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 800116456
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c5eb2d6ea4db9103c40128f80a6b1e9c61c74361d322d35133c0a28f24cb09a
|
| 3 |
size 800116456
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 406743412
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06af85245b156b52abd3f96b264adf158da36ce02e88802b626699b9b1efe90d
|
| 3 |
size 406743412
|
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:c4c4b49ebd10e72da64aaeee9a2568e4948c257827da60f7c3a9021a559f2182
|
| 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 sha256:9ba2dfce0937a08ee177ecd4ee2c0d73bc25d6c21d394bb71764724c742c652e
|
| 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": 5.877,
|
| 1090 |
"eval_steps_per_second": 1.469,
|
| 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": 0.9112640619277954,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.007006358270130143,
|
| 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": 5.877,
|
| 1090 |
"eval_steps_per_second": 1.469,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.005289800493948258,
|
| 1095 |
+
"grad_norm": 4.701993465423584,
|
| 1096 |
+
"learning_rate": 2.5833315789473687e-05,
|
| 1097 |
+
"loss": 0.8749,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.0053248322852989085,
|
| 1102 |
+
"grad_norm": 4.541272163391113,
|
| 1103 |
+
"learning_rate": 2.5306105263157895e-05,
|
| 1104 |
+
"loss": 0.8578,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.00535986407664956,
|
| 1109 |
+
"grad_norm": 6.385204792022705,
|
| 1110 |
+
"learning_rate": 2.4778894736842104e-05,
|
| 1111 |
+
"loss": 1.0571,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.00539489586800021,
|
| 1116 |
+
"grad_norm": 6.275009632110596,
|
| 1117 |
+
"learning_rate": 2.4251684210526315e-05,
|
| 1118 |
+
"loss": 1.1863,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.0054299276593508606,
|
| 1123 |
+
"grad_norm": 5.322296619415283,
|
| 1124 |
+
"learning_rate": 2.3724473684210524e-05,
|
| 1125 |
+
"loss": 0.9377,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.005464959450701512,
|
| 1130 |
+
"grad_norm": 6.121055603027344,
|
| 1131 |
+
"learning_rate": 2.3197263157894735e-05,
|
| 1132 |
+
"loss": 1.1512,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.005499991242052162,
|
| 1137 |
+
"grad_norm": 6.184394359588623,
|
| 1138 |
+
"learning_rate": 2.2670052631578947e-05,
|
| 1139 |
+
"loss": 1.1134,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.005535023033402813,
|
| 1144 |
+
"grad_norm": 6.6305437088012695,
|
| 1145 |
+
"learning_rate": 2.214284210526316e-05,
|
| 1146 |
+
"loss": 1.0825,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.005570054824753464,
|
| 1151 |
+
"grad_norm": 8.778796195983887,
|
| 1152 |
+
"learning_rate": 2.161563157894737e-05,
|
| 1153 |
+
"loss": 0.8035,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.005605086616104114,
|
| 1158 |
+
"grad_norm": 8.88864803314209,
|
| 1159 |
+
"learning_rate": 2.108842105263158e-05,
|
| 1160 |
+
"loss": 1.6535,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.005640118407454766,
|
| 1165 |
+
"grad_norm": 7.5164713859558105,
|
| 1166 |
+
"learning_rate": 2.056121052631579e-05,
|
| 1167 |
+
"loss": 0.9809,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.005675150198805416,
|
| 1172 |
+
"grad_norm": 7.345613956451416,
|
| 1173 |
+
"learning_rate": 2.0034e-05,
|
| 1174 |
+
"loss": 1.6875,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.0057101819901560665,
|
| 1179 |
+
"grad_norm": 6.933657646179199,
|
| 1180 |
+
"learning_rate": 1.950678947368421e-05,
|
| 1181 |
+
"loss": 1.3107,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.005745213781506718,
|
| 1186 |
+
"grad_norm": 7.372086048126221,
|
| 1187 |
+
"learning_rate": 1.897957894736842e-05,
|
| 1188 |
+
"loss": 1.4343,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.005780245572857368,
|
| 1193 |
+
"grad_norm": 6.22285270690918,
|
| 1194 |
+
"learning_rate": 1.845236842105263e-05,
|
| 1195 |
+
"loss": 0.9742,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.0058152773642080186,
|
| 1200 |
+
"grad_norm": 8.803730964660645,
|
| 1201 |
+
"learning_rate": 1.792515789473684e-05,
|
| 1202 |
+
"loss": 1.3178,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.00585030915555867,
|
| 1207 |
+
"grad_norm": 12.660039901733398,
|
| 1208 |
+
"learning_rate": 1.7397947368421053e-05,
|
| 1209 |
+
"loss": 1.9204,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.00588534094690932,
|
| 1214 |
+
"grad_norm": 7.340970039367676,
|
| 1215 |
+
"learning_rate": 1.687073684210526e-05,
|
| 1216 |
+
"loss": 1.4054,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.005920372738259971,
|
| 1221 |
+
"grad_norm": 4.593935489654541,
|
| 1222 |
+
"learning_rate": 1.6343526315789473e-05,
|
| 1223 |
+
"loss": 0.7033,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.005955404529610622,
|
| 1228 |
+
"grad_norm": 4.283302307128906,
|
| 1229 |
+
"learning_rate": 1.5816315789473685e-05,
|
| 1230 |
+
"loss": 0.6679,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.005990436320961272,
|
| 1235 |
+
"grad_norm": 5.512580394744873,
|
| 1236 |
+
"learning_rate": 1.5289105263157896e-05,
|
| 1237 |
+
"loss": 0.8829,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.006025468112311923,
|
| 1242 |
+
"grad_norm": 4.068453311920166,
|
| 1243 |
+
"learning_rate": 1.4761894736842103e-05,
|
| 1244 |
+
"loss": 0.5252,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.006060499903662574,
|
| 1249 |
+
"grad_norm": 6.23944091796875,
|
| 1250 |
+
"learning_rate": 1.4234684210526314e-05,
|
| 1251 |
+
"loss": 0.9646,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.0060955316950132244,
|
| 1256 |
+
"grad_norm": 6.521369934082031,
|
| 1257 |
+
"learning_rate": 1.3707473684210528e-05,
|
| 1258 |
+
"loss": 0.8696,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.006130563486363875,
|
| 1263 |
+
"grad_norm": 4.816810607910156,
|
| 1264 |
+
"learning_rate": 1.3180263157894736e-05,
|
| 1265 |
+
"loss": 0.786,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.006165595277714526,
|
| 1270 |
+
"grad_norm": 4.4193501472473145,
|
| 1271 |
+
"learning_rate": 1.2653052631578948e-05,
|
| 1272 |
+
"loss": 0.6175,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.0062006270690651765,
|
| 1277 |
+
"grad_norm": 4.809851169586182,
|
| 1278 |
+
"learning_rate": 1.2125842105263158e-05,
|
| 1279 |
+
"loss": 0.6917,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.006235658860415827,
|
| 1284 |
+
"grad_norm": 4.602668285369873,
|
| 1285 |
+
"learning_rate": 1.1598631578947368e-05,
|
| 1286 |
+
"loss": 0.7125,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.006270690651766478,
|
| 1291 |
+
"grad_norm": 5.745820045471191,
|
| 1292 |
+
"learning_rate": 1.107142105263158e-05,
|
| 1293 |
+
"loss": 0.9309,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.006305722443117129,
|
| 1298 |
+
"grad_norm": 5.068687438964844,
|
| 1299 |
+
"learning_rate": 1.054421052631579e-05,
|
| 1300 |
+
"loss": 0.7615,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.00634075423446778,
|
| 1305 |
+
"grad_norm": 5.800779342651367,
|
| 1306 |
+
"learning_rate": 1.0017e-05,
|
| 1307 |
+
"loss": 1.0696,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.00637578602581843,
|
| 1312 |
+
"grad_norm": 4.405969142913818,
|
| 1313 |
+
"learning_rate": 9.48978947368421e-06,
|
| 1314 |
+
"loss": 0.6197,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.006410817817169081,
|
| 1319 |
+
"grad_norm": 4.871210098266602,
|
| 1320 |
+
"learning_rate": 8.96257894736842e-06,
|
| 1321 |
+
"loss": 0.6756,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.006445849608519732,
|
| 1326 |
+
"grad_norm": 6.21035623550415,
|
| 1327 |
+
"learning_rate": 8.43536842105263e-06,
|
| 1328 |
+
"loss": 1.0503,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.0064808813998703824,
|
| 1333 |
+
"grad_norm": 5.283048152923584,
|
| 1334 |
+
"learning_rate": 7.908157894736842e-06,
|
| 1335 |
+
"loss": 0.8885,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.006515913191221033,
|
| 1340 |
+
"grad_norm": 6.8126349449157715,
|
| 1341 |
+
"learning_rate": 7.380947368421051e-06,
|
| 1342 |
+
"loss": 0.8942,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.006550944982571684,
|
| 1347 |
+
"grad_norm": 6.314110279083252,
|
| 1348 |
+
"learning_rate": 6.853736842105264e-06,
|
| 1349 |
+
"loss": 0.8951,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.0065859767739223345,
|
| 1354 |
+
"grad_norm": 4.6299333572387695,
|
| 1355 |
+
"learning_rate": 6.326526315789474e-06,
|
| 1356 |
+
"loss": 0.5277,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.006621008565272985,
|
| 1361 |
+
"grad_norm": 4.60901403427124,
|
| 1362 |
+
"learning_rate": 5.799315789473684e-06,
|
| 1363 |
+
"loss": 0.6088,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.006656040356623636,
|
| 1368 |
+
"grad_norm": 4.363032341003418,
|
| 1369 |
+
"learning_rate": 5.272105263157895e-06,
|
| 1370 |
+
"loss": 0.6022,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.006691072147974287,
|
| 1375 |
+
"grad_norm": 6.278995990753174,
|
| 1376 |
+
"learning_rate": 4.744894736842105e-06,
|
| 1377 |
+
"loss": 0.9941,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.006726103939324937,
|
| 1382 |
+
"grad_norm": 4.180647850036621,
|
| 1383 |
+
"learning_rate": 4.217684210526315e-06,
|
| 1384 |
+
"loss": 0.5374,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.006761135730675588,
|
| 1389 |
+
"grad_norm": 7.0714111328125,
|
| 1390 |
+
"learning_rate": 3.6904736842105257e-06,
|
| 1391 |
+
"loss": 0.8828,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.006796167522026239,
|
| 1396 |
+
"grad_norm": 4.836719036102295,
|
| 1397 |
+
"learning_rate": 3.163263157894737e-06,
|
| 1398 |
+
"loss": 0.8575,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.006831199313376889,
|
| 1403 |
+
"grad_norm": 6.586860656738281,
|
| 1404 |
+
"learning_rate": 2.6360526315789473e-06,
|
| 1405 |
+
"loss": 1.0594,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.00686623110472754,
|
| 1410 |
+
"grad_norm": 6.527482986450195,
|
| 1411 |
+
"learning_rate": 2.1088421052631577e-06,
|
| 1412 |
+
"loss": 0.7441,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.006901262896078191,
|
| 1417 |
+
"grad_norm": 5.505125045776367,
|
| 1418 |
+
"learning_rate": 1.5816315789473685e-06,
|
| 1419 |
+
"loss": 0.6487,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.006936294687428841,
|
| 1424 |
+
"grad_norm": 5.350231170654297,
|
| 1425 |
+
"learning_rate": 1.0544210526315788e-06,
|
| 1426 |
+
"loss": 0.7856,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.0069713264787794925,
|
| 1431 |
+
"grad_norm": 5.1863179206848145,
|
| 1432 |
+
"learning_rate": 5.272105263157894e-07,
|
| 1433 |
+
"loss": 0.5979,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.007006358270130143,
|
| 1438 |
+
"grad_norm": 4.770188808441162,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.5592,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.007006358270130143,
|
| 1445 |
+
"eval_loss": 0.9112640619277954,
|
| 1446 |
+
"eval_runtime": 2048.644,
|
| 1447 |
+
"eval_samples_per_second": 5.867,
|
| 1448 |
+
"eval_steps_per_second": 1.467,
|
| 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": 1.0571696306965709e+17,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|