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 313820248
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:061273cae7d7391c9cbd8707e8416b2db4430f963b62c2d87ee2c5ca5abe9289
|
| 3 |
size 313820248
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 159641092
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd51e97228e32a544c0331c83a86e9fbde4253ee4fe75e393a535e978fd9ce78
|
| 3 |
size 159641092
|
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 sha256:6a6342d38f1970d10c6888e47c48974a4c5eab8a7fac69cb76e117deb2b294f0
|
| 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 sha256:36c6d837152cc4853064add4c61272c62a18db4bbfe14e332929026ad210cee2
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 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": 16.925,
|
| 1090 |
"eval_steps_per_second": 4.232,
|
| 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": 1.9446079730987549,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.005479527116809819,
|
| 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": 16.925,
|
| 1090 |
"eval_steps_per_second": 4.232,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.004137042973191413,
|
| 1095 |
+
"grad_norm": 10.242443084716797,
|
| 1096 |
+
"learning_rate": 2.6073157894736845e-05,
|
| 1097 |
+
"loss": 2.8813,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.0041644406087754625,
|
| 1102 |
+
"grad_norm": 11.027935981750488,
|
| 1103 |
+
"learning_rate": 2.554105263157895e-05,
|
| 1104 |
+
"loss": 3.2701,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.004191838244359512,
|
| 1109 |
+
"grad_norm": 9.913683891296387,
|
| 1110 |
+
"learning_rate": 2.5008947368421052e-05,
|
| 1111 |
+
"loss": 2.8378,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.004219235879943561,
|
| 1116 |
+
"grad_norm": 12.305196762084961,
|
| 1117 |
+
"learning_rate": 2.447684210526316e-05,
|
| 1118 |
+
"loss": 3.3966,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.00424663351552761,
|
| 1123 |
+
"grad_norm": 14.736776351928711,
|
| 1124 |
+
"learning_rate": 2.3944736842105262e-05,
|
| 1125 |
+
"loss": 2.936,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.004274031151111659,
|
| 1130 |
+
"grad_norm": 15.716378211975098,
|
| 1131 |
+
"learning_rate": 2.341263157894737e-05,
|
| 1132 |
+
"loss": 3.3793,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.004301428786695708,
|
| 1137 |
+
"grad_norm": 11.29692554473877,
|
| 1138 |
+
"learning_rate": 2.2880526315789475e-05,
|
| 1139 |
+
"loss": 2.5899,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.004328826422279757,
|
| 1144 |
+
"grad_norm": 8.92076587677002,
|
| 1145 |
+
"learning_rate": 2.234842105263158e-05,
|
| 1146 |
+
"loss": 1.5897,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.004356224057863806,
|
| 1151 |
+
"grad_norm": 10.286359786987305,
|
| 1152 |
+
"learning_rate": 2.1816315789473685e-05,
|
| 1153 |
+
"loss": 2.0679,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.004383621693447855,
|
| 1158 |
+
"grad_norm": 10.094871520996094,
|
| 1159 |
+
"learning_rate": 2.128421052631579e-05,
|
| 1160 |
+
"loss": 2.2023,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.0044110193290319046,
|
| 1165 |
+
"grad_norm": 8.398151397705078,
|
| 1166 |
+
"learning_rate": 2.0752105263157895e-05,
|
| 1167 |
+
"loss": 1.7198,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.004438416964615954,
|
| 1172 |
+
"grad_norm": 9.89030647277832,
|
| 1173 |
+
"learning_rate": 2.0220000000000003e-05,
|
| 1174 |
+
"loss": 1.8957,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.004465814600200003,
|
| 1179 |
+
"grad_norm": 10.257231712341309,
|
| 1180 |
+
"learning_rate": 1.9687894736842104e-05,
|
| 1181 |
+
"loss": 1.8288,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.004493212235784052,
|
| 1186 |
+
"grad_norm": 10.972249984741211,
|
| 1187 |
+
"learning_rate": 1.9155789473684213e-05,
|
| 1188 |
+
"loss": 2.3046,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.004520609871368101,
|
| 1193 |
+
"grad_norm": 9.473671913146973,
|
| 1194 |
+
"learning_rate": 1.8623684210526314e-05,
|
| 1195 |
+
"loss": 1.5979,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.00454800750695215,
|
| 1200 |
+
"grad_norm": 8.295541763305664,
|
| 1201 |
+
"learning_rate": 1.8091578947368423e-05,
|
| 1202 |
+
"loss": 1.6066,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.004575405142536199,
|
| 1207 |
+
"grad_norm": 9.380114555358887,
|
| 1208 |
+
"learning_rate": 1.7559473684210528e-05,
|
| 1209 |
+
"loss": 1.382,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.004602802778120248,
|
| 1214 |
+
"grad_norm": 10.417853355407715,
|
| 1215 |
+
"learning_rate": 1.7027368421052632e-05,
|
| 1216 |
+
"loss": 2.454,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.0046302004137042975,
|
| 1221 |
+
"grad_norm": 10.452378273010254,
|
| 1222 |
+
"learning_rate": 1.6495263157894737e-05,
|
| 1223 |
+
"loss": 1.9223,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.004657598049288347,
|
| 1228 |
+
"grad_norm": 9.896018981933594,
|
| 1229 |
+
"learning_rate": 1.5963157894736842e-05,
|
| 1230 |
+
"loss": 1.8119,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.004684995684872396,
|
| 1235 |
+
"grad_norm": 9.311156272888184,
|
| 1236 |
+
"learning_rate": 1.5431052631578947e-05,
|
| 1237 |
+
"loss": 1.5882,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.004712393320456445,
|
| 1242 |
+
"grad_norm": 10.566994667053223,
|
| 1243 |
+
"learning_rate": 1.4898947368421052e-05,
|
| 1244 |
+
"loss": 1.7865,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.004739790956040494,
|
| 1249 |
+
"grad_norm": 13.512009620666504,
|
| 1250 |
+
"learning_rate": 1.4366842105263159e-05,
|
| 1251 |
+
"loss": 3.2459,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.004767188591624543,
|
| 1256 |
+
"grad_norm": 9.658906936645508,
|
| 1257 |
+
"learning_rate": 1.3834736842105265e-05,
|
| 1258 |
+
"loss": 1.6884,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.004794586227208592,
|
| 1263 |
+
"grad_norm": 9.381290435791016,
|
| 1264 |
+
"learning_rate": 1.3302631578947369e-05,
|
| 1265 |
+
"loss": 1.6764,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.004821983862792641,
|
| 1270 |
+
"grad_norm": 11.110421180725098,
|
| 1271 |
+
"learning_rate": 1.2770526315789475e-05,
|
| 1272 |
+
"loss": 2.4533,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.0048493814983766904,
|
| 1277 |
+
"grad_norm": 9.552355766296387,
|
| 1278 |
+
"learning_rate": 1.223842105263158e-05,
|
| 1279 |
+
"loss": 1.587,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.0048767791339607396,
|
| 1284 |
+
"grad_norm": 10.369064331054688,
|
| 1285 |
+
"learning_rate": 1.1706315789473685e-05,
|
| 1286 |
+
"loss": 1.5635,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.004904176769544789,
|
| 1291 |
+
"grad_norm": 10.4714994430542,
|
| 1292 |
+
"learning_rate": 1.117421052631579e-05,
|
| 1293 |
+
"loss": 1.3165,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.004931574405128838,
|
| 1298 |
+
"grad_norm": 10.99134635925293,
|
| 1299 |
+
"learning_rate": 1.0642105263157895e-05,
|
| 1300 |
+
"loss": 1.9887,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.004958972040712886,
|
| 1305 |
+
"grad_norm": 11.243077278137207,
|
| 1306 |
+
"learning_rate": 1.0110000000000001e-05,
|
| 1307 |
+
"loss": 2.0445,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.004986369676296935,
|
| 1312 |
+
"grad_norm": 9.404143333435059,
|
| 1313 |
+
"learning_rate": 9.577894736842106e-06,
|
| 1314 |
+
"loss": 1.9587,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.005013767311880984,
|
| 1319 |
+
"grad_norm": 8.410197257995605,
|
| 1320 |
+
"learning_rate": 9.045789473684211e-06,
|
| 1321 |
+
"loss": 1.8646,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.005041164947465033,
|
| 1326 |
+
"grad_norm": 7.286149501800537,
|
| 1327 |
+
"learning_rate": 8.513684210526316e-06,
|
| 1328 |
+
"loss": 1.2129,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.0050685625830490825,
|
| 1333 |
+
"grad_norm": 10.829649925231934,
|
| 1334 |
+
"learning_rate": 7.981578947368421e-06,
|
| 1335 |
+
"loss": 2.1754,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.005095960218633132,
|
| 1340 |
+
"grad_norm": 9.724632263183594,
|
| 1341 |
+
"learning_rate": 7.449473684210526e-06,
|
| 1342 |
+
"loss": 1.3908,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.005123357854217181,
|
| 1347 |
+
"grad_norm": 9.229701042175293,
|
| 1348 |
+
"learning_rate": 6.917368421052633e-06,
|
| 1349 |
+
"loss": 1.6759,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.00515075548980123,
|
| 1354 |
+
"grad_norm": 9.659087181091309,
|
| 1355 |
+
"learning_rate": 6.385263157894738e-06,
|
| 1356 |
+
"loss": 1.6113,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.005178153125385279,
|
| 1361 |
+
"grad_norm": 10.842117309570312,
|
| 1362 |
+
"learning_rate": 5.8531578947368425e-06,
|
| 1363 |
+
"loss": 2.3648,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.005205550760969328,
|
| 1368 |
+
"grad_norm": 10.12624740600586,
|
| 1369 |
+
"learning_rate": 5.321052631578947e-06,
|
| 1370 |
+
"loss": 1.6541,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.005232948396553377,
|
| 1375 |
+
"grad_norm": 9.375452041625977,
|
| 1376 |
+
"learning_rate": 4.788947368421053e-06,
|
| 1377 |
+
"loss": 1.9107,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.005260346032137426,
|
| 1382 |
+
"grad_norm": 10.81548023223877,
|
| 1383 |
+
"learning_rate": 4.256842105263158e-06,
|
| 1384 |
+
"loss": 1.9993,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.0052877436677214755,
|
| 1389 |
+
"grad_norm": 8.572677612304688,
|
| 1390 |
+
"learning_rate": 3.724736842105263e-06,
|
| 1391 |
+
"loss": 1.7091,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.005315141303305525,
|
| 1396 |
+
"grad_norm": 11.520868301391602,
|
| 1397 |
+
"learning_rate": 3.192631578947369e-06,
|
| 1398 |
+
"loss": 2.1969,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.005342538938889574,
|
| 1403 |
+
"grad_norm": 10.084508895874023,
|
| 1404 |
+
"learning_rate": 2.6605263157894737e-06,
|
| 1405 |
+
"loss": 1.4943,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.005369936574473623,
|
| 1410 |
+
"grad_norm": 10.452617645263672,
|
| 1411 |
+
"learning_rate": 2.128421052631579e-06,
|
| 1412 |
+
"loss": 1.5151,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.005397334210057672,
|
| 1417 |
+
"grad_norm": 8.461989402770996,
|
| 1418 |
+
"learning_rate": 1.5963157894736844e-06,
|
| 1419 |
+
"loss": 1.3936,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.005424731845641721,
|
| 1424 |
+
"grad_norm": 8.975988388061523,
|
| 1425 |
+
"learning_rate": 1.0642105263157895e-06,
|
| 1426 |
+
"loss": 1.3449,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.00545212948122577,
|
| 1431 |
+
"grad_norm": 9.221831321716309,
|
| 1432 |
+
"learning_rate": 5.321052631578948e-07,
|
| 1433 |
+
"loss": 1.0431,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.005479527116809819,
|
| 1438 |
+
"grad_norm": 9.018491744995117,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.1321,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.005479527116809819,
|
| 1445 |
+
"eval_loss": 1.9446079730987549,
|
| 1446 |
+
"eval_runtime": 906.8244,
|
| 1447 |
+
"eval_samples_per_second": 16.948,
|
| 1448 |
+
"eval_steps_per_second": 4.238,
|
| 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": 2.303878615793664e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|