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 14293800
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f786e0c7c0081a7d5822e0101e35ed3e93606b93af7788f51b7d45d18e369c69
|
| 3 |
size 14293800
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 7579748
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b2bcc486b2929cbcb510281b4245a3539dc13cba4dc0c5e3ca09fda7434a4b
|
| 3 |
size 7579748
|
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 sha256:166393d4ae9838aa53f83c2732b4695f992a2b8a71330c02e3342d5f37b1344e
|
| 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:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 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": 71.661,
|
| 1090 |
"eval_steps_per_second": 35.831,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -1103,12 +1461,12 @@
|
|
| 1103 |
"should_evaluate": false,
|
| 1104 |
"should_log": false,
|
| 1105 |
"should_save": true,
|
| 1106 |
-
"should_training_stop":
|
| 1107 |
},
|
| 1108 |
"attributes": {}
|
| 1109 |
}
|
| 1110 |
},
|
| 1111 |
-
"total_flos":
|
| 1112 |
"train_batch_size": 2,
|
| 1113 |
"trial_name": null,
|
| 1114 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.016675351745700884,
|
| 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": 71.661,
|
| 1090 |
"eval_steps_per_second": 35.831,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.01258989056800417,
|
| 1095 |
+
"grad_norm": 3.8532228469848633,
|
| 1096 |
+
"learning_rate": 3.106465908814342e-05,
|
| 1097 |
+
"loss": 9.0608,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.012673267326732674,
|
| 1102 |
+
"grad_norm": 4.6140456199646,
|
| 1103 |
+
"learning_rate": 2.9876321572751144e-05,
|
| 1104 |
+
"loss": 7.3028,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.012756644085461177,
|
| 1109 |
+
"grad_norm": 4.772500514984131,
|
| 1110 |
+
"learning_rate": 2.87071551708603e-05,
|
| 1111 |
+
"loss": 10.0175,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.012840020844189682,
|
| 1116 |
+
"grad_norm": 4.909071445465088,
|
| 1117 |
+
"learning_rate": 2.7557479520891104e-05,
|
| 1118 |
+
"loss": 9.2292,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.012923397602918187,
|
| 1123 |
+
"grad_norm": 4.347821235656738,
|
| 1124 |
+
"learning_rate": 2.6427608932686843e-05,
|
| 1125 |
+
"loss": 7.6785,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.01300677436164669,
|
| 1130 |
+
"grad_norm": 5.958515644073486,
|
| 1131 |
+
"learning_rate": 2.5317852301584643e-05,
|
| 1132 |
+
"loss": 10.8612,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.013090151120375195,
|
| 1137 |
+
"grad_norm": 4.036256790161133,
|
| 1138 |
+
"learning_rate": 2.422851302396655e-05,
|
| 1139 |
+
"loss": 6.5377,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.0131735278791037,
|
| 1144 |
+
"grad_norm": 4.0767436027526855,
|
| 1145 |
+
"learning_rate": 2.315988891431412e-05,
|
| 1146 |
+
"loss": 6.9137,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.013256904637832204,
|
| 1151 |
+
"grad_norm": 4.559920787811279,
|
| 1152 |
+
"learning_rate": 2.2112272123788768e-05,
|
| 1153 |
+
"loss": 7.8971,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.013340281396560709,
|
| 1158 |
+
"grad_norm": 3.1472551822662354,
|
| 1159 |
+
"learning_rate": 2.1085949060360654e-05,
|
| 1160 |
+
"loss": 5.2795,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.013423658155289214,
|
| 1165 |
+
"grad_norm": 4.643826961517334,
|
| 1166 |
+
"learning_rate": 2.008120031050753e-05,
|
| 1167 |
+
"loss": 10.4631,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.013507034914017717,
|
| 1172 |
+
"grad_norm": 5.551768779754639,
|
| 1173 |
+
"learning_rate": 1.9098300562505266e-05,
|
| 1174 |
+
"loss": 8.5777,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.013590411672746222,
|
| 1179 |
+
"grad_norm": 3.418463706970215,
|
| 1180 |
+
"learning_rate": 1.8137518531330767e-05,
|
| 1181 |
+
"loss": 5.9437,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.013673788431474727,
|
| 1186 |
+
"grad_norm": 4.048105239868164,
|
| 1187 |
+
"learning_rate": 1.7199116885197995e-05,
|
| 1188 |
+
"loss": 7.9703,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.013757165190203232,
|
| 1193 |
+
"grad_norm": 3.720338821411133,
|
| 1194 |
+
"learning_rate": 1.6283352173747145e-05,
|
| 1195 |
+
"loss": 7.5605,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.013840541948931735,
|
| 1200 |
+
"grad_norm": 4.476045608520508,
|
| 1201 |
+
"learning_rate": 1.5390474757906446e-05,
|
| 1202 |
+
"loss": 7.0048,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.01392391870766024,
|
| 1207 |
+
"grad_norm": 4.96762228012085,
|
| 1208 |
+
"learning_rate": 1.4520728741446089e-05,
|
| 1209 |
+
"loss": 10.7742,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.014007295466388745,
|
| 1214 |
+
"grad_norm": 4.895275592803955,
|
| 1215 |
+
"learning_rate": 1.3674351904242611e-05,
|
| 1216 |
+
"loss": 6.773,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.014090672225117248,
|
| 1221 |
+
"grad_norm": 5.70258903503418,
|
| 1222 |
+
"learning_rate": 1.2851575637272262e-05,
|
| 1223 |
+
"loss": 11.6797,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.014174048983845753,
|
| 1228 |
+
"grad_norm": 3.3568615913391113,
|
| 1229 |
+
"learning_rate": 1.2052624879351104e-05,
|
| 1230 |
+
"loss": 6.4714,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.014257425742574258,
|
| 1235 |
+
"grad_norm": 4.252028465270996,
|
| 1236 |
+
"learning_rate": 1.1277718055638819e-05,
|
| 1237 |
+
"loss": 7.7119,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.014340802501302761,
|
| 1242 |
+
"grad_norm": 4.521555423736572,
|
| 1243 |
+
"learning_rate": 1.0527067017923654e-05,
|
| 1244 |
+
"loss": 7.6881,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.014424179260031266,
|
| 1249 |
+
"grad_norm": 4.935907363891602,
|
| 1250 |
+
"learning_rate": 9.80087698670411e-06,
|
| 1251 |
+
"loss": 8.6496,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.014507556018759771,
|
| 1256 |
+
"grad_norm": 3.695267915725708,
|
| 1257 |
+
"learning_rate": 9.09934649508375e-06,
|
| 1258 |
+
"loss": 7.9681,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.014590932777488274,
|
| 1263 |
+
"grad_norm": 4.178027629852295,
|
| 1264 |
+
"learning_rate": 8.422667334494249e-06,
|
| 1265 |
+
"loss": 8.4342,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.01467430953621678,
|
| 1270 |
+
"grad_norm": 4.292721748352051,
|
| 1271 |
+
"learning_rate": 7.771024502261526e-06,
|
| 1272 |
+
"loss": 8.0612,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.014757686294945284,
|
| 1277 |
+
"grad_norm": 5.052070140838623,
|
| 1278 |
+
"learning_rate": 7.144596151029303e-06,
|
| 1279 |
+
"loss": 7.641,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.01484106305367379,
|
| 1284 |
+
"grad_norm": 5.070157527923584,
|
| 1285 |
+
"learning_rate": 6.543553540053926e-06,
|
| 1286 |
+
"loss": 7.9055,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.014924439812402292,
|
| 1291 |
+
"grad_norm": 4.510176658630371,
|
| 1292 |
+
"learning_rate": 5.968060988383883e-06,
|
| 1293 |
+
"loss": 6.882,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.015007816571130797,
|
| 1298 |
+
"grad_norm": 4.591582775115967,
|
| 1299 |
+
"learning_rate": 5.418275829936537e-06,
|
| 1300 |
+
"loss": 7.9564,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.015091193329859302,
|
| 1305 |
+
"grad_norm": 5.847330570220947,
|
| 1306 |
+
"learning_rate": 4.8943483704846475e-06,
|
| 1307 |
+
"loss": 9.3527,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.015174570088587806,
|
| 1312 |
+
"grad_norm": 4.053606033325195,
|
| 1313 |
+
"learning_rate": 4.3964218465642355e-06,
|
| 1314 |
+
"loss": 8.5674,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.01525794684731631,
|
| 1319 |
+
"grad_norm": 4.323848247528076,
|
| 1320 |
+
"learning_rate": 3.924632386315186e-06,
|
| 1321 |
+
"loss": 8.7715,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.015341323606044815,
|
| 1326 |
+
"grad_norm": 4.508976459503174,
|
| 1327 |
+
"learning_rate": 3.4791089722651436e-06,
|
| 1328 |
+
"loss": 9.1552,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.015424700364773319,
|
| 1333 |
+
"grad_norm": 3.246110439300537,
|
| 1334 |
+
"learning_rate": 3.059973406066963e-06,
|
| 1335 |
+
"loss": 8.1741,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.015508077123501824,
|
| 1340 |
+
"grad_norm": 4.064354419708252,
|
| 1341 |
+
"learning_rate": 2.667340275199426e-06,
|
| 1342 |
+
"loss": 9.1723,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.015591453882230329,
|
| 1347 |
+
"grad_norm": 4.16738748550415,
|
| 1348 |
+
"learning_rate": 2.3013169216400733e-06,
|
| 1349 |
+
"loss": 7.7564,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.015674830640958832,
|
| 1354 |
+
"grad_norm": 3.58866810798645,
|
| 1355 |
+
"learning_rate": 1.9620034125190644e-06,
|
| 1356 |
+
"loss": 8.4719,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.01575820739968734,
|
| 1361 |
+
"grad_norm": 4.435379505157471,
|
| 1362 |
+
"learning_rate": 1.6494925127617634e-06,
|
| 1363 |
+
"loss": 8.5871,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.015841584158415842,
|
| 1368 |
+
"grad_norm": 4.594212532043457,
|
| 1369 |
+
"learning_rate": 1.3638696597277679e-06,
|
| 1370 |
+
"loss": 8.6829,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.015924960917144345,
|
| 1375 |
+
"grad_norm": 5.113223552703857,
|
| 1376 |
+
"learning_rate": 1.1052129398531507e-06,
|
| 1377 |
+
"loss": 7.9665,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.01600833767587285,
|
| 1382 |
+
"grad_norm": 3.7875256538391113,
|
| 1383 |
+
"learning_rate": 8.735930673024806e-07,
|
| 1384 |
+
"loss": 6.4576,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.016091714434601355,
|
| 1389 |
+
"grad_norm": 3.661071300506592,
|
| 1390 |
+
"learning_rate": 6.690733646361857e-07,
|
| 1391 |
+
"loss": 6.8199,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.016175091193329858,
|
| 1396 |
+
"grad_norm": 4.465787887573242,
|
| 1397 |
+
"learning_rate": 4.917097454988584e-07,
|
| 1398 |
+
"loss": 8.3244,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.016258467952058365,
|
| 1403 |
+
"grad_norm": 4.833078861236572,
|
| 1404 |
+
"learning_rate": 3.415506993330153e-07,
|
| 1405 |
+
"loss": 8.3167,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.016341844710786868,
|
| 1410 |
+
"grad_norm": 3.7651824951171875,
|
| 1411 |
+
"learning_rate": 2.1863727812254653e-07,
|
| 1412 |
+
"loss": 6.5716,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.01642522146951537,
|
| 1417 |
+
"grad_norm": 4.892351150512695,
|
| 1418 |
+
"learning_rate": 1.230030851695263e-07,
|
| 1419 |
+
"loss": 7.0042,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.016508598228243878,
|
| 1424 |
+
"grad_norm": 3.952244758605957,
|
| 1425 |
+
"learning_rate": 5.467426590739511e-08,
|
| 1426 |
+
"loss": 7.8461,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.01659197498697238,
|
| 1431 |
+
"grad_norm": 3.891923427581787,
|
| 1432 |
+
"learning_rate": 1.3669500753099585e-08,
|
| 1433 |
+
"loss": 7.6043,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.016675351745700884,
|
| 1438 |
+
"grad_norm": 5.590742588043213,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 10.1178,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.016675351745700884,
|
| 1445 |
+
"eval_loss": 1.9614673852920532,
|
| 1446 |
+
"eval_runtime": 69.1641,
|
| 1447 |
+
"eval_samples_per_second": 73.015,
|
| 1448 |
+
"eval_steps_per_second": 36.507,
|
| 1449 |
+
"step": 200
|
| 1450 |
}
|
| 1451 |
],
|
| 1452 |
"logging_steps": 1,
|
|
|
|
| 1461 |
"should_evaluate": false,
|
| 1462 |
"should_log": false,
|
| 1463 |
"should_save": true,
|
| 1464 |
+
"should_training_stop": true
|
| 1465 |
},
|
| 1466 |
"attributes": {}
|
| 1467 |
}
|
| 1468 |
},
|
| 1469 |
+
"total_flos": 1821610856153088.0,
|
| 1470 |
"train_batch_size": 2,
|
| 1471 |
"trial_name": null,
|
| 1472 |
"trial_params": null
|