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 402688040
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99f7c8e9a51a63a584c9ffca15a650a3e9bf9c7f287bd029e46ae2c34fa3fd15
|
| 3 |
size 402688040
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 805522170
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84aac0690d09f86f349d64621c122e39d9afaebb427ef858fc1e8149acafafd1
|
| 3 |
size 805522170
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:803de0aaf47f343f0e8ba74b22296a593665fa296eaad0f2fcd5d129f206c682
|
| 3 |
size 14244
|
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:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
|
| 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": 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": 18.764,
|
| 1090 |
"eval_steps_per_second": 9.384,
|
| 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": 1.
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.224632740020752,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.060966316110349035,
|
| 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": 18.764,
|
| 1090 |
"eval_steps_per_second": 9.384,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.04602956866331352,
|
| 1095 |
+
"grad_norm": 0.9370346665382385,
|
| 1096 |
+
"learning_rate": 1.9136088935510362e-05,
|
| 1097 |
+
"loss": 4.6741,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.046334400243865266,
|
| 1102 |
+
"grad_norm": 0.9067674279212952,
|
| 1103 |
+
"learning_rate": 1.8414449687337464e-05,
|
| 1104 |
+
"loss": 4.6304,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.04663923182441701,
|
| 1109 |
+
"grad_norm": 1.0935213565826416,
|
| 1110 |
+
"learning_rate": 1.7703596875660645e-05,
|
| 1111 |
+
"loss": 5.5383,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.046944063404968754,
|
| 1116 |
+
"grad_norm": 1.1216908693313599,
|
| 1117 |
+
"learning_rate": 1.700377325606388e-05,
|
| 1118 |
+
"loss": 6.1104,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.0472488949855205,
|
| 1123 |
+
"grad_norm": 1.2409911155700684,
|
| 1124 |
+
"learning_rate": 1.631521781767214e-05,
|
| 1125 |
+
"loss": 5.6602,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.04755372656607224,
|
| 1130 |
+
"grad_norm": 0.9131847023963928,
|
| 1131 |
+
"learning_rate": 1.5638165701536868e-05,
|
| 1132 |
+
"loss": 6.2138,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.04785855814662399,
|
| 1137 |
+
"grad_norm": 1.2213008403778076,
|
| 1138 |
+
"learning_rate": 1.4972848120335453e-05,
|
| 1139 |
+
"loss": 6.5254,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.04816338972717574,
|
| 1144 |
+
"grad_norm": 0.9096271991729736,
|
| 1145 |
+
"learning_rate": 1.4319492279412388e-05,
|
| 1146 |
+
"loss": 5.9392,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.04846822130772748,
|
| 1151 |
+
"grad_norm": 0.866348147392273,
|
| 1152 |
+
"learning_rate": 1.3678321299188801e-05,
|
| 1153 |
+
"loss": 4.8568,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.048773052888279225,
|
| 1158 |
+
"grad_norm": 0.8141571283340454,
|
| 1159 |
+
"learning_rate": 1.3049554138967051e-05,
|
| 1160 |
+
"loss": 5.4341,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.04907788446883097,
|
| 1165 |
+
"grad_norm": 0.8729768395423889,
|
| 1166 |
+
"learning_rate": 1.2433405522156332e-05,
|
| 1167 |
+
"loss": 5.0825,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.04938271604938271,
|
| 1172 |
+
"grad_norm": 0.880744993686676,
|
| 1173 |
+
"learning_rate": 1.183008586294485e-05,
|
| 1174 |
+
"loss": 5.1073,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.049687547629934464,
|
| 1179 |
+
"grad_norm": 0.8431662321090698,
|
| 1180 |
+
"learning_rate": 1.1239801194443506e-05,
|
| 1181 |
+
"loss": 6.6863,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.04999237921048621,
|
| 1186 |
+
"grad_norm": 0.9774351119995117,
|
| 1187 |
+
"learning_rate": 1.066275309832584e-05,
|
| 1188 |
+
"loss": 4.8752,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.05029721079103795,
|
| 1193 |
+
"grad_norm": 0.8619078993797302,
|
| 1194 |
+
"learning_rate": 1.0099138635988026e-05,
|
| 1195 |
+
"loss": 5.8747,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.050602042371589696,
|
| 1200 |
+
"grad_norm": 0.7690417766571045,
|
| 1201 |
+
"learning_rate": 9.549150281252633e-06,
|
| 1202 |
+
"loss": 5.261,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.05090687395214144,
|
| 1207 |
+
"grad_norm": 0.8820409178733826,
|
| 1208 |
+
"learning_rate": 9.012975854638949e-06,
|
| 1209 |
+
"loss": 5.8991,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.051211705532693184,
|
| 1214 |
+
"grad_norm": 1.0724667310714722,
|
| 1215 |
+
"learning_rate": 8.490798459222476e-06,
|
| 1216 |
+
"loss": 5.0322,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.051516537113244935,
|
| 1221 |
+
"grad_norm": 0.9853336215019226,
|
| 1222 |
+
"learning_rate": 7.982796418105371e-06,
|
| 1223 |
+
"loss": 5.3792,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.05182136869379668,
|
| 1228 |
+
"grad_norm": 0.913477897644043,
|
| 1229 |
+
"learning_rate": 7.489143213519301e-06,
|
| 1230 |
+
"loss": 6.1459,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.05212620027434842,
|
| 1235 |
+
"grad_norm": 0.9908555746078491,
|
| 1236 |
+
"learning_rate": 7.010007427581378e-06,
|
| 1237 |
+
"loss": 4.3843,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.05243103185490017,
|
| 1242 |
+
"grad_norm": 0.8242432475090027,
|
| 1243 |
+
"learning_rate": 6.5455526847235825e-06,
|
| 1244 |
+
"loss": 5.4643,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.05273586343545191,
|
| 1249 |
+
"grad_norm": 0.8281580209732056,
|
| 1250 |
+
"learning_rate": 6.0959375958151045e-06,
|
| 1251 |
+
"loss": 5.3037,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.053040695016003656,
|
| 1256 |
+
"grad_norm": 0.7910247445106506,
|
| 1257 |
+
"learning_rate": 5.6613157039969055e-06,
|
| 1258 |
+
"loss": 4.6242,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.053345526596555407,
|
| 1263 |
+
"grad_norm": 0.8933544158935547,
|
| 1264 |
+
"learning_rate": 5.241835432246889e-06,
|
| 1265 |
+
"loss": 5.4644,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.05365035817710715,
|
| 1270 |
+
"grad_norm": 0.9154403805732727,
|
| 1271 |
+
"learning_rate": 4.837640032693558e-06,
|
| 1272 |
+
"loss": 5.3111,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.053955189757658895,
|
| 1277 |
+
"grad_norm": 0.833807110786438,
|
| 1278 |
+
"learning_rate": 4.448867537695578e-06,
|
| 1279 |
+
"loss": 3.8325,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.05426002133821064,
|
| 1284 |
+
"grad_norm": 0.8899303674697876,
|
| 1285 |
+
"learning_rate": 4.075650712703849e-06,
|
| 1286 |
+
"loss": 5.2321,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.05456485291876238,
|
| 1291 |
+
"grad_norm": 0.8820135593414307,
|
| 1292 |
+
"learning_rate": 3.71811701092219e-06,
|
| 1293 |
+
"loss": 4.4328,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.05486968449931413,
|
| 1298 |
+
"grad_norm": 1.0561301708221436,
|
| 1299 |
+
"learning_rate": 3.376388529782215e-06,
|
| 1300 |
+
"loss": 6.0862,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.05517451607986587,
|
| 1305 |
+
"grad_norm": 0.9490888714790344,
|
| 1306 |
+
"learning_rate": 3.0505819692471792e-06,
|
| 1307 |
+
"loss": 4.5827,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.05547934766041762,
|
| 1312 |
+
"grad_norm": 0.9599933624267578,
|
| 1313 |
+
"learning_rate": 2.7408085919590264e-06,
|
| 1314 |
+
"loss": 5.1208,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.055784179240969366,
|
| 1319 |
+
"grad_norm": 1.0407111644744873,
|
| 1320 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 1321 |
+
"loss": 4.6982,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.05608901082152111,
|
| 1326 |
+
"grad_norm": 0.9729002118110657,
|
| 1327 |
+
"learning_rate": 2.1697790249779636e-06,
|
| 1328 |
+
"loss": 4.3347,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.056393842402072854,
|
| 1333 |
+
"grad_norm": 1.0244466066360474,
|
| 1334 |
+
"learning_rate": 1.908717841359048e-06,
|
| 1335 |
+
"loss": 4.8428,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.0566986739826246,
|
| 1340 |
+
"grad_norm": 0.9946762323379517,
|
| 1341 |
+
"learning_rate": 1.6640797865406288e-06,
|
| 1342 |
+
"loss": 4.1583,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.05700350556317634,
|
| 1347 |
+
"grad_norm": 1.0568474531173706,
|
| 1348 |
+
"learning_rate": 1.4359484041943038e-06,
|
| 1349 |
+
"loss": 4.2906,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.05730833714372809,
|
| 1354 |
+
"grad_norm": 0.9759791493415833,
|
| 1355 |
+
"learning_rate": 1.2244016009781701e-06,
|
| 1356 |
+
"loss": 4.1194,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.05761316872427984,
|
| 1361 |
+
"grad_norm": 0.9902230501174927,
|
| 1362 |
+
"learning_rate": 1.0295116199317057e-06,
|
| 1363 |
+
"loss": 4.2028,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.05791800030483158,
|
| 1368 |
+
"grad_norm": 1.1896251440048218,
|
| 1369 |
+
"learning_rate": 8.513450158049108e-07,
|
| 1370 |
+
"loss": 3.8738,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.058222831885383325,
|
| 1375 |
+
"grad_norm": 1.0268330574035645,
|
| 1376 |
+
"learning_rate": 6.899626323298713e-07,
|
| 1377 |
+
"loss": 3.3157,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.05852766346593507,
|
| 1382 |
+
"grad_norm": 1.0296571254730225,
|
| 1383 |
+
"learning_rate": 5.454195814427021e-07,
|
| 1384 |
+
"loss": 3.7593,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.05883249504648681,
|
| 1389 |
+
"grad_norm": 1.1712251901626587,
|
| 1390 |
+
"learning_rate": 4.177652244628627e-07,
|
| 1391 |
+
"loss": 3.9181,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.059137326627038564,
|
| 1396 |
+
"grad_norm": 1.2218458652496338,
|
| 1397 |
+
"learning_rate": 3.0704315523631953e-07,
|
| 1398 |
+
"loss": 3.2565,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.05944215820759031,
|
| 1403 |
+
"grad_norm": 1.21880042552948,
|
| 1404 |
+
"learning_rate": 2.1329118524827662e-07,
|
| 1405 |
+
"loss": 3.3098,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.05974698978814205,
|
| 1410 |
+
"grad_norm": 1.210938572883606,
|
| 1411 |
+
"learning_rate": 1.3654133071059893e-07,
|
| 1412 |
+
"loss": 3.1741,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.060051821368693796,
|
| 1417 |
+
"grad_norm": 1.3736565113067627,
|
| 1418 |
+
"learning_rate": 7.681980162830282e-08,
|
| 1419 |
+
"loss": 3.1215,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.06035665294924554,
|
| 1424 |
+
"grad_norm": 1.5788041353225708,
|
| 1425 |
+
"learning_rate": 3.4146992848854695e-08,
|
| 1426 |
+
"loss": 3.0409,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.060661484529797284,
|
| 1431 |
+
"grad_norm": 2.2263410091400146,
|
| 1432 |
+
"learning_rate": 8.537477097364522e-09,
|
| 1433 |
+
"loss": 3.291,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.060966316110349035,
|
| 1438 |
+
"grad_norm": 4.716347694396973,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 3.6232,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.060966316110349035,
|
| 1445 |
+
"eval_loss": 1.224632740020752,
|
| 1446 |
+
"eval_runtime": 294.8119,
|
| 1447 |
+
"eval_samples_per_second": 18.741,
|
| 1448 |
+
"eval_steps_per_second": 9.372,
|
| 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": 1.5071184206954496e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|