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 522227376
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f599aa0c0a049fb7ee912cf3835441176123724e829b85db2d58880b25ae3f7e
|
| 3 |
size 522227376
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 265476436
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af02c82fd042017d904dcb83a7958fe1758c1f4bd454598a93c25e2c1185b08e
|
| 3 |
size 265476436
|
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 sha256:94778b2c0a4fafa19b9b9664a360321d3d7bcf837bddaa94e0390eb59a308100
|
| 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 sha256:3709ad194ceda6ee92d3d2c8f2dd5203a40bedaa701af97b45dc02564222704e
|
| 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": 10.081,
|
| 1090 |
"eval_steps_per_second": 2.52,
|
| 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": 1.8669476509094238,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.016857010409203926,
|
| 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": 10.081,
|
| 1090 |
"eval_steps_per_second": 2.52,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.012727042858948965,
|
| 1095 |
+
"grad_norm": 1.3897639513015747,
|
| 1096 |
+
"learning_rate": 2.597e-05,
|
| 1097 |
+
"loss": 3.8315,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.012811327910994985,
|
| 1102 |
+
"grad_norm": 1.3828065395355225,
|
| 1103 |
+
"learning_rate": 2.544e-05,
|
| 1104 |
+
"loss": 3.6809,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.012895612963041005,
|
| 1109 |
+
"grad_norm": 1.3566617965698242,
|
| 1110 |
+
"learning_rate": 2.4909999999999997e-05,
|
| 1111 |
+
"loss": 3.5872,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.012979898015087024,
|
| 1116 |
+
"grad_norm": 1.3214489221572876,
|
| 1117 |
+
"learning_rate": 2.438e-05,
|
| 1118 |
+
"loss": 3.4207,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.013064183067133044,
|
| 1123 |
+
"grad_norm": 1.2196868658065796,
|
| 1124 |
+
"learning_rate": 2.3849999999999997e-05,
|
| 1125 |
+
"loss": 3.2518,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.013148468119179064,
|
| 1130 |
+
"grad_norm": 1.3787480592727661,
|
| 1131 |
+
"learning_rate": 2.3319999999999997e-05,
|
| 1132 |
+
"loss": 3.3574,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.013232753171225083,
|
| 1137 |
+
"grad_norm": 1.224331021308899,
|
| 1138 |
+
"learning_rate": 2.279e-05,
|
| 1139 |
+
"loss": 3.4614,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.013317038223271103,
|
| 1144 |
+
"grad_norm": 1.382997751235962,
|
| 1145 |
+
"learning_rate": 2.2259999999999997e-05,
|
| 1146 |
+
"loss": 3.9046,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.013401323275317123,
|
| 1151 |
+
"grad_norm": 1.3192687034606934,
|
| 1152 |
+
"learning_rate": 2.173e-05,
|
| 1153 |
+
"loss": 3.7665,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.013485608327363141,
|
| 1158 |
+
"grad_norm": 1.4856247901916504,
|
| 1159 |
+
"learning_rate": 2.1199999999999997e-05,
|
| 1160 |
+
"loss": 4.2557,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.013569893379409162,
|
| 1165 |
+
"grad_norm": 1.4664103984832764,
|
| 1166 |
+
"learning_rate": 2.067e-05,
|
| 1167 |
+
"loss": 3.8251,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.013654178431455182,
|
| 1172 |
+
"grad_norm": 1.472501516342163,
|
| 1173 |
+
"learning_rate": 2.014e-05,
|
| 1174 |
+
"loss": 4.0414,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.0137384634835012,
|
| 1179 |
+
"grad_norm": 1.5374277830123901,
|
| 1180 |
+
"learning_rate": 1.9609999999999997e-05,
|
| 1181 |
+
"loss": 3.7686,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.01382274853554722,
|
| 1186 |
+
"grad_norm": 1.382415771484375,
|
| 1187 |
+
"learning_rate": 1.908e-05,
|
| 1188 |
+
"loss": 3.3308,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.01390703358759324,
|
| 1193 |
+
"grad_norm": 1.4553520679473877,
|
| 1194 |
+
"learning_rate": 1.8549999999999997e-05,
|
| 1195 |
+
"loss": 3.8213,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.01399131863963926,
|
| 1200 |
+
"grad_norm": 1.5830438137054443,
|
| 1201 |
+
"learning_rate": 1.802e-05,
|
| 1202 |
+
"loss": 3.9779,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.01407560369168528,
|
| 1207 |
+
"grad_norm": 1.6630796194076538,
|
| 1208 |
+
"learning_rate": 1.749e-05,
|
| 1209 |
+
"loss": 4.2908,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.0141598887437313,
|
| 1214 |
+
"grad_norm": 1.6110979318618774,
|
| 1215 |
+
"learning_rate": 1.696e-05,
|
| 1216 |
+
"loss": 3.3741,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.01424417379577732,
|
| 1221 |
+
"grad_norm": 1.5861139297485352,
|
| 1222 |
+
"learning_rate": 1.643e-05,
|
| 1223 |
+
"loss": 3.9935,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.014328458847823338,
|
| 1228 |
+
"grad_norm": 1.6507846117019653,
|
| 1229 |
+
"learning_rate": 1.5899999999999997e-05,
|
| 1230 |
+
"loss": 3.4942,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.014412743899869358,
|
| 1235 |
+
"grad_norm": 1.7398327589035034,
|
| 1236 |
+
"learning_rate": 1.537e-05,
|
| 1237 |
+
"loss": 4.0904,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.014497028951915378,
|
| 1242 |
+
"grad_norm": 1.7537189722061157,
|
| 1243 |
+
"learning_rate": 1.4839999999999999e-05,
|
| 1244 |
+
"loss": 3.7626,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.014581314003961397,
|
| 1249 |
+
"grad_norm": 1.6175459623336792,
|
| 1250 |
+
"learning_rate": 1.4309999999999999e-05,
|
| 1251 |
+
"loss": 3.7885,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.014665599056007417,
|
| 1256 |
+
"grad_norm": 1.7866084575653076,
|
| 1257 |
+
"learning_rate": 1.378e-05,
|
| 1258 |
+
"loss": 3.5248,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.014749884108053437,
|
| 1263 |
+
"grad_norm": 1.7713515758514404,
|
| 1264 |
+
"learning_rate": 1.3249999999999999e-05,
|
| 1265 |
+
"loss": 3.9378,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.014834169160099456,
|
| 1270 |
+
"grad_norm": 1.9118940830230713,
|
| 1271 |
+
"learning_rate": 1.272e-05,
|
| 1272 |
+
"loss": 4.1767,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.014918454212145476,
|
| 1277 |
+
"grad_norm": 1.8637574911117554,
|
| 1278 |
+
"learning_rate": 1.219e-05,
|
| 1279 |
+
"loss": 3.8656,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.015002739264191496,
|
| 1284 |
+
"grad_norm": 1.828238844871521,
|
| 1285 |
+
"learning_rate": 1.1659999999999998e-05,
|
| 1286 |
+
"loss": 4.0391,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.015087024316237515,
|
| 1291 |
+
"grad_norm": 2.0488600730895996,
|
| 1292 |
+
"learning_rate": 1.1129999999999998e-05,
|
| 1293 |
+
"loss": 3.922,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.015171309368283535,
|
| 1298 |
+
"grad_norm": 2.0183472633361816,
|
| 1299 |
+
"learning_rate": 1.0599999999999998e-05,
|
| 1300 |
+
"loss": 4.2234,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.015255594420329555,
|
| 1305 |
+
"grad_norm": 2.070134401321411,
|
| 1306 |
+
"learning_rate": 1.007e-05,
|
| 1307 |
+
"loss": 3.918,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.015339879472375573,
|
| 1312 |
+
"grad_norm": 2.2498276233673096,
|
| 1313 |
+
"learning_rate": 9.54e-06,
|
| 1314 |
+
"loss": 3.9867,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.015424164524421594,
|
| 1319 |
+
"grad_norm": 2.2584664821624756,
|
| 1320 |
+
"learning_rate": 9.01e-06,
|
| 1321 |
+
"loss": 4.0252,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.015508449576467614,
|
| 1326 |
+
"grad_norm": 2.067579507827759,
|
| 1327 |
+
"learning_rate": 8.48e-06,
|
| 1328 |
+
"loss": 3.7084,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.015592734628513634,
|
| 1333 |
+
"grad_norm": 2.0557119846343994,
|
| 1334 |
+
"learning_rate": 7.949999999999998e-06,
|
| 1335 |
+
"loss": 3.7976,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.015677019680559654,
|
| 1340 |
+
"grad_norm": 2.188267707824707,
|
| 1341 |
+
"learning_rate": 7.419999999999999e-06,
|
| 1342 |
+
"loss": 3.9759,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.01576130473260567,
|
| 1347 |
+
"grad_norm": 2.3321714401245117,
|
| 1348 |
+
"learning_rate": 6.89e-06,
|
| 1349 |
+
"loss": 4.3558,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.01584558978465169,
|
| 1354 |
+
"grad_norm": 2.385741949081421,
|
| 1355 |
+
"learning_rate": 6.36e-06,
|
| 1356 |
+
"loss": 3.8495,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.01592987483669771,
|
| 1361 |
+
"grad_norm": 2.042713165283203,
|
| 1362 |
+
"learning_rate": 5.829999999999999e-06,
|
| 1363 |
+
"loss": 3.6389,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.01601415988874373,
|
| 1368 |
+
"grad_norm": 2.288698434829712,
|
| 1369 |
+
"learning_rate": 5.299999999999999e-06,
|
| 1370 |
+
"loss": 4.0149,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.01609844494078975,
|
| 1375 |
+
"grad_norm": 2.1924726963043213,
|
| 1376 |
+
"learning_rate": 4.77e-06,
|
| 1377 |
+
"loss": 3.9639,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.016182729992835772,
|
| 1382 |
+
"grad_norm": 2.3209054470062256,
|
| 1383 |
+
"learning_rate": 4.24e-06,
|
| 1384 |
+
"loss": 3.4898,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.01626701504488179,
|
| 1389 |
+
"grad_norm": 2.477083206176758,
|
| 1390 |
+
"learning_rate": 3.7099999999999996e-06,
|
| 1391 |
+
"loss": 3.2621,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.01635130009692781,
|
| 1396 |
+
"grad_norm": 2.740098237991333,
|
| 1397 |
+
"learning_rate": 3.18e-06,
|
| 1398 |
+
"loss": 3.6511,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.01643558514897383,
|
| 1403 |
+
"grad_norm": 2.6082754135131836,
|
| 1404 |
+
"learning_rate": 2.6499999999999996e-06,
|
| 1405 |
+
"loss": 3.6124,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.01651987020101985,
|
| 1410 |
+
"grad_norm": 2.774245023727417,
|
| 1411 |
+
"learning_rate": 2.12e-06,
|
| 1412 |
+
"loss": 3.2226,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.01660415525306587,
|
| 1417 |
+
"grad_norm": 2.7693519592285156,
|
| 1418 |
+
"learning_rate": 1.59e-06,
|
| 1419 |
+
"loss": 3.2539,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.01668844030511189,
|
| 1424 |
+
"grad_norm": 2.846680164337158,
|
| 1425 |
+
"learning_rate": 1.06e-06,
|
| 1426 |
+
"loss": 2.9483,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.01677272535715791,
|
| 1431 |
+
"grad_norm": 3.2634568214416504,
|
| 1432 |
+
"learning_rate": 5.3e-07,
|
| 1433 |
+
"loss": 3.4867,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.016857010409203926,
|
| 1438 |
+
"grad_norm": 3.9992029666900635,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 3.4449,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.016857010409203926,
|
| 1445 |
+
"eval_loss": 1.8669476509094238,
|
| 1446 |
+
"eval_runtime": 496.0136,
|
| 1447 |
+
"eval_samples_per_second": 10.072,
|
| 1448 |
+
"eval_steps_per_second": 2.518,
|
| 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": 6.6422040428544e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|