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 295488936
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffaf883fc385079c57bf021b7dc58799f0dec4828a0ebdd1bbc84e5ebb83981f
|
| 3 |
size 295488936
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 150486964
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e84cd6cb7e5b85ed3ec25043395ff0d973d7a06f33d7df9e118c17703e300e82
|
| 3 |
size 150486964
|
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:a58486af876877381eb5dbf3618452ae42ba583e80b1b38ac8ce63df105745f4
|
| 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 sha256:270d5b76e0540a768d0013e19b752b236361c518c523b09d15ce4542642a8f4c
|
| 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": 23.243,
|
| 1090 |
"eval_steps_per_second": 5.811,
|
| 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": 1.
|
| 1121 |
"train_batch_size": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.3765602111816406,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.0033675135963361453,
|
| 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": 23.243,
|
| 1090 |
"eval_steps_per_second": 5.811,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.0025424727652337896,
|
| 1095 |
+
"grad_norm": 2.052712917327881,
|
| 1096 |
+
"learning_rate": 2.5841052631578947e-05,
|
| 1097 |
+
"loss": 1.1378,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.0025593103332154704,
|
| 1102 |
+
"grad_norm": 2.1128897666931152,
|
| 1103 |
+
"learning_rate": 2.5313684210526316e-05,
|
| 1104 |
+
"loss": 1.3605,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.002576147901197151,
|
| 1109 |
+
"grad_norm": 2.1170766353607178,
|
| 1110 |
+
"learning_rate": 2.4786315789473682e-05,
|
| 1111 |
+
"loss": 1.4332,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.002592985469178832,
|
| 1116 |
+
"grad_norm": 2.010960340499878,
|
| 1117 |
+
"learning_rate": 2.425894736842105e-05,
|
| 1118 |
+
"loss": 1.1023,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.0026098230371605123,
|
| 1123 |
+
"grad_norm": 2.1023123264312744,
|
| 1124 |
+
"learning_rate": 2.373157894736842e-05,
|
| 1125 |
+
"loss": 1.072,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.002626660605142193,
|
| 1130 |
+
"grad_norm": 2.092069149017334,
|
| 1131 |
+
"learning_rate": 2.3204210526315788e-05,
|
| 1132 |
+
"loss": 1.1955,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.002643498173123874,
|
| 1137 |
+
"grad_norm": 1.9164916276931763,
|
| 1138 |
+
"learning_rate": 2.2676842105263157e-05,
|
| 1139 |
+
"loss": 1.0552,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.0026603357411055547,
|
| 1144 |
+
"grad_norm": 2.0108814239501953,
|
| 1145 |
+
"learning_rate": 2.2149473684210526e-05,
|
| 1146 |
+
"loss": 1.1003,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.0026771733090872355,
|
| 1151 |
+
"grad_norm": 2.4528539180755615,
|
| 1152 |
+
"learning_rate": 2.1622105263157895e-05,
|
| 1153 |
+
"loss": 1.2307,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.0026940108770689163,
|
| 1158 |
+
"grad_norm": 2.039097547531128,
|
| 1159 |
+
"learning_rate": 2.109473684210526e-05,
|
| 1160 |
+
"loss": 1.4402,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.0027108484450505967,
|
| 1165 |
+
"grad_norm": 2.0241639614105225,
|
| 1166 |
+
"learning_rate": 2.0567368421052632e-05,
|
| 1167 |
+
"loss": 1.0238,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.0027276860130322775,
|
| 1172 |
+
"grad_norm": 2.2333381175994873,
|
| 1173 |
+
"learning_rate": 2.004e-05,
|
| 1174 |
+
"loss": 1.4316,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.0027445235810139583,
|
| 1179 |
+
"grad_norm": 3.605776071548462,
|
| 1180 |
+
"learning_rate": 1.9512631578947367e-05,
|
| 1181 |
+
"loss": 1.4198,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.002761361148995639,
|
| 1186 |
+
"grad_norm": 2.655592203140259,
|
| 1187 |
+
"learning_rate": 1.8985263157894736e-05,
|
| 1188 |
+
"loss": 1.4189,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.00277819871697732,
|
| 1193 |
+
"grad_norm": 2.0426361560821533,
|
| 1194 |
+
"learning_rate": 1.8457894736842104e-05,
|
| 1195 |
+
"loss": 1.3986,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.0027950362849590007,
|
| 1200 |
+
"grad_norm": 2.3004188537597656,
|
| 1201 |
+
"learning_rate": 1.7930526315789473e-05,
|
| 1202 |
+
"loss": 1.4445,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.002811873852940681,
|
| 1207 |
+
"grad_norm": 2.9400241374969482,
|
| 1208 |
+
"learning_rate": 1.7403157894736842e-05,
|
| 1209 |
+
"loss": 1.8047,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.002828711420922362,
|
| 1214 |
+
"grad_norm": 2.0418825149536133,
|
| 1215 |
+
"learning_rate": 1.687578947368421e-05,
|
| 1216 |
+
"loss": 0.9261,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.0028455489889040427,
|
| 1221 |
+
"grad_norm": 2.0925211906433105,
|
| 1222 |
+
"learning_rate": 1.634842105263158e-05,
|
| 1223 |
+
"loss": 1.239,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.0028623865568857235,
|
| 1228 |
+
"grad_norm": 1.980811357498169,
|
| 1229 |
+
"learning_rate": 1.5821052631578945e-05,
|
| 1230 |
+
"loss": 1.1719,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.0028792241248674043,
|
| 1235 |
+
"grad_norm": 1.8791331052780151,
|
| 1236 |
+
"learning_rate": 1.5293684210526314e-05,
|
| 1237 |
+
"loss": 1.0443,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.002896061692849085,
|
| 1242 |
+
"grad_norm": 2.597561836242676,
|
| 1243 |
+
"learning_rate": 1.4766315789473683e-05,
|
| 1244 |
+
"loss": 1.6261,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.0029128992608307655,
|
| 1249 |
+
"grad_norm": 2.3997042179107666,
|
| 1250 |
+
"learning_rate": 1.4238947368421052e-05,
|
| 1251 |
+
"loss": 1.5704,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.0029297368288124463,
|
| 1256 |
+
"grad_norm": 2.247018575668335,
|
| 1257 |
+
"learning_rate": 1.3711578947368422e-05,
|
| 1258 |
+
"loss": 1.1917,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.002946574396794127,
|
| 1263 |
+
"grad_norm": 2.259775400161743,
|
| 1264 |
+
"learning_rate": 1.3184210526315788e-05,
|
| 1265 |
+
"loss": 1.2214,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.002963411964775808,
|
| 1270 |
+
"grad_norm": 2.2527711391448975,
|
| 1271 |
+
"learning_rate": 1.2656842105263158e-05,
|
| 1272 |
+
"loss": 1.5402,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.0029802495327574887,
|
| 1277 |
+
"grad_norm": 2.1394917964935303,
|
| 1278 |
+
"learning_rate": 1.2129473684210525e-05,
|
| 1279 |
+
"loss": 1.2132,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.002997087100739169,
|
| 1284 |
+
"grad_norm": 2.873786687850952,
|
| 1285 |
+
"learning_rate": 1.1602105263157894e-05,
|
| 1286 |
+
"loss": 1.5172,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.00301392466872085,
|
| 1291 |
+
"grad_norm": 2.6829400062561035,
|
| 1292 |
+
"learning_rate": 1.1074736842105263e-05,
|
| 1293 |
+
"loss": 1.3914,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.0030307622367025306,
|
| 1298 |
+
"grad_norm": 2.2460923194885254,
|
| 1299 |
+
"learning_rate": 1.054736842105263e-05,
|
| 1300 |
+
"loss": 1.5042,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.0030475998046842114,
|
| 1305 |
+
"grad_norm": 2.6708035469055176,
|
| 1306 |
+
"learning_rate": 1.002e-05,
|
| 1307 |
+
"loss": 1.4609,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.0030644373726658922,
|
| 1312 |
+
"grad_norm": 2.341792345046997,
|
| 1313 |
+
"learning_rate": 9.492631578947368e-06,
|
| 1314 |
+
"loss": 1.4356,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.003081274940647573,
|
| 1319 |
+
"grad_norm": 2.573974132537842,
|
| 1320 |
+
"learning_rate": 8.965263157894737e-06,
|
| 1321 |
+
"loss": 1.3329,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.0030981125086292534,
|
| 1326 |
+
"grad_norm": 2.623440742492676,
|
| 1327 |
+
"learning_rate": 8.437894736842105e-06,
|
| 1328 |
+
"loss": 1.6932,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.003114950076610934,
|
| 1333 |
+
"grad_norm": 2.461622714996338,
|
| 1334 |
+
"learning_rate": 7.910526315789473e-06,
|
| 1335 |
+
"loss": 1.7272,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.003131787644592615,
|
| 1340 |
+
"grad_norm": 2.7509238719940186,
|
| 1341 |
+
"learning_rate": 7.383157894736841e-06,
|
| 1342 |
+
"loss": 1.6634,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.003148625212574296,
|
| 1347 |
+
"grad_norm": 2.2685606479644775,
|
| 1348 |
+
"learning_rate": 6.855789473684211e-06,
|
| 1349 |
+
"loss": 1.4343,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.0031654627805559766,
|
| 1354 |
+
"grad_norm": 2.3239376544952393,
|
| 1355 |
+
"learning_rate": 6.328421052631579e-06,
|
| 1356 |
+
"loss": 1.1757,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.0031823003485376574,
|
| 1361 |
+
"grad_norm": 2.999512195587158,
|
| 1362 |
+
"learning_rate": 5.801052631578947e-06,
|
| 1363 |
+
"loss": 1.5189,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.0031991379165193378,
|
| 1368 |
+
"grad_norm": 3.1640262603759766,
|
| 1369 |
+
"learning_rate": 5.273684210526315e-06,
|
| 1370 |
+
"loss": 1.6939,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.0032159754845010186,
|
| 1375 |
+
"grad_norm": 2.9750168323516846,
|
| 1376 |
+
"learning_rate": 4.746315789473684e-06,
|
| 1377 |
+
"loss": 1.5518,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.0032328130524826994,
|
| 1382 |
+
"grad_norm": 3.184924840927124,
|
| 1383 |
+
"learning_rate": 4.218947368421053e-06,
|
| 1384 |
+
"loss": 1.7013,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.00324965062046438,
|
| 1389 |
+
"grad_norm": 2.749739170074463,
|
| 1390 |
+
"learning_rate": 3.6915789473684207e-06,
|
| 1391 |
+
"loss": 1.4346,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.003266488188446061,
|
| 1396 |
+
"grad_norm": 2.0912322998046875,
|
| 1397 |
+
"learning_rate": 3.1642105263157895e-06,
|
| 1398 |
+
"loss": 1.3179,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.0032833257564277418,
|
| 1403 |
+
"grad_norm": 2.998617172241211,
|
| 1404 |
+
"learning_rate": 2.6368421052631575e-06,
|
| 1405 |
+
"loss": 1.5083,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.003300163324409422,
|
| 1410 |
+
"grad_norm": 3.401614189147949,
|
| 1411 |
+
"learning_rate": 2.1094736842105264e-06,
|
| 1412 |
+
"loss": 1.9612,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.003317000892391103,
|
| 1417 |
+
"grad_norm": 3.49855637550354,
|
| 1418 |
+
"learning_rate": 1.5821052631578948e-06,
|
| 1419 |
+
"loss": 1.6094,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.0033338384603727837,
|
| 1424 |
+
"grad_norm": 2.917076349258423,
|
| 1425 |
+
"learning_rate": 1.0547368421052632e-06,
|
| 1426 |
+
"loss": 1.3097,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.0033506760283544645,
|
| 1431 |
+
"grad_norm": 3.7073705196380615,
|
| 1432 |
+
"learning_rate": 5.273684210526316e-07,
|
| 1433 |
+
"loss": 1.7215,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.0033675135963361453,
|
| 1438 |
+
"grad_norm": 4.6814703941345215,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.9333,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.0033675135963361453,
|
| 1445 |
+
"eval_loss": 1.3765602111816406,
|
| 1446 |
+
"eval_runtime": 1074.3994,
|
| 1447 |
+
"eval_samples_per_second": 23.275,
|
| 1448 |
+
"eval_steps_per_second": 5.819,
|
| 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": 1.367527271694336e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|