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 645975704
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0323b4a58308037e469680b9bfb1b8b01bfbb35a6c067db3b205ce6afd77e20
|
| 3 |
size 645975704
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 328468404
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7be146ea174b49420c7a2cec1584b7f51f009e6556fe4b5d72194eaf567a0055
|
| 3 |
size 328468404
|
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 sha256:212ecee7ba5bbad66868b4f13a31101fb6a6055516f2090d01279bc6d5e12910
|
| 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": 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": 9.4,
|
| 1090 |
"eval_steps_per_second": 2.351,
|
| 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": 0.983881413936615,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.03251239535072747,
|
| 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": 9.4,
|
| 1090 |
"eval_steps_per_second": 2.351,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.024546858489799237,
|
| 1095 |
+
"grad_norm": 0.32013484835624695,
|
| 1096 |
+
"learning_rate": 2.5944210526315793e-05,
|
| 1097 |
+
"loss": 0.9826,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.024709420466552872,
|
| 1102 |
+
"grad_norm": 0.34136995673179626,
|
| 1103 |
+
"learning_rate": 2.5414736842105266e-05,
|
| 1104 |
+
"loss": 0.9456,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.02487198244330651,
|
| 1109 |
+
"grad_norm": 0.35575228929519653,
|
| 1110 |
+
"learning_rate": 2.4885263157894737e-05,
|
| 1111 |
+
"loss": 0.9309,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.02503454442006015,
|
| 1116 |
+
"grad_norm": 0.39715224504470825,
|
| 1117 |
+
"learning_rate": 2.4355789473684214e-05,
|
| 1118 |
+
"loss": 1.0874,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.025197106396813784,
|
| 1123 |
+
"grad_norm": 0.39866402745246887,
|
| 1124 |
+
"learning_rate": 2.3826315789473684e-05,
|
| 1125 |
+
"loss": 0.9358,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.025359668373567422,
|
| 1130 |
+
"grad_norm": 0.39832454919815063,
|
| 1131 |
+
"learning_rate": 2.3296842105263158e-05,
|
| 1132 |
+
"loss": 1.0743,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.02552223035032106,
|
| 1137 |
+
"grad_norm": 0.40810534358024597,
|
| 1138 |
+
"learning_rate": 2.2767368421052635e-05,
|
| 1139 |
+
"loss": 0.9787,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.0256847923270747,
|
| 1144 |
+
"grad_norm": 0.38781747221946716,
|
| 1145 |
+
"learning_rate": 2.2237894736842105e-05,
|
| 1146 |
+
"loss": 0.8989,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.025847354303828333,
|
| 1151 |
+
"grad_norm": 0.4570434093475342,
|
| 1152 |
+
"learning_rate": 2.170842105263158e-05,
|
| 1153 |
+
"loss": 0.9888,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.026009916280581972,
|
| 1158 |
+
"grad_norm": 0.4297999143600464,
|
| 1159 |
+
"learning_rate": 2.1178947368421053e-05,
|
| 1160 |
+
"loss": 0.9206,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.02617247825733561,
|
| 1165 |
+
"grad_norm": 0.42393121123313904,
|
| 1166 |
+
"learning_rate": 2.0649473684210527e-05,
|
| 1167 |
+
"loss": 0.9191,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.026335040234089245,
|
| 1172 |
+
"grad_norm": 0.43705666065216064,
|
| 1173 |
+
"learning_rate": 2.0120000000000004e-05,
|
| 1174 |
+
"loss": 0.9721,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.026497602210842883,
|
| 1179 |
+
"grad_norm": 0.46401333808898926,
|
| 1180 |
+
"learning_rate": 1.9590526315789474e-05,
|
| 1181 |
+
"loss": 1.0054,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.02666016418759652,
|
| 1186 |
+
"grad_norm": 0.45111915469169617,
|
| 1187 |
+
"learning_rate": 1.9061052631578948e-05,
|
| 1188 |
+
"loss": 0.8965,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.02682272616435016,
|
| 1193 |
+
"grad_norm": 0.4912633001804352,
|
| 1194 |
+
"learning_rate": 1.8531578947368422e-05,
|
| 1195 |
+
"loss": 1.1235,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.026985288141103795,
|
| 1200 |
+
"grad_norm": 0.551999568939209,
|
| 1201 |
+
"learning_rate": 1.8002105263157896e-05,
|
| 1202 |
+
"loss": 1.0657,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.027147850117857433,
|
| 1207 |
+
"grad_norm": 0.5471257567405701,
|
| 1208 |
+
"learning_rate": 1.747263157894737e-05,
|
| 1209 |
+
"loss": 1.0765,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.02731041209461107,
|
| 1214 |
+
"grad_norm": 0.6052240133285522,
|
| 1215 |
+
"learning_rate": 1.6943157894736843e-05,
|
| 1216 |
+
"loss": 1.2019,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.027472974071364707,
|
| 1221 |
+
"grad_norm": 0.6268660426139832,
|
| 1222 |
+
"learning_rate": 1.6413684210526317e-05,
|
| 1223 |
+
"loss": 1.1699,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.027635536048118345,
|
| 1228 |
+
"grad_norm": 0.5555728673934937,
|
| 1229 |
+
"learning_rate": 1.588421052631579e-05,
|
| 1230 |
+
"loss": 0.9256,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.027798098024871983,
|
| 1235 |
+
"grad_norm": 0.6148643493652344,
|
| 1236 |
+
"learning_rate": 1.5354736842105264e-05,
|
| 1237 |
+
"loss": 0.9823,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.027960660001625618,
|
| 1242 |
+
"grad_norm": 0.6582595705986023,
|
| 1243 |
+
"learning_rate": 1.4825263157894736e-05,
|
| 1244 |
+
"loss": 1.1272,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.028123221978379256,
|
| 1249 |
+
"grad_norm": 0.657721996307373,
|
| 1250 |
+
"learning_rate": 1.4295789473684212e-05,
|
| 1251 |
+
"loss": 1.0821,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.028285783955132895,
|
| 1256 |
+
"grad_norm": 0.7575223445892334,
|
| 1257 |
+
"learning_rate": 1.3766315789473686e-05,
|
| 1258 |
+
"loss": 1.1628,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.028448345931886533,
|
| 1263 |
+
"grad_norm": 0.7547634243965149,
|
| 1264 |
+
"learning_rate": 1.3236842105263158e-05,
|
| 1265 |
+
"loss": 1.1852,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.028610907908640168,
|
| 1270 |
+
"grad_norm": 0.9611251950263977,
|
| 1271 |
+
"learning_rate": 1.2707368421052633e-05,
|
| 1272 |
+
"loss": 0.9881,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.028773469885393806,
|
| 1277 |
+
"grad_norm": 0.9127490520477295,
|
| 1278 |
+
"learning_rate": 1.2177894736842107e-05,
|
| 1279 |
+
"loss": 1.0568,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.028936031862147445,
|
| 1284 |
+
"grad_norm": 0.7519910931587219,
|
| 1285 |
+
"learning_rate": 1.1648421052631579e-05,
|
| 1286 |
+
"loss": 0.8341,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.02909859383890108,
|
| 1291 |
+
"grad_norm": 0.9325132369995117,
|
| 1292 |
+
"learning_rate": 1.1118947368421053e-05,
|
| 1293 |
+
"loss": 0.9248,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.029261155815654718,
|
| 1298 |
+
"grad_norm": 0.8238653540611267,
|
| 1299 |
+
"learning_rate": 1.0589473684210526e-05,
|
| 1300 |
+
"loss": 0.8453,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.029423717792408356,
|
| 1305 |
+
"grad_norm": 1.0096287727355957,
|
| 1306 |
+
"learning_rate": 1.0060000000000002e-05,
|
| 1307 |
+
"loss": 1.2289,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.029586279769161995,
|
| 1312 |
+
"grad_norm": 1.232429027557373,
|
| 1313 |
+
"learning_rate": 9.530526315789474e-06,
|
| 1314 |
+
"loss": 1.0992,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.02974884174591563,
|
| 1319 |
+
"grad_norm": 1.225100040435791,
|
| 1320 |
+
"learning_rate": 9.001052631578948e-06,
|
| 1321 |
+
"loss": 1.0505,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.029911403722669268,
|
| 1326 |
+
"grad_norm": 1.947990894317627,
|
| 1327 |
+
"learning_rate": 8.471578947368422e-06,
|
| 1328 |
+
"loss": 1.2918,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.030073965699422906,
|
| 1333 |
+
"grad_norm": 1.6593623161315918,
|
| 1334 |
+
"learning_rate": 7.942105263157895e-06,
|
| 1335 |
+
"loss": 1.2474,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.03023652767617654,
|
| 1340 |
+
"grad_norm": 1.3890700340270996,
|
| 1341 |
+
"learning_rate": 7.412631578947368e-06,
|
| 1342 |
+
"loss": 1.1882,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.03039908965293018,
|
| 1347 |
+
"grad_norm": 1.4280545711517334,
|
| 1348 |
+
"learning_rate": 6.883157894736843e-06,
|
| 1349 |
+
"loss": 1.2195,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.030561651629683818,
|
| 1354 |
+
"grad_norm": 1.4920859336853027,
|
| 1355 |
+
"learning_rate": 6.3536842105263166e-06,
|
| 1356 |
+
"loss": 0.8529,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.030724213606437453,
|
| 1361 |
+
"grad_norm": 1.9819258451461792,
|
| 1362 |
+
"learning_rate": 5.8242105263157895e-06,
|
| 1363 |
+
"loss": 0.9768,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.03088677558319109,
|
| 1368 |
+
"grad_norm": 1.6569184064865112,
|
| 1369 |
+
"learning_rate": 5.294736842105263e-06,
|
| 1370 |
+
"loss": 1.1028,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.03104933755994473,
|
| 1375 |
+
"grad_norm": 1.5863397121429443,
|
| 1376 |
+
"learning_rate": 4.765263157894737e-06,
|
| 1377 |
+
"loss": 0.9491,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.031211899536698368,
|
| 1382 |
+
"grad_norm": 1.8544268608093262,
|
| 1383 |
+
"learning_rate": 4.235789473684211e-06,
|
| 1384 |
+
"loss": 0.9581,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.031374461513452,
|
| 1389 |
+
"grad_norm": 1.6126660108566284,
|
| 1390 |
+
"learning_rate": 3.706315789473684e-06,
|
| 1391 |
+
"loss": 0.5916,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.031537023490205644,
|
| 1396 |
+
"grad_norm": 2.3393468856811523,
|
| 1397 |
+
"learning_rate": 3.1768421052631583e-06,
|
| 1398 |
+
"loss": 0.9394,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.03169958546695928,
|
| 1403 |
+
"grad_norm": 1.8670778274536133,
|
| 1404 |
+
"learning_rate": 2.6473684210526316e-06,
|
| 1405 |
+
"loss": 0.905,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.031862147443712914,
|
| 1410 |
+
"grad_norm": 2.77335786819458,
|
| 1411 |
+
"learning_rate": 2.1178947368421054e-06,
|
| 1412 |
+
"loss": 0.9273,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.032024709420466556,
|
| 1417 |
+
"grad_norm": 3.024428367614746,
|
| 1418 |
+
"learning_rate": 1.5884210526315791e-06,
|
| 1419 |
+
"loss": 1.3273,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.03218727139722019,
|
| 1424 |
+
"grad_norm": 2.7640976905822754,
|
| 1425 |
+
"learning_rate": 1.0589473684210527e-06,
|
| 1426 |
+
"loss": 0.9206,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.032349833373973826,
|
| 1431 |
+
"grad_norm": 2.9897639751434326,
|
| 1432 |
+
"learning_rate": 5.294736842105263e-07,
|
| 1433 |
+
"loss": 1.0956,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.03251239535072747,
|
| 1438 |
+
"grad_norm": 3.9954426288604736,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.2385,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.03251239535072747,
|
| 1445 |
+
"eval_loss": 0.983881413936615,
|
| 1446 |
+
"eval_runtime": 275.5247,
|
| 1447 |
+
"eval_samples_per_second": 9.404,
|
| 1448 |
+
"eval_steps_per_second": 2.352,
|
| 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": 7.127217035280384e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|