Training in progress, step 200, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 201892112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f65b146918d021220752f65440f179345116f149d6c3efb9f0e45759ca7c63c3
|
| 3 |
size 201892112
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 102864548
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3807e9b51612e40ebf772f45d36539109c77b9398381b360c7295fee27d309e
|
| 3 |
size 102864548
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14180
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4ffb701c2f7b82d37d66c78b82347c99411b95c5c981d1b06bc49af5f43173d
|
| 3 |
size 14180
|
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:a032dcbe590e69725a7fa9cedb5934521429cb4c18983c09c5035cbcaaeebd93
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1089,6 +1089,364 @@
|
|
| 1089 |
"eval_samples_per_second": 42.976,
|
| 1090 |
"eval_steps_per_second": 10.746,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -1112,12 +1470,12 @@
|
|
| 1112 |
"should_evaluate": false,
|
| 1113 |
"should_log": false,
|
| 1114 |
"should_save": true,
|
| 1115 |
-
"should_training_stop":
|
| 1116 |
},
|
| 1117 |
"attributes": {}
|
| 1118 |
}
|
| 1119 |
},
|
| 1120 |
-
"total_flos":
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.696293830871582,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.03715745471435207,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1089 |
"eval_samples_per_second": 42.976,
|
| 1090 |
"eval_steps_per_second": 10.746,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.02805387830933581,
|
| 1095 |
+
"grad_norm": 0.8277557492256165,
|
| 1096 |
+
"learning_rate": 1.242586363525737e-05,
|
| 1097 |
+
"loss": 0.6744,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.02823966558290757,
|
| 1102 |
+
"grad_norm": 1.129407286643982,
|
| 1103 |
+
"learning_rate": 1.1950528629100457e-05,
|
| 1104 |
+
"loss": 0.8988,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.028425452856479332,
|
| 1109 |
+
"grad_norm": 1.1117703914642334,
|
| 1110 |
+
"learning_rate": 1.1482862068344121e-05,
|
| 1111 |
+
"loss": 0.8987,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.02861124013005109,
|
| 1116 |
+
"grad_norm": 1.274944543838501,
|
| 1117 |
+
"learning_rate": 1.1022991808356442e-05,
|
| 1118 |
+
"loss": 0.9714,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.028797027403622853,
|
| 1123 |
+
"grad_norm": 1.413684368133545,
|
| 1124 |
+
"learning_rate": 1.0571043573074737e-05,
|
| 1125 |
+
"loss": 1.0464,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.028982814677194612,
|
| 1130 |
+
"grad_norm": 1.2533186674118042,
|
| 1131 |
+
"learning_rate": 1.0127140920633857e-05,
|
| 1132 |
+
"loss": 0.8553,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.029168601950766374,
|
| 1137 |
+
"grad_norm": 0.9504323601722717,
|
| 1138 |
+
"learning_rate": 9.69140520958662e-06,
|
| 1139 |
+
"loss": 0.6454,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.029354389224338133,
|
| 1144 |
+
"grad_norm": 0.9204007387161255,
|
| 1145 |
+
"learning_rate": 9.263955565725648e-06,
|
| 1146 |
+
"loss": 0.733,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.02954017649790989,
|
| 1151 |
+
"grad_norm": 0.8115749359130859,
|
| 1152 |
+
"learning_rate": 8.844908849515509e-06,
|
| 1153 |
+
"loss": 0.6411,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.029725963771481654,
|
| 1158 |
+
"grad_norm": 0.7680659294128418,
|
| 1159 |
+
"learning_rate": 8.434379624144261e-06,
|
| 1160 |
+
"loss": 0.6213,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.029911751045053413,
|
| 1165 |
+
"grad_norm": 0.7348408699035645,
|
| 1166 |
+
"learning_rate": 8.032480124203013e-06,
|
| 1167 |
+
"loss": 0.608,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.030097538318625175,
|
| 1172 |
+
"grad_norm": 0.690196692943573,
|
| 1173 |
+
"learning_rate": 7.639320225002106e-06,
|
| 1174 |
+
"loss": 0.5074,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.030283325592196934,
|
| 1179 |
+
"grad_norm": 0.7912430167198181,
|
| 1180 |
+
"learning_rate": 7.255007412532307e-06,
|
| 1181 |
+
"loss": 0.6236,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.030469112865768696,
|
| 1186 |
+
"grad_norm": 0.8454386591911316,
|
| 1187 |
+
"learning_rate": 6.8796467540791986e-06,
|
| 1188 |
+
"loss": 0.773,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.030654900139340455,
|
| 1193 |
+
"grad_norm": 0.7565322518348694,
|
| 1194 |
+
"learning_rate": 6.513340869498859e-06,
|
| 1195 |
+
"loss": 0.5278,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.030840687412912217,
|
| 1200 |
+
"grad_norm": 0.7427991032600403,
|
| 1201 |
+
"learning_rate": 6.1561899031625794e-06,
|
| 1202 |
+
"loss": 0.5895,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.031026474686483976,
|
| 1207 |
+
"grad_norm": 0.72712242603302,
|
| 1208 |
+
"learning_rate": 5.808291496578435e-06,
|
| 1209 |
+
"loss": 0.554,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.031212261960055738,
|
| 1214 |
+
"grad_norm": 0.8168418407440186,
|
| 1215 |
+
"learning_rate": 5.469740761697044e-06,
|
| 1216 |
+
"loss": 0.5795,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.0313980492336275,
|
| 1221 |
+
"grad_norm": 0.7900062203407288,
|
| 1222 |
+
"learning_rate": 5.140630254908905e-06,
|
| 1223 |
+
"loss": 0.6155,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.03158383650719926,
|
| 1228 |
+
"grad_norm": 0.7631322741508484,
|
| 1229 |
+
"learning_rate": 4.821049951740442e-06,
|
| 1230 |
+
"loss": 0.6395,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.031769623780771014,
|
| 1235 |
+
"grad_norm": 0.8723105788230896,
|
| 1236 |
+
"learning_rate": 4.511087222255528e-06,
|
| 1237 |
+
"loss": 0.7083,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.031955411054342776,
|
| 1242 |
+
"grad_norm": 0.8694934248924255,
|
| 1243 |
+
"learning_rate": 4.2108268071694616e-06,
|
| 1244 |
+
"loss": 0.6848,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.03214119832791454,
|
| 1249 |
+
"grad_norm": 0.8055874109268188,
|
| 1250 |
+
"learning_rate": 3.9203507946816445e-06,
|
| 1251 |
+
"loss": 0.6301,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.0323269856014863,
|
| 1256 |
+
"grad_norm": 0.782102644443512,
|
| 1257 |
+
"learning_rate": 3.6397385980335e-06,
|
| 1258 |
+
"loss": 0.5799,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.032512772875058056,
|
| 1263 |
+
"grad_norm": 0.9123784303665161,
|
| 1264 |
+
"learning_rate": 3.3690669337977e-06,
|
| 1265 |
+
"loss": 0.6572,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.03269856014862982,
|
| 1270 |
+
"grad_norm": 0.8065102100372314,
|
| 1271 |
+
"learning_rate": 3.1084098009046106e-06,
|
| 1272 |
+
"loss": 0.6309,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.03288434742220158,
|
| 1277 |
+
"grad_norm": 0.7722126841545105,
|
| 1278 |
+
"learning_rate": 2.8578384604117217e-06,
|
| 1279 |
+
"loss": 0.5781,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.03307013469577334,
|
| 1284 |
+
"grad_norm": 0.8441624641418457,
|
| 1285 |
+
"learning_rate": 2.6174214160215704e-06,
|
| 1286 |
+
"loss": 0.625,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.0332559219693451,
|
| 1291 |
+
"grad_norm": 0.7183513045310974,
|
| 1292 |
+
"learning_rate": 2.3872243953535535e-06,
|
| 1293 |
+
"loss": 0.5938,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.03344170924291686,
|
| 1298 |
+
"grad_norm": 0.8442609310150146,
|
| 1299 |
+
"learning_rate": 2.1673103319746146e-06,
|
| 1300 |
+
"loss": 0.6409,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.03362749651648862,
|
| 1305 |
+
"grad_norm": 0.7444936633110046,
|
| 1306 |
+
"learning_rate": 1.957739348193859e-06,
|
| 1307 |
+
"loss": 0.6137,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.03381328379006038,
|
| 1312 |
+
"grad_norm": 0.851841390132904,
|
| 1313 |
+
"learning_rate": 1.7585687386256944e-06,
|
| 1314 |
+
"loss": 0.5644,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.03399907106363214,
|
| 1319 |
+
"grad_norm": 0.7763927578926086,
|
| 1320 |
+
"learning_rate": 1.5698529545260744e-06,
|
| 1321 |
+
"loss": 0.556,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.0341848583372039,
|
| 1326 |
+
"grad_norm": 0.7218007445335388,
|
| 1327 |
+
"learning_rate": 1.3916435889060575e-06,
|
| 1328 |
+
"loss": 0.5211,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.034370645610775664,
|
| 1333 |
+
"grad_norm": 0.8408937454223633,
|
| 1334 |
+
"learning_rate": 1.2239893624267852e-06,
|
| 1335 |
+
"loss": 0.6682,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.03455643288434742,
|
| 1340 |
+
"grad_norm": 0.8628000020980835,
|
| 1341 |
+
"learning_rate": 1.0669361100797704e-06,
|
| 1342 |
+
"loss": 0.6878,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.03474222015791918,
|
| 1347 |
+
"grad_norm": 0.8714439272880554,
|
| 1348 |
+
"learning_rate": 9.205267686560293e-07,
|
| 1349 |
+
"loss": 0.6547,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.034928007431490944,
|
| 1354 |
+
"grad_norm": 0.7619119882583618,
|
| 1355 |
+
"learning_rate": 7.848013650076258e-07,
|
| 1356 |
+
"loss": 0.5769,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.035113794705062706,
|
| 1361 |
+
"grad_norm": 0.9454699158668518,
|
| 1362 |
+
"learning_rate": 6.597970051047053e-07,
|
| 1363 |
+
"loss": 0.6948,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.03529958197863446,
|
| 1368 |
+
"grad_norm": 0.7809498906135559,
|
| 1369 |
+
"learning_rate": 5.455478638911071e-07,
|
| 1370 |
+
"loss": 0.657,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.035485369252206224,
|
| 1375 |
+
"grad_norm": 0.9400784373283386,
|
| 1376 |
+
"learning_rate": 4.420851759412603e-07,
|
| 1377 |
+
"loss": 0.723,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.035671156525777986,
|
| 1382 |
+
"grad_norm": 1.0285460948944092,
|
| 1383 |
+
"learning_rate": 3.4943722692099224e-07,
|
| 1384 |
+
"loss": 0.8145,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.03585694379934974,
|
| 1389 |
+
"grad_norm": 1.0024358034133911,
|
| 1390 |
+
"learning_rate": 2.676293458544743e-07,
|
| 1391 |
+
"loss": 0.8062,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.036042731072921504,
|
| 1396 |
+
"grad_norm": 0.9210175275802612,
|
| 1397 |
+
"learning_rate": 1.9668389819954338e-07,
|
| 1398 |
+
"loss": 0.7595,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.036228518346493266,
|
| 1403 |
+
"grad_norm": 1.0221508741378784,
|
| 1404 |
+
"learning_rate": 1.3662027973320614e-07,
|
| 1405 |
+
"loss": 0.7836,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.03641430562006503,
|
| 1410 |
+
"grad_norm": 0.9825165271759033,
|
| 1411 |
+
"learning_rate": 8.745491124901861e-08,
|
| 1412 |
+
"loss": 0.8122,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.03660009289363678,
|
| 1417 |
+
"grad_norm": 1.2274169921875,
|
| 1418 |
+
"learning_rate": 4.920123406781052e-08,
|
| 1419 |
+
"loss": 0.9055,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.036785880167208546,
|
| 1424 |
+
"grad_norm": 1.0650230646133423,
|
| 1425 |
+
"learning_rate": 2.1869706362958044e-08,
|
| 1426 |
+
"loss": 0.7219,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.03697166744078031,
|
| 1431 |
+
"grad_norm": 1.0528210401535034,
|
| 1432 |
+
"learning_rate": 5.467800301239834e-09,
|
| 1433 |
+
"loss": 0.6992,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.03715745471435207,
|
| 1438 |
+
"grad_norm": 1.143416166305542,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.808,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.03715745471435207,
|
| 1445 |
+
"eval_loss": 0.696293830871582,
|
| 1446 |
+
"eval_runtime": 210.9668,
|
| 1447 |
+
"eval_samples_per_second": 42.974,
|
| 1448 |
+
"eval_steps_per_second": 10.746,
|
| 1449 |
+
"step": 200
|
| 1450 |
}
|
| 1451 |
],
|
| 1452 |
"logging_steps": 1,
|
|
|
|
| 1470 |
"should_evaluate": false,
|
| 1471 |
"should_log": false,
|
| 1472 |
"should_save": true,
|
| 1473 |
+
"should_training_stop": true
|
| 1474 |
},
|
| 1475 |
"attributes": {}
|
| 1476 |
}
|
| 1477 |
},
|
| 1478 |
+
"total_flos": 4.895574321423974e+16,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|