Training in progress, step 200, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +371 -5
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 335604696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a340ff9a40ba658d0c744209a2fa0151200c9f23889b0d92e41f0190892b01b7
|
| 3 |
size 335604696
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 671466706
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0b5bfa21a4dbe217e27a3d149dcfd87731ff44fcd3cd42067bb73da45f2b6e8
|
| 3 |
size 671466706
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19f03c2303110485fc660785bbccce570b07139509cf4d5ec583a48e9d40a234
|
| 3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d03a54159528aa62893dfcff671b177327b382313312bf10b737e9ae0e77063a
|
| 3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fb0d06c2a9f9feb6c9bb923b3bf15c2a29ca8ead96ef8521a04b055e1308d6f
|
| 3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b5b9e2666027290fca18ec3d5097f875dee68f229bf9cbd686339b9b0ef83bb
|
| 3 |
size 15024
|
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 sha256:54f74800e5401bd6d4b5db174f4498f3d514e0af0e4938764d8ef955fdaf3681
|
| 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":
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1113,6 +1113,372 @@
|
|
| 1113 |
"eval_samples_per_second": 20.276,
|
| 1114 |
"eval_steps_per_second": 5.272,
|
| 1115 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
|
@@ -1141,7 +1507,7 @@
|
|
| 1141 |
"attributes": {}
|
| 1142 |
}
|
| 1143 |
},
|
| 1144 |
-
"total_flos":
|
| 1145 |
"train_batch_size": 1,
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.2711719274520874,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 1.034928848641656,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1113 |
"eval_samples_per_second": 20.276,
|
| 1114 |
"eval_steps_per_second": 5.272,
|
| 1115 |
"step": 150
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.7813712807244502,
|
| 1119 |
+
"grad_norm": 42.78679275512695,
|
| 1120 |
+
"learning_rate": 8.111050937205231e-05,
|
| 1121 |
+
"loss": 18.7941,
|
| 1122 |
+
"step": 151
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.7865459249676585,
|
| 1126 |
+
"grad_norm": 25.310531616210938,
|
| 1127 |
+
"learning_rate": 8.084756472298504e-05,
|
| 1128 |
+
"loss": 17.3761,
|
| 1129 |
+
"step": 152
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.7917205692108668,
|
| 1133 |
+
"grad_norm": 26.00894546508789,
|
| 1134 |
+
"learning_rate": 8.05832963772275e-05,
|
| 1135 |
+
"loss": 16.5988,
|
| 1136 |
+
"step": 153
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.796895213454075,
|
| 1140 |
+
"grad_norm": 31.627395629882812,
|
| 1141 |
+
"learning_rate": 8.031771786840027e-05,
|
| 1142 |
+
"loss": 17.0581,
|
| 1143 |
+
"step": 154
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.8020698576972833,
|
| 1147 |
+
"grad_norm": 24.270063400268555,
|
| 1148 |
+
"learning_rate": 8.005084279721962e-05,
|
| 1149 |
+
"loss": 17.2211,
|
| 1150 |
+
"step": 155
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.8072445019404916,
|
| 1154 |
+
"grad_norm": 19.81817626953125,
|
| 1155 |
+
"learning_rate": 7.978268483080086e-05,
|
| 1156 |
+
"loss": 16.7364,
|
| 1157 |
+
"step": 156
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.8124191461836999,
|
| 1161 |
+
"grad_norm": 25.11359214782715,
|
| 1162 |
+
"learning_rate": 7.951325770195858e-05,
|
| 1163 |
+
"loss": 16.9734,
|
| 1164 |
+
"step": 157
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.8175937904269082,
|
| 1168 |
+
"grad_norm": 24.607805252075195,
|
| 1169 |
+
"learning_rate": 7.924257520850318e-05,
|
| 1170 |
+
"loss": 17.2824,
|
| 1171 |
+
"step": 158
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.8227684346701164,
|
| 1175 |
+
"grad_norm": 37.20039367675781,
|
| 1176 |
+
"learning_rate": 7.897065121253442e-05,
|
| 1177 |
+
"loss": 21.952,
|
| 1178 |
+
"step": 159
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.8279430789133247,
|
| 1182 |
+
"grad_norm": 39.281612396240234,
|
| 1183 |
+
"learning_rate": 7.86974996397315e-05,
|
| 1184 |
+
"loss": 21.6825,
|
| 1185 |
+
"step": 160
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.833117723156533,
|
| 1189 |
+
"grad_norm": 37.44650650024414,
|
| 1190 |
+
"learning_rate": 7.842313447863978e-05,
|
| 1191 |
+
"loss": 20.3417,
|
| 1192 |
+
"step": 161
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.8382923673997412,
|
| 1196 |
+
"grad_norm": 34.385738372802734,
|
| 1197 |
+
"learning_rate": 7.814756977995459e-05,
|
| 1198 |
+
"loss": 20.6472,
|
| 1199 |
+
"step": 162
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.8434670116429496,
|
| 1203 |
+
"grad_norm": 33.13866424560547,
|
| 1204 |
+
"learning_rate": 7.78708196558015e-05,
|
| 1205 |
+
"loss": 19.1521,
|
| 1206 |
+
"step": 163
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.8486416558861578,
|
| 1210 |
+
"grad_norm": 33.19305419921875,
|
| 1211 |
+
"learning_rate": 7.75928982790137e-05,
|
| 1212 |
+
"loss": 17.8224,
|
| 1213 |
+
"step": 164
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.8538163001293662,
|
| 1217 |
+
"grad_norm": 23.117149353027344,
|
| 1218 |
+
"learning_rate": 7.73138198824062e-05,
|
| 1219 |
+
"loss": 17.1422,
|
| 1220 |
+
"step": 165
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.8589909443725744,
|
| 1224 |
+
"grad_norm": 20.45843505859375,
|
| 1225 |
+
"learning_rate": 7.703359875804689e-05,
|
| 1226 |
+
"loss": 16.8825,
|
| 1227 |
+
"step": 166
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.8641655886157826,
|
| 1231 |
+
"grad_norm": 25.545473098754883,
|
| 1232 |
+
"learning_rate": 7.675224925652463e-05,
|
| 1233 |
+
"loss": 16.9471,
|
| 1234 |
+
"step": 167
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.869340232858991,
|
| 1238 |
+
"grad_norm": 25.315954208374023,
|
| 1239 |
+
"learning_rate": 7.646978578621437e-05,
|
| 1240 |
+
"loss": 16.7291,
|
| 1241 |
+
"step": 168
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.8745148771021992,
|
| 1245 |
+
"grad_norm": 21.237030029296875,
|
| 1246 |
+
"learning_rate": 7.618622281253924e-05,
|
| 1247 |
+
"loss": 16.8548,
|
| 1248 |
+
"step": 169
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.8796895213454075,
|
| 1252 |
+
"grad_norm": 20.109127044677734,
|
| 1253 |
+
"learning_rate": 7.590157485722982e-05,
|
| 1254 |
+
"loss": 16.2734,
|
| 1255 |
+
"step": 170
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.8848641655886158,
|
| 1259 |
+
"grad_norm": 28.761709213256836,
|
| 1260 |
+
"learning_rate": 7.561585649758028e-05,
|
| 1261 |
+
"loss": 18.0656,
|
| 1262 |
+
"step": 171
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.890038809831824,
|
| 1266 |
+
"grad_norm": 42.106163024902344,
|
| 1267 |
+
"learning_rate": 7.532908236570209e-05,
|
| 1268 |
+
"loss": 21.5631,
|
| 1269 |
+
"step": 172
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.8952134540750324,
|
| 1273 |
+
"grad_norm": 34.408836364746094,
|
| 1274 |
+
"learning_rate": 7.504126714777451e-05,
|
| 1275 |
+
"loss": 20.1863,
|
| 1276 |
+
"step": 173
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.9003880983182406,
|
| 1280 |
+
"grad_norm": 34.73509216308594,
|
| 1281 |
+
"learning_rate": 7.475242558329254e-05,
|
| 1282 |
+
"loss": 20.1942,
|
| 1283 |
+
"step": 174
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.9055627425614489,
|
| 1287 |
+
"grad_norm": 42.28166198730469,
|
| 1288 |
+
"learning_rate": 7.446257246431213e-05,
|
| 1289 |
+
"loss": 19.6754,
|
| 1290 |
+
"step": 175
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.9055627425614489,
|
| 1294 |
+
"eval_loss": 0.2736213207244873,
|
| 1295 |
+
"eval_runtime": 2.4637,
|
| 1296 |
+
"eval_samples_per_second": 20.295,
|
| 1297 |
+
"eval_steps_per_second": 5.277,
|
| 1298 |
+
"step": 175
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.9107373868046572,
|
| 1302 |
+
"grad_norm": 24.5119571685791,
|
| 1303 |
+
"learning_rate": 7.417172263469256e-05,
|
| 1304 |
+
"loss": 16.8454,
|
| 1305 |
+
"step": 176
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.9159120310478654,
|
| 1309 |
+
"grad_norm": 21.90869903564453,
|
| 1310 |
+
"learning_rate": 7.387989098933635e-05,
|
| 1311 |
+
"loss": 17.0339,
|
| 1312 |
+
"step": 177
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.9210866752910737,
|
| 1316 |
+
"grad_norm": 19.313365936279297,
|
| 1317 |
+
"learning_rate": 7.358709247342646e-05,
|
| 1318 |
+
"loss": 16.8579,
|
| 1319 |
+
"step": 178
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.926261319534282,
|
| 1323 |
+
"grad_norm": 19.5049991607666,
|
| 1324 |
+
"learning_rate": 7.329334208166084e-05,
|
| 1325 |
+
"loss": 16.6727,
|
| 1326 |
+
"step": 179
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.9314359637774903,
|
| 1330 |
+
"grad_norm": 21.2435359954834,
|
| 1331 |
+
"learning_rate": 7.299865485748463e-05,
|
| 1332 |
+
"loss": 16.5497,
|
| 1333 |
+
"step": 180
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.9366106080206986,
|
| 1337 |
+
"grad_norm": 20.878833770751953,
|
| 1338 |
+
"learning_rate": 7.270304589231966e-05,
|
| 1339 |
+
"loss": 16.565,
|
| 1340 |
+
"step": 181
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.9417852522639069,
|
| 1344 |
+
"grad_norm": 19.161964416503906,
|
| 1345 |
+
"learning_rate": 7.24065303247917e-05,
|
| 1346 |
+
"loss": 15.7553,
|
| 1347 |
+
"step": 182
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.9469598965071151,
|
| 1351 |
+
"grad_norm": 20.745361328125,
|
| 1352 |
+
"learning_rate": 7.21091233399551e-05,
|
| 1353 |
+
"loss": 15.9131,
|
| 1354 |
+
"step": 183
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.9521345407503234,
|
| 1358 |
+
"grad_norm": 27.22768211364746,
|
| 1359 |
+
"learning_rate": 7.181084016851518e-05,
|
| 1360 |
+
"loss": 20.1224,
|
| 1361 |
+
"step": 184
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.9573091849935317,
|
| 1365 |
+
"grad_norm": 33.0516242980957,
|
| 1366 |
+
"learning_rate": 7.151169608604823e-05,
|
| 1367 |
+
"loss": 20.905,
|
| 1368 |
+
"step": 185
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.96248382923674,
|
| 1372 |
+
"grad_norm": 33.2736701965332,
|
| 1373 |
+
"learning_rate": 7.121170641221921e-05,
|
| 1374 |
+
"loss": 20.3362,
|
| 1375 |
+
"step": 186
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.9676584734799483,
|
| 1379 |
+
"grad_norm": 34.649681091308594,
|
| 1380 |
+
"learning_rate": 7.091088650999727e-05,
|
| 1381 |
+
"loss": 20.4311,
|
| 1382 |
+
"step": 187
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.9728331177231565,
|
| 1386 |
+
"grad_norm": 32.207275390625,
|
| 1387 |
+
"learning_rate": 7.060925178486883e-05,
|
| 1388 |
+
"loss": 18.6855,
|
| 1389 |
+
"step": 188
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.9780077619663649,
|
| 1393 |
+
"grad_norm": 26.237972259521484,
|
| 1394 |
+
"learning_rate": 7.030681768404885e-05,
|
| 1395 |
+
"loss": 16.7824,
|
| 1396 |
+
"step": 189
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.9831824062095731,
|
| 1400 |
+
"grad_norm": 20.84476661682129,
|
| 1401 |
+
"learning_rate": 7.000359969568959e-05,
|
| 1402 |
+
"loss": 16.19,
|
| 1403 |
+
"step": 190
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.9883570504527813,
|
| 1407 |
+
"grad_norm": 22.17355728149414,
|
| 1408 |
+
"learning_rate": 6.96996133480875e-05,
|
| 1409 |
+
"loss": 16.6938,
|
| 1410 |
+
"step": 191
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.9935316946959897,
|
| 1414 |
+
"grad_norm": 38.83606719970703,
|
| 1415 |
+
"learning_rate": 6.9394874208888e-05,
|
| 1416 |
+
"loss": 20.4554,
|
| 1417 |
+
"step": 192
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.9987063389391979,
|
| 1421 |
+
"grad_norm": 48.76588439941406,
|
| 1422 |
+
"learning_rate": 6.908939788428818e-05,
|
| 1423 |
+
"loss": 19.718,
|
| 1424 |
+
"step": 193
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.0038809831824063,
|
| 1428 |
+
"grad_norm": 28.960180282592773,
|
| 1429 |
+
"learning_rate": 6.878320001823764e-05,
|
| 1430 |
+
"loss": 16.514,
|
| 1431 |
+
"step": 194
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.0090556274256144,
|
| 1435 |
+
"grad_norm": 22.513782501220703,
|
| 1436 |
+
"learning_rate": 6.847629629163734e-05,
|
| 1437 |
+
"loss": 14.5428,
|
| 1438 |
+
"step": 195
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.0142302716688227,
|
| 1442 |
+
"grad_norm": 19.849233627319336,
|
| 1443 |
+
"learning_rate": 6.816870242153649e-05,
|
| 1444 |
+
"loss": 13.8245,
|
| 1445 |
+
"step": 196
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.019404915912031,
|
| 1449 |
+
"grad_norm": 18.695232391357422,
|
| 1450 |
+
"learning_rate": 6.786043416032772e-05,
|
| 1451 |
+
"loss": 13.3732,
|
| 1452 |
+
"step": 197
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.0245795601552394,
|
| 1456 |
+
"grad_norm": 19.380321502685547,
|
| 1457 |
+
"learning_rate": 6.755150729494033e-05,
|
| 1458 |
+
"loss": 13.551,
|
| 1459 |
+
"step": 198
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.0297542043984476,
|
| 1463 |
+
"grad_norm": 21.321197509765625,
|
| 1464 |
+
"learning_rate": 6.724193764603185e-05,
|
| 1465 |
+
"loss": 13.3021,
|
| 1466 |
+
"step": 199
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.034928848641656,
|
| 1470 |
+
"grad_norm": 21.382387161254883,
|
| 1471 |
+
"learning_rate": 6.693174106717781e-05,
|
| 1472 |
+
"loss": 12.9263,
|
| 1473 |
+
"step": 200
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.034928848641656,
|
| 1477 |
+
"eval_loss": 0.2711719274520874,
|
| 1478 |
+
"eval_runtime": 2.4664,
|
| 1479 |
+
"eval_samples_per_second": 20.272,
|
| 1480 |
+
"eval_steps_per_second": 5.271,
|
| 1481 |
+
"step": 200
|
| 1482 |
}
|
| 1483 |
],
|
| 1484 |
"logging_steps": 1,
|
|
|
|
| 1507 |
"attributes": {}
|
| 1508 |
}
|
| 1509 |
},
|
| 1510 |
+
"total_flos": 4.66786752355369e+18,
|
| 1511 |
"train_batch_size": 1,
|
| 1512 |
"trial_name": null,
|
| 1513 |
"trial_params": null
|