": 9.785049511387383e-06, |
| "loss": 0.0569, |
| "mean_token_accuracy": 0.9796285480260849, |
| "step": 1267 |
| }, |
| { |
| "epoch": 7.416422287390029, |
| "grad_norm": 0.3108898649235883, |
| "learning_rate": 9.759883693365287e-06, |
| "loss": 0.067, |
| "mean_token_accuracy": 0.9790755361318588, |
| "step": 1268 |
| }, |
| { |
| "epoch": 7.422287390029325, |
| "grad_norm": 0.45200323631058287, |
| "learning_rate": 9.734762302021923e-06, |
| "loss": 0.05, |
| "mean_token_accuracy": 0.9834395200014114, |
| "step": 1269 |
| }, |
| { |
| "epoch": 7.428152492668621, |
| "grad_norm": 0.3597198573653463, |
| "learning_rate": 9.709685428537794e-06, |
| "loss": 0.0556, |
| "mean_token_accuracy": 0.9842453375458717, |
| "step": 1270 |
| }, |
| { |
| "epoch": 7.4340175953079175, |
| "grad_norm": 0.3091752948831815, |
| "learning_rate": 9.684653163931823e-06, |
| "loss": 0.0634, |
| "mean_token_accuracy": 0.9818849861621857, |
| "step": 1271 |
| }, |
| { |
| "epoch": 7.439882697947214, |
| "grad_norm": 0.28491665560399426, |
| "learning_rate": 9.659665599061019e-06, |
| "loss": 0.0646, |
| "mean_token_accuracy": 0.9791956692934036, |
| "step": 1272 |
| }, |
| { |
| "epoch": 7.44574780058651, |
| "grad_norm": 0.3585720040589971, |
| "learning_rate": 9.634722824620154e-06, |
| "loss": 0.0546, |
| "mean_token_accuracy": 0.9820611029863358, |
| "step": 1273 |
| }, |
| { |
| "epoch": 7.451612903225806, |
| "grad_norm": 0.22510237073905628, |
| "learning_rate": 9.609824931141423e-06, |
| "loss": 0.0542, |
| "mean_token_accuracy": 0.9816134124994278, |
| "step": 1274 |
| }, |
| { |
| "epoch": 7.457478005865102, |
| "grad_norm": 0.2976725521857549, |
| "learning_rate": 9.584972008994123e-06, |
| "loss": 0.0608, |
| "mean_token_accuracy": 0.9823539853096008, |
| "step": 1275 |
| }, |
| { |
| "epoch": 7.463343108504398, |
| "grad_norm": 0.381204550554821, |
| "learning_rate": 9.560164148384328e-06, |
| "loss": 0.0706, |
| "mean_token_accuracy": 0.9788034185767174, |
| "step": 1276 |
| }, |
| { |
| "epoch": 7.469208211143695, |
| "grad_norm": 0.3902598224526612, |
| "learning_rate": 9.53540143935455e-06, |
| "loss": 0.0625, |
| "mean_token_accuracy": 0.9800604283809662, |
| "step": 1277 |
| }, |
| { |
| "epoch": 7.475073313782991, |
| "grad_norm": 0.32985512212133755, |
| "learning_rate": 9.510683971783425e-06, |
| "loss": 0.0772, |
| "mean_token_accuracy": 0.9780596867203712, |
| "step": 1278 |
| }, |
| { |
| "epoch": 7.480938416422287, |
| "grad_norm": 0.30612003390693643, |
| "learning_rate": 9.486011835385372e-06, |
| "loss": 0.0444, |
| "mean_token_accuracy": 0.9867977499961853, |
| "step": 1279 |
| }, |
| { |
| "epoch": 7.486803519061583, |
| "grad_norm": 0.23145050100573172, |
| "learning_rate": 9.461385119710282e-06, |
| "loss": 0.0646, |
| "mean_token_accuracy": 0.9781039953231812, |
| "step": 1280 |
| }, |
| { |
| "epoch": 7.492668621700879, |
| "grad_norm": 0.3258792257767987, |
| "learning_rate": 9.436803914143189e-06, |
| "loss": 0.0682, |
| "mean_token_accuracy": 0.9785692542791367, |
| "step": 1281 |
| }, |
| { |
| "epoch": 7.4985337243401755, |
| "grad_norm": 0.3648664332592761, |
| "learning_rate": 9.41226830790394e-06, |
| "loss": 0.0572, |
| "mean_token_accuracy": 0.9803744629025459, |
| "step": 1282 |
| }, |
| { |
| "epoch": 7.504398826979472, |
| "grad_norm": 0.3949674277365223, |
| "learning_rate": 9.387778390046881e-06, |
| "loss": 0.0601, |
| "mean_token_accuracy": 0.9812920317053795, |
| "step": 1283 |
| }, |
| { |
| "epoch": 7.510263929618768, |
| "grad_norm": 0.41069422084481105, |
| "learning_rate": 9.363334249460519e-06, |
| "loss": 0.06, |
| "mean_token_accuracy": 0.9833412170410156, |
| "step": 1284 |
| }, |
| { |
| "epoch": 7.516129032258064, |
| "grad_norm": 0.3014214279503322, |
| "learning_rate": 9.338935974867213e-06, |
| "loss": 0.0626, |
| "mean_token_accuracy": 0.9807936921715736, |
| "step": 1285 |
| }, |
| { |
| "epoch": 7.52199413489736, |
| "grad_norm": 0.33124061212021144, |
| "learning_rate": 9.314583654822844e-06, |
| "loss": 0.062, |
| "mean_token_accuracy": 0.9802020415663719, |
| "step": 1286 |
| }, |
| { |
| "epoch": 7.527859237536656, |
| "grad_norm": 0.29393245792581324, |
| "learning_rate": 9.290277377716503e-06, |
| "loss": 0.0653, |
| "mean_token_accuracy": 0.9785585701465607, |
| "step": 1287 |
| }, |
| { |
| "epoch": 7.533724340175953, |
| "grad_norm": 0.27560201878621987, |
| "learning_rate": 9.266017231770155e-06, |
| "loss": 0.0534, |
| "mean_token_accuracy": 0.9817678108811378, |
| "step": 1288 |
| }, |
| { |
| "epoch": 7.539589442815249, |
| "grad_norm": 0.4356751897841947, |
| "learning_rate": 9.241803305038333e-06, |
| "loss": 0.0621, |
| "mean_token_accuracy": 0.9805284291505814, |
| "step": 1289 |
| }, |
| { |
| "epoch": 7.545454545454545, |
| "grad_norm": 0.3108842343684137, |
| "learning_rate": 9.217635685407813e-06, |
| "loss": 0.0592, |
| "mean_token_accuracy": 0.9813688769936562, |
| "step": 1290 |
| }, |
| { |
| "epoch": 7.551319648093841, |
| "grad_norm": 0.23658671346849064, |
| "learning_rate": 9.19351446059729e-06, |
| "loss": 0.0518, |
| "mean_token_accuracy": 0.9847207292914391, |
| "step": 1291 |
| }, |
| { |
| "epoch": 7.557184750733137, |
| "grad_norm": 0.31455427308213524, |
| "learning_rate": 9.16943971815708e-06, |
| "loss": 0.0584, |
| "mean_token_accuracy": 0.9820144027471542, |
| "step": 1292 |
| }, |
| { |
| "epoch": 7.563049853372434, |
| "grad_norm": 0.31471404836881833, |
| "learning_rate": 9.145411545468756e-06, |
| "loss": 0.0522, |
| "mean_token_accuracy": 0.981374055147171, |
| "step": 1293 |
| }, |
| { |
| "epoch": 7.568914956011731, |
| "grad_norm": 0.49747244115547473, |
| "learning_rate": 9.121430029744893e-06, |
| "loss": 0.0573, |
| "mean_token_accuracy": 0.982080303132534, |
| "step": 1294 |
| }, |
| { |
| "epoch": 7.574780058651027, |
| "grad_norm": 0.4291736011020313, |
| "learning_rate": 9.097495258028703e-06, |
| "loss": 0.0622, |
| "mean_token_accuracy": 0.9802661165595055, |
| "step": 1295 |
| }, |
| { |
| "epoch": 7.580645161290323, |
| "grad_norm": 0.3477579573197191, |
| "learning_rate": 9.073607317193742e-06, |
| "loss": 0.0541, |
| "mean_token_accuracy": 0.9810939654707909, |
| "step": 1296 |
| }, |
| { |
| "epoch": 7.586510263929619, |
| "grad_norm": 0.24442389845319185, |
| "learning_rate": 9.049766293943589e-06, |
| "loss": 0.0638, |
| "mean_token_accuracy": 0.980124719440937, |
| "step": 1297 |
| }, |
| { |
| "epoch": 7.592375366568915, |
| "grad_norm": 0.45274589019511546, |
| "learning_rate": 9.025972274811527e-06, |
| "loss": 0.0575, |
| "mean_token_accuracy": 0.9824511334300041, |
| "step": 1298 |
| }, |
| { |
| "epoch": 7.5982404692082115, |
| "grad_norm": 0.38649873217195, |
| "learning_rate": 9.002225346160238e-06, |
| "loss": 0.0617, |
| "mean_token_accuracy": 0.9798657670617104, |
| "step": 1299 |
| }, |
| { |
| "epoch": 7.604105571847508, |
| "grad_norm": 0.37509806099205384, |
| "learning_rate": 8.97852559418148e-06, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9814462289214134, |
| "step": 1300 |
| }, |
| { |
| "epoch": 7.609970674486804, |
| "grad_norm": 0.2609647266083045, |
| "learning_rate": 8.954873104895787e-06, |
| "loss": 0.0545, |
| "mean_token_accuracy": 0.9840743094682693, |
| "step": 1301 |
| }, |
| { |
| "epoch": 7.6158357771261, |
| "grad_norm": 0.2692253345151723, |
| "learning_rate": 8.931267964152132e-06, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9792167991399765, |
| "step": 1302 |
| }, |
| { |
| "epoch": 7.621700879765396, |
| "grad_norm": 0.29179020681580975, |
| "learning_rate": 8.907710257627651e-06, |
| "loss": 0.0564, |
| "mean_token_accuracy": 0.9830718636512756, |
| "step": 1303 |
| }, |
| { |
| "epoch": 7.627565982404692, |
| "grad_norm": 0.25775769089056455, |
| "learning_rate": 8.884200070827303e-06, |
| "loss": 0.0563, |
| "mean_token_accuracy": 0.9800078570842743, |
| "step": 1304 |
| }, |
| { |
| "epoch": 7.633431085043989, |
| "grad_norm": 0.4126676449382726, |
| "learning_rate": 8.86073748908357e-06, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9821161031723022, |
| "step": 1305 |
| }, |
| { |
| "epoch": 7.639296187683285, |
| "grad_norm": 0.29909785778360326, |
| "learning_rate": 8.837322597556146e-06, |
| "loss": 0.059, |
| "mean_token_accuracy": 0.9825484231114388, |
| "step": 1306 |
| }, |
| { |
| "epoch": 7.645161290322581, |
| "grad_norm": 0.41894554694492725, |
| "learning_rate": 8.813955481231633e-06, |
| "loss": 0.0706, |
| "mean_token_accuracy": 0.9785730615258217, |
| "step": 1307 |
| }, |
| { |
| "epoch": 7.651026392961877, |
| "grad_norm": 0.2968772340024343, |
| "learning_rate": 8.790636224923221e-06, |
| "loss": 0.0602, |
| "mean_token_accuracy": 0.9801525101065636, |
| "step": 1308 |
| }, |
| { |
| "epoch": 7.656891495601173, |
| "grad_norm": 0.3409136197791452, |
| "learning_rate": 8.767364913270399e-06, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9808881357312202, |
| "step": 1309 |
| }, |
| { |
| "epoch": 7.6627565982404695, |
| "grad_norm": 0.243416715563901, |
| "learning_rate": 8.744141630738624e-06, |
| "loss": 0.0629, |
| "mean_token_accuracy": 0.9808500409126282, |
| "step": 1310 |
| }, |
| { |
| "epoch": 7.668621700879766, |
| "grad_norm": 0.33758735751589425, |
| "learning_rate": 8.720966461619038e-06, |
| "loss": 0.0707, |
| "mean_token_accuracy": 0.9802355766296387, |
| "step": 1311 |
| }, |
| { |
| "epoch": 7.674486803519062, |
| "grad_norm": 0.4117699771693344, |
| "learning_rate": 8.69783949002814e-06, |
| "loss": 0.0572, |
| "mean_token_accuracy": 0.9822903126478195, |
| "step": 1312 |
| }, |
| { |
| "epoch": 7.680351906158358, |
| "grad_norm": 0.331202089534723, |
| "learning_rate": 8.6747607999075e-06, |
| "loss": 0.0482, |
| "mean_token_accuracy": 0.984705850481987, |
| "step": 1313 |
| }, |
| { |
| "epoch": 7.686217008797654, |
| "grad_norm": 0.2749224689840326, |
| "learning_rate": 8.651730475023435e-06, |
| "loss": 0.0655, |
| "mean_token_accuracy": 0.9800895005464554, |
| "step": 1314 |
| }, |
| { |
| "epoch": 7.69208211143695, |
| "grad_norm": 0.37140200419744357, |
| "learning_rate": 8.628748598966739e-06, |
| "loss": 0.0567, |
| "mean_token_accuracy": 0.9798331558704376, |
| "step": 1315 |
| }, |
| { |
| "epoch": 7.697947214076247, |
| "grad_norm": 0.3956036602768011, |
| "learning_rate": 8.605815255152323e-06, |
| "loss": 0.0665, |
| "mean_token_accuracy": 0.9770996049046516, |
| "step": 1316 |
| }, |
| { |
| "epoch": 7.703812316715543, |
| "grad_norm": 0.3731369409155563, |
| "learning_rate": 8.582930526818973e-06, |
| "loss": 0.0667, |
| "mean_token_accuracy": 0.979367084801197, |
| "step": 1317 |
| }, |
| { |
| "epoch": 7.709677419354839, |
| "grad_norm": 0.35123845927188907, |
| "learning_rate": 8.560094497029008e-06, |
| "loss": 0.061, |
| "mean_token_accuracy": 0.9824322983622551, |
| "step": 1318 |
| }, |
| { |
| "epoch": 7.715542521994135, |
| "grad_norm": 0.3332715311648278, |
| "learning_rate": 8.537307248667992e-06, |
| "loss": 0.0605, |
| "mean_token_accuracy": 0.9805798158049583, |
| "step": 1319 |
| }, |
| { |
| "epoch": 7.721407624633431, |
| "grad_norm": 0.2682497870558032, |
| "learning_rate": 8.514568864444432e-06, |
| "loss": 0.0667, |
| "mean_token_accuracy": 0.9799603000283241, |
| "step": 1320 |
| }, |
| { |
| "epoch": 7.7272727272727275, |
| "grad_norm": 0.26843962718932374, |
| "learning_rate": 8.491879426889483e-06, |
| "loss": 0.0555, |
| "mean_token_accuracy": 0.9824989885091782, |
| "step": 1321 |
| }, |
| { |
| "epoch": 7.733137829912024, |
| "grad_norm": 0.3124980756288478, |
| "learning_rate": 8.469239018356636e-06, |
| "loss": 0.0645, |
| "mean_token_accuracy": 0.9792848080396652, |
| "step": 1322 |
| }, |
| { |
| "epoch": 7.73900293255132, |
| "grad_norm": 0.2547941571233965, |
| "learning_rate": 8.446647721021435e-06, |
| "loss": 0.0705, |
| "mean_token_accuracy": 0.9791503623127937, |
| "step": 1323 |
| }, |
| { |
| "epoch": 7.744868035190616, |
| "grad_norm": 0.2767295357262834, |
| "learning_rate": 8.424105616881161e-06, |
| "loss": 0.0598, |
| "mean_token_accuracy": 0.9829093441367149, |
| "step": 1324 |
| }, |
| { |
| "epoch": 7.750733137829912, |
| "grad_norm": 0.4218056274326058, |
| "learning_rate": 8.40161278775455e-06, |
| "loss": 0.0611, |
| "mean_token_accuracy": 0.9812097251415253, |
| "step": 1325 |
| }, |
| { |
| "epoch": 7.756598240469208, |
| "grad_norm": 0.44385073200436737, |
| "learning_rate": 8.379169315281485e-06, |
| "loss": 0.0626, |
| "mean_token_accuracy": 0.9803273901343346, |
| "step": 1326 |
| }, |
| { |
| "epoch": 7.762463343108505, |
| "grad_norm": 0.23419463894081147, |
| "learning_rate": 8.356775280922708e-06, |
| "loss": 0.0663, |
| "mean_token_accuracy": 0.9805652052164078, |
| "step": 1327 |
| }, |
| { |
| "epoch": 7.768328445747801, |
| "grad_norm": 0.4823100451315824, |
| "learning_rate": 8.334430765959522e-06, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.9788806363940239, |
| "step": 1328 |
| }, |
| { |
| "epoch": 7.774193548387097, |
| "grad_norm": 0.3331813586088315, |
| "learning_rate": 8.312135851493494e-06, |
| "loss": 0.068, |
| "mean_token_accuracy": 0.9783801510930061, |
| "step": 1329 |
| }, |
| { |
| "epoch": 7.780058651026393, |
| "grad_norm": 0.37329187672139424, |
| "learning_rate": 8.28989061844615e-06, |
| "loss": 0.0512, |
| "mean_token_accuracy": 0.9843535274267197, |
| "step": 1330 |
| }, |
| { |
| "epoch": 7.785923753665689, |
| "grad_norm": 0.35298920655862964, |
| "learning_rate": 8.267695147558705e-06, |
| "loss": 0.0666, |
| "mean_token_accuracy": 0.9796379655599594, |
| "step": 1331 |
| }, |
| { |
| "epoch": 7.7917888563049855, |
| "grad_norm": 0.3039385846017442, |
| "learning_rate": 8.245549519391758e-06, |
| "loss": 0.0658, |
| "mean_token_accuracy": 0.9795048087835312, |
| "step": 1332 |
| }, |
| { |
| "epoch": 7.797653958944282, |
| "grad_norm": 0.2917560128374259, |
| "learning_rate": 8.22345381432499e-06, |
| "loss": 0.0619, |
| "mean_token_accuracy": 0.9815476760268211, |
| "step": 1333 |
| }, |
| { |
| "epoch": 7.803519061583578, |
| "grad_norm": 0.2569382185033971, |
| "learning_rate": 8.201408112556893e-06, |
| "loss": 0.0583, |
| "mean_token_accuracy": 0.9816262051463127, |
| "step": 1334 |
| }, |
| { |
| "epoch": 7.809384164222874, |
| "grad_norm": 0.2582699795899447, |
| "learning_rate": 8.179412494104457e-06, |
| "loss": 0.0604, |
| "mean_token_accuracy": 0.9799763336777687, |
| "step": 1335 |
| }, |
| { |
| "epoch": 7.81524926686217, |
| "grad_norm": 0.33387844068648576, |
| "learning_rate": 8.15746703880289e-06, |
| "loss": 0.0593, |
| "mean_token_accuracy": 0.9802704155445099, |
| "step": 1336 |
| }, |
| { |
| "epoch": 7.821114369501466, |
| "grad_norm": 0.2281458888766081, |
| "learning_rate": 8.135571826305339e-06, |
| "loss": 0.0534, |
| "mean_token_accuracy": 0.9816608652472496, |
| "step": 1337 |
| }, |
| { |
| "epoch": 7.826979472140763, |
| "grad_norm": 0.2814723881376163, |
| "learning_rate": 8.113726936082576e-06, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.9795441180467606, |
| "step": 1338 |
| }, |
| { |
| "epoch": 7.832844574780059, |
| "grad_norm": 0.3449545305260099, |
| "learning_rate": 8.091932447422737e-06, |
| "loss": 0.0622, |
| "mean_token_accuracy": 0.9795658588409424, |
| "step": 1339 |
| }, |
| { |
| "epoch": 7.838709677419355, |
| "grad_norm": 0.25471326027068014, |
| "learning_rate": 8.070188439431005e-06, |
| "loss": 0.0572, |
| "mean_token_accuracy": 0.9819264709949493, |
| "step": 1340 |
| }, |
| { |
| "epoch": 7.844574780058651, |
| "grad_norm": 0.2074367412183043, |
| "learning_rate": 8.048494991029352e-06, |
| "loss": 0.0561, |
| "mean_token_accuracy": 0.9814460799098015, |
| "step": 1341 |
| }, |
| { |
| "epoch": 7.850439882697947, |
| "grad_norm": 0.40755999120243874, |
| "learning_rate": 8.02685218095624e-06, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9809698536992073, |
| "step": 1342 |
| }, |
| { |
| "epoch": 7.8563049853372435, |
| "grad_norm": 0.3097454344053614, |
| "learning_rate": 8.005260087766318e-06, |
| "loss": 0.0639, |
| "mean_token_accuracy": 0.9798981621861458, |
| "step": 1343 |
| }, |
| { |
| "epoch": 7.86217008797654, |
| "grad_norm": 0.33298759837101477, |
| "learning_rate": 7.983718789830167e-06, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9803447499871254, |
| "step": 1344 |
| }, |
| { |
| "epoch": 7.868035190615836, |
| "grad_norm": 0.32489000595638734, |
| "learning_rate": 7.962228365333999e-06, |
| "loss": 0.0649, |
| "mean_token_accuracy": 0.9803356230258942, |
| "step": 1345 |
| }, |
| { |
| "epoch": 7.873900293255132, |
| "grad_norm": 0.2251061914600319, |
| "learning_rate": 7.940788892279375e-06, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.981585755944252, |
| "step": 1346 |
| }, |
| { |
| "epoch": 7.879765395894428, |
| "grad_norm": 0.23969743573221897, |
| "learning_rate": 7.919400448482928e-06, |
| "loss": 0.059, |
| "mean_token_accuracy": 0.9801178500056267, |
| "step": 1347 |
| }, |
| { |
| "epoch": 7.885630498533724, |
| "grad_norm": 0.3011598459943263, |
| "learning_rate": 7.898063111576066e-06, |
| "loss": 0.0593, |
| "mean_token_accuracy": 0.9817268326878548, |
| "step": 1348 |
| }, |
| { |
| "epoch": 7.891495601173021, |
| "grad_norm": 0.22688728416225185, |
| "learning_rate": 7.876776959004706e-06, |
| "loss": 0.0746, |
| "mean_token_accuracy": 0.9755787774920464, |
| "step": 1349 |
| }, |
| { |
| "epoch": 7.897360703812317, |
| "grad_norm": 0.29581805400389327, |
| "learning_rate": 7.855542068028981e-06, |
| "loss": 0.0549, |
| "mean_token_accuracy": 0.9815276637673378, |
| "step": 1350 |
| }, |
| { |
| "epoch": 7.903225806451613, |
| "grad_norm": 0.3134630356485751, |
| "learning_rate": 7.834358515722977e-06, |
| "loss": 0.0571, |
| "mean_token_accuracy": 0.9830066785216331, |
| "step": 1351 |
| }, |
| { |
| "epoch": 7.909090909090909, |
| "grad_norm": 0.31023619130265473, |
| "learning_rate": 7.813226378974427e-06, |
| "loss": 0.0613, |
| "mean_token_accuracy": 0.9804256185889244, |
| "step": 1352 |
| }, |
| { |
| "epoch": 7.914956011730205, |
| "grad_norm": 0.3167269601942049, |
| "learning_rate": 7.792145734484455e-06, |
| "loss": 0.0583, |
| "mean_token_accuracy": 0.9800725728273392, |
| "step": 1353 |
| }, |
| { |
| "epoch": 7.9208211143695015, |
| "grad_norm": 0.3579728764570681, |
| "learning_rate": 7.771116658767286e-06, |
| "loss": 0.0673, |
| "mean_token_accuracy": 0.9805974140763283, |
| "step": 1354 |
| }, |
| { |
| "epoch": 7.926686217008798, |
| "grad_norm": 0.28576336706359023, |
| "learning_rate": 7.750139228149978e-06, |
| "loss": 0.069, |
| "mean_token_accuracy": 0.9772385880351067, |
| "step": 1355 |
| }, |
| { |
| "epoch": 7.932551319648094, |
| "grad_norm": 0.3127217642738492, |
| "learning_rate": 7.729213518772121e-06, |
| "loss": 0.0566, |
| "mean_token_accuracy": 0.9827322363853455, |
| "step": 1356 |
| }, |
| { |
| "epoch": 7.93841642228739, |
| "grad_norm": 0.3143837781915121, |
| "learning_rate": 7.708339606585591e-06, |
| "loss": 0.0623, |
| "mean_token_accuracy": 0.9770531207323074, |
| "step": 1357 |
| }, |
| { |
| "epoch": 7.944281524926686, |
| "grad_norm": 0.3220229393336074, |
| "learning_rate": 7.687517567354266e-06, |
| "loss": 0.0747, |
| "mean_token_accuracy": 0.9770351573824883, |
| "step": 1358 |
| }, |
| { |
| "epoch": 7.9501466275659824, |
| "grad_norm": 0.425406819172546, |
| "learning_rate": 7.66674747665373e-06, |
| "loss": 0.0567, |
| "mean_token_accuracy": 0.9808967933058739, |
| "step": 1359 |
| }, |
| { |
| "epoch": 7.956011730205279, |
| "grad_norm": 0.4078670819905106, |
| "learning_rate": 7.646029409871029e-06, |
| "loss": 0.0641, |
| "mean_token_accuracy": 0.9776945933699608, |
| "step": 1360 |
| }, |
| { |
| "epoch": 7.961876832844575, |
| "grad_norm": 0.25029954580605374, |
| "learning_rate": 7.625363442204379e-06, |
| "loss": 0.0494, |
| "mean_token_accuracy": 0.984387032687664, |
| "step": 1361 |
| }, |
| { |
| "epoch": 7.967741935483871, |
| "grad_norm": 0.3067346484833591, |
| "learning_rate": 7.604749648662892e-06, |
| "loss": 0.0599, |
| "mean_token_accuracy": 0.9821083396673203, |
| "step": 1362 |
| }, |
| { |
| "epoch": 7.973607038123167, |
| "grad_norm": 0.3034537440779158, |
| "learning_rate": 7.584188104066317e-06, |
| "loss": 0.0537, |
| "mean_token_accuracy": 0.9811761453747749, |
| "step": 1363 |
| }, |
| { |
| "epoch": 7.979472140762463, |
| "grad_norm": 0.2676727146076349, |
| "learning_rate": 7.563678883044754e-06, |
| "loss": 0.0693, |
| "mean_token_accuracy": 0.9785163179039955, |
| "step": 1364 |
| }, |
| { |
| "epoch": 7.9853372434017595, |
| "grad_norm": 0.2628017567235926, |
| "learning_rate": 7.5432220600383935e-06, |
| "loss": 0.0701, |
| "mean_token_accuracy": 0.9787680581212044, |
| "step": 1365 |
| }, |
| { |
| "epoch": 7.991202346041056, |
| "grad_norm": 0.24809405335761472, |
| "learning_rate": 7.522817709297241e-06, |
| "loss": 0.0577, |
| "mean_token_accuracy": 0.9816685542464256, |
| "step": 1366 |
| }, |
| { |
| "epoch": 7.997067448680352, |
| "grad_norm": 0.2842505637743014, |
| "learning_rate": 7.502465904880849e-06, |
| "loss": 0.0612, |
| "mean_token_accuracy": 0.9808202460408211, |
| "step": 1367 |
| }, |
| { |
| "epoch": 8.0, |
| "grad_norm": 0.41987617913313496, |
| "learning_rate": 7.482166720658046e-06, |
| "loss": 0.0578, |
| "mean_token_accuracy": 0.9846701323986053, |
| "step": 1368 |
| }, |
| { |
| "epoch": 8.005865102639296, |
| "grad_norm": 0.214916141983213, |
| "learning_rate": 7.461920230306674e-06, |
| "loss": 0.0578, |
| "mean_token_accuracy": 0.9811231270432472, |
| "step": 1369 |
| }, |
| { |
| "epoch": 8.011730205278592, |
| "grad_norm": 0.2648143776987859, |
| "learning_rate": 7.441726507313318e-06, |
| "loss": 0.0509, |
| "mean_token_accuracy": 0.9820636063814163, |
| "step": 1370 |
| }, |
| { |
| "epoch": 8.017595307917889, |
| "grad_norm": 0.2201043806212357, |
| "learning_rate": 7.421585624973033e-06, |
| "loss": 0.0578, |
| "mean_token_accuracy": 0.9809773191809654, |
| "step": 1371 |
| }, |
| { |
| "epoch": 8.023460410557185, |
| "grad_norm": 0.19563315326882122, |
| "learning_rate": 7.4014976563890915e-06, |
| "loss": 0.0485, |
| "mean_token_accuracy": 0.9839671179652214, |
| "step": 1372 |
| }, |
| { |
| "epoch": 8.029325513196481, |
| "grad_norm": 0.20556851418206967, |
| "learning_rate": 7.381462674472702e-06, |
| "loss": 0.0498, |
| "mean_token_accuracy": 0.9850044846534729, |
| "step": 1373 |
| }, |
| { |
| "epoch": 8.035190615835777, |
| "grad_norm": 0.19766018394025286, |
| "learning_rate": 7.36148075194276e-06, |
| "loss": 0.051, |
| "mean_token_accuracy": 0.9836961477994919, |
| "step": 1374 |
| }, |
| { |
| "epoch": 8.041055718475073, |
| "grad_norm": 0.25314626449489763, |
| "learning_rate": 7.341551961325574e-06, |
| "loss": 0.051, |
| "mean_token_accuracy": 0.98270533233881, |
| "step": 1375 |
| }, |
| { |
| "epoch": 8.04692082111437, |
| "grad_norm": 0.3115274548014052, |
| "learning_rate": 7.3216763749546025e-06, |
| "loss": 0.0502, |
| "mean_token_accuracy": 0.9859990701079369, |
| "step": 1376 |
| }, |
| { |
| "epoch": 8.052785923753666, |
| "grad_norm": 0.21757031889947906, |
| "learning_rate": 7.301854064970202e-06, |
| "loss": 0.0529, |
| "mean_token_accuracy": 0.9847300946712494, |
| "step": 1377 |
| }, |
| { |
| "epoch": 8.058651026392962, |
| "grad_norm": 0.23951796689802396, |
| "learning_rate": 7.282085103319349e-06, |
| "loss": 0.0524, |
| "mean_token_accuracy": 0.9825025796890259, |
| "step": 1378 |
| }, |
| { |
| "epoch": 8.064516129032258, |
| "grad_norm": 0.23680698926945376, |
| "learning_rate": 7.2623695617553934e-06, |
| "loss": 0.0565, |
| "mean_token_accuracy": 0.9824689403176308, |
| "step": 1379 |
| }, |
| { |
| "epoch": 8.070381231671554, |
| "grad_norm": 0.22535881218387918, |
| "learning_rate": 7.242707511837781e-06, |
| "loss": 0.0491, |
| "mean_token_accuracy": 0.9835941642522812, |
| "step": 1380 |
| }, |
| { |
| "epoch": 8.07624633431085, |
| "grad_norm": 0.2785402711221106, |
| "learning_rate": 7.223099024931817e-06, |
| "loss": 0.0468, |
| "mean_token_accuracy": 0.9862391352653503, |
| "step": 1381 |
| }, |
| { |
| "epoch": 8.082111436950147, |
| "grad_norm": 0.2993996716485423, |
| "learning_rate": 7.203544172208387e-06, |
| "loss": 0.0551, |
| "mean_token_accuracy": 0.9826711639761925, |
| "step": 1382 |
| }, |
| { |
| "epoch": 8.087976539589443, |
| "grad_norm": 0.24507275921485255, |
| "learning_rate": 7.184043024643712e-06, |
| "loss": 0.0532, |
| "mean_token_accuracy": 0.9831705465912819, |
| "step": 1383 |
| }, |
| { |
| "epoch": 8.093841642228739, |
| "grad_norm": 0.3103281371140337, |
| "learning_rate": 7.16459565301908e-06, |
| "loss": 0.0532, |
| "mean_token_accuracy": 0.9835177212953568, |
| "step": 1384 |
| }, |
| { |
| "epoch": 8.099706744868035, |
| "grad_norm": 0.25126193604629965, |
| "learning_rate": 7.145202127920598e-06, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9802353978157043, |
| "step": 1385 |
| }, |
| { |
| "epoch": 8.105571847507331, |
| "grad_norm": 0.31079694307967204, |
| "learning_rate": 7.125862519738924e-06, |
| "loss": 0.0548, |
| "mean_token_accuracy": 0.981208898127079, |
| "step": 1386 |
| }, |
| { |
| "epoch": 8.111436950146627, |
| "grad_norm": 0.243430501615171, |
| "learning_rate": 7.106576898669031e-06, |
| "loss": 0.0565, |
| "mean_token_accuracy": 0.9828232526779175, |
| "step": 1387 |
| }, |
| { |
| "epoch": 8.117302052785924, |
| "grad_norm": 0.29248007573235113, |
| "learning_rate": 7.087345334709931e-06, |
| "loss": 0.0581, |
| "mean_token_accuracy": 0.9782914444804192, |
| "step": 1388 |
| }, |
| { |
| "epoch": 8.12316715542522, |
| "grad_norm": 0.23983735227252295, |
| "learning_rate": 7.068167897664433e-06, |
| "loss": 0.0574, |
| "mean_token_accuracy": 0.9791986420750618, |
| "step": 1389 |
| }, |
| { |
| "epoch": 8.129032258064516, |
| "grad_norm": 0.25763068213117407, |
| "learning_rate": 7.0490446571388925e-06, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.982701949775219, |
| "step": 1390 |
| }, |
| { |
| "epoch": 8.134897360703812, |
| "grad_norm": 0.31395890478128136, |
| "learning_rate": 7.0299756825429465e-06, |
| "loss": 0.0535, |
| "mean_token_accuracy": 0.9816442281007767, |
| "step": 1391 |
| }, |
| { |
| "epoch": 8.140762463343108, |
| "grad_norm": 0.36881180696205157, |
| "learning_rate": 7.010961043089277e-06, |
| "loss": 0.0457, |
| "mean_token_accuracy": 0.9867331683635712, |
| "step": 1392 |
| }, |
| { |
| "epoch": 8.146627565982405, |
| "grad_norm": 0.22371030335071296, |
| "learning_rate": 6.992000807793333e-06, |
| "loss": 0.0504, |
| "mean_token_accuracy": 0.9831229224801064, |
| "step": 1393 |
| }, |
| { |
| "epoch": 8.1524926686217, |
| "grad_norm": 0.23527634028093716, |
| "learning_rate": 6.973095045473124e-06, |
| "loss": 0.057, |
| "mean_token_accuracy": 0.9822418987751007, |
| "step": 1394 |
| }, |
| { |
| "epoch": 8.158357771260997, |
| "grad_norm": 0.3098862024215743, |
| "learning_rate": 6.954243824748922e-06, |
| "loss": 0.0597, |
| "mean_token_accuracy": 0.9828020483255386, |
| "step": 1395 |
| }, |
| { |
| "epoch": 8.164222873900293, |
| "grad_norm": 0.2078992554645412, |
| "learning_rate": 6.93544721404305e-06, |
| "loss": 0.0521, |
| "mean_token_accuracy": 0.9825119003653526, |
| "step": 1396 |
| }, |
| { |
| "epoch": 8.17008797653959, |
| "grad_norm": 0.432128734720523, |
| "learning_rate": 6.916705281579612e-06, |
| "loss": 0.0567, |
| "mean_token_accuracy": 0.9820001050829887, |
| "step": 1397 |
| }, |
| { |
| "epoch": 8.175953079178885, |
| "grad_norm": 0.24054569811011123, |
| "learning_rate": 6.898018095384252e-06, |
| "loss": 0.0657, |
| "mean_token_accuracy": 0.9803327471017838, |
| "step": 1398 |
| }, |
| { |
| "epoch": 8.181818181818182, |
| "grad_norm": 0.30936846417548536, |
| "learning_rate": 6.879385723283913e-06, |
| "loss": 0.0549, |
| "mean_token_accuracy": 0.9830240309238434, |
| "step": 1399 |
| }, |
| { |
| "epoch": 8.187683284457478, |
| "grad_norm": 0.20708706141150313, |
| "learning_rate": 6.8608082329065775e-06, |
| "loss": 0.0536, |
| "mean_token_accuracy": 0.9839501082897186, |
| "step": 1400 |
| }, |
| { |
| "epoch": 8.193548387096774, |
| "grad_norm": 0.4109806587663491, |
| "learning_rate": 6.842285691681032e-06, |
| "loss": 0.0672, |
| "mean_token_accuracy": 0.9807805866003036, |
| "step": 1401 |
| }, |
| { |
| "epoch": 8.19941348973607, |
| "grad_norm": 0.33459586080943454, |
| "learning_rate": 6.8238181668366244e-06, |
| "loss": 0.0506, |
| "mean_token_accuracy": 0.9823162779211998, |
| "step": 1402 |
| }, |
| { |
| "epoch": 8.205278592375366, |
| "grad_norm": 0.23204687344932642, |
| "learning_rate": 6.805405725403006e-06, |
| "loss": 0.059, |
| "mean_token_accuracy": 0.981462337076664, |
| "step": 1403 |
| }, |
| { |
| "epoch": 8.211143695014663, |
| "grad_norm": 0.24387787551349369, |
| "learning_rate": 6.787048434209906e-06, |
| "loss": 0.0559, |
| "mean_token_accuracy": 0.9810043722391129, |
| "step": 1404 |
| }, |
| { |
| "epoch": 8.217008797653959, |
| "grad_norm": 0.24111998738404342, |
| "learning_rate": 6.768746359886882e-06, |
| "loss": 0.0552, |
| "mean_token_accuracy": 0.9823629483580589, |
| "step": 1405 |
| }, |
| { |
| "epoch": 8.222873900293255, |
| "grad_norm": 0.2164729282188346, |
| "learning_rate": 6.750499568863061e-06, |
| "loss": 0.0554, |
| "mean_token_accuracy": 0.9823937118053436, |
| "step": 1406 |
| }, |
| { |
| "epoch": 8.228739002932551, |
| "grad_norm": 0.3701551999536545, |
| "learning_rate": 6.732308127366931e-06, |
| "loss": 0.0639, |
| "mean_token_accuracy": 0.9803007692098618, |
| "step": 1407 |
| }, |
| { |
| "epoch": 8.234604105571847, |
| "grad_norm": 0.2602007603930705, |
| "learning_rate": 6.714172101426077e-06, |
| "loss": 0.0586, |
| "mean_token_accuracy": 0.9811219796538353, |
| "step": 1408 |
| }, |
| { |
| "epoch": 8.240469208211143, |
| "grad_norm": 0.1814905190223246, |
| "learning_rate": 6.696091556866948e-06, |
| "loss": 0.0446, |
| "mean_token_accuracy": 0.9854880273342133, |
| "step": 1409 |
| }, |
| { |
| "epoch": 8.24633431085044, |
| "grad_norm": 0.2478857316703125, |
| "learning_rate": 6.678066559314622e-06, |
| "loss": 0.0615, |
| "mean_token_accuracy": 0.9804988503456116, |
| "step": 1410 |
| }, |
| { |
| "epoch": 8.252199413489736, |
| "grad_norm": 0.23841278471860133, |
| "learning_rate": 6.660097174192556e-06, |
| "loss": 0.0572, |
| "mean_token_accuracy": 0.9817399382591248, |
| "step": 1411 |
| }, |
| { |
| "epoch": 8.258064516129032, |
| "grad_norm": 0.2565046678967367, |
| "learning_rate": 6.642183466722363e-06, |
| "loss": 0.0573, |
| "mean_token_accuracy": 0.980897068977356, |
| "step": 1412 |
| }, |
| { |
| "epoch": 8.263929618768328, |
| "grad_norm": 0.2463098769541463, |
| "learning_rate": 6.624325501923565e-06, |
| "loss": 0.0573, |
| "mean_token_accuracy": 0.9820313602685928, |
| "step": 1413 |
| }, |
| { |
| "epoch": 8.269794721407624, |
| "grad_norm": 0.24504153100466936, |
| "learning_rate": 6.606523344613362e-06, |
| "loss": 0.061, |
| "mean_token_accuracy": 0.9795975983142853, |
| "step": 1414 |
| }, |
| { |
| "epoch": 8.27565982404692, |
| "grad_norm": 0.22361167881403213, |
| "learning_rate": 6.588777059406397e-06, |
| "loss": 0.0571, |
| "mean_token_accuracy": 0.9831408709287643, |
| "step": 1415 |
| }, |
| { |
| "epoch": 8.281524926686217, |
| "grad_norm": 0.18291052131426874, |
| "learning_rate": 6.571086710714516e-06, |
| "loss": 0.0478, |
| "mean_token_accuracy": 0.9837886691093445, |
| "step": 1416 |
| }, |
| { |
| "epoch": 8.287390029325513, |
| "grad_norm": 0.23482128316494943, |
| "learning_rate": 6.553452362746543e-06, |
| "loss": 0.0592, |
| "mean_token_accuracy": 0.9811000153422356, |
| "step": 1417 |
| }, |
| { |
| "epoch": 8.29325513196481, |
| "grad_norm": 0.2571114682551005, |
| "learning_rate": 6.5358740795080335e-06, |
| "loss": 0.0659, |
| "mean_token_accuracy": 0.9779541790485382, |
| "step": 1418 |
| }, |
| { |
| "epoch": 8.299120234604105, |
| "grad_norm": 0.3411374440781876, |
| "learning_rate": 6.518351924801061e-06, |
| "loss": 0.0623, |
| "mean_token_accuracy": 0.9813627898693085, |
| "step": 1419 |
| }, |
| { |
| "epoch": 8.304985337243401, |
| "grad_norm": 0.32170991105288976, |
| "learning_rate": 6.500885962223969e-06, |
| "loss": 0.0569, |
| "mean_token_accuracy": 0.9852675199508667, |
| "step": 1420 |
| }, |
| { |
| "epoch": 8.310850439882698, |
| "grad_norm": 0.2520903886069418, |
| "learning_rate": 6.483476255171146e-06, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.9805245026946068, |
| "step": 1421 |
| }, |
| { |
| "epoch": 8.316715542521994, |
| "grad_norm": 0.35309257782861436, |
| "learning_rate": 6.4661228668328015e-06, |
| "loss": 0.0543, |
| "mean_token_accuracy": 0.983853705227375, |
| "step": 1422 |
| }, |
| { |
| "epoch": 8.32258064516129, |
| "grad_norm": 0.27103047498821015, |
| "learning_rate": 6.448825860194722e-06, |
| "loss": 0.0609, |
| "mean_token_accuracy": 0.981744721531868, |
| "step": 1423 |
| }, |
| { |
| "epoch": 8.328445747800586, |
| "grad_norm": 0.3668875312033516, |
| "learning_rate": 6.431585298038057e-06, |
| "loss": 0.0436, |
| "mean_token_accuracy": 0.9858937785029411, |
| "step": 1424 |
| }, |
| { |
| "epoch": 8.334310850439882, |
| "grad_norm": 0.21839281047639716, |
| "learning_rate": 6.414401242939087e-06, |
| "loss": 0.0598, |
| "mean_token_accuracy": 0.9812084659934044, |
| "step": 1425 |
| }, |
| { |
| "epoch": 8.340175953079179, |
| "grad_norm": 0.2888554299502811, |
| "learning_rate": 6.397273757268987e-06, |
| "loss": 0.0579, |
| "mean_token_accuracy": 0.9844140931963921, |
| "step": 1426 |
| }, |
| { |
| "epoch": 8.346041055718475, |
| "grad_norm": 0.24613171679315907, |
| "learning_rate": 6.380202903193616e-06, |
| "loss": 0.0631, |
| "mean_token_accuracy": 0.9819495007395744, |
| "step": 1427 |
| }, |
| { |
| "epoch": 8.351906158357771, |
| "grad_norm": 0.22714519725510895, |
| "learning_rate": 6.363188742673281e-06, |
| "loss": 0.0567, |
| "mean_token_accuracy": 0.9815320670604706, |
| "step": 1428 |
| }, |
| { |
| "epoch": 8.357771260997067, |
| "grad_norm": 0.3202332452186219, |
| "learning_rate": 6.346231337462513e-06, |
| "loss": 0.0554, |
| "mean_token_accuracy": 0.982030026614666, |
| "step": 1429 |
| }, |
| { |
| "epoch": 8.363636363636363, |
| "grad_norm": 0.316039144956545, |
| "learning_rate": 6.329330749109839e-06, |
| "loss": 0.0691, |
| "mean_token_accuracy": 0.9775633811950684, |
| "step": 1430 |
| }, |
| { |
| "epoch": 8.36950146627566, |
| "grad_norm": 0.2181845443857865, |
| "learning_rate": 6.312487038957573e-06, |
| "loss": 0.056, |
| "mean_token_accuracy": 0.9824205189943314, |
| "step": 1431 |
| }, |
| { |
| "epoch": 8.375366568914956, |
| "grad_norm": 0.22328961022302585, |
| "learning_rate": 6.295700268141579e-06, |
| "loss": 0.0496, |
| "mean_token_accuracy": 0.9836017712950706, |
| "step": 1432 |
| }, |
| { |
| "epoch": 8.381231671554252, |
| "grad_norm": 0.19937915686885815, |
| "learning_rate": 6.2789704975910574e-06, |
| "loss": 0.049, |
| "mean_token_accuracy": 0.982590489089489, |
| "step": 1433 |
| }, |
| { |
| "epoch": 8.387096774193548, |
| "grad_norm": 0.24150867763099138, |
| "learning_rate": 6.262297788028316e-06, |
| "loss": 0.0513, |
| "mean_token_accuracy": 0.981402613222599, |
| "step": 1434 |
| }, |
| { |
| "epoch": 8.392961876832844, |
| "grad_norm": 0.2795051735249161, |
| "learning_rate": 6.245682199968556e-06, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9804069846868515, |
| "step": 1435 |
| }, |
| { |
| "epoch": 8.39882697947214, |
| "grad_norm": 0.25783232931813, |
| "learning_rate": 6.229123793719656e-06, |
| "loss": 0.0569, |
| "mean_token_accuracy": 0.9817790612578392, |
| "step": 1436 |
| }, |
| { |
| "epoch": 8.404692082111437, |
| "grad_norm": 0.30486166707710477, |
| "learning_rate": 6.21262262938194e-06, |
| "loss": 0.0536, |
| "mean_token_accuracy": 0.9836645349860191, |
| "step": 1437 |
| }, |
| { |
| "epoch": 8.410557184750733, |
| "grad_norm": 0.27233965999418625, |
| "learning_rate": 6.196178766847969e-06, |
| "loss": 0.0551, |
| "mean_token_accuracy": 0.9816263765096664, |
| "step": 1438 |
| }, |
| { |
| "epoch": 8.416422287390029, |
| "grad_norm": 0.24723015413758212, |
| "learning_rate": 6.1797922658023264e-06, |
| "loss": 0.0639, |
| "mean_token_accuracy": 0.9785666167736053, |
| "step": 1439 |
| }, |
| { |
| "epoch": 8.422287390029325, |
| "grad_norm": 0.21982320056204013, |
| "learning_rate": 6.16346318572139e-06, |
| "loss": 0.0547, |
| "mean_token_accuracy": 0.982805423438549, |
| "step": 1440 |
| }, |
| { |
| "epoch": 8.428152492668621, |
| "grad_norm": 0.28335201007211935, |
| "learning_rate": 6.147191585873128e-06, |
| "loss": 0.0626, |
| "mean_token_accuracy": 0.9803605228662491, |
| "step": 1441 |
| }, |
| { |
| "epoch": 8.434017595307918, |
| "grad_norm": 0.2103051058451436, |
| "learning_rate": 6.130977525316878e-06, |
| "loss": 0.0578, |
| "mean_token_accuracy": 0.9820494800806046, |
| "step": 1442 |
| }, |
| { |
| "epoch": 8.439882697947214, |
| "grad_norm": 0.205299410579196, |
| "learning_rate": 6.114821062903125e-06, |
| "loss": 0.0548, |
| "mean_token_accuracy": 0.982606902718544, |
| "step": 1443 |
| }, |
| { |
| "epoch": 8.44574780058651, |
| "grad_norm": 0.22390637291501272, |
| "learning_rate": 6.098722257273303e-06, |
| "loss": 0.0547, |
| "mean_token_accuracy": 0.9798173382878304, |
| "step": 1444 |
| }, |
| { |
| "epoch": 8.451612903225806, |
| "grad_norm": 0.2771499590517391, |
| "learning_rate": 6.082681166859579e-06, |
| "loss": 0.0636, |
| "mean_token_accuracy": 0.9806607887148857, |
| "step": 1445 |
| }, |
| { |
| "epoch": 8.457478005865102, |
| "grad_norm": 0.4554475097871347, |
| "learning_rate": 6.066697849884629e-06, |
| "loss": 0.0633, |
| "mean_token_accuracy": 0.9796369150280952, |
| "step": 1446 |
| }, |
| { |
| "epoch": 8.463343108504398, |
| "grad_norm": 0.19216615352509395, |
| "learning_rate": 6.0507723643614415e-06, |
| "loss": 0.0436, |
| "mean_token_accuracy": 0.9855980426073074, |
| "step": 1447 |
| }, |
| { |
| "epoch": 8.469208211143695, |
| "grad_norm": 0.22727652768343684, |
| "learning_rate": 6.034904768093095e-06, |
| "loss": 0.057, |
| "mean_token_accuracy": 0.9814287722110748, |
| "step": 1448 |
| }, |
| { |
| "epoch": 8.47507331378299, |
| "grad_norm": 0.22752398618013056, |
| "learning_rate": 6.019095118672557e-06, |
| "loss": 0.0618, |
| "mean_token_accuracy": 0.9799441695213318, |
| "step": 1449 |
| }, |
| { |
| "epoch": 8.480938416422287, |
| "grad_norm": 0.24193075900923788, |
| "learning_rate": 6.003343473482469e-06, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9827790260314941, |
| "step": 1450 |
| }, |
| { |
| "epoch": 8.486803519061583, |
| "grad_norm": 0.24392059844002878, |
| "learning_rate": 5.98764988969494e-06, |
| "loss": 0.0595, |
| "mean_token_accuracy": 0.9794244691729546, |
| "step": 1451 |
| }, |
| { |
| "epoch": 8.49266862170088, |
| "grad_norm": 0.21220940879325176, |
| "learning_rate": 5.972014424271344e-06, |
| "loss": 0.0502, |
| "mean_token_accuracy": 0.9840523451566696, |
| "step": 1452 |
| }, |
| { |
| "epoch": 8.498533724340176, |
| "grad_norm": 0.3847730117232794, |
| "learning_rate": 5.956437133962103e-06, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9817788973450661, |
| "step": 1453 |
| }, |
| { |
| "epoch": 8.504398826979472, |
| "grad_norm": 0.35439580902846674, |
| "learning_rate": 5.94091807530649e-06, |
| "loss": 0.0592, |
| "mean_token_accuracy": 0.9799836799502373, |
| "step": 1454 |
| }, |
| { |
| "epoch": 8.510263929618768, |
| "grad_norm": 0.2448678361420796, |
| "learning_rate": 5.925457304632421e-06, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9810876250267029, |
| "step": 1455 |
| }, |
| { |
| "epoch": 8.516129032258064, |
| "grad_norm": 0.2546365410929796, |
| "learning_rate": 5.91005487805625e-06, |
| "loss": 0.0655, |
| "mean_token_accuracy": 0.9798986539244652, |
| "step": 1456 |
| }, |
| { |
| "epoch": 8.52199413489736, |
| "grad_norm": 0.22510297002392768, |
| "learning_rate": 5.894710851482563e-06, |
| "loss": 0.0556, |
| "mean_token_accuracy": 0.983493484556675, |
| "step": 1457 |
| }, |
| { |
| "epoch": 8.527859237536656, |
| "grad_norm": 0.24029196708436434, |
| "learning_rate": 5.879425280603981e-06, |
| "loss": 0.0585, |
| "mean_token_accuracy": 0.9817355275154114, |
| "step": 1458 |
| }, |
| { |
| "epoch": 8.533724340175953, |
| "grad_norm": 0.2948271453952541, |
| "learning_rate": 5.864198220900952e-06, |
| "loss": 0.054, |
| "mean_token_accuracy": 0.9828294068574905, |
| "step": 1459 |
| }, |
| { |
| "epoch": 8.539589442815249, |
| "grad_norm": 0.24715359464949893, |
| "learning_rate": 5.849029727641552e-06, |
| "loss": 0.0573, |
| "mean_token_accuracy": 0.9808838665485382, |
| "step": 1460 |
| }, |
| { |
| "epoch": 8.545454545454545, |
| "grad_norm": 0.22895910866616212, |
| "learning_rate": 5.833919855881286e-06, |
| "loss": 0.0587, |
| "mean_token_accuracy": 0.9810523241758347, |
| "step": 1461 |
| }, |
| { |
| "epoch": 8.551319648093841, |
| "grad_norm": 0.23923347448065085, |
| "learning_rate": 5.818868660462886e-06, |
| "loss": 0.053, |
| "mean_token_accuracy": 0.9833957925438881, |
| "step": 1462 |
| }, |
| { |
| "epoch": 8.557184750733137, |
| "grad_norm": 0.20995234181528383, |
| "learning_rate": 5.803876196016114e-06, |
| "loss": 0.0536, |
| "mean_token_accuracy": 0.9848415032029152, |
| "step": 1463 |
| }, |
| { |
| "epoch": 8.563049853372434, |
| "grad_norm": 0.3313140616468372, |
| "learning_rate": 5.788942516957561e-06, |
| "loss": 0.0554, |
| "mean_token_accuracy": 0.9830712005496025, |
| "step": 1464 |
| }, |
| { |
| "epoch": 8.56891495601173, |
| "grad_norm": 0.25299926535599937, |
| "learning_rate": 5.774067677490448e-06, |
| "loss": 0.0618, |
| "mean_token_accuracy": 0.9809750616550446, |
| "step": 1465 |
| }, |
| { |
| "epoch": 8.574780058651026, |
| "grad_norm": 0.26249947027843634, |
| "learning_rate": 5.759251731604435e-06, |
| "loss": 0.05, |
| "mean_token_accuracy": 0.9828970730304718, |
| "step": 1466 |
| }, |
| { |
| "epoch": 8.580645161290322, |
| "grad_norm": 0.2515681497508488, |
| "learning_rate": 5.744494733075424e-06, |
| "loss": 0.057, |
| "mean_token_accuracy": 0.9812851548194885, |
| "step": 1467 |
| }, |
| { |
| "epoch": 8.586510263929618, |
| "grad_norm": 0.20645851852940889, |
| "learning_rate": 5.729796735465359e-06, |
| "loss": 0.0563, |
| "mean_token_accuracy": 0.9807659089565277, |
| "step": 1468 |
| }, |
| { |
| "epoch": 8.592375366568914, |
| "grad_norm": 0.23265625943253596, |
| "learning_rate": 5.7151577921220356e-06, |
| "loss": 0.0578, |
| "mean_token_accuracy": 0.981408916413784, |
| "step": 1469 |
| }, |
| { |
| "epoch": 8.59824046920821, |
| "grad_norm": 0.18593301851214442, |
| "learning_rate": 5.7005779561789046e-06, |
| "loss": 0.0479, |
| "mean_token_accuracy": 0.9842170625925064, |
| "step": 1470 |
| }, |
| { |
| "epoch": 8.604105571847507, |
| "grad_norm": 0.38192119047399087, |
| "learning_rate": 5.686057280554882e-06, |
| "loss": 0.0535, |
| "mean_token_accuracy": 0.9830747321248055, |
| "step": 1471 |
| }, |
| { |
| "epoch": 8.609970674486803, |
| "grad_norm": 0.22481461210294473, |
| "learning_rate": 5.671595817954157e-06, |
| "loss": 0.0554, |
| "mean_token_accuracy": 0.9830892011523247, |
| "step": 1472 |
| }, |
| { |
| "epoch": 8.6158357771261, |
| "grad_norm": 0.2898055226555559, |
| "learning_rate": 5.657193620865997e-06, |
| "loss": 0.0542, |
| "mean_token_accuracy": 0.9828846156597137, |
| "step": 1473 |
| }, |
| { |
| "epoch": 8.621700879765395, |
| "grad_norm": 0.4735079320278208, |
| "learning_rate": 5.642850741564562e-06, |
| "loss": 0.0672, |
| "mean_token_accuracy": 0.9807828441262245, |
| "step": 1474 |
| }, |
| { |
| "epoch": 8.627565982404692, |
| "grad_norm": 0.23634331953871995, |
| "learning_rate": 5.62856723210871e-06, |
| "loss": 0.0577, |
| "mean_token_accuracy": 0.9808989763259888, |
| "step": 1475 |
| }, |
| { |
| "epoch": 8.633431085043988, |
| "grad_norm": 0.30034970883591433, |
| "learning_rate": 5.614343144341814e-06, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9796464666724205, |
| "step": 1476 |
| }, |
| { |
| "epoch": 8.639296187683284, |
| "grad_norm": 0.1988418114892257, |
| "learning_rate": 5.600178529891564e-06, |
| "loss": 0.05, |
| "mean_token_accuracy": 0.9832219183444977, |
| "step": 1477 |
| }, |
| { |
| "epoch": 8.64516129032258, |
| "grad_norm": 0.2733706899404459, |
| "learning_rate": 5.58607344016979e-06, |
| "loss": 0.0655, |
| "mean_token_accuracy": 0.9781039133667946, |
| "step": 1478 |
| }, |
| { |
| "epoch": 8.651026392961876, |
| "grad_norm": 0.21042727535719943, |
| "learning_rate": 5.5720279263722795e-06, |
| "loss": 0.0533, |
| "mean_token_accuracy": 0.9818021357059479, |
| "step": 1479 |
| }, |
| { |
| "epoch": 8.656891495601172, |
| "grad_norm": 0.24661902402025798, |
| "learning_rate": 5.558042039478564e-06, |
| "loss": 0.0531, |
| "mean_token_accuracy": 0.9816571772098541, |
| "step": 1480 |
| }, |
| { |
| "epoch": 8.662756598240469, |
| "grad_norm": 0.2470785047648527, |
| "learning_rate": 5.544115830251769e-06, |
| "loss": 0.0638, |
| "mean_token_accuracy": 0.9801130592823029, |
| "step": 1481 |
| }, |
| { |
| "epoch": 8.668621700879765, |
| "grad_norm": 0.276592842472206, |
| "learning_rate": 5.530249349238407e-06, |
| "loss": 0.0572, |
| "mean_token_accuracy": 0.9824761971831322, |
| "step": 1482 |
| }, |
| { |
| "epoch": 8.674486803519061, |
| "grad_norm": 0.27445814157641885, |
| "learning_rate": 5.516442646768207e-06, |
| "loss": 0.063, |
| "mean_token_accuracy": 0.9772898554801941, |
| "step": 1483 |
| }, |
| { |
| "epoch": 8.680351906158357, |
| "grad_norm": 0.2249695783332849, |
| "learning_rate": 5.502695772953922e-06, |
| "loss": 0.063, |
| "mean_token_accuracy": 0.9796239584684372, |
| "step": 1484 |
| }, |
| { |
| "epoch": 8.686217008797653, |
| "grad_norm": 0.24349980523835593, |
| "learning_rate": 5.489008777691151e-06, |
| "loss": 0.0559, |
| "mean_token_accuracy": 0.9837216436862946, |
| "step": 1485 |
| }, |
| { |
| "epoch": 8.69208211143695, |
| "grad_norm": 0.440521910978946, |
| "learning_rate": 5.475381710658161e-06, |
| "loss": 0.0607, |
| "mean_token_accuracy": 0.9804883822798729, |
| "step": 1486 |
| }, |
| { |
| "epoch": 8.697947214076246, |
| "grad_norm": 0.2554597984182961, |
| "learning_rate": 5.4618146213157e-06, |
| "loss": 0.0641, |
| "mean_token_accuracy": 0.9781029522418976, |
| "step": 1487 |
| }, |
| { |
| "epoch": 8.703812316715542, |
| "grad_norm": 0.47861781564254957, |
| "learning_rate": 5.448307558906822e-06, |
| "loss": 0.0646, |
| "mean_token_accuracy": 0.9812514930963516, |
| "step": 1488 |
| }, |
| { |
| "epoch": 8.709677419354838, |
| "grad_norm": 0.2930027638485088, |
| "learning_rate": 5.434860572456711e-06, |
| "loss": 0.0559, |
| "mean_token_accuracy": 0.9799815565347672, |
| "step": 1489 |
| }, |
| { |
| "epoch": 8.715542521994134, |
| "grad_norm": 0.22677059107025838, |
| "learning_rate": 5.421473710772496e-06, |
| "loss": 0.0569, |
| "mean_token_accuracy": 0.9823431074619293, |
| "step": 1490 |
| }, |
| { |
| "epoch": 8.72140762463343, |
| "grad_norm": 0.258704788971786, |
| "learning_rate": 5.408147022443077e-06, |
| "loss": 0.0524, |
| "mean_token_accuracy": 0.9814721569418907, |
| "step": 1491 |
| }, |
| { |
| "epoch": 8.727272727272727, |
| "grad_norm": 0.2273206164374934, |
| "learning_rate": 5.39488055583895e-06, |
| "loss": 0.0601, |
| "mean_token_accuracy": 0.9824408814311028, |
| "step": 1492 |
| }, |
| { |
| "epoch": 8.733137829912023, |
| "grad_norm": 0.2502689684955035, |
| "learning_rate": 5.3816743591120365e-06, |
| "loss": 0.0565, |
| "mean_token_accuracy": 0.9813073575496674, |
| "step": 1493 |
| }, |
| { |
| "epoch": 8.739002932551319, |
| "grad_norm": 0.23368312729472407, |
| "learning_rate": 5.368528480195492e-06, |
| "loss": 0.0593, |
| "mean_token_accuracy": 0.9821663275361061, |
| "step": 1494 |
| }, |
| { |
| "epoch": 8.744868035190615, |
| "grad_norm": 0.1687899775907795, |
| "learning_rate": 5.355442966803544e-06, |
| "loss": 0.0459, |
| "mean_token_accuracy": 0.9838021844625473, |
| "step": 1495 |
| }, |
| { |
| "epoch": 8.750733137829911, |
| "grad_norm": 0.430656839260121, |
| "learning_rate": 5.342417866431326e-06, |
| "loss": 0.0645, |
| "mean_token_accuracy": 0.978046216070652, |
| "step": 1496 |
| }, |
| { |
| "epoch": 8.756598240469208, |
| "grad_norm": 0.2379693424056092, |
| "learning_rate": 5.329453226354692e-06, |
| "loss": 0.0589, |
| "mean_token_accuracy": 0.9819848984479904, |
| "step": 1497 |
| }, |
| { |
| "epoch": 8.762463343108504, |
| "grad_norm": 0.21809785004029345, |
| "learning_rate": 5.31654909363005e-06, |
| "loss": 0.0559, |
| "mean_token_accuracy": 0.9828894585371017, |
| "step": 1498 |
| }, |
| { |
| "epoch": 8.7683284457478, |
| "grad_norm": 0.27329055037352745, |
| "learning_rate": 5.303705515094187e-06, |
| "loss": 0.0687, |
| "mean_token_accuracy": 0.9799009263515472, |
| "step": 1499 |
| }, |
| { |
| "epoch": 8.774193548387096, |
| "grad_norm": 0.2757990646414536, |
| "learning_rate": 5.290922537364109e-06, |
| "loss": 0.0671, |
| "mean_token_accuracy": 0.9762155041098595, |
| "step": 1500 |
| }, |
| { |
| "epoch": 8.780058651026392, |
| "grad_norm": 0.22185210710048459, |
| "learning_rate": 5.278200206836861e-06, |
| "loss": 0.0591, |
| "mean_token_accuracy": 0.980154275894165, |
| "step": 1501 |
| }, |
| { |
| "epoch": 8.785923753665688, |
| "grad_norm": 0.22047265984608966, |
| "learning_rate": 5.265538569689365e-06, |
| "loss": 0.0538, |
| "mean_token_accuracy": 0.9819122850894928, |
| "step": 1502 |
| }, |
| { |
| "epoch": 8.791788856304985, |
| "grad_norm": 0.20721791327320876, |
| "learning_rate": 5.25293767187825e-06, |
| "loss": 0.0529, |
| "mean_token_accuracy": 0.9842581674456596, |
| "step": 1503 |
| }, |
| { |
| "epoch": 8.79765395894428, |
| "grad_norm": 0.2591529652741556, |
| "learning_rate": 5.240397559139685e-06, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9804480522871017, |
| "step": 1504 |
| }, |
| { |
| "epoch": 8.803519061583577, |
| "grad_norm": 0.19629905391668, |
| "learning_rate": 5.227918276989215e-06, |
| "loss": 0.0541, |
| "mean_token_accuracy": 0.9810454174876213, |
| "step": 1505 |
| }, |
| { |
| "epoch": 8.809384164222873, |
| "grad_norm": 0.24900270526978613, |
| "learning_rate": 5.2154998707215976e-06, |
| "loss": 0.0554, |
| "mean_token_accuracy": 0.9797688350081444, |
| "step": 1506 |
| }, |
| { |
| "epoch": 8.81524926686217, |
| "grad_norm": 0.35646628836269056, |
| "learning_rate": 5.203142385410628e-06, |
| "loss": 0.0542, |
| "mean_token_accuracy": 0.9833614900708199, |
| "step": 1507 |
| }, |
| { |
| "epoch": 8.821114369501466, |
| "grad_norm": 0.21844551824759018, |
| "learning_rate": 5.190845865908987e-06, |
| "loss": 0.0527, |
| "mean_token_accuracy": 0.9799956232309341, |
| "step": 1508 |
| }, |
| { |
| "epoch": 8.826979472140762, |
| "grad_norm": 0.27531658663437253, |
| "learning_rate": 5.178610356848075e-06, |
| "loss": 0.0588, |
| "mean_token_accuracy": 0.9806870818138123, |
| "step": 1509 |
| }, |
| { |
| "epoch": 8.832844574780058, |
| "grad_norm": 0.27548218874842867, |
| "learning_rate": 5.166435902637848e-06, |
| "loss": 0.0533, |
| "mean_token_accuracy": 0.9819175824522972, |
| "step": 1510 |
| }, |
| { |
| "epoch": 8.838709677419354, |
| "grad_norm": 0.21735665267404067, |
| "learning_rate": 5.154322547466658e-06, |
| "loss": 0.0524, |
| "mean_token_accuracy": 0.9834935739636421, |
| "step": 1511 |
| }, |
| { |
| "epoch": 8.84457478005865, |
| "grad_norm": 0.23058685157888828, |
| "learning_rate": 5.142270335301095e-06, |
| "loss": 0.053, |
| "mean_token_accuracy": 0.9823649004101753, |
| "step": 1512 |
| }, |
| { |
| "epoch": 8.850439882697946, |
| "grad_norm": 0.24988833053602405, |
| "learning_rate": 5.130279309885817e-06, |
| "loss": 0.0537, |
| "mean_token_accuracy": 0.9819278046488762, |
| "step": 1513 |
| }, |
| { |
| "epoch": 8.856304985337243, |
| "grad_norm": 0.26317833073022107, |
| "learning_rate": 5.118349514743404e-06, |
| "loss": 0.0642, |
| "mean_token_accuracy": 0.9782841205596924, |
| "step": 1514 |
| }, |
| { |
| "epoch": 8.862170087976539, |
| "grad_norm": 0.2734025499041476, |
| "learning_rate": 5.1064809931741975e-06, |
| "loss": 0.0676, |
| "mean_token_accuracy": 0.9794860184192657, |
| "step": 1515 |
| }, |
| { |
| "epoch": 8.868035190615835, |
| "grad_norm": 0.2055012084171587, |
| "learning_rate": 5.094673788256137e-06, |
| "loss": 0.0527, |
| "mean_token_accuracy": 0.9848830178380013, |
| "step": 1516 |
| }, |
| { |
| "epoch": 8.873900293255131, |
| "grad_norm": 0.2619226204611417, |
| "learning_rate": 5.082927942844603e-06, |
| "loss": 0.0635, |
| "mean_token_accuracy": 0.9811034798622131, |
| "step": 1517 |
| }, |
| { |
| "epoch": 8.879765395894427, |
| "grad_norm": 0.22565654238279362, |
| "learning_rate": 5.0712434995722734e-06, |
| "loss": 0.0566, |
| "mean_token_accuracy": 0.9808684885501862, |
| "step": 1518 |
| }, |
| { |
| "epoch": 8.885630498533724, |
| "grad_norm": 0.3079929186156211, |
| "learning_rate": 5.059620500848964e-06, |
| "loss": 0.06, |
| "mean_token_accuracy": 0.9821002259850502, |
| "step": 1519 |
| }, |
| { |
| "epoch": 8.89149560117302, |
| "grad_norm": 0.24670531669936663, |
| "learning_rate": 5.048058988861455e-06, |
| "loss": 0.0573, |
| "mean_token_accuracy": 0.9818818718194962, |
| "step": 1520 |
| }, |
| { |
| "epoch": 8.897360703812316, |
| "grad_norm": 0.21141946255543642, |
| "learning_rate": 5.0365590055733715e-06, |
| "loss": 0.0535, |
| "mean_token_accuracy": 0.9837949275970459, |
| "step": 1521 |
| }, |
| { |
| "epoch": 8.903225806451612, |
| "grad_norm": 0.27230889518189605, |
| "learning_rate": 5.025120592725009e-06, |
| "loss": 0.0628, |
| "mean_token_accuracy": 0.9804145693778992, |
| "step": 1522 |
| }, |
| { |
| "epoch": 8.909090909090908, |
| "grad_norm": 0.2255957667866212, |
| "learning_rate": 5.013743791833187e-06, |
| "loss": 0.0595, |
| "mean_token_accuracy": 0.9818353727459908, |
| "step": 1523 |
| }, |
| { |
| "epoch": 8.914956011730204, |
| "grad_norm": 0.3038137068972412, |
| "learning_rate": 5.002428644191094e-06, |
| "loss": 0.0584, |
| "mean_token_accuracy": 0.9827196970582008, |
| "step": 1524 |
| }, |
| { |
| "epoch": 8.9208211143695, |
| "grad_norm": 0.3100553005258722, |
| "learning_rate": 4.991175190868148e-06, |
| "loss": 0.0591, |
| "mean_token_accuracy": 0.9823226183652878, |
| "step": 1525 |
| }, |
| { |
| "epoch": 8.926686217008797, |
| "grad_norm": 0.22422743936182463, |
| "learning_rate": 4.9799834727098415e-06, |
| "loss": 0.0527, |
| "mean_token_accuracy": 0.9827243983745575, |
| "step": 1526 |
| }, |
| { |
| "epoch": 8.932551319648093, |
| "grad_norm": 0.263359825362434, |
| "learning_rate": 4.968853530337587e-06, |
| "loss": 0.0599, |
| "mean_token_accuracy": 0.981306865811348, |
| "step": 1527 |
| }, |
| { |
| "epoch": 8.93841642228739, |
| "grad_norm": 0.19382255427509223, |
| "learning_rate": 4.957785404148585e-06, |
| "loss": 0.0499, |
| "mean_token_accuracy": 0.9806587025523186, |
| "step": 1528 |
| }, |
| { |
| "epoch": 8.944281524926687, |
| "grad_norm": 0.25528185564658207, |
| "learning_rate": 4.946779134315662e-06, |
| "loss": 0.0628, |
| "mean_token_accuracy": 0.9796261489391327, |
| "step": 1529 |
| }, |
| { |
| "epoch": 8.950146627565982, |
| "grad_norm": 0.3398157063816798, |
| "learning_rate": 4.935834760787133e-06, |
| "loss": 0.0583, |
| "mean_token_accuracy": 0.9820915162563324, |
| "step": 1530 |
| }, |
| { |
| "epoch": 8.95601173020528, |
| "grad_norm": 0.2587597902562318, |
| "learning_rate": 4.924952323286651e-06, |
| "loss": 0.0585, |
| "mean_token_accuracy": 0.9807931408286095, |
| "step": 1531 |
| }, |
| { |
| "epoch": 8.961876832844574, |
| "grad_norm": 0.24341885443424222, |
| "learning_rate": 4.91413186131307e-06, |
| "loss": 0.0581, |
| "mean_token_accuracy": 0.9816311299800873, |
| "step": 1532 |
| }, |
| { |
| "epoch": 8.967741935483872, |
| "grad_norm": 0.23486359475035062, |
| "learning_rate": 4.9033734141402964e-06, |
| "loss": 0.0584, |
| "mean_token_accuracy": 0.9809052050113678, |
| "step": 1533 |
| }, |
| { |
| "epoch": 8.973607038123166, |
| "grad_norm": 0.21784879087173917, |
| "learning_rate": 4.892677020817151e-06, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.980447068810463, |
| "step": 1534 |
| }, |
| { |
| "epoch": 8.979472140762464, |
| "grad_norm": 0.3280892494362136, |
| "learning_rate": 4.8820427201672195e-06, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9797915667295456, |
| "step": 1535 |
| }, |
| { |
| "epoch": 8.985337243401759, |
| "grad_norm": 0.25362092329151553, |
| "learning_rate": 4.871470550788717e-06, |
| "loss": 0.064, |
| "mean_token_accuracy": 0.9781641364097595, |
| "step": 1536 |
| }, |
| { |
| "epoch": 8.991202346041057, |
| "grad_norm": 0.23260324944709893, |
| "learning_rate": 4.860960551054352e-06, |
| "loss": 0.0582, |
| "mean_token_accuracy": 0.9819280281662941, |
| "step": 1537 |
| }, |
| { |
| "epoch": 8.997067448680351, |
| "grad_norm": 0.2142235937949736, |
| "learning_rate": 4.850512759111177e-06, |
| "loss": 0.0566, |
| "mean_token_accuracy": 0.980823814868927, |
| "step": 1538 |
| }, |
| { |
| "epoch": 9.0, |
| "grad_norm": 0.2142235937949736, |
| "learning_rate": 4.840127212880457e-06, |
| "loss": 0.0498, |
| "mean_token_accuracy": 0.9837545901536942, |
| "step": 1539 |
| }, |
| { |
| "epoch": 9.005865102639296, |
| "grad_norm": 0.3027656081008066, |
| "learning_rate": 4.82980395005753e-06, |
| "loss": 0.0544, |
| "mean_token_accuracy": 0.983098641037941, |
| "step": 1540 |
| }, |
| { |
| "epoch": 9.011730205278592, |
| "grad_norm": 0.2411809393362278, |
| "learning_rate": 4.8195430081116715e-06, |
| "loss": 0.0573, |
| "mean_token_accuracy": 0.9815821573138237, |
| "step": 1541 |
| }, |
| { |
| "epoch": 9.017595307917889, |
| "grad_norm": 0.23641839942255174, |
| "learning_rate": 4.809344424285959e-06, |
| "loss": 0.0476, |
| "mean_token_accuracy": 0.9846600145101547, |
| "step": 1542 |
| }, |
| { |
| "epoch": 9.023460410557185, |
| "grad_norm": 0.23003438448199545, |
| "learning_rate": 4.799208235597129e-06, |
| "loss": 0.0582, |
| "mean_token_accuracy": 0.9806374609470367, |
| "step": 1543 |
| }, |
| { |
| "epoch": 9.029325513196481, |
| "grad_norm": 0.23956336736168363, |
| "learning_rate": 4.7891344788354535e-06, |
| "loss": 0.056, |
| "mean_token_accuracy": 0.9814530238509178, |
| "step": 1544 |
| }, |
| { |
| "epoch": 9.035190615835777, |
| "grad_norm": 0.23610643970912315, |
| "learning_rate": 4.779123190564601e-06, |
| "loss": 0.0624, |
| "mean_token_accuracy": 0.9810673967003822, |
| "step": 1545 |
| }, |
| { |
| "epoch": 9.041055718475073, |
| "grad_norm": 0.22732253531742116, |
| "learning_rate": 4.769174407121508e-06, |
| "loss": 0.0518, |
| "mean_token_accuracy": 0.9831937104463577, |
| "step": 1546 |
| }, |
| { |
| "epoch": 9.04692082111437, |
| "grad_norm": 0.1962674139871125, |
| "learning_rate": 4.7592881646162336e-06, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.979876346886158, |
| "step": 1547 |
| }, |
| { |
| "epoch": 9.052785923753666, |
| "grad_norm": 0.2539982090762478, |
| "learning_rate": 4.749464498931852e-06, |
| "loss": 0.0461, |
| "mean_token_accuracy": 0.9838007912039757, |
| "step": 1548 |
| }, |
| { |
| "epoch": 9.058651026392962, |
| "grad_norm": 0.2087119802614843, |
| "learning_rate": 4.739703445724296e-06, |
| "loss": 0.0558, |
| "mean_token_accuracy": 0.9843602925539017, |
| "step": 1549 |
| }, |
| { |
| "epoch": 9.064516129032258, |
| "grad_norm": 0.329300231457707, |
| "learning_rate": 4.730005040422253e-06, |
| "loss": 0.0505, |
| "mean_token_accuracy": 0.9836215823888779, |
| "step": 1550 |
| }, |
| { |
| "epoch": 9.070381231671554, |
| "grad_norm": 0.22188010507420589, |
| "learning_rate": 4.720369318227014e-06, |
| "loss": 0.0496, |
| "mean_token_accuracy": 0.9835997819900513, |
| "step": 1551 |
| }, |
| { |
| "epoch": 9.07624633431085, |
| "grad_norm": 0.2046135402728503, |
| "learning_rate": 4.710796314112358e-06, |
| "loss": 0.0535, |
| "mean_token_accuracy": 0.9827775880694389, |
| "step": 1552 |
| }, |
| { |
| "epoch": 9.082111436950147, |
| "grad_norm": 0.22732327773733813, |
| "learning_rate": 4.701286062824425e-06, |
| "loss": 0.051, |
| "mean_token_accuracy": 0.9828957170248032, |
| "step": 1553 |
| }, |
| { |
| "epoch": 9.087976539589443, |
| "grad_norm": 0.242034790415479, |
| "learning_rate": 4.691838598881587e-06, |
| "loss": 0.0563, |
| "mean_token_accuracy": 0.9820270240306854, |
| "step": 1554 |
| }, |
| { |
| "epoch": 9.093841642228739, |
| "grad_norm": 0.20508126696203113, |
| "learning_rate": 4.68245395657432e-06, |
| "loss": 0.0518, |
| "mean_token_accuracy": 0.984300933778286, |
| "step": 1555 |
| }, |
| { |
| "epoch": 9.099706744868035, |
| "grad_norm": 0.20201114000920736, |
| "learning_rate": 4.673132169965089e-06, |
| "loss": 0.0516, |
| "mean_token_accuracy": 0.984064131975174, |
| "step": 1556 |
| }, |
| { |
| "epoch": 9.105571847507331, |
| "grad_norm": 0.18703109160266437, |
| "learning_rate": 4.663873272888212e-06, |
| "loss": 0.0475, |
| "mean_token_accuracy": 0.9858269169926643, |
| "step": 1557 |
| }, |
| { |
| "epoch": 9.111436950146627, |
| "grad_norm": 0.1948057279735745, |
| "learning_rate": 4.654677298949746e-06, |
| "loss": 0.0524, |
| "mean_token_accuracy": 0.9818159490823746, |
| "step": 1558 |
| }, |
| { |
| "epoch": 9.117302052785924, |
| "grad_norm": 0.2596533136977546, |
| "learning_rate": 4.645544281527362e-06, |
| "loss": 0.0547, |
| "mean_token_accuracy": 0.9818684533238411, |
| "step": 1559 |
| }, |
| { |
| "epoch": 9.12316715542522, |
| "grad_norm": 0.20182485325445904, |
| "learning_rate": 4.636474253770226e-06, |
| "loss": 0.0456, |
| "mean_token_accuracy": 0.9834398329257965, |
| "step": 1560 |
| }, |
| { |
| "epoch": 9.129032258064516, |
| "grad_norm": 0.21517039851897404, |
| "learning_rate": 4.627467248598876e-06, |
| "loss": 0.0532, |
| "mean_token_accuracy": 0.9830020219087601, |
| "step": 1561 |
| }, |
| { |
| "epoch": 9.134897360703812, |
| "grad_norm": 0.22131489560960235, |
| "learning_rate": 4.618523298705101e-06, |
| "loss": 0.0524, |
| "mean_token_accuracy": 0.98325315117836, |
| "step": 1562 |
| }, |
| { |
| "epoch": 9.140762463343108, |
| "grad_norm": 0.252039124629233, |
| "learning_rate": 4.609642436551828e-06, |
| "loss": 0.0516, |
| "mean_token_accuracy": 0.9828849211335182, |
| "step": 1563 |
| }, |
| { |
| "epoch": 9.146627565982405, |
| "grad_norm": 0.19354071592940614, |
| "learning_rate": 4.600824694373e-06, |
| "loss": 0.0482, |
| "mean_token_accuracy": 0.9855695217847824, |
| "step": 1564 |
| }, |
| { |
| "epoch": 9.1524926686217, |
| "grad_norm": 0.21751293046724127, |
| "learning_rate": 4.592070104173461e-06, |
| "loss": 0.0514, |
| "mean_token_accuracy": 0.9841759204864502, |
| "step": 1565 |
| }, |
| { |
| "epoch": 9.158357771260997, |
| "grad_norm": 0.20587402678942707, |
| "learning_rate": 4.583378697728835e-06, |
| "loss": 0.0527, |
| "mean_token_accuracy": 0.9819434061646461, |
| "step": 1566 |
| }, |
| { |
| "epoch": 9.164222873900293, |
| "grad_norm": 0.20305161489535564, |
| "learning_rate": 4.574750506585419e-06, |
| "loss": 0.0481, |
| "mean_token_accuracy": 0.9825012981891632, |
| "step": 1567 |
| }, |
| { |
| "epoch": 9.17008797653959, |
| "grad_norm": 0.235658681817122, |
| "learning_rate": 4.566185562060062e-06, |
| "loss": 0.0568, |
| "mean_token_accuracy": 0.9813750684261322, |
| "step": 1568 |
| }, |
| { |
| "epoch": 9.175953079178885, |
| "grad_norm": 0.23612311691624208, |
| "learning_rate": 4.557683895240052e-06, |
| "loss": 0.0568, |
| "mean_token_accuracy": 0.9832897707819939, |
| "step": 1569 |
| }, |
| { |
| "epoch": 9.181818181818182, |
| "grad_norm": 0.3283150789529255, |
| "learning_rate": 4.549245536983009e-06, |
| "loss": 0.0528, |
| "mean_token_accuracy": 0.9832657352089882, |
| "step": 1570 |
| }, |
| { |
| "epoch": 9.187683284457478, |
| "grad_norm": 0.2399360533000912, |
| "learning_rate": 4.540870517916765e-06, |
| "loss": 0.0525, |
| "mean_token_accuracy": 0.9828476384282112, |
| "step": 1571 |
| }, |
| { |
| "epoch": 9.193548387096774, |
| "grad_norm": 0.22784069298248552, |
| "learning_rate": 4.532558868439249e-06, |
| "loss": 0.0543, |
| "mean_token_accuracy": 0.9832234308123589, |
| "step": 1572 |
| }, |
| { |
| "epoch": 9.19941348973607, |
| "grad_norm": 0.2026105144234623, |
| "learning_rate": 4.524310618718403e-06, |
| "loss": 0.0517, |
| "mean_token_accuracy": 0.9834396690130234, |
| "step": 1573 |
| }, |
| { |
| "epoch": 9.205278592375366, |
| "grad_norm": 0.22618016171675648, |
| "learning_rate": 4.516125798692037e-06, |
| "loss": 0.0523, |
| "mean_token_accuracy": 0.9837358370423317, |
| "step": 1574 |
| }, |
| { |
| "epoch": 9.211143695014663, |
| "grad_norm": 0.23485766896731308, |
| "learning_rate": 4.508004438067742e-06, |
| "loss": 0.0568, |
| "mean_token_accuracy": 0.9811383709311485, |
| "step": 1575 |
| }, |
| { |
| "epoch": 9.217008797653959, |
| "grad_norm": 0.21454767504403688, |
| "learning_rate": 4.4999465663227785e-06, |
| "loss": 0.0494, |
| "mean_token_accuracy": 0.9843669608235359, |
| "step": 1576 |
| }, |
| { |
| "epoch": 9.222873900293255, |
| "grad_norm": 0.30069431080169556, |
| "learning_rate": 4.491952212703964e-06, |
| "loss": 0.055, |
| "mean_token_accuracy": 0.9814217612147331, |
| "step": 1577 |
| }, |
| { |
| "epoch": 9.228739002932551, |
| "grad_norm": 0.21290384341664184, |
| "learning_rate": 4.484021406227576e-06, |
| "loss": 0.0535, |
| "mean_token_accuracy": 0.9824668392539024, |
| "step": 1578 |
| }, |
| { |
| "epoch": 9.234604105571847, |
| "grad_norm": 0.2559674489279034, |
| "learning_rate": 4.476154175679239e-06, |
| "loss": 0.0569, |
| "mean_token_accuracy": 0.9815589785575867, |
| "step": 1579 |
| }, |
| { |
| "epoch": 9.240469208211143, |
| "grad_norm": 0.21187515075412042, |
| "learning_rate": 4.468350549613822e-06, |
| "loss": 0.0457, |
| "mean_token_accuracy": 0.9843628779053688, |
| "step": 1580 |
| }, |
| { |
| "epoch": 9.24633431085044, |
| "grad_norm": 0.2721970935911764, |
| "learning_rate": 4.460610556355333e-06, |
| "loss": 0.0578, |
| "mean_token_accuracy": 0.9794795215129852, |
| "step": 1581 |
| }, |
| { |
| "epoch": 9.252199413489736, |
| "grad_norm": 0.20751982847364947, |
| "learning_rate": 4.452934223996824e-06, |
| "loss": 0.0491, |
| "mean_token_accuracy": 0.9839389324188232, |
| "step": 1582 |
| }, |
| { |
| "epoch": 9.258064516129032, |
| "grad_norm": 0.3425707212666822, |
| "learning_rate": 4.445321580400281e-06, |
| "loss": 0.0518, |
| "mean_token_accuracy": 0.9814067259430885, |
| "step": 1583 |
| }, |
| { |
| "epoch": 9.263929618768328, |
| "grad_norm": 0.2169421398120668, |
| "learning_rate": 4.437772653196527e-06, |
| "loss": 0.0558, |
| "mean_token_accuracy": 0.9849090501666069, |
| "step": 1584 |
| }, |
| { |
| "epoch": 9.269794721407624, |
| "grad_norm": 0.2442231991992943, |
| "learning_rate": 4.430287469785118e-06, |
| "loss": 0.0639, |
| "mean_token_accuracy": 0.9791273474693298, |
| "step": 1585 |
| }, |
| { |
| "epoch": 9.27565982404692, |
| "grad_norm": 0.2636751350455331, |
| "learning_rate": 4.422866057334246e-06, |
| "loss": 0.0563, |
| "mean_token_accuracy": 0.9829349890351295, |
| "step": 1586 |
| }, |
| { |
| "epoch": 9.281524926686217, |
| "grad_norm": 0.22338220479863272, |
| "learning_rate": 4.415508442780642e-06, |
| "loss": 0.057, |
| "mean_token_accuracy": 0.9812466502189636, |
| "step": 1587 |
| }, |
| { |
| "epoch": 9.287390029325513, |
| "grad_norm": 0.2211547461370018, |
| "learning_rate": 4.408214652829473e-06, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9828761592507362, |
| "step": 1588 |
| }, |
| { |
| "epoch": 9.29325513196481, |
| "grad_norm": 0.19198791621262234, |
| "learning_rate": 4.400984713954253e-06, |
| "loss": 0.0444, |
| "mean_token_accuracy": 0.985915943980217, |
| "step": 1589 |
| }, |
| { |
| "epoch": 9.299120234604105, |
| "grad_norm": 0.21221727583615227, |
| "learning_rate": 4.39381865239674e-06, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9805979430675507, |
| "step": 1590 |
| }, |
| { |
| "epoch": 9.304985337243401, |
| "grad_norm": 0.24745045411421357, |
| "learning_rate": 4.386716494166842e-06, |
| "loss": 0.0566, |
| "mean_token_accuracy": 0.9807746484875679, |
| "step": 1591 |
| }, |
| { |
| "epoch": 9.310850439882698, |
| "grad_norm": 0.2576436309116627, |
| "learning_rate": 4.379678265042529e-06, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9808614030480385, |
| "step": 1592 |
| }, |
| { |
| "epoch": 9.316715542521994, |
| "grad_norm": 0.23874035411062744, |
| "learning_rate": 4.372703990569725e-06, |
| "loss": 0.0561, |
| "mean_token_accuracy": 0.9833986386656761, |
| "step": 1593 |
| }, |
| { |
| "epoch": 9.32258064516129, |
| "grad_norm": 0.23684781792614845, |
| "learning_rate": 4.365793696062231e-06, |
| "loss": 0.0575, |
| "mean_token_accuracy": 0.9813083857297897, |
| "step": 1594 |
| }, |
| { |
| "epoch": 9.328445747800586, |
| "grad_norm": 0.23172577740881103, |
| "learning_rate": 4.358947406601626e-06, |
| "loss": 0.0505, |
| "mean_token_accuracy": 0.9838670641183853, |
| "step": 1595 |
| }, |
| { |
| "epoch": 9.334310850439882, |
| "grad_norm": 0.32230792952388126, |
| "learning_rate": 4.352165147037177e-06, |
| "loss": 0.054, |
| "mean_token_accuracy": 0.9821716770529747, |
| "step": 1596 |
| }, |
| { |
| "epoch": 9.340175953079179, |
| "grad_norm": 0.22343750102594195, |
| "learning_rate": 4.345446941985741e-06, |
| "loss": 0.0507, |
| "mean_token_accuracy": 0.9818222150206566, |
| "step": 1597 |
| }, |
| { |
| "epoch": 9.346041055718475, |
| "grad_norm": 0.20437357064777317, |
| "learning_rate": 4.338792815831698e-06, |
| "loss": 0.0531, |
| "mean_token_accuracy": 0.9799600020051003, |
| "step": 1598 |
| }, |
| { |
| "epoch": 9.351906158357771, |
| "grad_norm": 0.3676726838740866, |
| "learning_rate": 4.332202792726832e-06, |
| "loss": 0.0602, |
| "mean_token_accuracy": 0.9805522412061691, |
| "step": 1599 |
| }, |
| { |
| "epoch": 9.357771260997067, |
| "grad_norm": 0.23353133360423867, |
| "learning_rate": 4.3256768965902684e-06, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.9794843345880508, |
| "step": 1600 |
| }, |
| { |
| "epoch": 9.363636363636363, |
| "grad_norm": 0.27706490550836466, |
| "learning_rate": 4.319215151108373e-06, |
| "loss": 0.066, |
| "mean_token_accuracy": 0.978282243013382, |
| "step": 1601 |
| }, |
| { |
| "epoch": 9.36950146627566, |
| "grad_norm": 0.23756310821917054, |
| "learning_rate": 4.312817579734673e-06, |
| "loss": 0.0527, |
| "mean_token_accuracy": 0.9850875586271286, |
| "step": 1602 |
| }, |
| { |
| "epoch": 9.375366568914956, |
| "grad_norm": 0.22823060889515634, |
| "learning_rate": 4.306484205689768e-06, |
| "loss": 0.0584, |
| "mean_token_accuracy": 0.9804537519812584, |
| "step": 1603 |
| }, |
| { |
| "epoch": 9.381231671554252, |
| "grad_norm": 0.22815559277400072, |
| "learning_rate": 4.300215051961248e-06, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.9819799065589905, |
| "step": 1604 |
| }, |
| { |
| "epoch": 9.387096774193548, |
| "grad_norm": 0.21826257691327555, |
| "learning_rate": 4.2940101413036115e-06, |
| "loss": 0.051, |
| "mean_token_accuracy": 0.9844619482755661, |
| "step": 1605 |
| }, |
| { |
| "epoch": 9.392961876832844, |
| "grad_norm": 0.2655912410779273, |
| "learning_rate": 4.287869496238174e-06, |
| "loss": 0.0606, |
| "mean_token_accuracy": 0.9803177416324615, |
| "step": 1606 |
| }, |
| { |
| "epoch": 9.39882697947214, |
| "grad_norm": 0.2083047435091801, |
| "learning_rate": 4.281793139053001e-06, |
| "loss": 0.0533, |
| "mean_token_accuracy": 0.9825778752565384, |
| "step": 1607 |
| }, |
| { |
| "epoch": 9.404692082111437, |
| "grad_norm": 0.22682792436802207, |
| "learning_rate": 4.275781091802811e-06, |
| "loss": 0.0675, |
| "mean_token_accuracy": 0.9798205196857452, |
| "step": 1608 |
| }, |
| { |
| "epoch": 9.410557184750733, |
| "grad_norm": 0.26954582422977497, |
| "learning_rate": 4.26983337630891e-06, |
| "loss": 0.0562, |
| "mean_token_accuracy": 0.9811637997627258, |
| "step": 1609 |
| }, |
| { |
| "epoch": 9.416422287390029, |
| "grad_norm": 0.2744435039549544, |
| "learning_rate": 4.263950014159103e-06, |
| "loss": 0.0586, |
| "mean_token_accuracy": 0.9808680191636086, |
| "step": 1610 |
| }, |
| { |
| "epoch": 9.422287390029325, |
| "grad_norm": 0.2074828213741738, |
| "learning_rate": 4.258131026707618e-06, |
| "loss": 0.0492, |
| "mean_token_accuracy": 0.9836182445287704, |
| "step": 1611 |
| }, |
| { |
| "epoch": 9.428152492668621, |
| "grad_norm": 0.21893167411728395, |
| "learning_rate": 4.2523764350750305e-06, |
| "loss": 0.0587, |
| "mean_token_accuracy": 0.9815453141927719, |
| "step": 1612 |
| }, |
| { |
| "epoch": 9.434017595307918, |
| "grad_norm": 0.20889606834325938, |
| "learning_rate": 4.246686260148179e-06, |
| "loss": 0.0529, |
| "mean_token_accuracy": 0.9829302057623863, |
| "step": 1613 |
| }, |
| { |
| "epoch": 9.439882697947214, |
| "grad_norm": 0.2541914199711263, |
| "learning_rate": 4.241060522580108e-06, |
| "loss": 0.065, |
| "mean_token_accuracy": 0.9794387221336365, |
| "step": 1614 |
| }, |
| { |
| "epoch": 9.44574780058651, |
| "grad_norm": 0.24296870473167126, |
| "learning_rate": 4.2354992427899674e-06, |
| "loss": 0.0513, |
| "mean_token_accuracy": 0.9835287109017372, |
| "step": 1615 |
| }, |
| { |
| "epoch": 9.451612903225806, |
| "grad_norm": 0.24498569083766547, |
| "learning_rate": 4.23000244096296e-06, |
| "loss": 0.0545, |
| "mean_token_accuracy": 0.981740228831768, |
| "step": 1616 |
| }, |
| { |
| "epoch": 9.457478005865102, |
| "grad_norm": 0.2085082101365372, |
| "learning_rate": 4.224570137050254e-06, |
| "loss": 0.0443, |
| "mean_token_accuracy": 0.9854484051465988, |
| "step": 1617 |
| }, |
| { |
| "epoch": 9.463343108504398, |
| "grad_norm": 0.19598121580283992, |
| "learning_rate": 4.219202350768919e-06, |
| "loss": 0.0545, |
| "mean_token_accuracy": 0.9815690070390701, |
| "step": 1618 |
| }, |
| { |
| "epoch": 9.469208211143695, |
| "grad_norm": 0.20469125288940168, |
| "learning_rate": 4.213899101601853e-06, |
| "loss": 0.0546, |
| "mean_token_accuracy": 0.9825413748621941, |
| "step": 1619 |
| }, |
| { |
| "epoch": 9.47507331378299, |
| "grad_norm": 0.2160546209456866, |
| "learning_rate": 4.208660408797708e-06, |
| "loss": 0.0546, |
| "mean_token_accuracy": 0.9825544431805611, |
| "step": 1620 |
| }, |
| { |
| "epoch": 9.480938416422287, |
| "grad_norm": 0.2126729448550127, |
| "learning_rate": 4.203486291370821e-06, |
| "loss": 0.0526, |
| "mean_token_accuracy": 0.9841529130935669, |
| "step": 1621 |
| }, |
| { |
| "epoch": 9.486803519061583, |
| "grad_norm": 0.24411839934891127, |
| "learning_rate": 4.198376768101149e-06, |
| "loss": 0.0627, |
| "mean_token_accuracy": 0.9811530858278275, |
| "step": 1622 |
| }, |
| { |
| "epoch": 9.49266862170088, |
| "grad_norm": 0.23545992883807737, |
| "learning_rate": 4.193331857534198e-06, |
| "loss": 0.0515, |
| "mean_token_accuracy": 0.9828750714659691, |
| "step": 1623 |
| }, |
| { |
| "epoch": 9.498533724340176, |
| "grad_norm": 0.2004862274519284, |
| "learning_rate": 4.188351577980961e-06, |
| "loss": 0.0486, |
| "mean_token_accuracy": 0.9842849373817444, |
| "step": 1624 |
| }, |
| { |
| "epoch": 9.504398826979472, |
| "grad_norm": 0.20266526447683697, |
| "learning_rate": 4.183435947517836e-06, |
| "loss": 0.0511, |
| "mean_token_accuracy": 0.9830767437815666, |
| "step": 1625 |
| }, |
| { |
| "epoch": 9.510263929618768, |
| "grad_norm": 0.19607531767878525, |
| "learning_rate": 4.178584983986575e-06, |
| "loss": 0.0457, |
| "mean_token_accuracy": 0.9845829010009766, |
| "step": 1626 |
| }, |
| { |
| "epoch": 9.516129032258064, |
| "grad_norm": 0.1831840832037411, |
| "learning_rate": 4.173798704994221e-06, |
| "loss": 0.0502, |
| "mean_token_accuracy": 0.984029233455658, |
| "step": 1627 |
| }, |
| { |
| "epoch": 9.52199413489736, |
| "grad_norm": 0.22600559226813188, |
| "learning_rate": 4.169077127913031e-06, |
| "loss": 0.0611, |
| "mean_token_accuracy": 0.9794282466173172, |
| "step": 1628 |
| }, |
| { |
| "epoch": 9.527859237536656, |
| "grad_norm": 0.26377141694821216, |
| "learning_rate": 4.164420269880422e-06, |
| "loss": 0.0541, |
| "mean_token_accuracy": 0.9801126793026924, |
| "step": 1629 |
| }, |
| { |
| "epoch": 9.533724340175953, |
| "grad_norm": 0.222192265353475, |
| "learning_rate": 4.159828147798914e-06, |
| "loss": 0.0502, |
| "mean_token_accuracy": 0.98480124771595, |
| "step": 1630 |
| }, |
| { |
| "epoch": 9.539589442815249, |
| "grad_norm": 0.19974100668537378, |
| "learning_rate": 4.155300778336047e-06, |
| "loss": 0.0541, |
| "mean_token_accuracy": 0.9811222404241562, |
| "step": 1631 |
| }, |
| { |
| "epoch": 9.545454545454545, |
| "grad_norm": 0.24575424610156923, |
| "learning_rate": 4.150838177924349e-06, |
| "loss": 0.0525, |
| "mean_token_accuracy": 0.9847328960895538, |
| "step": 1632 |
| }, |
| { |
| "epoch": 9.551319648093841, |
| "grad_norm": 0.19911462815470113, |
| "learning_rate": 4.146440362761256e-06, |
| "loss": 0.0539, |
| "mean_token_accuracy": 0.9825382307171822, |
| "step": 1633 |
| }, |
| { |
| "epoch": 9.557184750733137, |
| "grad_norm": 0.20741651683611387, |
| "learning_rate": 4.142107348809058e-06, |
| "loss": 0.0595, |
| "mean_token_accuracy": 0.9808006957173347, |
| "step": 1634 |
| }, |
| { |
| "epoch": 9.563049853372434, |
| "grad_norm": 0.2183255912044281, |
| "learning_rate": 4.1378391517948505e-06, |
| "loss": 0.0492, |
| "mean_token_accuracy": 0.9852641671895981, |
| "step": 1635 |
| }, |
| { |
| "epoch": 9.56891495601173, |
| "grad_norm": 0.20745898164282808, |
| "learning_rate": 4.1336357872104614e-06, |
| "loss": 0.0556, |
| "mean_token_accuracy": 0.983629435300827, |
| "step": 1636 |
| }, |
| { |
| "epoch": 9.574780058651026, |
| "grad_norm": 0.22035964377547398, |
| "learning_rate": 4.12949727031241e-06, |
| "loss": 0.0556, |
| "mean_token_accuracy": 0.9830387458205223, |
| "step": 1637 |
| }, |
| { |
| "epoch": 9.580645161290322, |
| "grad_norm": 0.24377604786682897, |
| "learning_rate": 4.125423616121837e-06, |
| "loss": 0.0509, |
| "mean_token_accuracy": 0.9837193712592125, |
| "step": 1638 |
| }, |
| { |
| "epoch": 9.586510263929618, |
| "grad_norm": 0.17631889494983286, |
| "learning_rate": 4.121414839424464e-06, |
| "loss": 0.0516, |
| "mean_token_accuracy": 0.9836119785904884, |
| "step": 1639 |
| }, |
| { |
| "epoch": 9.592375366568914, |
| "grad_norm": 0.2222094804818117, |
| "learning_rate": 4.117470954770529e-06, |
| "loss": 0.0576, |
| "mean_token_accuracy": 0.9822694733738899, |
| "step": 1640 |
| }, |
| { |
| "epoch": 9.59824046920821, |
| "grad_norm": 0.17607834866947364, |
| "learning_rate": 4.1135919764747454e-06, |
| "loss": 0.0496, |
| "mean_token_accuracy": 0.9828854873776436, |
| "step": 1641 |
| }, |
| { |
| "epoch": 9.604105571847507, |
| "grad_norm": 0.19893350799495865, |
| "learning_rate": 4.109777918616235e-06, |
| "loss": 0.0557, |
| "mean_token_accuracy": 0.9839456379413605, |
| "step": 1642 |
| }, |
| { |
| "epoch": 9.609970674486803, |
| "grad_norm": 0.21733849157484478, |
| "learning_rate": 4.106028795038487e-06, |
| "loss": 0.0569, |
| "mean_token_accuracy": 0.9807590320706367, |
| "step": 1643 |
| }, |
| { |
| "epoch": 9.6158357771261, |
| "grad_norm": 0.2568971208282156, |
| "learning_rate": 4.102344619349307e-06, |
| "loss": 0.065, |
| "mean_token_accuracy": 0.9786679521203041, |
| "step": 1644 |
| }, |
| { |
| "epoch": 9.621700879765395, |
| "grad_norm": 0.2360837765560061, |
| "learning_rate": 4.098725404920763e-06, |
| "loss": 0.0621, |
| "mean_token_accuracy": 0.9808361381292343, |
| "step": 1645 |
| }, |
| { |
| "epoch": 9.627565982404692, |
| "grad_norm": 0.2611634274793871, |
| "learning_rate": 4.095171164889143e-06, |
| "loss": 0.0536, |
| "mean_token_accuracy": 0.9824008718132973, |
| "step": 1646 |
| }, |
| { |
| "epoch": 9.633431085043988, |
| "grad_norm": 0.21117695398237793, |
| "learning_rate": 4.091681912154903e-06, |
| "loss": 0.0545, |
| "mean_token_accuracy": 0.9811904802918434, |
| "step": 1647 |
| }, |
| { |
| "epoch": 9.639296187683284, |
| "grad_norm": 0.2557544201554423, |
| "learning_rate": 4.088257659382619e-06, |
| "loss": 0.069, |
| "mean_token_accuracy": 0.9788208901882172, |
| "step": 1648 |
| }, |
| { |
| "epoch": 9.64516129032258, |
| "grad_norm": 0.2513606648386977, |
| "learning_rate": 4.0848984190009495e-06, |
| "loss": 0.06, |
| "mean_token_accuracy": 0.9795089364051819, |
| "step": 1649 |
| }, |
| { |
| "epoch": 9.651026392961876, |
| "grad_norm": 0.18464453228546868, |
| "learning_rate": 4.081604203202577e-06, |
| "loss": 0.0473, |
| "mean_token_accuracy": 0.985549159348011, |
| "step": 1650 |
| }, |
| { |
| "epoch": 9.656891495601172, |
| "grad_norm": 0.18744575277483974, |
| "learning_rate": 4.078375023944175e-06, |
| "loss": 0.053, |
| "mean_token_accuracy": 0.983508974313736, |
| "step": 1651 |
| }, |
| { |
| "epoch": 9.662756598240469, |
| "grad_norm": 0.2210808736941966, |
| "learning_rate": 4.0752108929463625e-06, |
| "loss": 0.0615, |
| "mean_token_accuracy": 0.9779364317655563, |
| "step": 1652 |
| }, |
| { |
| "epoch": 9.668621700879765, |
| "grad_norm": 0.2443414624296323, |
| "learning_rate": 4.072111821693655e-06, |
| "loss": 0.0579, |
| "mean_token_accuracy": 0.9824973717331886, |
| "step": 1653 |
| }, |
| { |
| "epoch": 9.674486803519061, |
| "grad_norm": 0.22949116375142498, |
| "learning_rate": 4.069077821434429e-06, |
| "loss": 0.06, |
| "mean_token_accuracy": 0.9825471565127373, |
| "step": 1654 |
| }, |
| { |
| "epoch": 9.680351906158357, |
| "grad_norm": 0.2321839216945802, |
| "learning_rate": 4.06610890318088e-06, |
| "loss": 0.0513, |
| "mean_token_accuracy": 0.9831982627511024, |
| "step": 1655 |
| }, |
| { |
| "epoch": 9.686217008797653, |
| "grad_norm": 0.17846779813822697, |
| "learning_rate": 4.063205077708986e-06, |
| "loss": 0.0515, |
| "mean_token_accuracy": 0.984035462141037, |
| "step": 1656 |
| }, |
| { |
| "epoch": 9.69208211143695, |
| "grad_norm": 0.26334148518013256, |
| "learning_rate": 4.060366355558456e-06, |
| "loss": 0.057, |
| "mean_token_accuracy": 0.9798618927598, |
| "step": 1657 |
| }, |
| { |
| "epoch": 9.697947214076246, |
| "grad_norm": 0.22995803605804366, |
| "learning_rate": 4.057592747032707e-06, |
| "loss": 0.0672, |
| "mean_token_accuracy": 0.9782466292381287, |
| "step": 1658 |
| }, |
| { |
| "epoch": 9.703812316715542, |
| "grad_norm": 0.2818986728639512, |
| "learning_rate": 4.054884262198816e-06, |
| "loss": 0.0484, |
| "mean_token_accuracy": 0.982783667743206, |
| "step": 1659 |
| }, |
| { |
| "epoch": 9.709677419354838, |
| "grad_norm": 0.18386103736306297, |
| "learning_rate": 4.052240910887493e-06, |
| "loss": 0.0526, |
| "mean_token_accuracy": 0.984276570379734, |
| "step": 1660 |
| }, |
| { |
| "epoch": 9.715542521994134, |
| "grad_norm": 0.2116890836344024, |
| "learning_rate": 4.049662702693031e-06, |
| "loss": 0.0525, |
| "mean_token_accuracy": 0.9818199425935745, |
| "step": 1661 |
| }, |
| { |
| "epoch": 9.72140762463343, |
| "grad_norm": 0.21630284866054866, |
| "learning_rate": 4.047149646973288e-06, |
| "loss": 0.0542, |
| "mean_token_accuracy": 0.9806619063019753, |
| "step": 1662 |
| }, |
| { |
| "epoch": 9.727272727272727, |
| "grad_norm": 0.21371977729637454, |
| "learning_rate": 4.044701752849639e-06, |
| "loss": 0.0517, |
| "mean_token_accuracy": 0.9830491915345192, |
| "step": 1663 |
| }, |
| { |
| "epoch": 9.733137829912023, |
| "grad_norm": 0.19545948640696634, |
| "learning_rate": 4.042319029206954e-06, |
| "loss": 0.0497, |
| "mean_token_accuracy": 0.9841062873601913, |
| "step": 1664 |
| }, |
| { |
| "epoch": 9.739002932551319, |
| "grad_norm": 0.19578503009417925, |
| "learning_rate": 4.040001484693553e-06, |
| "loss": 0.0489, |
| "mean_token_accuracy": 0.9841093346476555, |
| "step": 1665 |
| }, |
| { |
| "epoch": 9.744868035190615, |
| "grad_norm": 0.2371983315755813, |
| "learning_rate": 4.037749127721191e-06, |
| "loss": 0.053, |
| "mean_token_accuracy": 0.9833494052290916, |
| "step": 1666 |
| }, |
| { |
| "epoch": 9.750733137829911, |
| "grad_norm": 0.19259742429604967, |
| "learning_rate": 4.03556196646501e-06, |
| "loss": 0.0496, |
| "mean_token_accuracy": 0.9846142753958702, |
| "step": 1667 |
| }, |
| { |
| "epoch": 9.756598240469208, |
| "grad_norm": 0.22286796311809612, |
| "learning_rate": 4.033440008863528e-06, |
| "loss": 0.0594, |
| "mean_token_accuracy": 0.9808065742254257, |
| "step": 1668 |
| }, |
| { |
| "epoch": 9.762463343108504, |
| "grad_norm": 0.22025704687640948, |
| "learning_rate": 4.031383262618588e-06, |
| "loss": 0.0595, |
| "mean_token_accuracy": 0.9809862375259399, |
| "step": 1669 |
| }, |
| { |
| "epoch": 9.7683284457478, |
| "grad_norm": 0.24252690715905784, |
| "learning_rate": 4.0293917351953505e-06, |
| "loss": 0.0548, |
| "mean_token_accuracy": 0.9827341809868813, |
| "step": 1670 |
| }, |
| { |
| "epoch": 9.774193548387096, |
| "grad_norm": 0.20870009759134936, |
| "learning_rate": 4.027465433822255e-06, |
| "loss": 0.0505, |
| "mean_token_accuracy": 0.9823991134762764, |
| "step": 1671 |
| }, |
| { |
| "epoch": 9.780058651026392, |
| "grad_norm": 0.21778727564935893, |
| "learning_rate": 4.025604365490999e-06, |
| "loss": 0.0533, |
| "mean_token_accuracy": 0.9838661327958107, |
| "step": 1672 |
| }, |
| { |
| "epoch": 9.785923753665688, |
| "grad_norm": 0.20561112970775772, |
| "learning_rate": 4.0238085369565085e-06, |
| "loss": 0.0531, |
| "mean_token_accuracy": 0.9828332811594009, |
| "step": 1673 |
| }, |
| { |
| "epoch": 9.791788856304985, |
| "grad_norm": 0.18298749159069347, |
| "learning_rate": 4.022077954736916e-06, |
| "loss": 0.0529, |
| "mean_token_accuracy": 0.9837350472807884, |
| "step": 1674 |
| }, |
| { |
| "epoch": 9.79765395894428, |
| "grad_norm": 0.23044165771776254, |
| "learning_rate": 4.020412625113535e-06, |
| "loss": 0.0531, |
| "mean_token_accuracy": 0.9837679117918015, |
| "step": 1675 |
| }, |
| { |
| "epoch": 9.803519061583577, |
| "grad_norm": 0.22929050117194524, |
| "learning_rate": 4.018812554130839e-06, |
| "loss": 0.0642, |
| "mean_token_accuracy": 0.9814090430736542, |
| "step": 1676 |
| }, |
| { |
| "epoch": 9.809384164222873, |
| "grad_norm": 0.24258828305446048, |
| "learning_rate": 4.01727774759644e-06, |
| "loss": 0.0579, |
| "mean_token_accuracy": 0.9815564751625061, |
| "step": 1677 |
| }, |
| { |
| "epoch": 9.81524926686217, |
| "grad_norm": 0.25774821859783087, |
| "learning_rate": 4.0158082110810695e-06, |
| "loss": 0.0522, |
| "mean_token_accuracy": 0.9827143624424934, |
| "step": 1678 |
| }, |
| { |
| "epoch": 9.821114369501466, |
| "grad_norm": 0.22573904277170584, |
| "learning_rate": 4.014403949918545e-06, |
| "loss": 0.0527, |
| "mean_token_accuracy": 0.9831245169043541, |
| "step": 1679 |
| }, |
| { |
| "epoch": 9.826979472140762, |
| "grad_norm": 0.22468139839540996, |
| "learning_rate": 4.0130649692057715e-06, |
| "loss": 0.0564, |
| "mean_token_accuracy": 0.9813647791743279, |
| "step": 1680 |
| }, |
| { |
| "epoch": 9.832844574780058, |
| "grad_norm": 0.22674431582862384, |
| "learning_rate": 4.01179127380271e-06, |
| "loss": 0.0601, |
| "mean_token_accuracy": 0.9805619269609451, |
| "step": 1681 |
| }, |
| { |
| "epoch": 9.838709677419354, |
| "grad_norm": 0.24116266207619552, |
| "learning_rate": 4.010582868332353e-06, |
| "loss": 0.0479, |
| "mean_token_accuracy": 0.9846414774656296, |
| "step": 1682 |
| }, |
| { |
| "epoch": 9.84457478005865, |
| "grad_norm": 0.2480489468253077, |
| "learning_rate": 4.009439757180732e-06, |
| "loss": 0.0554, |
| "mean_token_accuracy": 0.9797031283378601, |
| "step": 1683 |
| }, |
| { |
| "epoch": 9.850439882697946, |
| "grad_norm": 0.2612134501490512, |
| "learning_rate": 4.008361944496875e-06, |
| "loss": 0.0554, |
| "mean_token_accuracy": 0.981481671333313, |
| "step": 1684 |
| }, |
| { |
| "epoch": 9.856304985337243, |
| "grad_norm": 0.2626478258672696, |
| "learning_rate": 4.00734943419281e-06, |
| "loss": 0.0633, |
| "mean_token_accuracy": 0.9795757532119751, |
| "step": 1685 |
| }, |
| { |
| "epoch": 9.862170087976539, |
| "grad_norm": 0.25961503347240517, |
| "learning_rate": 4.006402229943534e-06, |
| "loss": 0.0571, |
| "mean_token_accuracy": 0.9808043912053108, |
| "step": 1686 |
| }, |
| { |
| "epoch": 9.868035190615835, |
| "grad_norm": 0.20225098537745445, |
| "learning_rate": 4.005520335187023e-06, |
| "loss": 0.0571, |
| "mean_token_accuracy": 0.9823412969708443, |
| "step": 1687 |
| }, |
| { |
| "epoch": 9.873900293255131, |
| "grad_norm": 0.24773203659800125, |
| "learning_rate": 4.004703753124195e-06, |
| "loss": 0.058, |
| "mean_token_accuracy": 0.9820492267608643, |
| "step": 1688 |
| }, |
| { |
| "epoch": 9.879765395894427, |
| "grad_norm": 0.19402283681662774, |
| "learning_rate": 4.003952486718913e-06, |
| "loss": 0.0495, |
| "mean_token_accuracy": 0.9836301207542419, |
| "step": 1689 |
| }, |
| { |
| "epoch": 9.885630498533724, |
| "grad_norm": 0.20474303626023752, |
| "learning_rate": 4.003266538697973e-06, |
| "loss": 0.0533, |
| "mean_token_accuracy": 0.9827889949083328, |
| "step": 1690 |
| }, |
| { |
| "epoch": 9.89149560117302, |
| "grad_norm": 0.21002275948618682, |
| "learning_rate": 4.002645911551086e-06, |
| "loss": 0.0494, |
| "mean_token_accuracy": 0.9827375486493111, |
| "step": 1691 |
| }, |
| { |
| "epoch": 9.897360703812316, |
| "grad_norm": 0.1929295301975364, |
| "learning_rate": 4.002090607530882e-06, |
| "loss": 0.0549, |
| "mean_token_accuracy": 0.9815536439418793, |
| "step": 1692 |
| }, |
| { |
| "epoch": 9.903225806451612, |
| "grad_norm": 0.23064941531004654, |
| "learning_rate": 4.001600628652887e-06, |
| "loss": 0.0648, |
| "mean_token_accuracy": 0.9779929518699646, |
| "step": 1693 |
| }, |
| { |
| "epoch": 9.909090909090908, |
| "grad_norm": 0.43219738924036005, |
| "learning_rate": 4.001175976695527e-06, |
| "loss": 0.0601, |
| "mean_token_accuracy": 0.9785007312893867, |
| "step": 1694 |
| }, |
| { |
| "epoch": 9.914956011730204, |
| "grad_norm": 0.21205310141711015, |
| "learning_rate": 4.000816653200117e-06, |
| "loss": 0.0474, |
| "mean_token_accuracy": 0.986022487282753, |
| "step": 1695 |
| }, |
| { |
| "epoch": 9.9208211143695, |
| "grad_norm": 0.22338455794977216, |
| "learning_rate": 4.000522659470857e-06, |
| "loss": 0.0532, |
| "mean_token_accuracy": 0.9828405454754829, |
| "step": 1696 |
| }, |
| { |
| "epoch": 9.926686217008797, |
| "grad_norm": 0.27487995501734275, |
| "learning_rate": 4.000293996574826e-06, |
| "loss": 0.0671, |
| "mean_token_accuracy": 0.9787180423736572, |
| "step": 1697 |
| }, |
| { |
| "epoch": 9.932551319648093, |
| "grad_norm": 0.2502076477797535, |
| "learning_rate": 4.000130665341977e-06, |
| "loss": 0.0645, |
| "mean_token_accuracy": 0.9796425253152847, |
| "step": 1698 |
| }, |
| { |
| "epoch": 9.93841642228739, |
| "grad_norm": 0.23598585484626972, |
| "learning_rate": 4.000032666365136e-06, |
| "loss": 0.0522, |
| "mean_token_accuracy": 0.9837642535567284, |
| "step": 1699 |
| }, |
| { |
| "epoch": 9.944281524926687, |
| "grad_norm": 0.22474153991468065, |
| "learning_rate": 4.000000000000001e-06, |
| "loss": 0.0534, |
| "mean_token_accuracy": 0.9821964651346207, |
| "step": 1700 |
| }, |
| { |
| "epoch": 9.944281524926687, |
| "step": 1700, |
| "total_flos": 15136392560640.0, |
| "train_loss": 0.18609273691826006, |
| "train_runtime": 35924.8672, |
| "train_samples_per_second": 1.518, |
| "train_steps_per_second": 0.047 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 1700, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 10, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 15136392560640.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
