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 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e0cffb309fd0b230d02862507273acca29051e5ff134bb25eb4835db1a7429d
|
| 3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 341314196
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45e97aba22cd2b82b72e255738f3a4f4cceb6c0513d972d8f70a4e9d72fb6b94
|
| 3 |
size 341314196
|
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 sha256:1d5cf493db0c0c7bc670cf116aec49a25e005f3ddbcaff15b7dda32f0edde2ba
|
| 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:c47edf82128c3f034f21204d4b9ce5c76cd3269748ce31061b148a0a389d049d
|
| 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": 7.819,
|
| 1090 |
"eval_steps_per_second": 1.97,
|
| 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": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.3729252815246582,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.2238388360380526,
|
| 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": 7.819,
|
| 1090 |
"eval_steps_per_second": 1.97,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.1689983212087297,
|
| 1095 |
+
"grad_norm": 0.5888712406158447,
|
| 1096 |
+
"learning_rate": 2.5944210526315793e-05,
|
| 1097 |
+
"loss": 1.4846,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.17011751538891998,
|
| 1102 |
+
"grad_norm": 0.6555752754211426,
|
| 1103 |
+
"learning_rate": 2.5414736842105266e-05,
|
| 1104 |
+
"loss": 2.1498,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.17123670956911025,
|
| 1109 |
+
"grad_norm": 0.5300792455673218,
|
| 1110 |
+
"learning_rate": 2.4885263157894737e-05,
|
| 1111 |
+
"loss": 1.4384,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.17235590374930052,
|
| 1116 |
+
"grad_norm": 0.6344078183174133,
|
| 1117 |
+
"learning_rate": 2.4355789473684214e-05,
|
| 1118 |
+
"loss": 1.8914,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.17347509792949076,
|
| 1123 |
+
"grad_norm": 0.6226881742477417,
|
| 1124 |
+
"learning_rate": 2.3826315789473684e-05,
|
| 1125 |
+
"loss": 2.2678,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.17459429210968103,
|
| 1130 |
+
"grad_norm": 0.5832647085189819,
|
| 1131 |
+
"learning_rate": 2.3296842105263158e-05,
|
| 1132 |
+
"loss": 1.9514,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.1757134862898713,
|
| 1137 |
+
"grad_norm": 0.7049195170402527,
|
| 1138 |
+
"learning_rate": 2.2767368421052635e-05,
|
| 1139 |
+
"loss": 2.2213,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.17683268047006157,
|
| 1144 |
+
"grad_norm": 0.5463729500770569,
|
| 1145 |
+
"learning_rate": 2.2237894736842105e-05,
|
| 1146 |
+
"loss": 1.7612,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.1779518746502518,
|
| 1151 |
+
"grad_norm": 0.48315393924713135,
|
| 1152 |
+
"learning_rate": 2.170842105263158e-05,
|
| 1153 |
+
"loss": 1.2555,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.17907106883044208,
|
| 1158 |
+
"grad_norm": 0.5512372851371765,
|
| 1159 |
+
"learning_rate": 2.1178947368421053e-05,
|
| 1160 |
+
"loss": 1.5839,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.18019026301063235,
|
| 1165 |
+
"grad_norm": 0.5438306927680969,
|
| 1166 |
+
"learning_rate": 2.0649473684210527e-05,
|
| 1167 |
+
"loss": 1.6096,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.18130945719082261,
|
| 1172 |
+
"grad_norm": 0.45787855982780457,
|
| 1173 |
+
"learning_rate": 2.0120000000000004e-05,
|
| 1174 |
+
"loss": 1.1068,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.18242865137101288,
|
| 1179 |
+
"grad_norm": 0.4952705204486847,
|
| 1180 |
+
"learning_rate": 1.9590526315789474e-05,
|
| 1181 |
+
"loss": 1.1894,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.18354784555120313,
|
| 1186 |
+
"grad_norm": 0.6114853024482727,
|
| 1187 |
+
"learning_rate": 1.9061052631578948e-05,
|
| 1188 |
+
"loss": 1.7787,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.1846670397313934,
|
| 1193 |
+
"grad_norm": 0.4656667709350586,
|
| 1194 |
+
"learning_rate": 1.8531578947368422e-05,
|
| 1195 |
+
"loss": 0.971,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.18578623391158366,
|
| 1200 |
+
"grad_norm": 0.6445344686508179,
|
| 1201 |
+
"learning_rate": 1.8002105263157896e-05,
|
| 1202 |
+
"loss": 1.7756,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.18690542809177393,
|
| 1207 |
+
"grad_norm": 0.5453393459320068,
|
| 1208 |
+
"learning_rate": 1.747263157894737e-05,
|
| 1209 |
+
"loss": 1.2964,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.18802462227196418,
|
| 1214 |
+
"grad_norm": 0.5461987853050232,
|
| 1215 |
+
"learning_rate": 1.6943157894736843e-05,
|
| 1216 |
+
"loss": 1.2804,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.18914381645215445,
|
| 1221 |
+
"grad_norm": 0.5559154748916626,
|
| 1222 |
+
"learning_rate": 1.6413684210526317e-05,
|
| 1223 |
+
"loss": 1.3295,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.19026301063234471,
|
| 1228 |
+
"grad_norm": 0.521136462688446,
|
| 1229 |
+
"learning_rate": 1.588421052631579e-05,
|
| 1230 |
+
"loss": 1.1399,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.19138220481253498,
|
| 1235 |
+
"grad_norm": 0.5922938585281372,
|
| 1236 |
+
"learning_rate": 1.5354736842105264e-05,
|
| 1237 |
+
"loss": 1.2445,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.19250139899272523,
|
| 1242 |
+
"grad_norm": 0.5375987887382507,
|
| 1243 |
+
"learning_rate": 1.4825263157894736e-05,
|
| 1244 |
+
"loss": 1.0522,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.1936205931729155,
|
| 1249 |
+
"grad_norm": 0.5461782217025757,
|
| 1250 |
+
"learning_rate": 1.4295789473684212e-05,
|
| 1251 |
+
"loss": 1.1601,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.19473978735310576,
|
| 1256 |
+
"grad_norm": 0.5203652381896973,
|
| 1257 |
+
"learning_rate": 1.3766315789473686e-05,
|
| 1258 |
+
"loss": 1.1082,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.19585898153329603,
|
| 1263 |
+
"grad_norm": 0.707985520362854,
|
| 1264 |
+
"learning_rate": 1.3236842105263158e-05,
|
| 1265 |
+
"loss": 1.8355,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.1969781757134863,
|
| 1270 |
+
"grad_norm": 0.5729698538780212,
|
| 1271 |
+
"learning_rate": 1.2707368421052633e-05,
|
| 1272 |
+
"loss": 1.0793,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.19809736989367654,
|
| 1277 |
+
"grad_norm": 0.5605016350746155,
|
| 1278 |
+
"learning_rate": 1.2177894736842107e-05,
|
| 1279 |
+
"loss": 1.0786,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.19921656407386681,
|
| 1284 |
+
"grad_norm": 0.495593398809433,
|
| 1285 |
+
"learning_rate": 1.1648421052631579e-05,
|
| 1286 |
+
"loss": 0.803,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.20033575825405708,
|
| 1291 |
+
"grad_norm": 0.5838123559951782,
|
| 1292 |
+
"learning_rate": 1.1118947368421053e-05,
|
| 1293 |
+
"loss": 1.1495,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.20145495243424735,
|
| 1298 |
+
"grad_norm": 0.5868124961853027,
|
| 1299 |
+
"learning_rate": 1.0589473684210526e-05,
|
| 1300 |
+
"loss": 1.1091,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.2025741466144376,
|
| 1305 |
+
"grad_norm": 0.6182821393013,
|
| 1306 |
+
"learning_rate": 1.0060000000000002e-05,
|
| 1307 |
+
"loss": 1.2361,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.20369334079462786,
|
| 1312 |
+
"grad_norm": 0.516312301158905,
|
| 1313 |
+
"learning_rate": 9.530526315789474e-06,
|
| 1314 |
+
"loss": 0.9179,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.20481253497481813,
|
| 1319 |
+
"grad_norm": 0.6000572443008423,
|
| 1320 |
+
"learning_rate": 9.001052631578948e-06,
|
| 1321 |
+
"loss": 1.0504,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.2059317291550084,
|
| 1326 |
+
"grad_norm": 0.632702112197876,
|
| 1327 |
+
"learning_rate": 8.471578947368422e-06,
|
| 1328 |
+
"loss": 1.2226,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.20705092333519864,
|
| 1333 |
+
"grad_norm": 0.587997317314148,
|
| 1334 |
+
"learning_rate": 7.942105263157895e-06,
|
| 1335 |
+
"loss": 1.0234,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.2081701175153889,
|
| 1340 |
+
"grad_norm": 0.6361390948295593,
|
| 1341 |
+
"learning_rate": 7.412631578947368e-06,
|
| 1342 |
+
"loss": 1.2129,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.20928931169557918,
|
| 1347 |
+
"grad_norm": 0.5540517568588257,
|
| 1348 |
+
"learning_rate": 6.883157894736843e-06,
|
| 1349 |
+
"loss": 0.8871,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.21040850587576945,
|
| 1354 |
+
"grad_norm": 0.6559872031211853,
|
| 1355 |
+
"learning_rate": 6.3536842105263166e-06,
|
| 1356 |
+
"loss": 1.1548,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.21152770005595972,
|
| 1361 |
+
"grad_norm": 0.7367547750473022,
|
| 1362 |
+
"learning_rate": 5.8242105263157895e-06,
|
| 1363 |
+
"loss": 1.4792,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.21264689423614996,
|
| 1368 |
+
"grad_norm": 0.6602901816368103,
|
| 1369 |
+
"learning_rate": 5.294736842105263e-06,
|
| 1370 |
+
"loss": 1.1934,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.21376608841634023,
|
| 1375 |
+
"grad_norm": 0.6574941873550415,
|
| 1376 |
+
"learning_rate": 4.765263157894737e-06,
|
| 1377 |
+
"loss": 0.9984,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.2148852825965305,
|
| 1382 |
+
"grad_norm": 0.6636906266212463,
|
| 1383 |
+
"learning_rate": 4.235789473684211e-06,
|
| 1384 |
+
"loss": 0.9586,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.21600447677672077,
|
| 1389 |
+
"grad_norm": 0.7810147404670715,
|
| 1390 |
+
"learning_rate": 3.706315789473684e-06,
|
| 1391 |
+
"loss": 1.3688,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.217123670956911,
|
| 1396 |
+
"grad_norm": 0.6754685640335083,
|
| 1397 |
+
"learning_rate": 3.1768421052631583e-06,
|
| 1398 |
+
"loss": 1.1149,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.21824286513710128,
|
| 1403 |
+
"grad_norm": 0.7550037503242493,
|
| 1404 |
+
"learning_rate": 2.6473684210526316e-06,
|
| 1405 |
+
"loss": 1.172,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.21936205931729155,
|
| 1410 |
+
"grad_norm": 0.8898350596427917,
|
| 1411 |
+
"learning_rate": 2.1178947368421054e-06,
|
| 1412 |
+
"loss": 1.4463,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.22048125349748182,
|
| 1417 |
+
"grad_norm": 0.8928287625312805,
|
| 1418 |
+
"learning_rate": 1.5884210526315791e-06,
|
| 1419 |
+
"loss": 1.1914,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.22160044767767206,
|
| 1424 |
+
"grad_norm": 1.2467180490493774,
|
| 1425 |
+
"learning_rate": 1.0589473684210527e-06,
|
| 1426 |
+
"loss": 1.2538,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.22271964185786233,
|
| 1431 |
+
"grad_norm": 1.032840371131897,
|
| 1432 |
+
"learning_rate": 5.294736842105263e-07,
|
| 1433 |
+
"loss": 1.4659,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.2238388360380526,
|
| 1438 |
+
"grad_norm": 1.5969254970550537,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 2.3837,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.2238388360380526,
|
| 1445 |
+
"eval_loss": 1.3729252815246582,
|
| 1446 |
+
"eval_runtime": 47.7822,
|
| 1447 |
+
"eval_samples_per_second": 7.89,
|
| 1448 |
+
"eval_steps_per_second": 1.988,
|
| 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": 8.48538888044544e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|