Training in progress, step 228, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 501168482
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36c48e9709004b33bdbbd28b1e33adaa806cd06a26e1f4d1bf6b5fedd784f297
|
| 3 |
size 501168482
|
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 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc3893adf12779f0d48b1513b948863c9f74d5b80bf37fd6bb3d143cbfff91ec
|
| 3 |
size 14512
|
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 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce62f71c8c10d088ccc652695dd03a663736071fc2cab92e5639ffdddbd4c788
|
| 3 |
size 14512
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8b5a959d9459f2fc9422d29e6b89c56e276e4fcd74ca81bc84eb9dc629ceec0
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 76,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1095,6 +1095,546 @@
|
|
| 1095 |
"eval_samples_per_second": 3.934,
|
| 1096 |
"eval_steps_per_second": 0.984,
|
| 1097 |
"step": 152
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1098 |
}
|
| 1099 |
],
|
| 1100 |
"logging_steps": 1,
|
|
@@ -1114,7 +1654,7 @@
|
|
| 1114 |
"attributes": {}
|
| 1115 |
}
|
| 1116 |
},
|
| 1117 |
-
"total_flos": 1.
|
| 1118 |
"train_batch_size": 2,
|
| 1119 |
"trial_name": null,
|
| 1120 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.06933779365924124,
|
| 5 |
"eval_steps": 76,
|
| 6 |
+
"global_step": 228,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1095 |
"eval_samples_per_second": 3.934,
|
| 1096 |
"eval_steps_per_second": 0.984,
|
| 1097 |
"step": 152
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.04652930890291188,
|
| 1101 |
+
"grad_norm": NaN,
|
| 1102 |
+
"learning_rate": 0.00012876842744353112,
|
| 1103 |
+
"loss": 0.0,
|
| 1104 |
+
"step": 153
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.04683342203299627,
|
| 1108 |
+
"grad_norm": NaN,
|
| 1109 |
+
"learning_rate": 0.00012757699791343186,
|
| 1110 |
+
"loss": 0.0,
|
| 1111 |
+
"step": 154
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.04713753516308067,
|
| 1115 |
+
"grad_norm": NaN,
|
| 1116 |
+
"learning_rate": 0.0001263813163162364,
|
| 1117 |
+
"loss": 0.0,
|
| 1118 |
+
"step": 155
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.04744164829316506,
|
| 1122 |
+
"grad_norm": NaN,
|
| 1123 |
+
"learning_rate": 0.00012518156701278019,
|
| 1124 |
+
"loss": 0.0,
|
| 1125 |
+
"step": 156
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.04774576142324945,
|
| 1129 |
+
"grad_norm": NaN,
|
| 1130 |
+
"learning_rate": 0.00012397793499109404,
|
| 1131 |
+
"loss": 0.0,
|
| 1132 |
+
"step": 157
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.04804987455333384,
|
| 1136 |
+
"grad_norm": NaN,
|
| 1137 |
+
"learning_rate": 0.00012277060583788064,
|
| 1138 |
+
"loss": 0.0,
|
| 1139 |
+
"step": 158
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.04835398768341823,
|
| 1143 |
+
"grad_norm": NaN,
|
| 1144 |
+
"learning_rate": 0.00012155976570989949,
|
| 1145 |
+
"loss": 0.0,
|
| 1146 |
+
"step": 159
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.04865810081350262,
|
| 1150 |
+
"grad_norm": NaN,
|
| 1151 |
+
"learning_rate": 0.0001203456013052634,
|
| 1152 |
+
"loss": 0.0,
|
| 1153 |
+
"step": 160
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.04896221394358701,
|
| 1157 |
+
"grad_norm": NaN,
|
| 1158 |
+
"learning_rate": 0.00011912829983465168,
|
| 1159 |
+
"loss": 0.0,
|
| 1160 |
+
"step": 161
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.04926632707367141,
|
| 1164 |
+
"grad_norm": NaN,
|
| 1165 |
+
"learning_rate": 0.00011790804899244452,
|
| 1166 |
+
"loss": 0.0,
|
| 1167 |
+
"step": 162
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.0495704402037558,
|
| 1171 |
+
"grad_norm": NaN,
|
| 1172 |
+
"learning_rate": 0.00011668503692778239,
|
| 1173 |
+
"loss": 0.0,
|
| 1174 |
+
"step": 163
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 0.04987455333384019,
|
| 1178 |
+
"grad_norm": NaN,
|
| 1179 |
+
"learning_rate": 0.0001154594522155557,
|
| 1180 |
+
"loss": 0.0,
|
| 1181 |
+
"step": 164
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.05017866646392458,
|
| 1185 |
+
"grad_norm": NaN,
|
| 1186 |
+
"learning_rate": 0.00011423148382732853,
|
| 1187 |
+
"loss": 0.0,
|
| 1188 |
+
"step": 165
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 0.05048277959400897,
|
| 1192 |
+
"grad_norm": NaN,
|
| 1193 |
+
"learning_rate": 0.00011300132110220134,
|
| 1194 |
+
"loss": 0.0,
|
| 1195 |
+
"step": 166
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 0.05078689272409336,
|
| 1199 |
+
"grad_norm": NaN,
|
| 1200 |
+
"learning_rate": 0.00011176915371761702,
|
| 1201 |
+
"loss": 0.0,
|
| 1202 |
+
"step": 167
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.05109100585417775,
|
| 1206 |
+
"grad_norm": NaN,
|
| 1207 |
+
"learning_rate": 0.00011053517166011471,
|
| 1208 |
+
"loss": 0.0,
|
| 1209 |
+
"step": 168
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.05139511898426215,
|
| 1213 |
+
"grad_norm": NaN,
|
| 1214 |
+
"learning_rate": 0.00010929956519603594,
|
| 1215 |
+
"loss": 0.0,
|
| 1216 |
+
"step": 169
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.05169923211434654,
|
| 1220 |
+
"grad_norm": NaN,
|
| 1221 |
+
"learning_rate": 0.0001080625248421878,
|
| 1222 |
+
"loss": 0.0,
|
| 1223 |
+
"step": 170
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 0.052003345244430926,
|
| 1227 |
+
"grad_norm": NaN,
|
| 1228 |
+
"learning_rate": 0.0001068242413364671,
|
| 1229 |
+
"loss": 0.0,
|
| 1230 |
+
"step": 171
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 0.05230745837451532,
|
| 1234 |
+
"grad_norm": NaN,
|
| 1235 |
+
"learning_rate": 0.00010558490560845107,
|
| 1236 |
+
"loss": 0.0,
|
| 1237 |
+
"step": 172
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 0.05261157150459971,
|
| 1241 |
+
"grad_norm": NaN,
|
| 1242 |
+
"learning_rate": 0.00010434470874995781,
|
| 1243 |
+
"loss": 0.0,
|
| 1244 |
+
"step": 173
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 0.0529156846346841,
|
| 1248 |
+
"grad_norm": NaN,
|
| 1249 |
+
"learning_rate": 0.00010310384198558225,
|
| 1250 |
+
"loss": 0.0,
|
| 1251 |
+
"step": 174
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.05321979776476849,
|
| 1255 |
+
"grad_norm": NaN,
|
| 1256 |
+
"learning_rate": 0.00010186249664321139,
|
| 1257 |
+
"loss": 0.0,
|
| 1258 |
+
"step": 175
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.05352391089485289,
|
| 1262 |
+
"grad_norm": NaN,
|
| 1263 |
+
"learning_rate": 0.00010062086412452352,
|
| 1264 |
+
"loss": 0.0,
|
| 1265 |
+
"step": 176
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.05382802402493728,
|
| 1269 |
+
"grad_norm": NaN,
|
| 1270 |
+
"learning_rate": 9.93791358754765e-05,
|
| 1271 |
+
"loss": 0.0,
|
| 1272 |
+
"step": 177
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.054132137155021666,
|
| 1276 |
+
"grad_norm": NaN,
|
| 1277 |
+
"learning_rate": 9.813750335678866e-05,
|
| 1278 |
+
"loss": 0.0,
|
| 1279 |
+
"step": 178
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.05443625028510606,
|
| 1283 |
+
"grad_norm": NaN,
|
| 1284 |
+
"learning_rate": 9.689615801441774e-05,
|
| 1285 |
+
"loss": 0.0,
|
| 1286 |
+
"step": 179
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.05474036341519045,
|
| 1290 |
+
"grad_norm": NaN,
|
| 1291 |
+
"learning_rate": 9.56552912500422e-05,
|
| 1292 |
+
"loss": 0.0,
|
| 1293 |
+
"step": 180
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.05504447654527484,
|
| 1297 |
+
"grad_norm": NaN,
|
| 1298 |
+
"learning_rate": 9.441509439154895e-05,
|
| 1299 |
+
"loss": 0.0,
|
| 1300 |
+
"step": 181
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.05534858967535923,
|
| 1304 |
+
"grad_norm": NaN,
|
| 1305 |
+
"learning_rate": 9.317575866353292e-05,
|
| 1306 |
+
"loss": 0.0,
|
| 1307 |
+
"step": 182
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.05565270280544363,
|
| 1311 |
+
"grad_norm": NaN,
|
| 1312 |
+
"learning_rate": 9.193747515781224e-05,
|
| 1313 |
+
"loss": 0.0,
|
| 1314 |
+
"step": 183
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.055956815935528016,
|
| 1318 |
+
"grad_norm": NaN,
|
| 1319 |
+
"learning_rate": 9.070043480396404e-05,
|
| 1320 |
+
"loss": 0.0,
|
| 1321 |
+
"step": 184
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.056260929065612406,
|
| 1325 |
+
"grad_norm": NaN,
|
| 1326 |
+
"learning_rate": 8.94648283398853e-05,
|
| 1327 |
+
"loss": 0.0,
|
| 1328 |
+
"step": 185
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.0565650421956968,
|
| 1332 |
+
"grad_norm": NaN,
|
| 1333 |
+
"learning_rate": 8.823084628238298e-05,
|
| 1334 |
+
"loss": 0.0,
|
| 1335 |
+
"step": 186
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.05686915532578119,
|
| 1339 |
+
"grad_norm": NaN,
|
| 1340 |
+
"learning_rate": 8.699867889779868e-05,
|
| 1341 |
+
"loss": 0.0,
|
| 1342 |
+
"step": 187
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 0.05717326845586558,
|
| 1346 |
+
"grad_norm": NaN,
|
| 1347 |
+
"learning_rate": 8.57685161726715e-05,
|
| 1348 |
+
"loss": 0.0,
|
| 1349 |
+
"step": 188
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.05747738158594997,
|
| 1353 |
+
"grad_norm": NaN,
|
| 1354 |
+
"learning_rate": 8.454054778444431e-05,
|
| 1355 |
+
"loss": 0.0,
|
| 1356 |
+
"step": 189
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 0.057781494716034366,
|
| 1360 |
+
"grad_norm": NaN,
|
| 1361 |
+
"learning_rate": 8.331496307221762e-05,
|
| 1362 |
+
"loss": 0.0,
|
| 1363 |
+
"step": 190
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.058085607846118756,
|
| 1367 |
+
"grad_norm": NaN,
|
| 1368 |
+
"learning_rate": 8.209195100755551e-05,
|
| 1369 |
+
"loss": 0.0,
|
| 1370 |
+
"step": 191
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.058389720976203145,
|
| 1374 |
+
"grad_norm": NaN,
|
| 1375 |
+
"learning_rate": 8.087170016534835e-05,
|
| 1376 |
+
"loss": 0.0,
|
| 1377 |
+
"step": 192
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.05869383410628754,
|
| 1381 |
+
"grad_norm": NaN,
|
| 1382 |
+
"learning_rate": 7.965439869473664e-05,
|
| 1383 |
+
"loss": 0.0,
|
| 1384 |
+
"step": 193
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 0.05899794723637193,
|
| 1388 |
+
"grad_norm": NaN,
|
| 1389 |
+
"learning_rate": 7.84402342901005e-05,
|
| 1390 |
+
"loss": 0.0,
|
| 1391 |
+
"step": 194
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 0.05930206036645632,
|
| 1395 |
+
"grad_norm": NaN,
|
| 1396 |
+
"learning_rate": 7.722939416211937e-05,
|
| 1397 |
+
"loss": 0.0,
|
| 1398 |
+
"step": 195
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 0.05960617349654071,
|
| 1402 |
+
"grad_norm": NaN,
|
| 1403 |
+
"learning_rate": 7.6022065008906e-05,
|
| 1404 |
+
"loss": 0.0,
|
| 1405 |
+
"step": 196
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.059910286626625106,
|
| 1409 |
+
"grad_norm": NaN,
|
| 1410 |
+
"learning_rate": 7.481843298721982e-05,
|
| 1411 |
+
"loss": 0.0,
|
| 1412 |
+
"step": 197
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 0.060214399756709495,
|
| 1416 |
+
"grad_norm": NaN,
|
| 1417 |
+
"learning_rate": 7.361868368376364e-05,
|
| 1418 |
+
"loss": 0.0,
|
| 1419 |
+
"step": 198
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.060518512886793885,
|
| 1423 |
+
"grad_norm": NaN,
|
| 1424 |
+
"learning_rate": 7.242300208656814e-05,
|
| 1425 |
+
"loss": 0.0,
|
| 1426 |
+
"step": 199
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.06082262601687828,
|
| 1430 |
+
"grad_norm": NaN,
|
| 1431 |
+
"learning_rate": 7.123157255646888e-05,
|
| 1432 |
+
"loss": 0.0,
|
| 1433 |
+
"step": 200
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 0.06112673914696267,
|
| 1437 |
+
"grad_norm": NaN,
|
| 1438 |
+
"learning_rate": 7.004457879867986e-05,
|
| 1439 |
+
"loss": 0.0,
|
| 1440 |
+
"step": 201
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 0.06143085227704706,
|
| 1444 |
+
"grad_norm": NaN,
|
| 1445 |
+
"learning_rate": 6.886220383446814e-05,
|
| 1446 |
+
"loss": 0.0,
|
| 1447 |
+
"step": 202
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 0.061734965407131456,
|
| 1451 |
+
"grad_norm": NaN,
|
| 1452 |
+
"learning_rate": 6.768462997293413e-05,
|
| 1453 |
+
"loss": 0.0,
|
| 1454 |
+
"step": 203
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 0.062039078537215846,
|
| 1458 |
+
"grad_norm": NaN,
|
| 1459 |
+
"learning_rate": 6.651203878290139e-05,
|
| 1460 |
+
"loss": 0.0,
|
| 1461 |
+
"step": 204
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 0.062343191667300235,
|
| 1465 |
+
"grad_norm": NaN,
|
| 1466 |
+
"learning_rate": 6.534461106492093e-05,
|
| 1467 |
+
"loss": 0.0,
|
| 1468 |
+
"step": 205
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 0.06264730479738463,
|
| 1472 |
+
"grad_norm": NaN,
|
| 1473 |
+
"learning_rate": 6.418252682339361e-05,
|
| 1474 |
+
"loss": 0.0,
|
| 1475 |
+
"step": 206
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 0.06295141792746901,
|
| 1479 |
+
"grad_norm": NaN,
|
| 1480 |
+
"learning_rate": 6.30259652388155e-05,
|
| 1481 |
+
"loss": 0.0,
|
| 1482 |
+
"step": 207
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 0.06325553105755341,
|
| 1486 |
+
"grad_norm": NaN,
|
| 1487 |
+
"learning_rate": 6.187510464015022e-05,
|
| 1488 |
+
"loss": 0.0,
|
| 1489 |
+
"step": 208
|
| 1490 |
+
},
|
| 1491 |
+
{
|
| 1492 |
+
"epoch": 0.0635596441876378,
|
| 1493 |
+
"grad_norm": NaN,
|
| 1494 |
+
"learning_rate": 6.0730122477332675e-05,
|
| 1495 |
+
"loss": 0.0,
|
| 1496 |
+
"step": 209
|
| 1497 |
+
},
|
| 1498 |
+
{
|
| 1499 |
+
"epoch": 0.06386375731772219,
|
| 1500 |
+
"grad_norm": NaN,
|
| 1501 |
+
"learning_rate": 5.9591195293908174e-05,
|
| 1502 |
+
"loss": 0.0,
|
| 1503 |
+
"step": 210
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 0.06416787044780659,
|
| 1507 |
+
"grad_norm": NaN,
|
| 1508 |
+
"learning_rate": 5.845849869981137e-05,
|
| 1509 |
+
"loss": 0.0,
|
| 1510 |
+
"step": 211
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 0.06447198357789098,
|
| 1514 |
+
"grad_norm": NaN,
|
| 1515 |
+
"learning_rate": 5.733220734428919e-05,
|
| 1516 |
+
"loss": 0.0,
|
| 1517 |
+
"step": 212
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 0.06477609670797536,
|
| 1521 |
+
"grad_norm": NaN,
|
| 1522 |
+
"learning_rate": 5.621249488897176e-05,
|
| 1523 |
+
"loss": 0.0,
|
| 1524 |
+
"step": 213
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 0.06508020983805976,
|
| 1528 |
+
"grad_norm": NaN,
|
| 1529 |
+
"learning_rate": 5.509953398109594e-05,
|
| 1530 |
+
"loss": 0.0,
|
| 1531 |
+
"step": 214
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 0.06538432296814414,
|
| 1535 |
+
"grad_norm": NaN,
|
| 1536 |
+
"learning_rate": 5.399349622688479e-05,
|
| 1537 |
+
"loss": 0.0,
|
| 1538 |
+
"step": 215
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 0.06568843609822854,
|
| 1542 |
+
"grad_norm": NaN,
|
| 1543 |
+
"learning_rate": 5.2894552165087916e-05,
|
| 1544 |
+
"loss": 0.0,
|
| 1545 |
+
"step": 216
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 0.06599254922831294,
|
| 1549 |
+
"grad_norm": NaN,
|
| 1550 |
+
"learning_rate": 5.1802871240686234e-05,
|
| 1551 |
+
"loss": 0.0,
|
| 1552 |
+
"step": 217
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 0.06629666235839732,
|
| 1556 |
+
"grad_norm": NaN,
|
| 1557 |
+
"learning_rate": 5.0718621778765476e-05,
|
| 1558 |
+
"loss": 0.0,
|
| 1559 |
+
"step": 218
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 0.06660077548848171,
|
| 1563 |
+
"grad_norm": NaN,
|
| 1564 |
+
"learning_rate": 4.9641970958562366e-05,
|
| 1565 |
+
"loss": 0.0,
|
| 1566 |
+
"step": 219
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 0.06690488861856611,
|
| 1570 |
+
"grad_norm": NaN,
|
| 1571 |
+
"learning_rate": 4.8573084787687326e-05,
|
| 1572 |
+
"loss": 0.0,
|
| 1573 |
+
"step": 220
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 0.0672090017486505,
|
| 1577 |
+
"grad_norm": NaN,
|
| 1578 |
+
"learning_rate": 4.751212807652806e-05,
|
| 1579 |
+
"loss": 0.0,
|
| 1580 |
+
"step": 221
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 0.06751311487873489,
|
| 1584 |
+
"grad_norm": NaN,
|
| 1585 |
+
"learning_rate": 4.6459264412837454e-05,
|
| 1586 |
+
"loss": 0.0,
|
| 1587 |
+
"step": 222
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 0.06781722800881929,
|
| 1591 |
+
"grad_norm": NaN,
|
| 1592 |
+
"learning_rate": 4.5414656136510334e-05,
|
| 1593 |
+
"loss": 0.0,
|
| 1594 |
+
"step": 223
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 0.06812134113890367,
|
| 1598 |
+
"grad_norm": NaN,
|
| 1599 |
+
"learning_rate": 4.437846431455249e-05,
|
| 1600 |
+
"loss": 0.0,
|
| 1601 |
+
"step": 224
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 0.06842545426898806,
|
| 1605 |
+
"grad_norm": NaN,
|
| 1606 |
+
"learning_rate": 4.335084871624572e-05,
|
| 1607 |
+
"loss": 0.0,
|
| 1608 |
+
"step": 225
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 0.06872956739907246,
|
| 1612 |
+
"grad_norm": NaN,
|
| 1613 |
+
"learning_rate": 4.2331967788513295e-05,
|
| 1614 |
+
"loss": 0.0,
|
| 1615 |
+
"step": 226
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 0.06903368052915684,
|
| 1619 |
+
"grad_norm": NaN,
|
| 1620 |
+
"learning_rate": 4.132197863148925e-05,
|
| 1621 |
+
"loss": 0.0,
|
| 1622 |
+
"step": 227
|
| 1623 |
+
},
|
| 1624 |
+
{
|
| 1625 |
+
"epoch": 0.06933779365924124,
|
| 1626 |
+
"grad_norm": NaN,
|
| 1627 |
+
"learning_rate": 4.0321036974295156e-05,
|
| 1628 |
+
"loss": 0.0,
|
| 1629 |
+
"step": 228
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 0.06933779365924124,
|
| 1633 |
+
"eval_loss": NaN,
|
| 1634 |
+
"eval_runtime": 1405.1275,
|
| 1635 |
+
"eval_samples_per_second": 3.941,
|
| 1636 |
+
"eval_steps_per_second": 0.986,
|
| 1637 |
+
"step": 228
|
| 1638 |
}
|
| 1639 |
],
|
| 1640 |
"logging_steps": 1,
|
|
|
|
| 1654 |
"attributes": {}
|
| 1655 |
}
|
| 1656 |
},
|
| 1657 |
+
"total_flos": 1.5612257832366244e+18,
|
| 1658 |
"train_batch_size": 2,
|
| 1659 |
"trial_name": null,
|
| 1660 |
"trial_params": null
|