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 sha256:19cd8af9a43a188d48d4ee78e4caf76e6e8aeb62d4ebbbbe0053dfdc8661e68b
|
| 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:d81e69137a5da2eb4b892d7be23fe5f270dd20b9f0f29e6b3021ea9febc5685e
|
| 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:b2c48f73842e891eb6c68489ba8e167639def86b833e4d9b7d57d381d0ecd7f2
|
| 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:a032dcbe590e69725a7fa9cedb5934521429cb4c18983c09c5035cbcaaeebd93
|
| 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": 12.765,
|
| 1090 |
"eval_steps_per_second": 3.192,
|
| 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": 1.1155003309249878,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.022313335006833458,
|
| 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": 12.765,
|
| 1090 |
"eval_steps_per_second": 3.192,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.016846567930159262,
|
| 1095 |
+
"grad_norm": 1.347996711730957,
|
| 1096 |
+
"learning_rate": 1.242586363525737e-05,
|
| 1097 |
+
"loss": 1.6669,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.01695813460519343,
|
| 1102 |
+
"grad_norm": 0.7223047018051147,
|
| 1103 |
+
"learning_rate": 1.1950528629100457e-05,
|
| 1104 |
+
"loss": 1.4154,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.017069701280227598,
|
| 1109 |
+
"grad_norm": 0.7790156006813049,
|
| 1110 |
+
"learning_rate": 1.1482862068344121e-05,
|
| 1111 |
+
"loss": 1.3367,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.017181267955261762,
|
| 1116 |
+
"grad_norm": 0.7638139128684998,
|
| 1117 |
+
"learning_rate": 1.1022991808356442e-05,
|
| 1118 |
+
"loss": 1.0699,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.01729283463029593,
|
| 1123 |
+
"grad_norm": 0.8289293646812439,
|
| 1124 |
+
"learning_rate": 1.0571043573074737e-05,
|
| 1125 |
+
"loss": 1.2266,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.017404401305330098,
|
| 1130 |
+
"grad_norm": 0.8301885724067688,
|
| 1131 |
+
"learning_rate": 1.0127140920633857e-05,
|
| 1132 |
+
"loss": 1.3556,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.017515967980364266,
|
| 1137 |
+
"grad_norm": 0.7769188284873962,
|
| 1138 |
+
"learning_rate": 9.69140520958662e-06,
|
| 1139 |
+
"loss": 1.3362,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.017627534655398434,
|
| 1144 |
+
"grad_norm": 0.8720978498458862,
|
| 1145 |
+
"learning_rate": 9.263955565725648e-06,
|
| 1146 |
+
"loss": 1.0811,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.017739101330432598,
|
| 1151 |
+
"grad_norm": 0.7598316073417664,
|
| 1152 |
+
"learning_rate": 8.844908849515509e-06,
|
| 1153 |
+
"loss": 1.0352,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.017850668005466766,
|
| 1158 |
+
"grad_norm": 0.7994357347488403,
|
| 1159 |
+
"learning_rate": 8.434379624144261e-06,
|
| 1160 |
+
"loss": 1.1984,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.017962234680500934,
|
| 1165 |
+
"grad_norm": 0.841153621673584,
|
| 1166 |
+
"learning_rate": 8.032480124203013e-06,
|
| 1167 |
+
"loss": 1.2358,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.018073801355535102,
|
| 1172 |
+
"grad_norm": 0.8118249773979187,
|
| 1173 |
+
"learning_rate": 7.639320225002106e-06,
|
| 1174 |
+
"loss": 1.0032,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.01818536803056927,
|
| 1179 |
+
"grad_norm": 0.753839373588562,
|
| 1180 |
+
"learning_rate": 7.255007412532307e-06,
|
| 1181 |
+
"loss": 1.1015,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.018296934705603438,
|
| 1186 |
+
"grad_norm": 0.7360984086990356,
|
| 1187 |
+
"learning_rate": 6.8796467540791986e-06,
|
| 1188 |
+
"loss": 1.1351,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.018408501380637602,
|
| 1193 |
+
"grad_norm": 0.8430283069610596,
|
| 1194 |
+
"learning_rate": 6.513340869498859e-06,
|
| 1195 |
+
"loss": 1.1797,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.01852006805567177,
|
| 1200 |
+
"grad_norm": 0.7918187975883484,
|
| 1201 |
+
"learning_rate": 6.1561899031625794e-06,
|
| 1202 |
+
"loss": 1.2193,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.018631634730705938,
|
| 1207 |
+
"grad_norm": 0.7992611527442932,
|
| 1208 |
+
"learning_rate": 5.808291496578435e-06,
|
| 1209 |
+
"loss": 1.268,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.018743201405740106,
|
| 1214 |
+
"grad_norm": 0.7855931520462036,
|
| 1215 |
+
"learning_rate": 5.469740761697044e-06,
|
| 1216 |
+
"loss": 1.178,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.018854768080774274,
|
| 1221 |
+
"grad_norm": 0.8650913834571838,
|
| 1222 |
+
"learning_rate": 5.140630254908905e-06,
|
| 1223 |
+
"loss": 1.2404,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.01896633475580844,
|
| 1228 |
+
"grad_norm": 0.8121924996376038,
|
| 1229 |
+
"learning_rate": 4.821049951740442e-06,
|
| 1230 |
+
"loss": 1.1776,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.019077901430842606,
|
| 1235 |
+
"grad_norm": 0.7831167578697205,
|
| 1236 |
+
"learning_rate": 4.511087222255528e-06,
|
| 1237 |
+
"loss": 1.2594,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.019189468105876774,
|
| 1242 |
+
"grad_norm": 0.8442049026489258,
|
| 1243 |
+
"learning_rate": 4.2108268071694616e-06,
|
| 1244 |
+
"loss": 0.9845,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.01930103478091094,
|
| 1249 |
+
"grad_norm": 0.9648184180259705,
|
| 1250 |
+
"learning_rate": 3.9203507946816445e-06,
|
| 1251 |
+
"loss": 1.1247,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.01941260145594511,
|
| 1256 |
+
"grad_norm": 0.814885139465332,
|
| 1257 |
+
"learning_rate": 3.6397385980335e-06,
|
| 1258 |
+
"loss": 1.3107,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.019524168130979278,
|
| 1263 |
+
"grad_norm": 0.8654019236564636,
|
| 1264 |
+
"learning_rate": 3.3690669337977e-06,
|
| 1265 |
+
"loss": 1.2594,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.019635734806013445,
|
| 1270 |
+
"grad_norm": 0.9481486678123474,
|
| 1271 |
+
"learning_rate": 3.1084098009046106e-06,
|
| 1272 |
+
"loss": 1.1462,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.01974730148104761,
|
| 1277 |
+
"grad_norm": 0.7980362772941589,
|
| 1278 |
+
"learning_rate": 2.8578384604117217e-06,
|
| 1279 |
+
"loss": 1.117,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.019858868156081778,
|
| 1284 |
+
"grad_norm": 0.8693552613258362,
|
| 1285 |
+
"learning_rate": 2.6174214160215704e-06,
|
| 1286 |
+
"loss": 1.1145,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.019970434831115946,
|
| 1291 |
+
"grad_norm": 0.8843334317207336,
|
| 1292 |
+
"learning_rate": 2.3872243953535535e-06,
|
| 1293 |
+
"loss": 1.0491,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.020082001506150114,
|
| 1298 |
+
"grad_norm": 0.8390738368034363,
|
| 1299 |
+
"learning_rate": 2.1673103319746146e-06,
|
| 1300 |
+
"loss": 0.9996,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.02019356818118428,
|
| 1305 |
+
"grad_norm": 0.9163740873336792,
|
| 1306 |
+
"learning_rate": 1.957739348193859e-06,
|
| 1307 |
+
"loss": 1.198,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.020305134856218446,
|
| 1312 |
+
"grad_norm": 0.8822169899940491,
|
| 1313 |
+
"learning_rate": 1.7585687386256944e-06,
|
| 1314 |
+
"loss": 1.0289,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.020416701531252614,
|
| 1319 |
+
"grad_norm": 0.8542013168334961,
|
| 1320 |
+
"learning_rate": 1.5698529545260744e-06,
|
| 1321 |
+
"loss": 0.9726,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.02052826820628678,
|
| 1326 |
+
"grad_norm": 0.9263859987258911,
|
| 1327 |
+
"learning_rate": 1.3916435889060575e-06,
|
| 1328 |
+
"loss": 1.1067,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.02063983488132095,
|
| 1333 |
+
"grad_norm": 0.9441400170326233,
|
| 1334 |
+
"learning_rate": 1.2239893624267852e-06,
|
| 1335 |
+
"loss": 1.1066,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.020751401556355117,
|
| 1340 |
+
"grad_norm": 0.9362796545028687,
|
| 1341 |
+
"learning_rate": 1.0669361100797704e-06,
|
| 1342 |
+
"loss": 1.0002,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.020862968231389285,
|
| 1347 |
+
"grad_norm": 0.9713947772979736,
|
| 1348 |
+
"learning_rate": 9.205267686560293e-07,
|
| 1349 |
+
"loss": 1.1045,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.02097453490642345,
|
| 1354 |
+
"grad_norm": 0.9421945214271545,
|
| 1355 |
+
"learning_rate": 7.848013650076258e-07,
|
| 1356 |
+
"loss": 1.094,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.021086101581457618,
|
| 1361 |
+
"grad_norm": 0.9486850500106812,
|
| 1362 |
+
"learning_rate": 6.597970051047053e-07,
|
| 1363 |
+
"loss": 1.0785,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.021197668256491786,
|
| 1368 |
+
"grad_norm": 1.1238409280776978,
|
| 1369 |
+
"learning_rate": 5.455478638911071e-07,
|
| 1370 |
+
"loss": 1.1079,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.021309234931525953,
|
| 1375 |
+
"grad_norm": 1.0330231189727783,
|
| 1376 |
+
"learning_rate": 4.420851759412603e-07,
|
| 1377 |
+
"loss": 0.9687,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.02142080160656012,
|
| 1382 |
+
"grad_norm": 1.064351201057434,
|
| 1383 |
+
"learning_rate": 3.4943722692099224e-07,
|
| 1384 |
+
"loss": 1.0296,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.02153236828159429,
|
| 1389 |
+
"grad_norm": 1.0056447982788086,
|
| 1390 |
+
"learning_rate": 2.676293458544743e-07,
|
| 1391 |
+
"loss": 0.9839,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.021643934956628454,
|
| 1396 |
+
"grad_norm": 1.1110754013061523,
|
| 1397 |
+
"learning_rate": 1.9668389819954338e-07,
|
| 1398 |
+
"loss": 0.9976,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.02175550163166262,
|
| 1403 |
+
"grad_norm": 1.2064679861068726,
|
| 1404 |
+
"learning_rate": 1.3662027973320614e-07,
|
| 1405 |
+
"loss": 1.1326,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.02186706830669679,
|
| 1410 |
+
"grad_norm": 1.1165443658828735,
|
| 1411 |
+
"learning_rate": 8.745491124901861e-08,
|
| 1412 |
+
"loss": 0.9374,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.021978634981730957,
|
| 1417 |
+
"grad_norm": 1.0634437799453735,
|
| 1418 |
+
"learning_rate": 4.920123406781052e-08,
|
| 1419 |
+
"loss": 0.979,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.022090201656765125,
|
| 1424 |
+
"grad_norm": 1.4238533973693848,
|
| 1425 |
+
"learning_rate": 2.1869706362958044e-08,
|
| 1426 |
+
"loss": 1.0523,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.022201768331799293,
|
| 1431 |
+
"grad_norm": 1.357772707939148,
|
| 1432 |
+
"learning_rate": 5.467800301239834e-09,
|
| 1433 |
+
"loss": 1.0345,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.022313335006833458,
|
| 1438 |
+
"grad_norm": 1.6248823404312134,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.9803,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.022313335006833458,
|
| 1445 |
+
"eval_loss": 1.1155003309249878,
|
| 1446 |
+
"eval_runtime": 1183.9514,
|
| 1447 |
+
"eval_samples_per_second": 12.751,
|
| 1448 |
+
"eval_steps_per_second": 3.188,
|
| 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": 3.08868155248214e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|