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 sha256:0fbbef11402e7901631c5b4f78fe9ca749215a9ea2c770faf33b684c6e1778f6
|
| 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:eed25f430dad014536cb59932770b715de65b3d686eeb710e06c7b910ae21ca2
|
| 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 sha256:249b9b2ab620ee3e17a6a4c1ff96d50d78be165aedd32c493062ba69c814cfdc
|
| 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:f5efc880080e0854e5765c7a5ea108f46d0ccbf30b054c9bbb5a2162a1c5babf
|
| 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": 19.204,
|
| 1090 |
"eval_steps_per_second": 4.801,
|
| 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": 1.6074018478393555,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.02050020500205002,
|
| 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": 19.204,
|
| 1090 |
"eval_steps_per_second": 4.801,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.015477654776547766,
|
| 1095 |
+
"grad_norm": 0.5801679491996765,
|
| 1096 |
+
"learning_rate": 2.5815263157894736e-05,
|
| 1097 |
+
"loss": 1.5924,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.015580155801558016,
|
| 1102 |
+
"grad_norm": 0.7414329051971436,
|
| 1103 |
+
"learning_rate": 2.528842105263158e-05,
|
| 1104 |
+
"loss": 1.8859,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.015682656826568265,
|
| 1109 |
+
"grad_norm": 0.7194873690605164,
|
| 1110 |
+
"learning_rate": 2.4761578947368418e-05,
|
| 1111 |
+
"loss": 1.7569,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.015785157851578517,
|
| 1116 |
+
"grad_norm": 0.7468145489692688,
|
| 1117 |
+
"learning_rate": 2.423473684210526e-05,
|
| 1118 |
+
"loss": 1.5206,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.015887658876588766,
|
| 1123 |
+
"grad_norm": 0.9180918335914612,
|
| 1124 |
+
"learning_rate": 2.3707894736842103e-05,
|
| 1125 |
+
"loss": 1.6067,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.015990159901599015,
|
| 1130 |
+
"grad_norm": 1.052054762840271,
|
| 1131 |
+
"learning_rate": 2.3181052631578946e-05,
|
| 1132 |
+
"loss": 1.5043,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.016092660926609267,
|
| 1137 |
+
"grad_norm": 0.8969054818153381,
|
| 1138 |
+
"learning_rate": 2.265421052631579e-05,
|
| 1139 |
+
"loss": 1.5507,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.016195161951619515,
|
| 1144 |
+
"grad_norm": 0.9579923152923584,
|
| 1145 |
+
"learning_rate": 2.212736842105263e-05,
|
| 1146 |
+
"loss": 1.5959,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.016297662976629768,
|
| 1151 |
+
"grad_norm": 1.0006402730941772,
|
| 1152 |
+
"learning_rate": 2.1600526315789474e-05,
|
| 1153 |
+
"loss": 1.6553,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.016400164001640016,
|
| 1158 |
+
"grad_norm": 1.090065598487854,
|
| 1159 |
+
"learning_rate": 2.1073684210526313e-05,
|
| 1160 |
+
"loss": 1.7441,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.016502665026650265,
|
| 1165 |
+
"grad_norm": 1.0853620767593384,
|
| 1166 |
+
"learning_rate": 2.0546842105263155e-05,
|
| 1167 |
+
"loss": 1.8341,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.016605166051660517,
|
| 1172 |
+
"grad_norm": 0.9956846833229065,
|
| 1173 |
+
"learning_rate": 2.002e-05,
|
| 1174 |
+
"loss": 1.7975,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.016707667076670766,
|
| 1179 |
+
"grad_norm": 1.2386821508407593,
|
| 1180 |
+
"learning_rate": 1.949315789473684e-05,
|
| 1181 |
+
"loss": 1.7063,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.016810168101681018,
|
| 1186 |
+
"grad_norm": 0.9561980962753296,
|
| 1187 |
+
"learning_rate": 1.8966315789473683e-05,
|
| 1188 |
+
"loss": 1.4661,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.016912669126691267,
|
| 1193 |
+
"grad_norm": 1.2328252792358398,
|
| 1194 |
+
"learning_rate": 1.8439473684210522e-05,
|
| 1195 |
+
"loss": 1.7836,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.017015170151701516,
|
| 1200 |
+
"grad_norm": 1.1177650690078735,
|
| 1201 |
+
"learning_rate": 1.791263157894737e-05,
|
| 1202 |
+
"loss": 1.7525,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.017117671176711768,
|
| 1207 |
+
"grad_norm": 1.012744426727295,
|
| 1208 |
+
"learning_rate": 1.738578947368421e-05,
|
| 1209 |
+
"loss": 1.5806,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.017220172201722016,
|
| 1214 |
+
"grad_norm": 1.1991872787475586,
|
| 1215 |
+
"learning_rate": 1.685894736842105e-05,
|
| 1216 |
+
"loss": 1.9107,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.01732267322673227,
|
| 1221 |
+
"grad_norm": 1.1519800424575806,
|
| 1222 |
+
"learning_rate": 1.6332105263157893e-05,
|
| 1223 |
+
"loss": 1.7668,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.017425174251742517,
|
| 1228 |
+
"grad_norm": 1.0659619569778442,
|
| 1229 |
+
"learning_rate": 1.5805263157894735e-05,
|
| 1230 |
+
"loss": 1.5949,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.017527675276752766,
|
| 1235 |
+
"grad_norm": 1.173683524131775,
|
| 1236 |
+
"learning_rate": 1.5278421052631578e-05,
|
| 1237 |
+
"loss": 1.4432,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.017630176301763018,
|
| 1242 |
+
"grad_norm": 1.2720458507537842,
|
| 1243 |
+
"learning_rate": 1.4751578947368419e-05,
|
| 1244 |
+
"loss": 1.6366,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.017732677326773267,
|
| 1249 |
+
"grad_norm": 1.412047266960144,
|
| 1250 |
+
"learning_rate": 1.4224736842105262e-05,
|
| 1251 |
+
"loss": 1.3457,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.01783517835178352,
|
| 1256 |
+
"grad_norm": 1.2512191534042358,
|
| 1257 |
+
"learning_rate": 1.3697894736842106e-05,
|
| 1258 |
+
"loss": 1.4677,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.017937679376793768,
|
| 1263 |
+
"grad_norm": 1.4642128944396973,
|
| 1264 |
+
"learning_rate": 1.3171052631578945e-05,
|
| 1265 |
+
"loss": 1.6189,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.018040180401804017,
|
| 1270 |
+
"grad_norm": 1.37020742893219,
|
| 1271 |
+
"learning_rate": 1.264421052631579e-05,
|
| 1272 |
+
"loss": 1.669,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.01814268142681427,
|
| 1277 |
+
"grad_norm": 1.3239974975585938,
|
| 1278 |
+
"learning_rate": 1.211736842105263e-05,
|
| 1279 |
+
"loss": 1.5652,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.018245182451824517,
|
| 1284 |
+
"grad_norm": 1.3516684770584106,
|
| 1285 |
+
"learning_rate": 1.1590526315789473e-05,
|
| 1286 |
+
"loss": 1.5116,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.01834768347683477,
|
| 1291 |
+
"grad_norm": 1.7171400785446167,
|
| 1292 |
+
"learning_rate": 1.1063684210526316e-05,
|
| 1293 |
+
"loss": 2.1205,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.01845018450184502,
|
| 1298 |
+
"grad_norm": 1.3495593070983887,
|
| 1299 |
+
"learning_rate": 1.0536842105263156e-05,
|
| 1300 |
+
"loss": 1.1325,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.018552685526855267,
|
| 1305 |
+
"grad_norm": 1.9317636489868164,
|
| 1306 |
+
"learning_rate": 1.001e-05,
|
| 1307 |
+
"loss": 1.5652,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.01865518655186552,
|
| 1312 |
+
"grad_norm": 2.422668695449829,
|
| 1313 |
+
"learning_rate": 9.483157894736842e-06,
|
| 1314 |
+
"loss": 1.5383,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.018757687576875768,
|
| 1319 |
+
"grad_norm": 2.1638026237487793,
|
| 1320 |
+
"learning_rate": 8.956315789473684e-06,
|
| 1321 |
+
"loss": 1.8706,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.01886018860188602,
|
| 1326 |
+
"grad_norm": 2.067598342895508,
|
| 1327 |
+
"learning_rate": 8.429473684210525e-06,
|
| 1328 |
+
"loss": 1.867,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.01896268962689627,
|
| 1333 |
+
"grad_norm": 2.594118118286133,
|
| 1334 |
+
"learning_rate": 7.902631578947368e-06,
|
| 1335 |
+
"loss": 1.5805,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.019065190651906518,
|
| 1340 |
+
"grad_norm": 2.4905567169189453,
|
| 1341 |
+
"learning_rate": 7.3757894736842095e-06,
|
| 1342 |
+
"loss": 1.0738,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.01916769167691677,
|
| 1347 |
+
"grad_norm": 2.5180282592773438,
|
| 1348 |
+
"learning_rate": 6.848947368421053e-06,
|
| 1349 |
+
"loss": 1.7173,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.01927019270192702,
|
| 1354 |
+
"grad_norm": 2.4175117015838623,
|
| 1355 |
+
"learning_rate": 6.322105263157895e-06,
|
| 1356 |
+
"loss": 1.5599,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.01937269372693727,
|
| 1361 |
+
"grad_norm": 2.6707475185394287,
|
| 1362 |
+
"learning_rate": 5.7952631578947365e-06,
|
| 1363 |
+
"loss": 1.3726,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.01947519475194752,
|
| 1368 |
+
"grad_norm": 3.7667629718780518,
|
| 1369 |
+
"learning_rate": 5.268421052631578e-06,
|
| 1370 |
+
"loss": 0.8815,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.019577695776957768,
|
| 1375 |
+
"grad_norm": 3.1217727661132812,
|
| 1376 |
+
"learning_rate": 4.741578947368421e-06,
|
| 1377 |
+
"loss": 1.5793,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.01968019680196802,
|
| 1382 |
+
"grad_norm": 3.0410215854644775,
|
| 1383 |
+
"learning_rate": 4.2147368421052626e-06,
|
| 1384 |
+
"loss": 1.5182,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.01978269782697827,
|
| 1389 |
+
"grad_norm": 2.907959222793579,
|
| 1390 |
+
"learning_rate": 3.6878947368421047e-06,
|
| 1391 |
+
"loss": 1.2825,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.01988519885198852,
|
| 1396 |
+
"grad_norm": 3.6714532375335693,
|
| 1397 |
+
"learning_rate": 3.1610526315789474e-06,
|
| 1398 |
+
"loss": 1.2199,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.01998769987699877,
|
| 1403 |
+
"grad_norm": 3.782942295074463,
|
| 1404 |
+
"learning_rate": 2.634210526315789e-06,
|
| 1405 |
+
"loss": 1.436,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.02009020090200902,
|
| 1410 |
+
"grad_norm": 4.33630895614624,
|
| 1411 |
+
"learning_rate": 2.1073684210526313e-06,
|
| 1412 |
+
"loss": 1.2589,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.02019270192701927,
|
| 1417 |
+
"grad_norm": 3.1009058952331543,
|
| 1418 |
+
"learning_rate": 1.5805263157894737e-06,
|
| 1419 |
+
"loss": 1.0389,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.02029520295202952,
|
| 1424 |
+
"grad_norm": 3.7881686687469482,
|
| 1425 |
+
"learning_rate": 1.0536842105263156e-06,
|
| 1426 |
+
"loss": 1.0837,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.02039770397703977,
|
| 1431 |
+
"grad_norm": 5.994607925415039,
|
| 1432 |
+
"learning_rate": 5.268421052631578e-07,
|
| 1433 |
+
"loss": 1.7627,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.02050020500205002,
|
| 1438 |
+
"grad_norm": 6.927132606506348,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.7932,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.02050020500205002,
|
| 1445 |
+
"eval_loss": 1.6074018478393555,
|
| 1446 |
+
"eval_runtime": 214.0108,
|
| 1447 |
+
"eval_samples_per_second": 19.195,
|
| 1448 |
+
"eval_steps_per_second": 4.799,
|
| 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
|