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 645975704
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3edb8bf1d0ccc6d0a6bbd6c5f80b548f2877681c734e9cbf3728233632a89173
|
| 3 |
size 645975704
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 328468404
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7da7046ae848e05a7db62fc091f53d07130df1c18963dfc0c580c3590db0446a
|
| 3 |
size 328468404
|
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 sha256:0f0e14df6959312e181575df4d63c4a7d90bb8b2df0b1b26d2ca6e478b5db01c
|
| 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 sha256:5c186522be8b385dca026dd73d1e109571521fa75822c734f2765fa171800e01
|
| 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": 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": 9.481,
|
| 1090 |
"eval_steps_per_second": 2.382,
|
| 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": 0.24321098625659943,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.21164021164021163,
|
| 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": 9.481,
|
| 1090 |
"eval_steps_per_second": 2.382,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.15978835978835979,
|
| 1095 |
+
"grad_norm": 1.0392180681228638,
|
| 1096 |
+
"learning_rate": 2.6150526315789476e-05,
|
| 1097 |
+
"loss": 0.0403,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.16084656084656085,
|
| 1102 |
+
"grad_norm": 1.738742709159851,
|
| 1103 |
+
"learning_rate": 2.561684210526316e-05,
|
| 1104 |
+
"loss": 0.1876,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.1619047619047619,
|
| 1109 |
+
"grad_norm": 1.2620779275894165,
|
| 1110 |
+
"learning_rate": 2.508315789473684e-05,
|
| 1111 |
+
"loss": 0.1012,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.16296296296296298,
|
| 1116 |
+
"grad_norm": 2.1409807205200195,
|
| 1117 |
+
"learning_rate": 2.4549473684210527e-05,
|
| 1118 |
+
"loss": 0.2515,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.164021164021164,
|
| 1123 |
+
"grad_norm": 0.6598687767982483,
|
| 1124 |
+
"learning_rate": 2.401578947368421e-05,
|
| 1125 |
+
"loss": 0.0336,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.16507936507936508,
|
| 1130 |
+
"grad_norm": 2.0522665977478027,
|
| 1131 |
+
"learning_rate": 2.3482105263157894e-05,
|
| 1132 |
+
"loss": 0.0748,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.16613756613756614,
|
| 1137 |
+
"grad_norm": 3.9888670444488525,
|
| 1138 |
+
"learning_rate": 2.294842105263158e-05,
|
| 1139 |
+
"loss": 0.3477,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.1671957671957672,
|
| 1144 |
+
"grad_norm": 1.104380488395691,
|
| 1145 |
+
"learning_rate": 2.241473684210526e-05,
|
| 1146 |
+
"loss": 0.1015,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.16825396825396827,
|
| 1151 |
+
"grad_norm": 2.145385503768921,
|
| 1152 |
+
"learning_rate": 2.1881052631578948e-05,
|
| 1153 |
+
"loss": 0.2046,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.1693121693121693,
|
| 1158 |
+
"grad_norm": 2.4562976360321045,
|
| 1159 |
+
"learning_rate": 2.134736842105263e-05,
|
| 1160 |
+
"loss": 0.2442,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.17037037037037037,
|
| 1165 |
+
"grad_norm": 2.2245967388153076,
|
| 1166 |
+
"learning_rate": 2.0813684210526315e-05,
|
| 1167 |
+
"loss": 0.4186,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.17142857142857143,
|
| 1172 |
+
"grad_norm": 2.019033432006836,
|
| 1173 |
+
"learning_rate": 2.0280000000000002e-05,
|
| 1174 |
+
"loss": 0.1792,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.1724867724867725,
|
| 1179 |
+
"grad_norm": 1.430423617362976,
|
| 1180 |
+
"learning_rate": 1.9746315789473683e-05,
|
| 1181 |
+
"loss": 0.0728,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.17354497354497356,
|
| 1186 |
+
"grad_norm": 1.957362413406372,
|
| 1187 |
+
"learning_rate": 1.921263157894737e-05,
|
| 1188 |
+
"loss": 0.1585,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.1746031746031746,
|
| 1193 |
+
"grad_norm": 1.5552687644958496,
|
| 1194 |
+
"learning_rate": 1.867894736842105e-05,
|
| 1195 |
+
"loss": 0.0985,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.17566137566137566,
|
| 1200 |
+
"grad_norm": 0.8113088607788086,
|
| 1201 |
+
"learning_rate": 1.8145263157894737e-05,
|
| 1202 |
+
"loss": 0.0418,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.17671957671957672,
|
| 1207 |
+
"grad_norm": 1.317171335220337,
|
| 1208 |
+
"learning_rate": 1.761157894736842e-05,
|
| 1209 |
+
"loss": 0.096,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.17777777777777778,
|
| 1214 |
+
"grad_norm": 2.197812795639038,
|
| 1215 |
+
"learning_rate": 1.7077894736842104e-05,
|
| 1216 |
+
"loss": 0.1626,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.17883597883597885,
|
| 1221 |
+
"grad_norm": 2.421410322189331,
|
| 1222 |
+
"learning_rate": 1.654421052631579e-05,
|
| 1223 |
+
"loss": 0.2939,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.17989417989417988,
|
| 1228 |
+
"grad_norm": 1.9575234651565552,
|
| 1229 |
+
"learning_rate": 1.601052631578947e-05,
|
| 1230 |
+
"loss": 0.1181,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.18095238095238095,
|
| 1235 |
+
"grad_norm": 2.36352801322937,
|
| 1236 |
+
"learning_rate": 1.5476842105263158e-05,
|
| 1237 |
+
"loss": 0.1494,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.182010582010582,
|
| 1242 |
+
"grad_norm": 2.2821767330169678,
|
| 1243 |
+
"learning_rate": 1.494315789473684e-05,
|
| 1244 |
+
"loss": 0.2514,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.18306878306878308,
|
| 1249 |
+
"grad_norm": 1.5309607982635498,
|
| 1250 |
+
"learning_rate": 1.4409473684210525e-05,
|
| 1251 |
+
"loss": 0.1239,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.18412698412698414,
|
| 1256 |
+
"grad_norm": 1.3841410875320435,
|
| 1257 |
+
"learning_rate": 1.387578947368421e-05,
|
| 1258 |
+
"loss": 0.0923,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.18518518518518517,
|
| 1263 |
+
"grad_norm": 3.6834170818328857,
|
| 1264 |
+
"learning_rate": 1.3342105263157894e-05,
|
| 1265 |
+
"loss": 0.3616,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.18624338624338624,
|
| 1270 |
+
"grad_norm": 2.0545542240142822,
|
| 1271 |
+
"learning_rate": 1.280842105263158e-05,
|
| 1272 |
+
"loss": 0.0803,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.1873015873015873,
|
| 1277 |
+
"grad_norm": 2.6623830795288086,
|
| 1278 |
+
"learning_rate": 1.2274736842105263e-05,
|
| 1279 |
+
"loss": 0.1061,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.18835978835978837,
|
| 1284 |
+
"grad_norm": 2.9348082542419434,
|
| 1285 |
+
"learning_rate": 1.1741052631578947e-05,
|
| 1286 |
+
"loss": 0.3249,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.18941798941798943,
|
| 1291 |
+
"grad_norm": 1.3830448389053345,
|
| 1292 |
+
"learning_rate": 1.120736842105263e-05,
|
| 1293 |
+
"loss": 0.0611,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.19047619047619047,
|
| 1298 |
+
"grad_norm": 3.927304744720459,
|
| 1299 |
+
"learning_rate": 1.0673684210526314e-05,
|
| 1300 |
+
"loss": 0.1971,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.19153439153439153,
|
| 1305 |
+
"grad_norm": 1.9497954845428467,
|
| 1306 |
+
"learning_rate": 1.0140000000000001e-05,
|
| 1307 |
+
"loss": 0.2122,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.1925925925925926,
|
| 1312 |
+
"grad_norm": 2.313905954360962,
|
| 1313 |
+
"learning_rate": 9.606315789473685e-06,
|
| 1314 |
+
"loss": 0.2029,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.19365079365079366,
|
| 1319 |
+
"grad_norm": 3.8197977542877197,
|
| 1320 |
+
"learning_rate": 9.072631578947368e-06,
|
| 1321 |
+
"loss": 0.7685,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.19470899470899472,
|
| 1326 |
+
"grad_norm": 1.723537802696228,
|
| 1327 |
+
"learning_rate": 8.538947368421052e-06,
|
| 1328 |
+
"loss": 0.4412,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.19576719576719576,
|
| 1333 |
+
"grad_norm": 3.3449349403381348,
|
| 1334 |
+
"learning_rate": 8.005263157894736e-06,
|
| 1335 |
+
"loss": 0.2243,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.19682539682539682,
|
| 1340 |
+
"grad_norm": 0.9286437034606934,
|
| 1341 |
+
"learning_rate": 7.47157894736842e-06,
|
| 1342 |
+
"loss": 0.0623,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.19788359788359788,
|
| 1347 |
+
"grad_norm": 3.832223415374756,
|
| 1348 |
+
"learning_rate": 6.937894736842105e-06,
|
| 1349 |
+
"loss": 0.3214,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.19894179894179895,
|
| 1354 |
+
"grad_norm": 2.1527602672576904,
|
| 1355 |
+
"learning_rate": 6.40421052631579e-06,
|
| 1356 |
+
"loss": 0.1369,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.2,
|
| 1361 |
+
"grad_norm": 1.3586947917938232,
|
| 1362 |
+
"learning_rate": 5.8705263157894735e-06,
|
| 1363 |
+
"loss": 0.072,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.20105820105820105,
|
| 1368 |
+
"grad_norm": 1.1720460653305054,
|
| 1369 |
+
"learning_rate": 5.336842105263157e-06,
|
| 1370 |
+
"loss": 0.0694,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.2021164021164021,
|
| 1375 |
+
"grad_norm": 1.863162875175476,
|
| 1376 |
+
"learning_rate": 4.803157894736842e-06,
|
| 1377 |
+
"loss": 0.154,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.20317460317460317,
|
| 1382 |
+
"grad_norm": 3.274844169616699,
|
| 1383 |
+
"learning_rate": 4.269473684210526e-06,
|
| 1384 |
+
"loss": 0.3523,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.20423280423280424,
|
| 1389 |
+
"grad_norm": 2.0571043491363525,
|
| 1390 |
+
"learning_rate": 3.73578947368421e-06,
|
| 1391 |
+
"loss": 0.1565,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.2052910052910053,
|
| 1396 |
+
"grad_norm": 2.8300046920776367,
|
| 1397 |
+
"learning_rate": 3.202105263157895e-06,
|
| 1398 |
+
"loss": 0.3163,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.20634920634920634,
|
| 1403 |
+
"grad_norm": 2.4953830242156982,
|
| 1404 |
+
"learning_rate": 2.6684210526315785e-06,
|
| 1405 |
+
"loss": 0.2559,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.2074074074074074,
|
| 1410 |
+
"grad_norm": 1.1636903285980225,
|
| 1411 |
+
"learning_rate": 2.134736842105263e-06,
|
| 1412 |
+
"loss": 0.0823,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.20846560846560847,
|
| 1417 |
+
"grad_norm": 3.529049873352051,
|
| 1418 |
+
"learning_rate": 1.6010526315789475e-06,
|
| 1419 |
+
"loss": 0.3016,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.20952380952380953,
|
| 1424 |
+
"grad_norm": 3.8077683448791504,
|
| 1425 |
+
"learning_rate": 1.0673684210526315e-06,
|
| 1426 |
+
"loss": 0.3713,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.2105820105820106,
|
| 1431 |
+
"grad_norm": 4.698509216308594,
|
| 1432 |
+
"learning_rate": 5.336842105263158e-07,
|
| 1433 |
+
"loss": 0.421,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.21164021164021163,
|
| 1438 |
+
"grad_norm": 5.6042633056640625,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.3003,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.21164021164021163,
|
| 1445 |
+
"eval_loss": 0.24321098625659943,
|
| 1446 |
+
"eval_runtime": 41.9092,
|
| 1447 |
+
"eval_samples_per_second": 9.497,
|
| 1448 |
+
"eval_steps_per_second": 2.386,
|
| 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": 7.1094434267136e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|