Training in progress, step 197, 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 767856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89364f463b527a11da8557f56f8ab4cac6639bfc2ed2bf07c8c9453cdb1dd41b
|
| 3 |
size 767856
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1601338
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83f2baca4e5a99d5bd7016c497d99af00cb4246734423e51d89e98cc8c471f4f
|
| 3 |
size 1601338
|
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 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c30fe295f0b259a809ad853bb8672487884a422870d8501aed68d885220286e
|
| 3 |
size 14512
|
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 14512
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd47d4fced5a0dab22c62999e86ff4551b4af31c3d3f64bbd9b85d9ce7325a23
|
| 3 |
size 14512
|
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:d13d01228630ef79635e3e573cca86001ee4a174ea024bff4409535f559a5e68
|
| 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 +1089,335 @@
|
|
| 1089 |
"eval_samples_per_second": 40.198,
|
| 1090 |
"eval_steps_per_second": 10.11,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -1103,12 +1432,12 @@
|
|
| 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": 0.9955780164245104,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 197,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1089 |
"eval_samples_per_second": 40.198,
|
| 1090 |
"eval_steps_per_second": 10.11,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.7631080227416298,
|
| 1095 |
+
"grad_norm": 1.57240629196167,
|
| 1096 |
+
"learning_rate": 2.2277043274773857e-05,
|
| 1097 |
+
"loss": 8.6231,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.7681617182564751,
|
| 1102 |
+
"grad_norm": 1.579606294631958,
|
| 1103 |
+
"learning_rate": 2.139416699389153e-05,
|
| 1104 |
+
"loss": 8.7382,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.7732154137713203,
|
| 1109 |
+
"grad_norm": 1.3761146068572998,
|
| 1110 |
+
"learning_rate": 2.0524355524417017e-05,
|
| 1111 |
+
"loss": 8.6744,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.7782691092861656,
|
| 1116 |
+
"grad_norm": 1.1861869096755981,
|
| 1117 |
+
"learning_rate": 1.966800612528723e-05,
|
| 1118 |
+
"loss": 8.5027,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.7833228048010107,
|
| 1123 |
+
"grad_norm": 1.0866706371307373,
|
| 1124 |
+
"learning_rate": 1.8825509907063327e-05,
|
| 1125 |
+
"loss": 8.4262,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.7883765003158559,
|
| 1130 |
+
"grad_norm": 1.204898476600647,
|
| 1131 |
+
"learning_rate": 1.7997251653303248e-05,
|
| 1132 |
+
"loss": 8.3984,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.7934301958307012,
|
| 1137 |
+
"grad_norm": 1.0119705200195312,
|
| 1138 |
+
"learning_rate": 1.7183609644824096e-05,
|
| 1139 |
+
"loss": 8.56,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.7984838913455464,
|
| 1144 |
+
"grad_norm": 0.953957200050354,
|
| 1145 |
+
"learning_rate": 1.6384955486934156e-05,
|
| 1146 |
+
"loss": 8.5253,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.8035375868603917,
|
| 1151 |
+
"grad_norm": 1.0408637523651123,
|
| 1152 |
+
"learning_rate": 1.5601653939714074e-05,
|
| 1153 |
+
"loss": 8.3057,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.8085912823752369,
|
| 1158 |
+
"grad_norm": 0.88932204246521,
|
| 1159 |
+
"learning_rate": 1.4834062751424015e-05,
|
| 1160 |
+
"loss": 8.4848,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.8136449778900822,
|
| 1165 |
+
"grad_norm": 0.8721324801445007,
|
| 1166 |
+
"learning_rate": 1.4082532495113626e-05,
|
| 1167 |
+
"loss": 8.5545,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.8186986734049273,
|
| 1172 |
+
"grad_norm": 0.8064855933189392,
|
| 1173 |
+
"learning_rate": 1.3347406408508695e-05,
|
| 1174 |
+
"loss": 8.4817,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.8237523689197725,
|
| 1179 |
+
"grad_norm": 0.9848885536193848,
|
| 1180 |
+
"learning_rate": 1.262902023724824e-05,
|
| 1181 |
+
"loss": 8.5021,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.8288060644346178,
|
| 1186 |
+
"grad_norm": 1.0922009944915771,
|
| 1187 |
+
"learning_rate": 1.1927702081543279e-05,
|
| 1188 |
+
"loss": 8.1272,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.833859759949463,
|
| 1193 |
+
"grad_norm": 0.9150477051734924,
|
| 1194 |
+
"learning_rate": 1.1243772246327416e-05,
|
| 1195 |
+
"loss": 8.3211,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.8389134554643083,
|
| 1200 |
+
"grad_norm": 1.0169014930725098,
|
| 1201 |
+
"learning_rate": 1.0577543094967612e-05,
|
| 1202 |
+
"loss": 8.3955,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.8439671509791535,
|
| 1207 |
+
"grad_norm": 1.039054036140442,
|
| 1208 |
+
"learning_rate": 9.929318906602175e-06,
|
| 1209 |
+
"loss": 8.3066,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.8490208464939988,
|
| 1214 |
+
"grad_norm": 1.2704006433486938,
|
| 1215 |
+
"learning_rate": 9.299395737170757e-06,
|
| 1216 |
+
"loss": 8.1375,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.8540745420088439,
|
| 1221 |
+
"grad_norm": 1.1755458116531372,
|
| 1222 |
+
"learning_rate": 8.688061284200266e-06,
|
| 1223 |
+
"loss": 8.1842,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.8591282375236892,
|
| 1228 |
+
"grad_norm": 1.1061482429504395,
|
| 1229 |
+
"learning_rate": 8.09559475540797e-06,
|
| 1230 |
+
"loss": 8.4689,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.8641819330385344,
|
| 1235 |
+
"grad_norm": 1.089499831199646,
|
| 1236 |
+
"learning_rate": 7.522266741182305e-06,
|
| 1237 |
+
"loss": 8.2855,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.8692356285533797,
|
| 1242 |
+
"grad_norm": 1.1633696556091309,
|
| 1243 |
+
"learning_rate": 6.968339090999187e-06,
|
| 1244 |
+
"loss": 8.4485,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.8742893240682249,
|
| 1249 |
+
"grad_norm": 1.172793984413147,
|
| 1250 |
+
"learning_rate": 6.43406479383053e-06,
|
| 1251 |
+
"loss": 8.4008,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.8793430195830702,
|
| 1256 |
+
"grad_norm": 1.4023175239562988,
|
| 1257 |
+
"learning_rate": 5.919687862599549e-06,
|
| 1258 |
+
"loss": 8.603,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.8843967150979154,
|
| 1263 |
+
"grad_norm": 2.343562602996826,
|
| 1264 |
+
"learning_rate": 5.425443222735527e-06,
|
| 1265 |
+
"loss": 8.4168,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.8894504106127605,
|
| 1270 |
+
"grad_norm": 1.2631791830062866,
|
| 1271 |
+
"learning_rate": 4.951556604879048e-06,
|
| 1272 |
+
"loss": 8.6435,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.8945041061276058,
|
| 1277 |
+
"grad_norm": 1.2387241125106812,
|
| 1278 |
+
"learning_rate": 4.498244441786675e-06,
|
| 1279 |
+
"loss": 8.5938,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.899557801642451,
|
| 1284 |
+
"grad_norm": 0.9759954214096069,
|
| 1285 |
+
"learning_rate": 4.065713769482082e-06,
|
| 1286 |
+
"loss": 8.7213,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.9046114971572963,
|
| 1291 |
+
"grad_norm": 0.8986900448799133,
|
| 1292 |
+
"learning_rate": 3.654162132698918e-06,
|
| 1293 |
+
"loss": 8.5998,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.9096651926721415,
|
| 1298 |
+
"grad_norm": 0.8717695474624634,
|
| 1299 |
+
"learning_rate": 3.2637774946584486e-06,
|
| 1300 |
+
"loss": 8.6061,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.9147188881869868,
|
| 1305 |
+
"grad_norm": 0.9505631327629089,
|
| 1306 |
+
"learning_rate": 2.894738151223331e-06,
|
| 1307 |
+
"loss": 8.5173,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.919772583701832,
|
| 1312 |
+
"grad_norm": 0.8661491870880127,
|
| 1313 |
+
"learning_rate": 2.547212649466568e-06,
|
| 1314 |
+
"loss": 8.5595,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.9248262792166771,
|
| 1319 |
+
"grad_norm": 0.8975613117218018,
|
| 1320 |
+
"learning_rate": 2.221359710692961e-06,
|
| 1321 |
+
"loss": 8.483,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.9298799747315224,
|
| 1326 |
+
"grad_norm": 0.8268275856971741,
|
| 1327 |
+
"learning_rate": 1.9173281579481892e-06,
|
| 1328 |
+
"loss": 8.4253,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.9349336702463676,
|
| 1333 |
+
"grad_norm": 0.9205915927886963,
|
| 1334 |
+
"learning_rate": 1.6352568480485276e-06,
|
| 1335 |
+
"loss": 8.5825,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.9399873657612129,
|
| 1340 |
+
"grad_norm": 0.8719313740730286,
|
| 1341 |
+
"learning_rate": 1.3752746081624467e-06,
|
| 1342 |
+
"loss": 8.3617,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.9450410612760581,
|
| 1347 |
+
"grad_norm": 0.9109625816345215,
|
| 1348 |
+
"learning_rate": 1.1375001769727999e-06,
|
| 1349 |
+
"loss": 8.3006,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.9500947567909034,
|
| 1354 |
+
"grad_norm": 0.8622517585754395,
|
| 1355 |
+
"learning_rate": 9.220421504467281e-07,
|
| 1356 |
+
"loss": 8.4956,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.9551484523057486,
|
| 1361 |
+
"grad_norm": 0.9728400707244873,
|
| 1362 |
+
"learning_rate": 7.289989322378732e-07,
|
| 1363 |
+
"loss": 8.4565,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.9602021478205938,
|
| 1368 |
+
"grad_norm": 0.9318665862083435,
|
| 1369 |
+
"learning_rate": 5.584586887435739e-07,
|
| 1370 |
+
"loss": 8.3316,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.965255843335439,
|
| 1375 |
+
"grad_norm": 0.9625034332275391,
|
| 1376 |
+
"learning_rate": 4.104993088376974e-07,
|
| 1377 |
+
"loss": 8.3455,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.9703095388502843,
|
| 1382 |
+
"grad_norm": 1.1241123676300049,
|
| 1383 |
+
"learning_rate": 2.851883682973233e-07,
|
| 1384 |
+
"loss": 8.0974,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.9753632343651295,
|
| 1389 |
+
"grad_norm": 1.197749137878418,
|
| 1390 |
+
"learning_rate": 1.8258309893965375e-07,
|
| 1391 |
+
"loss": 8.19,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.9804169298799748,
|
| 1396 |
+
"grad_norm": 0.9713776111602783,
|
| 1397 |
+
"learning_rate": 1.0273036248318324e-07,
|
| 1398 |
+
"loss": 8.4274,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.98547062539482,
|
| 1403 |
+
"grad_norm": 1.0657098293304443,
|
| 1404 |
+
"learning_rate": 4.566662914508579e-08,
|
| 1405 |
+
"loss": 8.2398,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.9905243209096652,
|
| 1410 |
+
"grad_norm": 1.2770274877548218,
|
| 1411 |
+
"learning_rate": 1.1417960984605458e-08,
|
| 1412 |
+
"loss": 8.5457,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.9955780164245104,
|
| 1417 |
+
"grad_norm": 1.4860167503356934,
|
| 1418 |
+
"learning_rate": 0.0,
|
| 1419 |
+
"loss": 8.5989,
|
| 1420 |
+
"step": 197
|
| 1421 |
}
|
| 1422 |
],
|
| 1423 |
"logging_steps": 1,
|
|
|
|
| 1432 |
"should_evaluate": false,
|
| 1433 |
"should_log": false,
|
| 1434 |
"should_save": true,
|
| 1435 |
+
"should_training_stop": true
|
| 1436 |
},
|
| 1437 |
"attributes": {}
|
| 1438 |
}
|
| 1439 |
},
|
| 1440 |
+
"total_flos": 223101181231104.0,
|
| 1441 |
"train_batch_size": 2,
|
| 1442 |
"trial_name": null,
|
| 1443 |
"trial_params": null
|