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 639691872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c93984d28c4a30b2a4ea5490d7bb7dd5b2ea6edb1fd13b1559a332c60f99a7dc
|
| 3 |
size 639691872
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 325339796
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06dcdaaee1ef9a675b005fa577ab41dedf3aba179f1b06f144edd21328b76b91
|
| 3 |
size 325339796
|
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:e1bc1eda3a83805b6948a665f2d0d43d38f9319042ad9a85e1c971894802b677
|
| 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 sha256:4f96196bd3544de2c28f6af356470f327df948539b0e3259c46b8a6786b633fd
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 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": 9.567,
|
| 1090 |
"eval_steps_per_second": 2.392,
|
| 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": 2.285676956176758,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.012832852101379532,
|
| 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": 9.567,
|
| 1090 |
"eval_steps_per_second": 2.392,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.009688803336541546,
|
| 1095 |
+
"grad_norm": 0.5816793441772461,
|
| 1096 |
+
"learning_rate": 2.599578947368421e-05,
|
| 1097 |
+
"loss": 2.272,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.009752967597048443,
|
| 1102 |
+
"grad_norm": 0.6882290244102478,
|
| 1103 |
+
"learning_rate": 2.5465263157894738e-05,
|
| 1104 |
+
"loss": 2.5153,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.009817131857555342,
|
| 1109 |
+
"grad_norm": 0.6470658779144287,
|
| 1110 |
+
"learning_rate": 2.493473684210526e-05,
|
| 1111 |
+
"loss": 2.5716,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.00988129611806224,
|
| 1116 |
+
"grad_norm": 0.6339399218559265,
|
| 1117 |
+
"learning_rate": 2.440421052631579e-05,
|
| 1118 |
+
"loss": 2.4833,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.009945460378569138,
|
| 1123 |
+
"grad_norm": 0.6225025057792664,
|
| 1124 |
+
"learning_rate": 2.3873684210526313e-05,
|
| 1125 |
+
"loss": 2.4854,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.010009624639076035,
|
| 1130 |
+
"grad_norm": 0.5143991112709045,
|
| 1131 |
+
"learning_rate": 2.3343157894736843e-05,
|
| 1132 |
+
"loss": 2.1436,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.010073788899582933,
|
| 1137 |
+
"grad_norm": 0.49274468421936035,
|
| 1138 |
+
"learning_rate": 2.281263157894737e-05,
|
| 1139 |
+
"loss": 2.2916,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.01013795316008983,
|
| 1144 |
+
"grad_norm": 0.5323902368545532,
|
| 1145 |
+
"learning_rate": 2.2282105263157892e-05,
|
| 1146 |
+
"loss": 2.3657,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.010202117420596728,
|
| 1151 |
+
"grad_norm": 0.5345289707183838,
|
| 1152 |
+
"learning_rate": 2.175157894736842e-05,
|
| 1153 |
+
"loss": 2.4812,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.010266281681103625,
|
| 1158 |
+
"grad_norm": 0.5379322171211243,
|
| 1159 |
+
"learning_rate": 2.1221052631578944e-05,
|
| 1160 |
+
"loss": 2.2686,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.010330445941610523,
|
| 1165 |
+
"grad_norm": 0.604354202747345,
|
| 1166 |
+
"learning_rate": 2.0690526315789474e-05,
|
| 1167 |
+
"loss": 2.2495,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.01039461020211742,
|
| 1172 |
+
"grad_norm": 0.6500736474990845,
|
| 1173 |
+
"learning_rate": 2.016e-05,
|
| 1174 |
+
"loss": 2.4631,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.010458774462624318,
|
| 1179 |
+
"grad_norm": 0.49164876341819763,
|
| 1180 |
+
"learning_rate": 1.9629473684210526e-05,
|
| 1181 |
+
"loss": 2.2647,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.010522938723131215,
|
| 1186 |
+
"grad_norm": 0.594844400882721,
|
| 1187 |
+
"learning_rate": 1.9098947368421053e-05,
|
| 1188 |
+
"loss": 2.2196,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.010587102983638113,
|
| 1193 |
+
"grad_norm": 0.6481039524078369,
|
| 1194 |
+
"learning_rate": 1.856842105263158e-05,
|
| 1195 |
+
"loss": 2.3019,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.01065126724414501,
|
| 1200 |
+
"grad_norm": 0.5919328927993774,
|
| 1201 |
+
"learning_rate": 1.8037894736842105e-05,
|
| 1202 |
+
"loss": 2.311,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.010715431504651908,
|
| 1207 |
+
"grad_norm": 0.7396532893180847,
|
| 1208 |
+
"learning_rate": 1.750736842105263e-05,
|
| 1209 |
+
"loss": 2.3443,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.010779595765158807,
|
| 1214 |
+
"grad_norm": 0.685646116733551,
|
| 1215 |
+
"learning_rate": 1.6976842105263157e-05,
|
| 1216 |
+
"loss": 2.2547,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.010843760025665705,
|
| 1221 |
+
"grad_norm": 0.6162258386611938,
|
| 1222 |
+
"learning_rate": 1.6446315789473684e-05,
|
| 1223 |
+
"loss": 2.4626,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.010907924286172602,
|
| 1228 |
+
"grad_norm": 0.6352111101150513,
|
| 1229 |
+
"learning_rate": 1.591578947368421e-05,
|
| 1230 |
+
"loss": 2.1036,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.0109720885466795,
|
| 1235 |
+
"grad_norm": 0.7053295969963074,
|
| 1236 |
+
"learning_rate": 1.5385263157894736e-05,
|
| 1237 |
+
"loss": 2.3642,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.011036252807186397,
|
| 1242 |
+
"grad_norm": 0.7251001000404358,
|
| 1243 |
+
"learning_rate": 1.485473684210526e-05,
|
| 1244 |
+
"loss": 2.1675,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.011100417067693295,
|
| 1249 |
+
"grad_norm": 0.7106326818466187,
|
| 1250 |
+
"learning_rate": 1.4324210526315789e-05,
|
| 1251 |
+
"loss": 2.3521,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.011164581328200193,
|
| 1256 |
+
"grad_norm": 0.7603542804718018,
|
| 1257 |
+
"learning_rate": 1.3793684210526316e-05,
|
| 1258 |
+
"loss": 2.3575,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.01122874558870709,
|
| 1263 |
+
"grad_norm": 0.8023301362991333,
|
| 1264 |
+
"learning_rate": 1.3263157894736841e-05,
|
| 1265 |
+
"loss": 2.5608,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.011292909849213988,
|
| 1270 |
+
"grad_norm": 0.7718851566314697,
|
| 1271 |
+
"learning_rate": 1.2732631578947369e-05,
|
| 1272 |
+
"loss": 2.3804,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.011357074109720885,
|
| 1277 |
+
"grad_norm": 0.7355964779853821,
|
| 1278 |
+
"learning_rate": 1.2202105263157895e-05,
|
| 1279 |
+
"loss": 2.405,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.011421238370227783,
|
| 1284 |
+
"grad_norm": 0.7612870335578918,
|
| 1285 |
+
"learning_rate": 1.1671578947368421e-05,
|
| 1286 |
+
"loss": 2.4048,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.01148540263073468,
|
| 1291 |
+
"grad_norm": 0.8487880229949951,
|
| 1292 |
+
"learning_rate": 1.1141052631578946e-05,
|
| 1293 |
+
"loss": 2.4957,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.011549566891241578,
|
| 1298 |
+
"grad_norm": 0.8127219080924988,
|
| 1299 |
+
"learning_rate": 1.0610526315789472e-05,
|
| 1300 |
+
"loss": 2.0812,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.011613731151748475,
|
| 1305 |
+
"grad_norm": 0.8771964907646179,
|
| 1306 |
+
"learning_rate": 1.008e-05,
|
| 1307 |
+
"loss": 2.2291,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.011677895412255375,
|
| 1312 |
+
"grad_norm": 0.8430835604667664,
|
| 1313 |
+
"learning_rate": 9.549473684210526e-06,
|
| 1314 |
+
"loss": 2.311,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.011742059672762272,
|
| 1319 |
+
"grad_norm": 0.8586536645889282,
|
| 1320 |
+
"learning_rate": 9.018947368421052e-06,
|
| 1321 |
+
"loss": 2.2969,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.01180622393326917,
|
| 1326 |
+
"grad_norm": 0.8553078770637512,
|
| 1327 |
+
"learning_rate": 8.488421052631579e-06,
|
| 1328 |
+
"loss": 2.1949,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.011870388193776067,
|
| 1333 |
+
"grad_norm": 0.9597827792167664,
|
| 1334 |
+
"learning_rate": 7.957894736842105e-06,
|
| 1335 |
+
"loss": 2.5663,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.011934552454282965,
|
| 1340 |
+
"grad_norm": 0.882953941822052,
|
| 1341 |
+
"learning_rate": 7.42736842105263e-06,
|
| 1342 |
+
"loss": 2.3545,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.011998716714789862,
|
| 1347 |
+
"grad_norm": 0.9397551417350769,
|
| 1348 |
+
"learning_rate": 6.896842105263158e-06,
|
| 1349 |
+
"loss": 2.2551,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.01206288097529676,
|
| 1354 |
+
"grad_norm": 0.8707554340362549,
|
| 1355 |
+
"learning_rate": 6.3663157894736845e-06,
|
| 1356 |
+
"loss": 2.3134,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.012127045235803657,
|
| 1361 |
+
"grad_norm": 0.8545828461647034,
|
| 1362 |
+
"learning_rate": 5.835789473684211e-06,
|
| 1363 |
+
"loss": 2.1863,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.012191209496310555,
|
| 1368 |
+
"grad_norm": 0.9791707396507263,
|
| 1369 |
+
"learning_rate": 5.305263157894736e-06,
|
| 1370 |
+
"loss": 2.1821,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.012255373756817452,
|
| 1375 |
+
"grad_norm": 1.0541386604309082,
|
| 1376 |
+
"learning_rate": 4.774736842105263e-06,
|
| 1377 |
+
"loss": 2.4222,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.01231953801732435,
|
| 1382 |
+
"grad_norm": 0.9878808259963989,
|
| 1383 |
+
"learning_rate": 4.244210526315789e-06,
|
| 1384 |
+
"loss": 2.1891,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.012383702277831247,
|
| 1389 |
+
"grad_norm": 0.9502939581871033,
|
| 1390 |
+
"learning_rate": 3.713684210526315e-06,
|
| 1391 |
+
"loss": 2.1575,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.012447866538338145,
|
| 1396 |
+
"grad_norm": 1.0325045585632324,
|
| 1397 |
+
"learning_rate": 3.1831578947368422e-06,
|
| 1398 |
+
"loss": 2.3336,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.012512030798845043,
|
| 1403 |
+
"grad_norm": 1.0161420106887817,
|
| 1404 |
+
"learning_rate": 2.652631578947368e-06,
|
| 1405 |
+
"loss": 2.3017,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.01257619505935194,
|
| 1410 |
+
"grad_norm": 1.029266357421875,
|
| 1411 |
+
"learning_rate": 2.1221052631578947e-06,
|
| 1412 |
+
"loss": 2.0349,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.01264035931985884,
|
| 1417 |
+
"grad_norm": 1.1255306005477905,
|
| 1418 |
+
"learning_rate": 1.5915789473684211e-06,
|
| 1419 |
+
"loss": 1.9766,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.012704523580365737,
|
| 1424 |
+
"grad_norm": 1.2201471328735352,
|
| 1425 |
+
"learning_rate": 1.0610526315789473e-06,
|
| 1426 |
+
"loss": 2.3093,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.012768687840872634,
|
| 1431 |
+
"grad_norm": 1.1325277090072632,
|
| 1432 |
+
"learning_rate": 5.305263157894737e-07,
|
| 1433 |
+
"loss": 2.373,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.012832852101379532,
|
| 1438 |
+
"grad_norm": 1.2911548614501953,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.9981,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.012832852101379532,
|
| 1445 |
+
"eval_loss": 2.285676956176758,
|
| 1446 |
+
"eval_runtime": 686.344,
|
| 1447 |
+
"eval_samples_per_second": 9.562,
|
| 1448 |
+
"eval_steps_per_second": 2.391,
|
| 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": 6.827631788320358e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|