Training in progress, step 1140
Browse files- last-checkpoint/{global_step857 → global_step1143}/mp_rank_00_model_states.pt +1 -1
- last-checkpoint/{global_step857 → global_step1143}/zero_pp_rank_0_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/{global_step857 → global_step1143}/zero_pp_rank_1_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/{global_step857 → global_step1143}/zero_pp_rank_2_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/{global_step857 → global_step1143}/zero_pp_rank_3_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/latest +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/trainer_state.json +345 -3
- pytorch_model.bin +1 -1
last-checkpoint/{global_step857 → global_step1143}/mp_rank_00_model_states.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5363072554
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b30eb2fb488eaec8a27bb0b26a171963d3112a31c76479ce8dfdd718e9567bf2
|
| 3 |
size 5363072554
|
last-checkpoint/{global_step857 → global_step1143}/zero_pp_rank_0_mp_rank_00_optim_states.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3946735038
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3e6445cc536442d208833ad59863f984bc71140490a8cd3e18575006fcdd4e1
|
| 3 |
size 3946735038
|
last-checkpoint/{global_step857 → global_step1143}/zero_pp_rank_1_mp_rank_00_optim_states.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3946736318
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11f87ca6a8d81d91ce9669ce0a0b132e16e31c589165b9dfc0f95bec607a1ce3
|
| 3 |
size 3946736318
|
last-checkpoint/{global_step857 → global_step1143}/zero_pp_rank_2_mp_rank_00_optim_states.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3946737086
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:076063a2d14362bcc0562f87c7d5497798acb4d6078c32ba220db1ed473f33c8
|
| 3 |
size 3946737086
|
last-checkpoint/{global_step857 → global_step1143}/zero_pp_rank_3_mp_rank_00_optim_states.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3946736574
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5e8189f9e1fe3d7e7bb628368a866880f0176b1f62f4c271d4ccf25c9e8e98a
|
| 3 |
size 3946736574
|
last-checkpoint/latest
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
global_step1143
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5363024236
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6d85bffffb2fe97ca10f0460ebc0b029a11e6d606ade9c54de58bcb6de72ec8
|
| 3 |
size 5363024236
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14583
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f6bc3b332b1d7b34dd8e7d7ed0389c868155059ddb1d908e9ac3feb6672b23c
|
| 3 |
size 14583
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14583
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8de5e0c7dadcd828a8d62fffc136e170202022509240a895985c7bc45cabbced
|
| 3 |
size 14583
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14583
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c420d12d8aa09a561480241f19154d4aedd8a866de54ed145d69f860bae6f94
|
| 3 |
size 14583
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14583
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec873fd7c31f869e7956f098c0d1e17d2296924b3c55e4971a059dd097690b6f
|
| 3 |
size 14583
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -1038,11 +1038,353 @@
|
|
| 1038 |
"learning_rate": 5e-05,
|
| 1039 |
"loss": 0.057,
|
| 1040 |
"step": 855
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1041 |
}
|
| 1042 |
],
|
| 1043 |
"max_steps": 1140,
|
| 1044 |
"num_train_epochs": 5,
|
| 1045 |
-
"total_flos":
|
| 1046 |
"trial_name": null,
|
| 1047 |
"trial_params": null
|
| 1048 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.996176952484981,
|
| 5 |
+
"global_step": 1140,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 1038 |
"learning_rate": 5e-05,
|
| 1039 |
"loss": 0.057,
|
| 1040 |
"step": 855
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 3.77,
|
| 1044 |
+
"learning_rate": 5e-05,
|
| 1045 |
+
"loss": 0.0539,
|
| 1046 |
+
"step": 860
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 3.79,
|
| 1050 |
+
"learning_rate": 5e-05,
|
| 1051 |
+
"loss": 0.0529,
|
| 1052 |
+
"step": 865
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.81,
|
| 1056 |
+
"learning_rate": 5e-05,
|
| 1057 |
+
"loss": 0.0552,
|
| 1058 |
+
"step": 870
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 3.83,
|
| 1062 |
+
"learning_rate": 5e-05,
|
| 1063 |
+
"loss": 0.0547,
|
| 1064 |
+
"step": 875
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 3.86,
|
| 1068 |
+
"learning_rate": 5e-05,
|
| 1069 |
+
"loss": 0.0553,
|
| 1070 |
+
"step": 880
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 3.88,
|
| 1074 |
+
"learning_rate": 5e-05,
|
| 1075 |
+
"loss": 0.0558,
|
| 1076 |
+
"step": 885
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 3.9,
|
| 1080 |
+
"learning_rate": 5e-05,
|
| 1081 |
+
"loss": 0.054,
|
| 1082 |
+
"step": 890
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 3.92,
|
| 1086 |
+
"learning_rate": 5e-05,
|
| 1087 |
+
"loss": 0.0549,
|
| 1088 |
+
"step": 895
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 3.94,
|
| 1092 |
+
"learning_rate": 5e-05,
|
| 1093 |
+
"loss": 0.0544,
|
| 1094 |
+
"step": 900
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 3.97,
|
| 1098 |
+
"learning_rate": 5e-05,
|
| 1099 |
+
"loss": 0.0558,
|
| 1100 |
+
"step": 905
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 3.99,
|
| 1104 |
+
"learning_rate": 5e-05,
|
| 1105 |
+
"loss": 0.0545,
|
| 1106 |
+
"step": 910
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 4.01,
|
| 1110 |
+
"learning_rate": 5e-05,
|
| 1111 |
+
"loss": 0.0604,
|
| 1112 |
+
"step": 915
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 4.03,
|
| 1116 |
+
"learning_rate": 5e-05,
|
| 1117 |
+
"loss": 0.0497,
|
| 1118 |
+
"step": 920
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 4.06,
|
| 1122 |
+
"learning_rate": 5e-05,
|
| 1123 |
+
"loss": 0.049,
|
| 1124 |
+
"step": 925
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 4.08,
|
| 1128 |
+
"learning_rate": 5e-05,
|
| 1129 |
+
"loss": 0.0488,
|
| 1130 |
+
"step": 930
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 4.1,
|
| 1134 |
+
"learning_rate": 5e-05,
|
| 1135 |
+
"loss": 0.0495,
|
| 1136 |
+
"step": 935
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 4.12,
|
| 1140 |
+
"learning_rate": 5e-05,
|
| 1141 |
+
"loss": 0.049,
|
| 1142 |
+
"step": 940
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 4.14,
|
| 1146 |
+
"learning_rate": 5e-05,
|
| 1147 |
+
"loss": 0.0502,
|
| 1148 |
+
"step": 945
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 4.17,
|
| 1152 |
+
"learning_rate": 5e-05,
|
| 1153 |
+
"loss": 0.0493,
|
| 1154 |
+
"step": 950
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 4.19,
|
| 1158 |
+
"learning_rate": 5e-05,
|
| 1159 |
+
"loss": 0.0496,
|
| 1160 |
+
"step": 955
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 4.21,
|
| 1164 |
+
"learning_rate": 5e-05,
|
| 1165 |
+
"loss": 0.0475,
|
| 1166 |
+
"step": 960
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 4.23,
|
| 1170 |
+
"learning_rate": 5e-05,
|
| 1171 |
+
"loss": 0.0486,
|
| 1172 |
+
"step": 965
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 4.25,
|
| 1176 |
+
"learning_rate": 5e-05,
|
| 1177 |
+
"loss": 0.0503,
|
| 1178 |
+
"step": 970
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 4.28,
|
| 1182 |
+
"learning_rate": 5e-05,
|
| 1183 |
+
"loss": 0.0508,
|
| 1184 |
+
"step": 975
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 4.3,
|
| 1188 |
+
"learning_rate": 5e-05,
|
| 1189 |
+
"loss": 0.0501,
|
| 1190 |
+
"step": 980
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 4.32,
|
| 1194 |
+
"learning_rate": 5e-05,
|
| 1195 |
+
"loss": 0.0499,
|
| 1196 |
+
"step": 985
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 4.34,
|
| 1200 |
+
"learning_rate": 5e-05,
|
| 1201 |
+
"loss": 0.0485,
|
| 1202 |
+
"step": 990
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 4.36,
|
| 1206 |
+
"learning_rate": 5e-05,
|
| 1207 |
+
"loss": 0.0494,
|
| 1208 |
+
"step": 995
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 4.38,
|
| 1212 |
+
"learning_rate": 5e-05,
|
| 1213 |
+
"loss": 0.0503,
|
| 1214 |
+
"step": 1000
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 4.41,
|
| 1218 |
+
"learning_rate": 5e-05,
|
| 1219 |
+
"loss": 0.0512,
|
| 1220 |
+
"step": 1005
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 4.43,
|
| 1224 |
+
"learning_rate": 5e-05,
|
| 1225 |
+
"loss": 0.0513,
|
| 1226 |
+
"step": 1010
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 4.45,
|
| 1230 |
+
"learning_rate": 5e-05,
|
| 1231 |
+
"loss": 0.0496,
|
| 1232 |
+
"step": 1015
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 4.47,
|
| 1236 |
+
"learning_rate": 5e-05,
|
| 1237 |
+
"loss": 0.0493,
|
| 1238 |
+
"step": 1020
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 4.49,
|
| 1242 |
+
"learning_rate": 5e-05,
|
| 1243 |
+
"loss": 0.0516,
|
| 1244 |
+
"step": 1025
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 4.52,
|
| 1248 |
+
"learning_rate": 5e-05,
|
| 1249 |
+
"loss": 0.0498,
|
| 1250 |
+
"step": 1030
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 4.54,
|
| 1254 |
+
"learning_rate": 5e-05,
|
| 1255 |
+
"loss": 0.0498,
|
| 1256 |
+
"step": 1035
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 4.56,
|
| 1260 |
+
"learning_rate": 5e-05,
|
| 1261 |
+
"loss": 0.0491,
|
| 1262 |
+
"step": 1040
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 4.58,
|
| 1266 |
+
"learning_rate": 5e-05,
|
| 1267 |
+
"loss": 0.047,
|
| 1268 |
+
"step": 1045
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 4.6,
|
| 1272 |
+
"learning_rate": 5e-05,
|
| 1273 |
+
"loss": 0.0493,
|
| 1274 |
+
"step": 1050
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 4.62,
|
| 1278 |
+
"learning_rate": 5e-05,
|
| 1279 |
+
"loss": 0.0488,
|
| 1280 |
+
"step": 1055
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 4.65,
|
| 1284 |
+
"learning_rate": 5e-05,
|
| 1285 |
+
"loss": 0.0502,
|
| 1286 |
+
"step": 1060
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 4.67,
|
| 1290 |
+
"learning_rate": 5e-05,
|
| 1291 |
+
"loss": 0.0511,
|
| 1292 |
+
"step": 1065
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 4.69,
|
| 1296 |
+
"learning_rate": 5e-05,
|
| 1297 |
+
"loss": 0.0498,
|
| 1298 |
+
"step": 1070
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 4.71,
|
| 1302 |
+
"learning_rate": 5e-05,
|
| 1303 |
+
"loss": 0.0511,
|
| 1304 |
+
"step": 1075
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 4.73,
|
| 1308 |
+
"learning_rate": 5e-05,
|
| 1309 |
+
"loss": 0.0498,
|
| 1310 |
+
"step": 1080
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 4.76,
|
| 1314 |
+
"learning_rate": 5e-05,
|
| 1315 |
+
"loss": 0.0521,
|
| 1316 |
+
"step": 1085
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 4.78,
|
| 1320 |
+
"learning_rate": 5e-05,
|
| 1321 |
+
"loss": 0.0503,
|
| 1322 |
+
"step": 1090
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 4.8,
|
| 1326 |
+
"learning_rate": 5e-05,
|
| 1327 |
+
"loss": 0.0509,
|
| 1328 |
+
"step": 1095
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 4.82,
|
| 1332 |
+
"learning_rate": 5e-05,
|
| 1333 |
+
"loss": 0.0523,
|
| 1334 |
+
"step": 1100
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 4.84,
|
| 1338 |
+
"learning_rate": 5e-05,
|
| 1339 |
+
"loss": 0.0465,
|
| 1340 |
+
"step": 1105
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 4.87,
|
| 1344 |
+
"learning_rate": 5e-05,
|
| 1345 |
+
"loss": 0.0521,
|
| 1346 |
+
"step": 1110
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 4.89,
|
| 1350 |
+
"learning_rate": 5e-05,
|
| 1351 |
+
"loss": 0.0488,
|
| 1352 |
+
"step": 1115
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 4.91,
|
| 1356 |
+
"learning_rate": 5e-05,
|
| 1357 |
+
"loss": 0.0488,
|
| 1358 |
+
"step": 1120
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 4.93,
|
| 1362 |
+
"learning_rate": 5e-05,
|
| 1363 |
+
"loss": 0.0502,
|
| 1364 |
+
"step": 1125
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 4.95,
|
| 1368 |
+
"learning_rate": 5e-05,
|
| 1369 |
+
"loss": 0.048,
|
| 1370 |
+
"step": 1130
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 4.97,
|
| 1374 |
+
"learning_rate": 5e-05,
|
| 1375 |
+
"loss": 0.0497,
|
| 1376 |
+
"step": 1135
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 5.0,
|
| 1380 |
+
"learning_rate": 5e-05,
|
| 1381 |
+
"loss": 0.0484,
|
| 1382 |
+
"step": 1140
|
| 1383 |
}
|
| 1384 |
],
|
| 1385 |
"max_steps": 1140,
|
| 1386 |
"num_train_epochs": 5,
|
| 1387 |
+
"total_flos": 8.693964764402942e+18,
|
| 1388 |
"trial_name": null,
|
| 1389 |
"trial_params": null
|
| 1390 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5363024236
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6d85bffffb2fe97ca10f0460ebc0b029a11e6d606ade9c54de58bcb6de72ec8
|
| 3 |
size 5363024236
|