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 639691872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d8af1e5071dce814f6c8764a88ae9b2f6ead7bb7bda21deb5a975009abee7e0
|
| 3 |
size 639691872
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 325339796
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:565f7f4347fe26836a5be5b21e8b8c7b61d5a693d8f03266951f3ce3ed1b7500
|
| 3 |
size 325339796
|
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 sha256:632b6e283ff8c2b15d8758b293828e69d1cf7d798162b5028d170187d1122a19
|
| 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 sha256:8fb6e84b61e1d7eca31b5c24862f17cdfbe140bbf377a76353176857bcb8fef1
|
| 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": 9.888,
|
| 1090 |
"eval_steps_per_second": 2.475,
|
| 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": 1.3859784603118896,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.055348000553480006,
|
| 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": 9.888,
|
| 1090 |
"eval_steps_per_second": 2.475,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.0417877404178774,
|
| 1095 |
+
"grad_norm": 0.6982325315475464,
|
| 1096 |
+
"learning_rate": 2.6098947368421053e-05,
|
| 1097 |
+
"loss": 2.6541,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.042064480420644805,
|
| 1102 |
+
"grad_norm": 0.6466959714889526,
|
| 1103 |
+
"learning_rate": 2.5566315789473684e-05,
|
| 1104 |
+
"loss": 2.7869,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.04234122042341221,
|
| 1109 |
+
"grad_norm": 0.5397589802742004,
|
| 1110 |
+
"learning_rate": 2.5033684210526312e-05,
|
| 1111 |
+
"loss": 1.9081,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.0426179604261796,
|
| 1116 |
+
"grad_norm": 0.5460906624794006,
|
| 1117 |
+
"learning_rate": 2.4501052631578947e-05,
|
| 1118 |
+
"loss": 1.5494,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.042894700428947004,
|
| 1123 |
+
"grad_norm": 0.5999884009361267,
|
| 1124 |
+
"learning_rate": 2.3968421052631575e-05,
|
| 1125 |
+
"loss": 1.7669,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.043171440431714406,
|
| 1130 |
+
"grad_norm": 0.6195064187049866,
|
| 1131 |
+
"learning_rate": 2.343578947368421e-05,
|
| 1132 |
+
"loss": 1.4744,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.04344818043448181,
|
| 1137 |
+
"grad_norm": 0.5452435612678528,
|
| 1138 |
+
"learning_rate": 2.290315789473684e-05,
|
| 1139 |
+
"loss": 1.5237,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.0437249204372492,
|
| 1144 |
+
"grad_norm": 0.6407039761543274,
|
| 1145 |
+
"learning_rate": 2.237052631578947e-05,
|
| 1146 |
+
"loss": 2.0735,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.044001660440016604,
|
| 1151 |
+
"grad_norm": 0.6194781064987183,
|
| 1152 |
+
"learning_rate": 2.1837894736842106e-05,
|
| 1153 |
+
"loss": 1.4127,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.044278400442784006,
|
| 1158 |
+
"grad_norm": 0.6215983629226685,
|
| 1159 |
+
"learning_rate": 2.1305263157894734e-05,
|
| 1160 |
+
"loss": 1.2298,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.0445551404455514,
|
| 1165 |
+
"grad_norm": 0.6356123685836792,
|
| 1166 |
+
"learning_rate": 2.0772631578947368e-05,
|
| 1167 |
+
"loss": 1.2279,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.0448318804483188,
|
| 1172 |
+
"grad_norm": 0.6377651691436768,
|
| 1173 |
+
"learning_rate": 2.024e-05,
|
| 1174 |
+
"loss": 1.1827,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.045108620451086205,
|
| 1179 |
+
"grad_norm": 0.6660798192024231,
|
| 1180 |
+
"learning_rate": 1.970736842105263e-05,
|
| 1181 |
+
"loss": 1.1657,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.04538536045385361,
|
| 1186 |
+
"grad_norm": 0.7134098410606384,
|
| 1187 |
+
"learning_rate": 1.917473684210526e-05,
|
| 1188 |
+
"loss": 1.5894,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.045662100456621,
|
| 1193 |
+
"grad_norm": 0.6191778182983398,
|
| 1194 |
+
"learning_rate": 1.8642105263157893e-05,
|
| 1195 |
+
"loss": 1.154,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.045938840459388404,
|
| 1200 |
+
"grad_norm": 0.6857507228851318,
|
| 1201 |
+
"learning_rate": 1.8109473684210524e-05,
|
| 1202 |
+
"loss": 1.3369,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.046215580462155806,
|
| 1207 |
+
"grad_norm": 0.6705174446105957,
|
| 1208 |
+
"learning_rate": 1.757684210526316e-05,
|
| 1209 |
+
"loss": 1.4583,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.04649232046492321,
|
| 1214 |
+
"grad_norm": 0.7063128352165222,
|
| 1215 |
+
"learning_rate": 1.704421052631579e-05,
|
| 1216 |
+
"loss": 1.3876,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.0467690604676906,
|
| 1221 |
+
"grad_norm": 0.7156012058258057,
|
| 1222 |
+
"learning_rate": 1.651157894736842e-05,
|
| 1223 |
+
"loss": 1.252,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.047045800470458005,
|
| 1228 |
+
"grad_norm": 0.7198076248168945,
|
| 1229 |
+
"learning_rate": 1.5978947368421052e-05,
|
| 1230 |
+
"loss": 1.3088,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.047322540473225407,
|
| 1235 |
+
"grad_norm": 0.7079565525054932,
|
| 1236 |
+
"learning_rate": 1.5446315789473683e-05,
|
| 1237 |
+
"loss": 1.1477,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.0475992804759928,
|
| 1242 |
+
"grad_norm": 0.7721232175827026,
|
| 1243 |
+
"learning_rate": 1.4913684210526314e-05,
|
| 1244 |
+
"loss": 1.2165,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.0478760204787602,
|
| 1249 |
+
"grad_norm": 0.772697389125824,
|
| 1250 |
+
"learning_rate": 1.4381052631578945e-05,
|
| 1251 |
+
"loss": 1.3874,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.048152760481527605,
|
| 1256 |
+
"grad_norm": 0.7915751338005066,
|
| 1257 |
+
"learning_rate": 1.3848421052631578e-05,
|
| 1258 |
+
"loss": 1.2733,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.04842950048429501,
|
| 1263 |
+
"grad_norm": 0.6995910406112671,
|
| 1264 |
+
"learning_rate": 1.331578947368421e-05,
|
| 1265 |
+
"loss": 1.1716,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.0487062404870624,
|
| 1270 |
+
"grad_norm": 0.8334876298904419,
|
| 1271 |
+
"learning_rate": 1.2783157894736842e-05,
|
| 1272 |
+
"loss": 1.2003,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.048982980489829804,
|
| 1277 |
+
"grad_norm": 0.7988669872283936,
|
| 1278 |
+
"learning_rate": 1.2250526315789473e-05,
|
| 1279 |
+
"loss": 1.2631,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.049259720492597206,
|
| 1284 |
+
"grad_norm": 0.7876620888710022,
|
| 1285 |
+
"learning_rate": 1.1717894736842105e-05,
|
| 1286 |
+
"loss": 1.144,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.04953646049536461,
|
| 1291 |
+
"grad_norm": 0.7998309135437012,
|
| 1292 |
+
"learning_rate": 1.1185263157894736e-05,
|
| 1293 |
+
"loss": 1.256,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.049813200498132,
|
| 1298 |
+
"grad_norm": 0.7581685781478882,
|
| 1299 |
+
"learning_rate": 1.0652631578947367e-05,
|
| 1300 |
+
"loss": 1.1314,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.050089940500899405,
|
| 1305 |
+
"grad_norm": 0.8552046418190002,
|
| 1306 |
+
"learning_rate": 1.012e-05,
|
| 1307 |
+
"loss": 1.2926,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.05036668050366681,
|
| 1312 |
+
"grad_norm": 0.7959903478622437,
|
| 1313 |
+
"learning_rate": 9.58736842105263e-06,
|
| 1314 |
+
"loss": 1.1671,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.0506434205064342,
|
| 1319 |
+
"grad_norm": 0.8624477982521057,
|
| 1320 |
+
"learning_rate": 9.054736842105262e-06,
|
| 1321 |
+
"loss": 1.2291,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.050920160509201604,
|
| 1326 |
+
"grad_norm": 0.7806897163391113,
|
| 1327 |
+
"learning_rate": 8.522105263157895e-06,
|
| 1328 |
+
"loss": 1.1011,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.051196900511969005,
|
| 1333 |
+
"grad_norm": 0.8457885980606079,
|
| 1334 |
+
"learning_rate": 7.989473684210526e-06,
|
| 1335 |
+
"loss": 1.2111,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.05147364051473641,
|
| 1340 |
+
"grad_norm": 0.912453830242157,
|
| 1341 |
+
"learning_rate": 7.456842105263157e-06,
|
| 1342 |
+
"loss": 1.2933,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.0517503805175038,
|
| 1347 |
+
"grad_norm": 0.8722508549690247,
|
| 1348 |
+
"learning_rate": 6.924210526315789e-06,
|
| 1349 |
+
"loss": 1.2674,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.052027120520271204,
|
| 1354 |
+
"grad_norm": 0.9331529140472412,
|
| 1355 |
+
"learning_rate": 6.391578947368421e-06,
|
| 1356 |
+
"loss": 1.3586,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.052303860523038606,
|
| 1361 |
+
"grad_norm": 0.9258183836936951,
|
| 1362 |
+
"learning_rate": 5.858947368421052e-06,
|
| 1363 |
+
"loss": 1.2182,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.05258060052580601,
|
| 1368 |
+
"grad_norm": 0.8901333212852478,
|
| 1369 |
+
"learning_rate": 5.326315789473683e-06,
|
| 1370 |
+
"loss": 1.3312,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.0528573405285734,
|
| 1375 |
+
"grad_norm": 0.9532617330551147,
|
| 1376 |
+
"learning_rate": 4.793684210526315e-06,
|
| 1377 |
+
"loss": 1.2047,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.053134080531340805,
|
| 1382 |
+
"grad_norm": 1.0242388248443604,
|
| 1383 |
+
"learning_rate": 4.261052631578947e-06,
|
| 1384 |
+
"loss": 1.3325,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.05341082053410821,
|
| 1389 |
+
"grad_norm": 1.0415493249893188,
|
| 1390 |
+
"learning_rate": 3.7284210526315786e-06,
|
| 1391 |
+
"loss": 1.4721,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.05368756053687561,
|
| 1396 |
+
"grad_norm": 1.0794676542282104,
|
| 1397 |
+
"learning_rate": 3.1957894736842106e-06,
|
| 1398 |
+
"loss": 1.2548,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.053964300539643004,
|
| 1403 |
+
"grad_norm": 0.989457368850708,
|
| 1404 |
+
"learning_rate": 2.6631578947368417e-06,
|
| 1405 |
+
"loss": 1.2458,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.054241040542410406,
|
| 1410 |
+
"grad_norm": 1.0559757947921753,
|
| 1411 |
+
"learning_rate": 2.1305263157894737e-06,
|
| 1412 |
+
"loss": 1.2328,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.05451778054517781,
|
| 1417 |
+
"grad_norm": 1.1546615362167358,
|
| 1418 |
+
"learning_rate": 1.5978947368421053e-06,
|
| 1419 |
+
"loss": 1.3439,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.0547945205479452,
|
| 1424 |
+
"grad_norm": 1.6110146045684814,
|
| 1425 |
+
"learning_rate": 1.0652631578947369e-06,
|
| 1426 |
+
"loss": 1.3329,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.055071260550712604,
|
| 1431 |
+
"grad_norm": 1.3636716604232788,
|
| 1432 |
+
"learning_rate": 5.326315789473684e-07,
|
| 1433 |
+
"loss": 1.4477,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.055348000553480006,
|
| 1438 |
+
"grad_norm": 1.5938727855682373,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.7578,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.055348000553480006,
|
| 1445 |
+
"eval_loss": 1.3859784603118896,
|
| 1446 |
+
"eval_runtime": 153.7767,
|
| 1447 |
+
"eval_samples_per_second": 9.897,
|
| 1448 |
+
"eval_steps_per_second": 2.478,
|
| 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": 6.669110068484506e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|