Training in progress, step 200, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +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/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +371 -5
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13587864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7019cb9aa201aea19db1270f90077e433f32992e44dade7548821d8c154f8dd
|
| 3 |
size 13587864
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 27273018
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:386c3f379a00095fe8496f8f431507c91666e8cfccb1ccdbd5d46ffa72194cd7
|
| 3 |
size 27273018
|
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 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a23fd22389371cc845ff538f36c85d6acc6b9021c5b65cb5faef2f7e821d95a8
|
| 3 |
size 15024
|
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 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fb312fb50ba43fd98c0b5fe4042c1e3ef9cd58378ec0d1e1bf5c56e15568b12
|
| 3 |
size 15024
|
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 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4689c594a2b486efb36e60e76c3ec318218071433606da34ac3dcedbc93ca127
|
| 3 |
size 15024
|
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 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ba2494af9fc250e587279ec6c23697d4a4eee3ba750a8eea5d8a07f578adf0b
|
| 3 |
size 15024
|
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 sha256:42c29d847f75ce9649efda10a945d3da08ad95d9c7cdbd2e690e733de315eb64
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 1.
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1113,6 +1113,372 @@
|
|
| 1113 |
"eval_samples_per_second": 178.678,
|
| 1114 |
"eval_steps_per_second": 46.456,
|
| 1115 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
|
@@ -1141,7 +1507,7 @@
|
|
| 1141 |
"attributes": {}
|
| 1142 |
}
|
| 1143 |
},
|
| 1144 |
-
"total_flos":
|
| 1145 |
"train_batch_size": 1,
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.6848325729370117,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 1.5252621544327931,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1113 |
"eval_samples_per_second": 178.678,
|
| 1114 |
"eval_steps_per_second": 46.456,
|
| 1115 |
"step": 150
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.1515729265967587,
|
| 1119 |
+
"grad_norm": 0.38320392370224,
|
| 1120 |
+
"learning_rate": 0.00013866280652782267,
|
| 1121 |
+
"loss": 1.6258,
|
| 1122 |
+
"step": 151
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 1.1591992373689228,
|
| 1126 |
+
"grad_norm": 0.3931479752063751,
|
| 1127 |
+
"learning_rate": 0.00013703996421405052,
|
| 1128 |
+
"loss": 1.6313,
|
| 1129 |
+
"step": 152
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 1.1668255481410867,
|
| 1133 |
+
"grad_norm": 0.4570615589618683,
|
| 1134 |
+
"learning_rate": 0.00013542133257882257,
|
| 1135 |
+
"loss": 1.6801,
|
| 1136 |
+
"step": 153
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 1.1744518589132507,
|
| 1140 |
+
"grad_norm": 0.47714921832084656,
|
| 1141 |
+
"learning_rate": 0.0001338071553821094,
|
| 1142 |
+
"loss": 1.6307,
|
| 1143 |
+
"step": 154
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 1.1820781696854148,
|
| 1147 |
+
"grad_norm": 0.4591121971607208,
|
| 1148 |
+
"learning_rate": 0.00013219767571305937,
|
| 1149 |
+
"loss": 1.7064,
|
| 1150 |
+
"step": 155
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.1897044804575787,
|
| 1154 |
+
"grad_norm": 0.5732882022857666,
|
| 1155 |
+
"learning_rate": 0.00013059313595339053,
|
| 1156 |
+
"loss": 1.7405,
|
| 1157 |
+
"step": 156
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.1973307912297426,
|
| 1161 |
+
"grad_norm": 0.4108792543411255,
|
| 1162 |
+
"learning_rate": 0.00012899377774088872,
|
| 1163 |
+
"loss": 1.6063,
|
| 1164 |
+
"step": 157
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.2049571020019065,
|
| 1168 |
+
"grad_norm": 0.42478087544441223,
|
| 1169 |
+
"learning_rate": 0.00012739984193301784,
|
| 1170 |
+
"loss": 1.5782,
|
| 1171 |
+
"step": 158
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 1.2125834127740704,
|
| 1175 |
+
"grad_norm": 0.44489574432373047,
|
| 1176 |
+
"learning_rate": 0.0001258115685706476,
|
| 1177 |
+
"loss": 1.5959,
|
| 1178 |
+
"step": 159
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 1.2202097235462346,
|
| 1182 |
+
"grad_norm": 0.41875404119491577,
|
| 1183 |
+
"learning_rate": 0.0001242291968419042,
|
| 1184 |
+
"loss": 1.6163,
|
| 1185 |
+
"step": 160
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 1.2278360343183985,
|
| 1189 |
+
"grad_norm": 0.3827251195907593,
|
| 1190 |
+
"learning_rate": 0.00012265296504614963,
|
| 1191 |
+
"loss": 1.6228,
|
| 1192 |
+
"step": 161
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 1.2354623450905624,
|
| 1196 |
+
"grad_norm": 0.3817841112613678,
|
| 1197 |
+
"learning_rate": 0.0001210831105580945,
|
| 1198 |
+
"loss": 1.5694,
|
| 1199 |
+
"step": 162
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.2430886558627263,
|
| 1203 |
+
"grad_norm": 0.3716193735599518,
|
| 1204 |
+
"learning_rate": 0.00011951986979205029,
|
| 1205 |
+
"loss": 1.6367,
|
| 1206 |
+
"step": 163
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 1.2507149666348902,
|
| 1210 |
+
"grad_norm": 0.37516316771507263,
|
| 1211 |
+
"learning_rate": 0.00011796347816632634,
|
| 1212 |
+
"loss": 1.6157,
|
| 1213 |
+
"step": 164
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.2583412774070544,
|
| 1217 |
+
"grad_norm": 0.4124738276004791,
|
| 1218 |
+
"learning_rate": 0.00011641417006777658,
|
| 1219 |
+
"loss": 1.5697,
|
| 1220 |
+
"step": 165
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 1.2659675881792183,
|
| 1224 |
+
"grad_norm": 0.4279733896255493,
|
| 1225 |
+
"learning_rate": 0.00011487217881650195,
|
| 1226 |
+
"loss": 1.6447,
|
| 1227 |
+
"step": 166
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 1.2735938989513822,
|
| 1231 |
+
"grad_norm": 0.4881094992160797,
|
| 1232 |
+
"learning_rate": 0.00011333773663071288,
|
| 1233 |
+
"loss": 1.6122,
|
| 1234 |
+
"step": 167
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.2812202097235463,
|
| 1238 |
+
"grad_norm": 0.521618127822876,
|
| 1239 |
+
"learning_rate": 0.00011181107459175851,
|
| 1240 |
+
"loss": 1.7202,
|
| 1241 |
+
"step": 168
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.2888465204957102,
|
| 1245 |
+
"grad_norm": 0.3777306079864502,
|
| 1246 |
+
"learning_rate": 0.00011029242260932638,
|
| 1247 |
+
"loss": 1.5756,
|
| 1248 |
+
"step": 169
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 1.2964728312678742,
|
| 1252 |
+
"grad_norm": 0.4733025133609772,
|
| 1253 |
+
"learning_rate": 0.000108782009386819,
|
| 1254 |
+
"loss": 1.6479,
|
| 1255 |
+
"step": 170
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 1.304099142040038,
|
| 1259 |
+
"grad_norm": 0.41860291361808777,
|
| 1260 |
+
"learning_rate": 0.00010728006238691194,
|
| 1261 |
+
"loss": 1.5983,
|
| 1262 |
+
"step": 171
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 1.311725452812202,
|
| 1266 |
+
"grad_norm": 0.46844813227653503,
|
| 1267 |
+
"learning_rate": 0.00010578680779729879,
|
| 1268 |
+
"loss": 1.578,
|
| 1269 |
+
"step": 172
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.3193517635843661,
|
| 1273 |
+
"grad_norm": 0.40656524896621704,
|
| 1274 |
+
"learning_rate": 0.0001043024704966281,
|
| 1275 |
+
"loss": 1.6255,
|
| 1276 |
+
"step": 173
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 1.32697807435653,
|
| 1280 |
+
"grad_norm": 0.38256990909576416,
|
| 1281 |
+
"learning_rate": 0.00010282727402063758,
|
| 1282 |
+
"loss": 1.5675,
|
| 1283 |
+
"step": 174
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.334604385128694,
|
| 1287 |
+
"grad_norm": 0.3779941201210022,
|
| 1288 |
+
"learning_rate": 0.00010136144052849031,
|
| 1289 |
+
"loss": 1.5789,
|
| 1290 |
+
"step": 175
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 1.334604385128694,
|
| 1294 |
+
"eval_loss": 1.695977807044983,
|
| 1295 |
+
"eval_runtime": 0.2808,
|
| 1296 |
+
"eval_samples_per_second": 178.081,
|
| 1297 |
+
"eval_steps_per_second": 46.301,
|
| 1298 |
+
"step": 175
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.342230695900858,
|
| 1302 |
+
"grad_norm": 0.3875720798969269,
|
| 1303 |
+
"learning_rate": 9.990519076931843e-05,
|
| 1304 |
+
"loss": 1.656,
|
| 1305 |
+
"step": 176
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.349857006673022,
|
| 1309 |
+
"grad_norm": 0.38068655133247375,
|
| 1310 |
+
"learning_rate": 9.845874404897915e-05,
|
| 1311 |
+
"loss": 1.623,
|
| 1312 |
+
"step": 177
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.357483317445186,
|
| 1316 |
+
"grad_norm": 0.4605511724948883,
|
| 1317 |
+
"learning_rate": 9.702231819702814e-05,
|
| 1318 |
+
"loss": 1.627,
|
| 1319 |
+
"step": 178
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.3651096282173498,
|
| 1323 |
+
"grad_norm": 0.4176296889781952,
|
| 1324 |
+
"learning_rate": 9.559612953391507e-05,
|
| 1325 |
+
"loss": 1.6706,
|
| 1326 |
+
"step": 179
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.3727359389895137,
|
| 1330 |
+
"grad_norm": 0.4767864942550659,
|
| 1331 |
+
"learning_rate": 9.418039283840671e-05,
|
| 1332 |
+
"loss": 1.6709,
|
| 1333 |
+
"step": 180
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.3803622497616779,
|
| 1337 |
+
"grad_norm": 0.567336916923523,
|
| 1338 |
+
"learning_rate": 9.27753213152419e-05,
|
| 1339 |
+
"loss": 1.8214,
|
| 1340 |
+
"step": 181
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.3879885605338418,
|
| 1344 |
+
"grad_norm": 0.4051623046398163,
|
| 1345 |
+
"learning_rate": 9.138112656302376e-05,
|
| 1346 |
+
"loss": 1.6248,
|
| 1347 |
+
"step": 182
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.3956148713060057,
|
| 1351 |
+
"grad_norm": 0.380164235830307,
|
| 1352 |
+
"learning_rate": 8.999801854235373e-05,
|
| 1353 |
+
"loss": 1.5668,
|
| 1354 |
+
"step": 183
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.4032411820781696,
|
| 1358 |
+
"grad_norm": 0.37853559851646423,
|
| 1359 |
+
"learning_rate": 8.862620554421221e-05,
|
| 1360 |
+
"loss": 1.6079,
|
| 1361 |
+
"step": 184
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.4108674928503335,
|
| 1365 |
+
"grad_norm": 0.38022464513778687,
|
| 1366 |
+
"learning_rate": 8.726589415859088e-05,
|
| 1367 |
+
"loss": 1.6109,
|
| 1368 |
+
"step": 185
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.4184938036224977,
|
| 1372 |
+
"grad_norm": 0.3726414442062378,
|
| 1373 |
+
"learning_rate": 8.591728924338075e-05,
|
| 1374 |
+
"loss": 1.5726,
|
| 1375 |
+
"step": 186
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.4261201143946616,
|
| 1379 |
+
"grad_norm": 0.39313751459121704,
|
| 1380 |
+
"learning_rate": 8.45805938935215e-05,
|
| 1381 |
+
"loss": 1.5881,
|
| 1382 |
+
"step": 187
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.4337464251668255,
|
| 1386 |
+
"grad_norm": 0.40941789746284485,
|
| 1387 |
+
"learning_rate": 8.325600941041607e-05,
|
| 1388 |
+
"loss": 1.6375,
|
| 1389 |
+
"step": 188
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.4413727359389896,
|
| 1393 |
+
"grad_norm": 0.38843002915382385,
|
| 1394 |
+
"learning_rate": 8.194373527161539e-05,
|
| 1395 |
+
"loss": 1.5911,
|
| 1396 |
+
"step": 189
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.4489990467111535,
|
| 1400 |
+
"grad_norm": 0.38351744413375854,
|
| 1401 |
+
"learning_rate": 8.064396910077785e-05,
|
| 1402 |
+
"loss": 1.6153,
|
| 1403 |
+
"step": 190
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.4566253574833175,
|
| 1407 |
+
"grad_norm": 0.42547914385795593,
|
| 1408 |
+
"learning_rate": 7.935690663790787e-05,
|
| 1409 |
+
"loss": 1.5872,
|
| 1410 |
+
"step": 191
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.4642516682554814,
|
| 1414 |
+
"grad_norm": 0.45052269101142883,
|
| 1415 |
+
"learning_rate": 7.808274170987818e-05,
|
| 1416 |
+
"loss": 1.6048,
|
| 1417 |
+
"step": 192
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.4718779790276453,
|
| 1421 |
+
"grad_norm": 0.5102285742759705,
|
| 1422 |
+
"learning_rate": 7.682166620124017e-05,
|
| 1423 |
+
"loss": 1.6611,
|
| 1424 |
+
"step": 193
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.4795042897998094,
|
| 1428 |
+
"grad_norm": 0.3973918855190277,
|
| 1429 |
+
"learning_rate": 7.55738700253268e-05,
|
| 1430 |
+
"loss": 1.6591,
|
| 1431 |
+
"step": 194
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.4871306005719733,
|
| 1435 |
+
"grad_norm": 0.4221573770046234,
|
| 1436 |
+
"learning_rate": 7.43395410956525e-05,
|
| 1437 |
+
"loss": 1.5788,
|
| 1438 |
+
"step": 195
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.4947569113441372,
|
| 1442 |
+
"grad_norm": 0.38037997484207153,
|
| 1443 |
+
"learning_rate": 7.311886529761383e-05,
|
| 1444 |
+
"loss": 1.543,
|
| 1445 |
+
"step": 196
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.5023832221163014,
|
| 1449 |
+
"grad_norm": 0.3961423635482788,
|
| 1450 |
+
"learning_rate": 7.191202646049596e-05,
|
| 1451 |
+
"loss": 1.5559,
|
| 1452 |
+
"step": 197
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.510009532888465,
|
| 1456 |
+
"grad_norm": 0.40945950150489807,
|
| 1457 |
+
"learning_rate": 7.071920632978867e-05,
|
| 1458 |
+
"loss": 1.6016,
|
| 1459 |
+
"step": 198
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.5176358436606292,
|
| 1463 |
+
"grad_norm": 0.3885650038719177,
|
| 1464 |
+
"learning_rate": 6.954058453981609e-05,
|
| 1465 |
+
"loss": 1.587,
|
| 1466 |
+
"step": 199
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.5252621544327931,
|
| 1470 |
+
"grad_norm": 0.4135299623012543,
|
| 1471 |
+
"learning_rate": 6.837633858668448e-05,
|
| 1472 |
+
"loss": 1.6103,
|
| 1473 |
+
"step": 200
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.5252621544327931,
|
| 1477 |
+
"eval_loss": 1.6848325729370117,
|
| 1478 |
+
"eval_runtime": 0.2814,
|
| 1479 |
+
"eval_samples_per_second": 177.685,
|
| 1480 |
+
"eval_steps_per_second": 46.198,
|
| 1481 |
+
"step": 200
|
| 1482 |
}
|
| 1483 |
],
|
| 1484 |
"logging_steps": 1,
|
|
|
|
| 1507 |
"attributes": {}
|
| 1508 |
}
|
| 1509 |
},
|
| 1510 |
+
"total_flos": 8.88560550936576e+16,
|
| 1511 |
"train_batch_size": 1,
|
| 1512 |
"trial_name": null,
|
| 1513 |
"trial_params": null
|