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 639691872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea17c10fc3e0d1fca2cbca97d6791fb21d0cc8b1d8b404b54a242a84018f1caf
|
| 3 |
size 639691872
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1279641042
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05b91d4ce032b17c778522c034dedf6a27c0231c044f23840f025bb1ff67354c
|
| 3 |
size 1279641042
|
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:e8ecd75598e972c810cf285aaa1e527eb3cd79801e76d98021a5e8cc302bbf63
|
| 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": 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": 7.212,
|
| 1090 |
"eval_steps_per_second": 3.607,
|
| 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": 0.6188913583755493,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.14057283429977158,
|
| 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": 7.212,
|
| 1090 |
"eval_steps_per_second": 3.607,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.10613248989632754,
|
| 1095 |
+
"grad_norm": 0.1557738333940506,
|
| 1096 |
+
"learning_rate": 1.9136088935510362e-05,
|
| 1097 |
+
"loss": 0.2682,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.10683535406782639,
|
| 1102 |
+
"grad_norm": 0.16045674681663513,
|
| 1103 |
+
"learning_rate": 1.8414449687337464e-05,
|
| 1104 |
+
"loss": 0.2497,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.10753821823932525,
|
| 1109 |
+
"grad_norm": 0.12793506681919098,
|
| 1110 |
+
"learning_rate": 1.7703596875660645e-05,
|
| 1111 |
+
"loss": 0.2241,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.10824108241082411,
|
| 1116 |
+
"grad_norm": 0.14981037378311157,
|
| 1117 |
+
"learning_rate": 1.700377325606388e-05,
|
| 1118 |
+
"loss": 0.2546,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.10894394658232297,
|
| 1123 |
+
"grad_norm": 0.14852780103683472,
|
| 1124 |
+
"learning_rate": 1.631521781767214e-05,
|
| 1125 |
+
"loss": 0.2791,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.10964681075382182,
|
| 1130 |
+
"grad_norm": 0.19065548479557037,
|
| 1131 |
+
"learning_rate": 1.5638165701536868e-05,
|
| 1132 |
+
"loss": 0.3471,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.11034967492532068,
|
| 1137 |
+
"grad_norm": 0.19516591727733612,
|
| 1138 |
+
"learning_rate": 1.4972848120335453e-05,
|
| 1139 |
+
"loss": 0.3812,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.11105253909681954,
|
| 1144 |
+
"grad_norm": 0.19356763362884521,
|
| 1145 |
+
"learning_rate": 1.4319492279412388e-05,
|
| 1146 |
+
"loss": 0.4681,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.1117554032683184,
|
| 1151 |
+
"grad_norm": 0.20971715450286865,
|
| 1152 |
+
"learning_rate": 1.3678321299188801e-05,
|
| 1153 |
+
"loss": 0.5021,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.11245826743981725,
|
| 1158 |
+
"grad_norm": 0.18173177540302277,
|
| 1159 |
+
"learning_rate": 1.3049554138967051e-05,
|
| 1160 |
+
"loss": 0.4129,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.11316113161131611,
|
| 1165 |
+
"grad_norm": 0.20953762531280518,
|
| 1166 |
+
"learning_rate": 1.2433405522156332e-05,
|
| 1167 |
+
"loss": 0.5283,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.11386399578281498,
|
| 1172 |
+
"grad_norm": 0.2320074439048767,
|
| 1173 |
+
"learning_rate": 1.183008586294485e-05,
|
| 1174 |
+
"loss": 0.5968,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.11456685995431383,
|
| 1179 |
+
"grad_norm": 0.231634259223938,
|
| 1180 |
+
"learning_rate": 1.1239801194443506e-05,
|
| 1181 |
+
"loss": 0.6878,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.11526972412581268,
|
| 1186 |
+
"grad_norm": 0.24556051194667816,
|
| 1187 |
+
"learning_rate": 1.066275309832584e-05,
|
| 1188 |
+
"loss": 0.5471,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.11597258829731154,
|
| 1193 |
+
"grad_norm": 0.2406870275735855,
|
| 1194 |
+
"learning_rate": 1.0099138635988026e-05,
|
| 1195 |
+
"loss": 0.64,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.1166754524688104,
|
| 1200 |
+
"grad_norm": 0.22864454984664917,
|
| 1201 |
+
"learning_rate": 9.549150281252633e-06,
|
| 1202 |
+
"loss": 0.6471,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.11737831664030926,
|
| 1207 |
+
"grad_norm": 0.24874155223369598,
|
| 1208 |
+
"learning_rate": 9.012975854638949e-06,
|
| 1209 |
+
"loss": 0.639,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.11808118081180811,
|
| 1214 |
+
"grad_norm": 0.23163682222366333,
|
| 1215 |
+
"learning_rate": 8.490798459222476e-06,
|
| 1216 |
+
"loss": 0.5323,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.11878404498330698,
|
| 1221 |
+
"grad_norm": 0.2423689216375351,
|
| 1222 |
+
"learning_rate": 7.982796418105371e-06,
|
| 1223 |
+
"loss": 0.6043,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.11948690915480584,
|
| 1228 |
+
"grad_norm": 0.2547641396522522,
|
| 1229 |
+
"learning_rate": 7.489143213519301e-06,
|
| 1230 |
+
"loss": 0.6641,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.12018977332630469,
|
| 1235 |
+
"grad_norm": 0.23600344359874725,
|
| 1236 |
+
"learning_rate": 7.010007427581378e-06,
|
| 1237 |
+
"loss": 0.5934,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.12089263749780355,
|
| 1242 |
+
"grad_norm": 0.252996563911438,
|
| 1243 |
+
"learning_rate": 6.5455526847235825e-06,
|
| 1244 |
+
"loss": 0.6689,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.12159550166930241,
|
| 1249 |
+
"grad_norm": 0.25687330961227417,
|
| 1250 |
+
"learning_rate": 6.0959375958151045e-06,
|
| 1251 |
+
"loss": 0.6246,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.12229836584080127,
|
| 1256 |
+
"grad_norm": 0.2583775222301483,
|
| 1257 |
+
"learning_rate": 5.6613157039969055e-06,
|
| 1258 |
+
"loss": 0.7533,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.12300123001230012,
|
| 1263 |
+
"grad_norm": 0.2819630801677704,
|
| 1264 |
+
"learning_rate": 5.241835432246889e-06,
|
| 1265 |
+
"loss": 0.7883,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.12370409418379898,
|
| 1270 |
+
"grad_norm": 0.28463077545166016,
|
| 1271 |
+
"learning_rate": 4.837640032693558e-06,
|
| 1272 |
+
"loss": 0.7116,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.12440695835529784,
|
| 1277 |
+
"grad_norm": 0.27820444107055664,
|
| 1278 |
+
"learning_rate": 4.448867537695578e-06,
|
| 1279 |
+
"loss": 0.8034,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.1251098225267967,
|
| 1284 |
+
"grad_norm": 0.27489644289016724,
|
| 1285 |
+
"learning_rate": 4.075650712703849e-06,
|
| 1286 |
+
"loss": 0.7264,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.12581268669829557,
|
| 1291 |
+
"grad_norm": 0.278911828994751,
|
| 1292 |
+
"learning_rate": 3.71811701092219e-06,
|
| 1293 |
+
"loss": 0.6959,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.1265155508697944,
|
| 1298 |
+
"grad_norm": 0.30769917368888855,
|
| 1299 |
+
"learning_rate": 3.376388529782215e-06,
|
| 1300 |
+
"loss": 0.7629,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.12721841504129328,
|
| 1305 |
+
"grad_norm": 0.34087008237838745,
|
| 1306 |
+
"learning_rate": 3.0505819692471792e-06,
|
| 1307 |
+
"loss": 0.7145,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.12792127921279212,
|
| 1312 |
+
"grad_norm": 0.3040371239185333,
|
| 1313 |
+
"learning_rate": 2.7408085919590264e-06,
|
| 1314 |
+
"loss": 0.6648,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.12862414338429098,
|
| 1319 |
+
"grad_norm": 0.38694098591804504,
|
| 1320 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 1321 |
+
"loss": 0.7641,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.12932700755578985,
|
| 1326 |
+
"grad_norm": 0.4117843210697174,
|
| 1327 |
+
"learning_rate": 2.1697790249779636e-06,
|
| 1328 |
+
"loss": 0.63,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.1300298717272887,
|
| 1333 |
+
"grad_norm": 0.37666454911231995,
|
| 1334 |
+
"learning_rate": 1.908717841359048e-06,
|
| 1335 |
+
"loss": 0.6769,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.13073273589878756,
|
| 1340 |
+
"grad_norm": 0.43295755982398987,
|
| 1341 |
+
"learning_rate": 1.6640797865406288e-06,
|
| 1342 |
+
"loss": 0.7073,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.13143560007028643,
|
| 1347 |
+
"grad_norm": 0.35277169942855835,
|
| 1348 |
+
"learning_rate": 1.4359484041943038e-06,
|
| 1349 |
+
"loss": 0.8309,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.13213846424178527,
|
| 1354 |
+
"grad_norm": 0.33917170763015747,
|
| 1355 |
+
"learning_rate": 1.2244016009781701e-06,
|
| 1356 |
+
"loss": 0.8627,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.13284132841328414,
|
| 1361 |
+
"grad_norm": 0.31541842222213745,
|
| 1362 |
+
"learning_rate": 1.0295116199317057e-06,
|
| 1363 |
+
"loss": 0.7763,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.13354419258478298,
|
| 1368 |
+
"grad_norm": 0.2880040109157562,
|
| 1369 |
+
"learning_rate": 8.513450158049108e-07,
|
| 1370 |
+
"loss": 0.8386,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.13424705675628185,
|
| 1375 |
+
"grad_norm": 0.28794756531715393,
|
| 1376 |
+
"learning_rate": 6.899626323298713e-07,
|
| 1377 |
+
"loss": 0.813,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.13494992092778071,
|
| 1382 |
+
"grad_norm": 0.27827584743499756,
|
| 1383 |
+
"learning_rate": 5.454195814427021e-07,
|
| 1384 |
+
"loss": 0.7758,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.13565278509927955,
|
| 1389 |
+
"grad_norm": 0.30274316668510437,
|
| 1390 |
+
"learning_rate": 4.177652244628627e-07,
|
| 1391 |
+
"loss": 0.8663,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.13635564927077842,
|
| 1396 |
+
"grad_norm": 0.33732908964157104,
|
| 1397 |
+
"learning_rate": 3.0704315523631953e-07,
|
| 1398 |
+
"loss": 0.8044,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.1370585134422773,
|
| 1403 |
+
"grad_norm": 0.34816497564315796,
|
| 1404 |
+
"learning_rate": 2.1329118524827662e-07,
|
| 1405 |
+
"loss": 0.8055,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.13776137761377613,
|
| 1410 |
+
"grad_norm": 0.3468110263347626,
|
| 1411 |
+
"learning_rate": 1.3654133071059893e-07,
|
| 1412 |
+
"loss": 0.8233,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.138464241785275,
|
| 1417 |
+
"grad_norm": 0.3623807430267334,
|
| 1418 |
+
"learning_rate": 7.681980162830282e-08,
|
| 1419 |
+
"loss": 0.8115,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.13916710595677384,
|
| 1424 |
+
"grad_norm": 0.3784177899360657,
|
| 1425 |
+
"learning_rate": 3.4146992848854695e-08,
|
| 1426 |
+
"loss": 0.8123,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.1398699701282727,
|
| 1431 |
+
"grad_norm": 0.40762758255004883,
|
| 1432 |
+
"learning_rate": 8.537477097364522e-09,
|
| 1433 |
+
"loss": 0.8745,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.14057283429977158,
|
| 1438 |
+
"grad_norm": 0.48295310139656067,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.8319,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.14057283429977158,
|
| 1445 |
+
"eval_loss": 0.6188913583755493,
|
| 1446 |
+
"eval_runtime": 332.2497,
|
| 1447 |
+
"eval_samples_per_second": 7.214,
|
| 1448 |
+
"eval_steps_per_second": 3.609,
|
| 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": 4.83803453718528e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|