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 1157746040
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bf3f3a27cebadaa79096029d40b34edd398925aab694b8195b52fef3a2d83f7
|
| 3 |
size 1157746040
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 588699796
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ce79a681b2fbabc12ebb11e94940a9738f5b89d6019b63ffb38a222dcbb21a5
|
| 3 |
size 588699796
|
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:bfaaf62584334c674d97256a5169fefa7a76f1d283e335fd23fafd3ab45f10a5
|
| 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 sha256:9abccd3ade815397c3a4e9cae178fd4a326a690915052661d8621974d592484a
|
| 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": 8.797,
|
| 1090 |
"eval_steps_per_second": 2.21,
|
| 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": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.5863075852394104,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.20171457387796268,
|
| 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": 8.797,
|
| 1090 |
"eval_steps_per_second": 2.21,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.15229450327786181,
|
| 1095 |
+
"grad_norm": 0.6352901458740234,
|
| 1096 |
+
"learning_rate": 2.583589473684211e-05,
|
| 1097 |
+
"loss": 0.5723,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.15330307614725164,
|
| 1102 |
+
"grad_norm": 0.6519777774810791,
|
| 1103 |
+
"learning_rate": 2.530863157894737e-05,
|
| 1104 |
+
"loss": 0.5986,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.15431164901664146,
|
| 1109 |
+
"grad_norm": 0.6912335753440857,
|
| 1110 |
+
"learning_rate": 2.4781368421052633e-05,
|
| 1111 |
+
"loss": 0.6372,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.15532022188603126,
|
| 1116 |
+
"grad_norm": 0.8081892728805542,
|
| 1117 |
+
"learning_rate": 2.4254105263157896e-05,
|
| 1118 |
+
"loss": 0.6308,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.15632879475542108,
|
| 1123 |
+
"grad_norm": 0.638839066028595,
|
| 1124 |
+
"learning_rate": 2.372684210526316e-05,
|
| 1125 |
+
"loss": 0.5209,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.1573373676248109,
|
| 1130 |
+
"grad_norm": 0.8660756945610046,
|
| 1131 |
+
"learning_rate": 2.3199578947368422e-05,
|
| 1132 |
+
"loss": 0.6188,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.1583459404942007,
|
| 1137 |
+
"grad_norm": 0.8016595244407654,
|
| 1138 |
+
"learning_rate": 2.2672315789473688e-05,
|
| 1139 |
+
"loss": 0.683,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.15935451336359052,
|
| 1144 |
+
"grad_norm": 0.7723732590675354,
|
| 1145 |
+
"learning_rate": 2.2145052631578948e-05,
|
| 1146 |
+
"loss": 0.5858,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.16036308623298035,
|
| 1151 |
+
"grad_norm": 0.7663549780845642,
|
| 1152 |
+
"learning_rate": 2.1617789473684214e-05,
|
| 1153 |
+
"loss": 0.6837,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.16137165910237014,
|
| 1158 |
+
"grad_norm": 0.6378078460693359,
|
| 1159 |
+
"learning_rate": 2.1090526315789473e-05,
|
| 1160 |
+
"loss": 0.5426,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.16238023197175996,
|
| 1165 |
+
"grad_norm": 0.6299136877059937,
|
| 1166 |
+
"learning_rate": 2.056326315789474e-05,
|
| 1167 |
+
"loss": 0.6205,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.16338880484114976,
|
| 1172 |
+
"grad_norm": 0.614180326461792,
|
| 1173 |
+
"learning_rate": 2.0036000000000003e-05,
|
| 1174 |
+
"loss": 0.645,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.16439737771053958,
|
| 1179 |
+
"grad_norm": 0.5849306583404541,
|
| 1180 |
+
"learning_rate": 1.9508736842105266e-05,
|
| 1181 |
+
"loss": 0.5969,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.1654059505799294,
|
| 1186 |
+
"grad_norm": 0.6921943426132202,
|
| 1187 |
+
"learning_rate": 1.898147368421053e-05,
|
| 1188 |
+
"loss": 0.6696,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.1664145234493192,
|
| 1193 |
+
"grad_norm": 0.6622946858406067,
|
| 1194 |
+
"learning_rate": 1.8454210526315788e-05,
|
| 1195 |
+
"loss": 0.5939,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.16742309631870902,
|
| 1200 |
+
"grad_norm": 0.5671906471252441,
|
| 1201 |
+
"learning_rate": 1.7926947368421054e-05,
|
| 1202 |
+
"loss": 0.4853,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.16843166918809885,
|
| 1207 |
+
"grad_norm": 0.5902379155158997,
|
| 1208 |
+
"learning_rate": 1.7399684210526317e-05,
|
| 1209 |
+
"loss": 0.5543,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.16944024205748864,
|
| 1214 |
+
"grad_norm": 0.6716185808181763,
|
| 1215 |
+
"learning_rate": 1.687242105263158e-05,
|
| 1216 |
+
"loss": 0.4996,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.17044881492687847,
|
| 1221 |
+
"grad_norm": 0.6331367492675781,
|
| 1222 |
+
"learning_rate": 1.6345157894736843e-05,
|
| 1223 |
+
"loss": 0.5686,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.1714573877962683,
|
| 1228 |
+
"grad_norm": 0.6758613586425781,
|
| 1229 |
+
"learning_rate": 1.5817894736842106e-05,
|
| 1230 |
+
"loss": 0.6115,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.17246596066565809,
|
| 1235 |
+
"grad_norm": 0.631222128868103,
|
| 1236 |
+
"learning_rate": 1.529063157894737e-05,
|
| 1237 |
+
"loss": 0.5845,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.1734745335350479,
|
| 1242 |
+
"grad_norm": 0.688679575920105,
|
| 1243 |
+
"learning_rate": 1.4763368421052632e-05,
|
| 1244 |
+
"loss": 0.5624,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.17448310640443773,
|
| 1249 |
+
"grad_norm": 0.6124164462089539,
|
| 1250 |
+
"learning_rate": 1.4236105263157895e-05,
|
| 1251 |
+
"loss": 0.5512,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.17549167927382753,
|
| 1256 |
+
"grad_norm": 0.7388119101524353,
|
| 1257 |
+
"learning_rate": 1.370884210526316e-05,
|
| 1258 |
+
"loss": 0.5659,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.17650025214321735,
|
| 1263 |
+
"grad_norm": 0.624447762966156,
|
| 1264 |
+
"learning_rate": 1.318157894736842e-05,
|
| 1265 |
+
"loss": 0.5343,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.17750882501260717,
|
| 1270 |
+
"grad_norm": 0.7680219411849976,
|
| 1271 |
+
"learning_rate": 1.2654315789473685e-05,
|
| 1272 |
+
"loss": 0.6469,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.17851739788199697,
|
| 1277 |
+
"grad_norm": 0.6990251541137695,
|
| 1278 |
+
"learning_rate": 1.2127052631578948e-05,
|
| 1279 |
+
"loss": 0.5686,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.1795259707513868,
|
| 1284 |
+
"grad_norm": 0.625948965549469,
|
| 1285 |
+
"learning_rate": 1.1599789473684211e-05,
|
| 1286 |
+
"loss": 0.5172,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.1805345436207766,
|
| 1291 |
+
"grad_norm": 0.7253612875938416,
|
| 1292 |
+
"learning_rate": 1.1072526315789474e-05,
|
| 1293 |
+
"loss": 0.648,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.1815431164901664,
|
| 1298 |
+
"grad_norm": 0.7192074060440063,
|
| 1299 |
+
"learning_rate": 1.0545263157894737e-05,
|
| 1300 |
+
"loss": 0.5826,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.18255168935955624,
|
| 1305 |
+
"grad_norm": 0.8760311603546143,
|
| 1306 |
+
"learning_rate": 1.0018000000000001e-05,
|
| 1307 |
+
"loss": 0.726,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.18356026222894603,
|
| 1312 |
+
"grad_norm": 0.7654669284820557,
|
| 1313 |
+
"learning_rate": 9.490736842105264e-06,
|
| 1314 |
+
"loss": 0.7193,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.18456883509833585,
|
| 1319 |
+
"grad_norm": 0.6888782382011414,
|
| 1320 |
+
"learning_rate": 8.963473684210527e-06,
|
| 1321 |
+
"loss": 0.5643,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.18557740796772568,
|
| 1326 |
+
"grad_norm": 0.7420192956924438,
|
| 1327 |
+
"learning_rate": 8.43621052631579e-06,
|
| 1328 |
+
"loss": 0.6996,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.18658598083711547,
|
| 1333 |
+
"grad_norm": 0.761364221572876,
|
| 1334 |
+
"learning_rate": 7.908947368421053e-06,
|
| 1335 |
+
"loss": 0.6823,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.1875945537065053,
|
| 1340 |
+
"grad_norm": 0.7957232594490051,
|
| 1341 |
+
"learning_rate": 7.381684210526316e-06,
|
| 1342 |
+
"loss": 0.6033,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.18860312657589512,
|
| 1347 |
+
"grad_norm": 0.7030571103096008,
|
| 1348 |
+
"learning_rate": 6.85442105263158e-06,
|
| 1349 |
+
"loss": 0.6799,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.18961169944528491,
|
| 1354 |
+
"grad_norm": 0.7977284789085388,
|
| 1355 |
+
"learning_rate": 6.3271578947368425e-06,
|
| 1356 |
+
"loss": 0.6251,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.19062027231467474,
|
| 1361 |
+
"grad_norm": 0.774628758430481,
|
| 1362 |
+
"learning_rate": 5.7998947368421054e-06,
|
| 1363 |
+
"loss": 0.5933,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.19162884518406456,
|
| 1368 |
+
"grad_norm": 0.7732921242713928,
|
| 1369 |
+
"learning_rate": 5.272631578947368e-06,
|
| 1370 |
+
"loss": 0.6884,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.19263741805345436,
|
| 1375 |
+
"grad_norm": 0.8167909979820251,
|
| 1376 |
+
"learning_rate": 4.745368421052632e-06,
|
| 1377 |
+
"loss": 0.6984,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.19364599092284418,
|
| 1382 |
+
"grad_norm": 0.7652740478515625,
|
| 1383 |
+
"learning_rate": 4.218105263157895e-06,
|
| 1384 |
+
"loss": 0.5643,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.19465456379223398,
|
| 1389 |
+
"grad_norm": 0.7798756957054138,
|
| 1390 |
+
"learning_rate": 3.690842105263158e-06,
|
| 1391 |
+
"loss": 0.5983,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.1956631366616238,
|
| 1396 |
+
"grad_norm": 0.894702136516571,
|
| 1397 |
+
"learning_rate": 3.1635789473684213e-06,
|
| 1398 |
+
"loss": 0.7333,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.19667170953101362,
|
| 1403 |
+
"grad_norm": 0.8882285952568054,
|
| 1404 |
+
"learning_rate": 2.636315789473684e-06,
|
| 1405 |
+
"loss": 0.7199,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.19768028240040342,
|
| 1410 |
+
"grad_norm": 1.022255778312683,
|
| 1411 |
+
"learning_rate": 2.1090526315789475e-06,
|
| 1412 |
+
"loss": 0.6327,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.19868885526979324,
|
| 1417 |
+
"grad_norm": 0.9281327128410339,
|
| 1418 |
+
"learning_rate": 1.5817894736842106e-06,
|
| 1419 |
+
"loss": 0.6983,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.19969742813918306,
|
| 1424 |
+
"grad_norm": 0.9630473256111145,
|
| 1425 |
+
"learning_rate": 1.0545263157894738e-06,
|
| 1426 |
+
"loss": 0.6424,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.20070600100857286,
|
| 1431 |
+
"grad_norm": 0.9315603971481323,
|
| 1432 |
+
"learning_rate": 5.272631578947369e-07,
|
| 1433 |
+
"loss": 0.6501,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.20171457387796268,
|
| 1438 |
+
"grad_norm": 1.1420410871505737,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.7652,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.20171457387796268,
|
| 1445 |
+
"eval_loss": 0.5863075852394104,
|
| 1446 |
+
"eval_runtime": 47.2866,
|
| 1447 |
+
"eval_samples_per_second": 8.84,
|
| 1448 |
+
"eval_steps_per_second": 2.221,
|
| 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": 1.733017139675136e+17,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|