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 871457448
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80ec8b28c19c85d1b37fd6a66efd02154d4ed07492ad4f99f6a7ca2f238b63a3
|
| 3 |
size 871457448
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 443280340
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:896b07b473df6c066f6943cf25d3f549c3da982ce10777a233fa9a096d2466a4
|
| 3 |
size 443280340
|
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 sha256:2c795ecc565271ef96d79e0256ef074f709506941a2513cc2908808c7323e441
|
| 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": 7.454,
|
| 1090 |
"eval_steps_per_second": 1.865,
|
| 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": 1.1349619626998901,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.03266372693124286,
|
| 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": 7.454,
|
| 1090 |
"eval_steps_per_second": 1.865,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.024661113833088357,
|
| 1095 |
+
"grad_norm": 0.5229954719543457,
|
| 1096 |
+
"learning_rate": 2.5815263157894736e-05,
|
| 1097 |
+
"loss": 0.9078,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.02482443246774457,
|
| 1102 |
+
"grad_norm": 0.4165619909763336,
|
| 1103 |
+
"learning_rate": 2.528842105263158e-05,
|
| 1104 |
+
"loss": 0.7202,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.024987751102400785,
|
| 1109 |
+
"grad_norm": 0.4411524832248688,
|
| 1110 |
+
"learning_rate": 2.4761578947368418e-05,
|
| 1111 |
+
"loss": 0.7657,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.025151069737056997,
|
| 1116 |
+
"grad_norm": 0.5870716571807861,
|
| 1117 |
+
"learning_rate": 2.423473684210526e-05,
|
| 1118 |
+
"loss": 0.9064,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.025314388371713212,
|
| 1123 |
+
"grad_norm": 0.5716325044631958,
|
| 1124 |
+
"learning_rate": 2.3707894736842103e-05,
|
| 1125 |
+
"loss": 0.7211,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.025477707006369428,
|
| 1130 |
+
"grad_norm": 0.5912550091743469,
|
| 1131 |
+
"learning_rate": 2.3181052631578946e-05,
|
| 1132 |
+
"loss": 0.9137,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.02564102564102564,
|
| 1137 |
+
"grad_norm": 0.49093204736709595,
|
| 1138 |
+
"learning_rate": 2.265421052631579e-05,
|
| 1139 |
+
"loss": 0.9175,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.025804344275681856,
|
| 1144 |
+
"grad_norm": 0.5379444360733032,
|
| 1145 |
+
"learning_rate": 2.212736842105263e-05,
|
| 1146 |
+
"loss": 1.0109,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.02596766291033807,
|
| 1151 |
+
"grad_norm": 0.5582550764083862,
|
| 1152 |
+
"learning_rate": 2.1600526315789474e-05,
|
| 1153 |
+
"loss": 0.9187,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.026130981544994283,
|
| 1158 |
+
"grad_norm": 0.5776020288467407,
|
| 1159 |
+
"learning_rate": 2.1073684210526313e-05,
|
| 1160 |
+
"loss": 0.8756,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.0262943001796505,
|
| 1165 |
+
"grad_norm": 0.6320648789405823,
|
| 1166 |
+
"learning_rate": 2.0546842105263155e-05,
|
| 1167 |
+
"loss": 1.002,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.02645761881430671,
|
| 1172 |
+
"grad_norm": 0.5884015560150146,
|
| 1173 |
+
"learning_rate": 2.002e-05,
|
| 1174 |
+
"loss": 0.82,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.026620937448962927,
|
| 1179 |
+
"grad_norm": 0.6072445511817932,
|
| 1180 |
+
"learning_rate": 1.949315789473684e-05,
|
| 1181 |
+
"loss": 0.9141,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.026784256083619142,
|
| 1186 |
+
"grad_norm": 0.578770637512207,
|
| 1187 |
+
"learning_rate": 1.8966315789473683e-05,
|
| 1188 |
+
"loss": 0.8936,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.026947574718275354,
|
| 1193 |
+
"grad_norm": 0.7762899994850159,
|
| 1194 |
+
"learning_rate": 1.8439473684210522e-05,
|
| 1195 |
+
"loss": 0.67,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.02711089335293157,
|
| 1200 |
+
"grad_norm": 0.7052147388458252,
|
| 1201 |
+
"learning_rate": 1.791263157894737e-05,
|
| 1202 |
+
"loss": 0.7984,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.027274211987587785,
|
| 1207 |
+
"grad_norm": 0.6481052041053772,
|
| 1208 |
+
"learning_rate": 1.738578947368421e-05,
|
| 1209 |
+
"loss": 0.9779,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.027437530622243998,
|
| 1214 |
+
"grad_norm": 0.6853712201118469,
|
| 1215 |
+
"learning_rate": 1.685894736842105e-05,
|
| 1216 |
+
"loss": 0.8923,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.027600849256900213,
|
| 1221 |
+
"grad_norm": 0.7015615105628967,
|
| 1222 |
+
"learning_rate": 1.6332105263157893e-05,
|
| 1223 |
+
"loss": 0.8661,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.027764167891556425,
|
| 1228 |
+
"grad_norm": 0.8164605498313904,
|
| 1229 |
+
"learning_rate": 1.5805263157894735e-05,
|
| 1230 |
+
"loss": 0.8789,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.02792748652621264,
|
| 1235 |
+
"grad_norm": 0.8073320984840393,
|
| 1236 |
+
"learning_rate": 1.5278421052631578e-05,
|
| 1237 |
+
"loss": 1.0431,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.028090805160868856,
|
| 1242 |
+
"grad_norm": 0.9141411185264587,
|
| 1243 |
+
"learning_rate": 1.4751578947368419e-05,
|
| 1244 |
+
"loss": 1.069,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.02825412379552507,
|
| 1249 |
+
"grad_norm": 1.0805171728134155,
|
| 1250 |
+
"learning_rate": 1.4224736842105262e-05,
|
| 1251 |
+
"loss": 1.0579,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.028417442430181284,
|
| 1256 |
+
"grad_norm": 0.8766102194786072,
|
| 1257 |
+
"learning_rate": 1.3697894736842106e-05,
|
| 1258 |
+
"loss": 0.7755,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.0285807610648375,
|
| 1263 |
+
"grad_norm": 0.9655460715293884,
|
| 1264 |
+
"learning_rate": 1.3171052631578945e-05,
|
| 1265 |
+
"loss": 0.967,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.02874407969949371,
|
| 1270 |
+
"grad_norm": 0.9592732787132263,
|
| 1271 |
+
"learning_rate": 1.264421052631579e-05,
|
| 1272 |
+
"loss": 0.9174,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.028907398334149927,
|
| 1277 |
+
"grad_norm": 1.3226499557495117,
|
| 1278 |
+
"learning_rate": 1.211736842105263e-05,
|
| 1279 |
+
"loss": 1.2512,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.02907071696880614,
|
| 1284 |
+
"grad_norm": 1.1680970191955566,
|
| 1285 |
+
"learning_rate": 1.1590526315789473e-05,
|
| 1286 |
+
"loss": 0.948,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.029234035603462355,
|
| 1291 |
+
"grad_norm": 1.0348116159439087,
|
| 1292 |
+
"learning_rate": 1.1063684210526316e-05,
|
| 1293 |
+
"loss": 0.8562,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.02939735423811857,
|
| 1298 |
+
"grad_norm": 1.6529384851455688,
|
| 1299 |
+
"learning_rate": 1.0536842105263156e-05,
|
| 1300 |
+
"loss": 1.1671,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.029560672872774783,
|
| 1305 |
+
"grad_norm": 1.5153594017028809,
|
| 1306 |
+
"learning_rate": 1.001e-05,
|
| 1307 |
+
"loss": 1.0921,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.029723991507430998,
|
| 1312 |
+
"grad_norm": 1.3825584650039673,
|
| 1313 |
+
"learning_rate": 9.483157894736842e-06,
|
| 1314 |
+
"loss": 1.1131,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.029887310142087214,
|
| 1319 |
+
"grad_norm": 2.2654531002044678,
|
| 1320 |
+
"learning_rate": 8.956315789473684e-06,
|
| 1321 |
+
"loss": 1.129,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.030050628776743426,
|
| 1326 |
+
"grad_norm": 1.8482561111450195,
|
| 1327 |
+
"learning_rate": 8.429473684210525e-06,
|
| 1328 |
+
"loss": 1.1118,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.03021394741139964,
|
| 1333 |
+
"grad_norm": 2.0934503078460693,
|
| 1334 |
+
"learning_rate": 7.902631578947368e-06,
|
| 1335 |
+
"loss": 1.0566,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.030377266046055854,
|
| 1340 |
+
"grad_norm": 2.0610568523406982,
|
| 1341 |
+
"learning_rate": 7.3757894736842095e-06,
|
| 1342 |
+
"loss": 1.5909,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.03054058468071207,
|
| 1347 |
+
"grad_norm": 2.510016918182373,
|
| 1348 |
+
"learning_rate": 6.848947368421053e-06,
|
| 1349 |
+
"loss": 1.1805,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.030703903315368285,
|
| 1354 |
+
"grad_norm": 2.6841964721679688,
|
| 1355 |
+
"learning_rate": 6.322105263157895e-06,
|
| 1356 |
+
"loss": 1.2795,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.030867221950024497,
|
| 1361 |
+
"grad_norm": 2.3344948291778564,
|
| 1362 |
+
"learning_rate": 5.7952631578947365e-06,
|
| 1363 |
+
"loss": 1.2345,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.031030540584680712,
|
| 1368 |
+
"grad_norm": 2.7954304218292236,
|
| 1369 |
+
"learning_rate": 5.268421052631578e-06,
|
| 1370 |
+
"loss": 1.2223,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.031193859219336928,
|
| 1375 |
+
"grad_norm": 2.858825922012329,
|
| 1376 |
+
"learning_rate": 4.741578947368421e-06,
|
| 1377 |
+
"loss": 1.7338,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.03135717785399314,
|
| 1382 |
+
"grad_norm": 3.322049856185913,
|
| 1383 |
+
"learning_rate": 4.2147368421052626e-06,
|
| 1384 |
+
"loss": 1.4427,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.03152049648864935,
|
| 1389 |
+
"grad_norm": 2.922865152359009,
|
| 1390 |
+
"learning_rate": 3.6878947368421047e-06,
|
| 1391 |
+
"loss": 1.5083,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.03168381512330557,
|
| 1396 |
+
"grad_norm": 4.792754173278809,
|
| 1397 |
+
"learning_rate": 3.1610526315789474e-06,
|
| 1398 |
+
"loss": 1.614,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.03184713375796178,
|
| 1403 |
+
"grad_norm": 2.5056612491607666,
|
| 1404 |
+
"learning_rate": 2.634210526315789e-06,
|
| 1405 |
+
"loss": 1.0081,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.032010452392617995,
|
| 1410 |
+
"grad_norm": 3.5326714515686035,
|
| 1411 |
+
"learning_rate": 2.1073684210526313e-06,
|
| 1412 |
+
"loss": 0.9609,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.032173771027274214,
|
| 1417 |
+
"grad_norm": 5.468371868133545,
|
| 1418 |
+
"learning_rate": 1.5805263157894737e-06,
|
| 1419 |
+
"loss": 2.8999,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.03233708966193043,
|
| 1424 |
+
"grad_norm": 5.357850074768066,
|
| 1425 |
+
"learning_rate": 1.0536842105263156e-06,
|
| 1426 |
+
"loss": 2.4673,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.03250040829658664,
|
| 1431 |
+
"grad_norm": 5.674871444702148,
|
| 1432 |
+
"learning_rate": 5.268421052631578e-07,
|
| 1433 |
+
"loss": 2.0768,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.03266372693124286,
|
| 1438 |
+
"grad_norm": 5.8404860496521,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.6252,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.03266372693124286,
|
| 1445 |
+
"eval_loss": 1.1349619626998901,
|
| 1446 |
+
"eval_runtime": 346.0024,
|
| 1447 |
+
"eval_samples_per_second": 7.451,
|
| 1448 |
+
"eval_steps_per_second": 1.864,
|
| 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": 8.65769979075625e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|