Training in progress, step 16000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 469337272
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afdb578d15df2a00bc32ac072285dcbcb069d3c9c5460861f886475efcd85164
|
| 3 |
size 469337272
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 938825803
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:267768100da374098cbc48ba8a341f59f95d2cdcc9d105034ef525f3293cf20d
|
| 3 |
size 938825803
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cbf49dc033886911a7348f81ce5fce24d65e1323060b1506778655086bd9a64
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cf800c433ec0091a4dde726685b2353c8f62332779c346afea00191f732952f
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 1000,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -944,6 +944,318 @@
|
|
| 944 |
"eval_samples_per_second": 84.026,
|
| 945 |
"eval_steps_per_second": 21.006,
|
| 946 |
"step": 12000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 947 |
}
|
| 948 |
],
|
| 949 |
"logging_steps": 100,
|
|
@@ -963,7 +1275,7 @@
|
|
| 963 |
"attributes": {}
|
| 964 |
}
|
| 965 |
},
|
| 966 |
-
"total_flos":
|
| 967 |
"train_batch_size": 22,
|
| 968 |
"trial_name": null,
|
| 969 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.14545454545454545,
|
| 6 |
"eval_steps": 1000,
|
| 7 |
+
"global_step": 16000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 944 |
"eval_samples_per_second": 84.026,
|
| 945 |
"eval_steps_per_second": 21.006,
|
| 946 |
"step": 12000
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.11,
|
| 950 |
+
"grad_norm": 0.16330398619174957,
|
| 951 |
+
"learning_rate": 0.0009710883898021361,
|
| 952 |
+
"loss": 2.98108154296875,
|
| 953 |
+
"step": 12100
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.11090909090909092,
|
| 957 |
+
"grad_norm": 0.16032378375530243,
|
| 958 |
+
"learning_rate": 0.0009706072655731501,
|
| 959 |
+
"loss": 2.975714111328125,
|
| 960 |
+
"step": 12200
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.11181818181818182,
|
| 964 |
+
"grad_norm": 0.15098635852336884,
|
| 965 |
+
"learning_rate": 0.00097012229225515,
|
| 966 |
+
"loss": 2.967715148925781,
|
| 967 |
+
"step": 12300
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 0.11272727272727273,
|
| 971 |
+
"grad_norm": 0.16129878163337708,
|
| 972 |
+
"learning_rate": 0.0009696334738147246,
|
| 973 |
+
"loss": 2.9537789916992185,
|
| 974 |
+
"step": 12400
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.11363636363636363,
|
| 978 |
+
"grad_norm": 0.1677810102701187,
|
| 979 |
+
"learning_rate": 0.0009691408142499116,
|
| 980 |
+
"loss": 2.9610797119140626,
|
| 981 |
+
"step": 12500
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.11454545454545455,
|
| 985 |
+
"grad_norm": 0.176312655210495,
|
| 986 |
+
"learning_rate": 0.0009686443175901656,
|
| 987 |
+
"loss": 3.0001925659179687,
|
| 988 |
+
"step": 12600
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 0.11545454545454545,
|
| 992 |
+
"grad_norm": 0.16458939015865326,
|
| 993 |
+
"learning_rate": 0.0009681439878963245,
|
| 994 |
+
"loss": 2.932486572265625,
|
| 995 |
+
"step": 12700
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 0.11636363636363636,
|
| 999 |
+
"grad_norm": 0.1687006801366806,
|
| 1000 |
+
"learning_rate": 0.0009676398292605766,
|
| 1001 |
+
"loss": 2.96806396484375,
|
| 1002 |
+
"step": 12800
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.11727272727272728,
|
| 1006 |
+
"grad_norm": 0.15523017942905426,
|
| 1007 |
+
"learning_rate": 0.0009671318458064269,
|
| 1008 |
+
"loss": 2.977980651855469,
|
| 1009 |
+
"step": 12900
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.11818181818181818,
|
| 1013 |
+
"grad_norm": 0.15686143934726715,
|
| 1014 |
+
"learning_rate": 0.0009666200416886638,
|
| 1015 |
+
"loss": 2.9614358520507813,
|
| 1016 |
+
"step": 13000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 0.11818181818181818,
|
| 1020 |
+
"eval_loss": 3.310213565826416,
|
| 1021 |
+
"eval_runtime": 6.7958,
|
| 1022 |
+
"eval_samples_per_second": 84.758,
|
| 1023 |
+
"eval_steps_per_second": 21.19,
|
| 1024 |
+
"step": 13000
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.1190909090909091,
|
| 1028 |
+
"grad_norm": 0.15569010376930237,
|
| 1029 |
+
"learning_rate": 0.0009661044210933246,
|
| 1030 |
+
"loss": 2.950162658691406,
|
| 1031 |
+
"step": 13100
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.12,
|
| 1035 |
+
"grad_norm": 0.15551169216632843,
|
| 1036 |
+
"learning_rate": 0.0009655849882376615,
|
| 1037 |
+
"loss": 2.9463400268554687,
|
| 1038 |
+
"step": 13200
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.12090909090909091,
|
| 1042 |
+
"grad_norm": 0.1576288491487503,
|
| 1043 |
+
"learning_rate": 0.0009650617473701073,
|
| 1044 |
+
"loss": 2.9366680908203127,
|
| 1045 |
+
"step": 13300
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.12181818181818181,
|
| 1049 |
+
"grad_norm": 0.16019435226917267,
|
| 1050 |
+
"learning_rate": 0.0009645347027702405,
|
| 1051 |
+
"loss": 2.9609390258789063,
|
| 1052 |
+
"step": 13400
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.12272727272727273,
|
| 1056 |
+
"grad_norm": 0.19406898319721222,
|
| 1057 |
+
"learning_rate": 0.0009640038587487499,
|
| 1058 |
+
"loss": 2.9381414794921876,
|
| 1059 |
+
"step": 13500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.12363636363636364,
|
| 1063 |
+
"grad_norm": 0.14867821335792542,
|
| 1064 |
+
"learning_rate": 0.0009634692196474001,
|
| 1065 |
+
"loss": 2.943419189453125,
|
| 1066 |
+
"step": 13600
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.12454545454545454,
|
| 1070 |
+
"grad_norm": 0.14702503383159637,
|
| 1071 |
+
"learning_rate": 0.0009629307898389953,
|
| 1072 |
+
"loss": 2.923211669921875,
|
| 1073 |
+
"step": 13700
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.12545454545454546,
|
| 1077 |
+
"grad_norm": 0.19858944416046143,
|
| 1078 |
+
"learning_rate": 0.0009623885737273442,
|
| 1079 |
+
"loss": 2.9624624633789063,
|
| 1080 |
+
"step": 13800
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.12636363636363637,
|
| 1084 |
+
"grad_norm": 0.15279068052768707,
|
| 1085 |
+
"learning_rate": 0.0009618425757472229,
|
| 1086 |
+
"loss": 2.9194540405273437,
|
| 1087 |
+
"step": 13900
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.12727272727272726,
|
| 1091 |
+
"grad_norm": 0.16745012998580933,
|
| 1092 |
+
"learning_rate": 0.0009612928003643404,
|
| 1093 |
+
"loss": 2.950616760253906,
|
| 1094 |
+
"step": 14000
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.12727272727272726,
|
| 1098 |
+
"eval_loss": 3.294524669647217,
|
| 1099 |
+
"eval_runtime": 6.7865,
|
| 1100 |
+
"eval_samples_per_second": 84.874,
|
| 1101 |
+
"eval_steps_per_second": 21.218,
|
| 1102 |
+
"step": 14000
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.12818181818181817,
|
| 1106 |
+
"grad_norm": 0.15464717149734497,
|
| 1107 |
+
"learning_rate": 0.0009607392520753,
|
| 1108 |
+
"loss": 2.936573791503906,
|
| 1109 |
+
"step": 14100
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.1290909090909091,
|
| 1113 |
+
"grad_norm": 0.17451342940330505,
|
| 1114 |
+
"learning_rate": 0.0009601819354075643,
|
| 1115 |
+
"loss": 2.9196566772460937,
|
| 1116 |
+
"step": 14200
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.13,
|
| 1120 |
+
"grad_norm": 0.15395045280456543,
|
| 1121 |
+
"learning_rate": 0.0009596208549194167,
|
| 1122 |
+
"loss": 2.9657086181640624,
|
| 1123 |
+
"step": 14300
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.13090909090909092,
|
| 1127 |
+
"grad_norm": 0.16990916430950165,
|
| 1128 |
+
"learning_rate": 0.0009590560151999256,
|
| 1129 |
+
"loss": 2.9283480834960938,
|
| 1130 |
+
"step": 14400
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.1318181818181818,
|
| 1134 |
+
"grad_norm": 0.14847813546657562,
|
| 1135 |
+
"learning_rate": 0.0009584874208689055,
|
| 1136 |
+
"loss": 2.9426678466796874,
|
| 1137 |
+
"step": 14500
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.13272727272727272,
|
| 1141 |
+
"grad_norm": 0.21499793231487274,
|
| 1142 |
+
"learning_rate": 0.00095791507657688,
|
| 1143 |
+
"loss": 2.9166836547851562,
|
| 1144 |
+
"step": 14600
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.13363636363636364,
|
| 1148 |
+
"grad_norm": 0.14092333614826202,
|
| 1149 |
+
"learning_rate": 0.0009573389870050435,
|
| 1150 |
+
"loss": 2.9289419555664065,
|
| 1151 |
+
"step": 14700
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.13454545454545455,
|
| 1155 |
+
"grad_norm": 0.15405072271823883,
|
| 1156 |
+
"learning_rate": 0.0009567591568652231,
|
| 1157 |
+
"loss": 2.9462161254882813,
|
| 1158 |
+
"step": 14800
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.13545454545454547,
|
| 1162 |
+
"grad_norm": 0.15389932692050934,
|
| 1163 |
+
"learning_rate": 0.00095617559089984,
|
| 1164 |
+
"loss": 2.9510357666015623,
|
| 1165 |
+
"step": 14900
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.13636363636363635,
|
| 1169 |
+
"grad_norm": 0.157777339220047,
|
| 1170 |
+
"learning_rate": 0.0009555882938818703,
|
| 1171 |
+
"loss": 2.9332815551757814,
|
| 1172 |
+
"step": 15000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.13636363636363635,
|
| 1176 |
+
"eval_loss": 3.2715365886688232,
|
| 1177 |
+
"eval_runtime": 6.8421,
|
| 1178 |
+
"eval_samples_per_second": 84.184,
|
| 1179 |
+
"eval_steps_per_second": 21.046,
|
| 1180 |
+
"step": 15000
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 0.13727272727272727,
|
| 1184 |
+
"grad_norm": 0.15498115122318268,
|
| 1185 |
+
"learning_rate": 0.0009549972706148067,
|
| 1186 |
+
"loss": 2.9289910888671873,
|
| 1187 |
+
"step": 15100
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 0.13818181818181818,
|
| 1191 |
+
"grad_norm": 0.17162440717220306,
|
| 1192 |
+
"learning_rate": 0.0009544025259326188,
|
| 1193 |
+
"loss": 2.9223281860351564,
|
| 1194 |
+
"step": 15200
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.1390909090909091,
|
| 1198 |
+
"grad_norm": 0.16399726271629333,
|
| 1199 |
+
"learning_rate": 0.0009538040646997133,
|
| 1200 |
+
"loss": 2.910879821777344,
|
| 1201 |
+
"step": 15300
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 0.14,
|
| 1205 |
+
"grad_norm": 0.20758388936519623,
|
| 1206 |
+
"learning_rate": 0.0009532018918108949,
|
| 1207 |
+
"loss": 2.9101876831054687,
|
| 1208 |
+
"step": 15400
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.1409090909090909,
|
| 1212 |
+
"grad_norm": 0.15389910340309143,
|
| 1213 |
+
"learning_rate": 0.0009525960121913253,
|
| 1214 |
+
"loss": 2.9736376953125,
|
| 1215 |
+
"step": 15500
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.14181818181818182,
|
| 1219 |
+
"grad_norm": 0.14939367771148682,
|
| 1220 |
+
"learning_rate": 0.0009519864307964842,
|
| 1221 |
+
"loss": 2.9354534912109376,
|
| 1222 |
+
"step": 15600
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 0.14272727272727273,
|
| 1226 |
+
"grad_norm": 0.18233561515808105,
|
| 1227 |
+
"learning_rate": 0.0009513731526121277,
|
| 1228 |
+
"loss": 2.9248681640625,
|
| 1229 |
+
"step": 15700
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.14363636363636365,
|
| 1233 |
+
"grad_norm": 0.16295863687992096,
|
| 1234 |
+
"learning_rate": 0.0009507561826542477,
|
| 1235 |
+
"loss": 2.92017578125,
|
| 1236 |
+
"step": 15800
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 0.14454545454545453,
|
| 1240 |
+
"grad_norm": 0.15371564030647278,
|
| 1241 |
+
"learning_rate": 0.0009501355259690314,
|
| 1242 |
+
"loss": 2.910662841796875,
|
| 1243 |
+
"step": 15900
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 0.14545454545454545,
|
| 1247 |
+
"grad_norm": 0.15596537292003632,
|
| 1248 |
+
"learning_rate": 0.0009495111876328195,
|
| 1249 |
+
"loss": 2.898775939941406,
|
| 1250 |
+
"step": 16000
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.14545454545454545,
|
| 1254 |
+
"eval_loss": 3.2674407958984375,
|
| 1255 |
+
"eval_runtime": 6.8454,
|
| 1256 |
+
"eval_samples_per_second": 84.143,
|
| 1257 |
+
"eval_steps_per_second": 21.036,
|
| 1258 |
+
"step": 16000
|
| 1259 |
}
|
| 1260 |
],
|
| 1261 |
"logging_steps": 100,
|
|
|
|
| 1275 |
"attributes": {}
|
| 1276 |
}
|
| 1277 |
},
|
| 1278 |
+
"total_flos": 3.98633295937536e+17,
|
| 1279 |
"train_batch_size": 22,
|
| 1280 |
"trial_name": null,
|
| 1281 |
"trial_params": null
|