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 389074464
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88394326c6bf61b6ca37609a77a3a8995ad0ea036c280091024e776229d4f51b
|
| 3 |
size 389074464
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 198011252
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b1429234fa94663056b0fa0c050763ad0b86040011535e31b3ea11d624e8a72
|
| 3 |
size 198011252
|
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:a1a13967d83048ef1e171f81ca5ff66f6dd7ae7af3b300a1f19451ef4991f7a5
|
| 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:c09a3e270daa077e38bac4ad605b0e6c9b43938bcf49dc3d62c3671f11248c14
|
| 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": 22.821,
|
| 1090 |
"eval_steps_per_second": 5.705,
|
| 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": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.8127896785736084,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.003842496085457113,
|
| 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": 22.821,
|
| 1090 |
"eval_steps_per_second": 5.705,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.0029010845445201204,
|
| 1095 |
+
"grad_norm": 0.3780750036239624,
|
| 1096 |
+
"learning_rate": 1.397909658966454e-05,
|
| 1097 |
+
"loss": 2.022,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.0029202970249474058,
|
| 1102 |
+
"grad_norm": 0.4781886637210846,
|
| 1103 |
+
"learning_rate": 1.3444344707738015e-05,
|
| 1104 |
+
"loss": 2.0794,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.002939509505374691,
|
| 1109 |
+
"grad_norm": 0.8120487332344055,
|
| 1110 |
+
"learning_rate": 1.2918219826887136e-05,
|
| 1111 |
+
"loss": 1.4991,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.002958721985801977,
|
| 1116 |
+
"grad_norm": 0.6794188618659973,
|
| 1117 |
+
"learning_rate": 1.2400865784400998e-05,
|
| 1118 |
+
"loss": 1.6916,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.0029779344662292625,
|
| 1123 |
+
"grad_norm": 0.8753079771995544,
|
| 1124 |
+
"learning_rate": 1.189242401970908e-05,
|
| 1125 |
+
"loss": 1.6724,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.0029971469466565483,
|
| 1130 |
+
"grad_norm": 0.9768186211585999,
|
| 1131 |
+
"learning_rate": 1.139303353571309e-05,
|
| 1132 |
+
"loss": 2.0687,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.0030163594270838337,
|
| 1137 |
+
"grad_norm": 0.9926120042800903,
|
| 1138 |
+
"learning_rate": 1.0902830860784946e-05,
|
| 1139 |
+
"loss": 1.5077,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.003035571907511119,
|
| 1144 |
+
"grad_norm": 0.7764493823051453,
|
| 1145 |
+
"learning_rate": 1.0421950011441355e-05,
|
| 1146 |
+
"loss": 1.8041,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.003054784387938405,
|
| 1151 |
+
"grad_norm": 1.189863681793213,
|
| 1152 |
+
"learning_rate": 9.950522455704946e-06,
|
| 1153 |
+
"loss": 1.5459,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.0030739968683656904,
|
| 1158 |
+
"grad_norm": 0.9329153895378113,
|
| 1159 |
+
"learning_rate": 9.488677077162294e-06,
|
| 1160 |
+
"loss": 2.1531,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.003093209348792976,
|
| 1165 |
+
"grad_norm": 0.9131903052330017,
|
| 1166 |
+
"learning_rate": 9.03654013972839e-06,
|
| 1167 |
+
"loss": 2.0871,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.0031124218292202617,
|
| 1172 |
+
"grad_norm": 1.1890541315078735,
|
| 1173 |
+
"learning_rate": 8.59423525312737e-06,
|
| 1174 |
+
"loss": 1.2826,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.003131634309647547,
|
| 1179 |
+
"grad_norm": 0.9106007218360901,
|
| 1180 |
+
"learning_rate": 8.161883339098845e-06,
|
| 1181 |
+
"loss": 1.9189,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.0031508467900748325,
|
| 1186 |
+
"grad_norm": 1.041857123374939,
|
| 1187 |
+
"learning_rate": 7.739602598339099e-06,
|
| 1188 |
+
"loss": 1.1295,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.0031700592705021183,
|
| 1193 |
+
"grad_norm": 1.1270183324813843,
|
| 1194 |
+
"learning_rate": 7.327508478186216e-06,
|
| 1195 |
+
"loss": 1.3541,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.0031892717509294038,
|
| 1200 |
+
"grad_norm": 1.1173748970031738,
|
| 1201 |
+
"learning_rate": 6.925713641057902e-06,
|
| 1202 |
+
"loss": 0.7724,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.003208484231356689,
|
| 1207 |
+
"grad_norm": 1.116767406463623,
|
| 1208 |
+
"learning_rate": 6.53432793365074e-06,
|
| 1209 |
+
"loss": 0.8932,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.003227696711783975,
|
| 1214 |
+
"grad_norm": 0.9970417618751526,
|
| 1215 |
+
"learning_rate": 6.153458356909174e-06,
|
| 1216 |
+
"loss": 1.0993,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.0032469091922112604,
|
| 1221 |
+
"grad_norm": 1.0910117626190186,
|
| 1222 |
+
"learning_rate": 5.783209036772518e-06,
|
| 1223 |
+
"loss": 0.9567,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.003266121672638546,
|
| 1228 |
+
"grad_norm": 1.4644685983657837,
|
| 1229 |
+
"learning_rate": 5.423681195707997e-06,
|
| 1230 |
+
"loss": 0.977,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.0032853341530658317,
|
| 1235 |
+
"grad_norm": 1.073829174041748,
|
| 1236 |
+
"learning_rate": 5.074973125037469e-06,
|
| 1237 |
+
"loss": 1.2876,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.003304546633493117,
|
| 1242 |
+
"grad_norm": 1.233479380607605,
|
| 1243 |
+
"learning_rate": 4.737180158065644e-06,
|
| 1244 |
+
"loss": 1.3618,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.0033237591139204025,
|
| 1249 |
+
"grad_norm": 1.34217369556427,
|
| 1250 |
+
"learning_rate": 4.41039464401685e-06,
|
| 1251 |
+
"loss": 1.3816,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.0033429715943476884,
|
| 1256 |
+
"grad_norm": 1.662285566329956,
|
| 1257 |
+
"learning_rate": 4.094705922787687e-06,
|
| 1258 |
+
"loss": 0.9877,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.003362184074774974,
|
| 1263 |
+
"grad_norm": 1.2599389553070068,
|
| 1264 |
+
"learning_rate": 3.7902003005224126e-06,
|
| 1265 |
+
"loss": 1.0554,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.0033813965552022592,
|
| 1270 |
+
"grad_norm": 1.3760629892349243,
|
| 1271 |
+
"learning_rate": 3.4969610260176865e-06,
|
| 1272 |
+
"loss": 1.3303,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.003400609035629545,
|
| 1277 |
+
"grad_norm": 1.4048978090286255,
|
| 1278 |
+
"learning_rate": 3.2150682679631867e-06,
|
| 1279 |
+
"loss": 1.2862,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.0034198215160568305,
|
| 1284 |
+
"grad_norm": 1.169244408607483,
|
| 1285 |
+
"learning_rate": 2.9445990930242668e-06,
|
| 1286 |
+
"loss": 1.0257,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.003439033996484116,
|
| 1291 |
+
"grad_norm": 1.1791973114013672,
|
| 1292 |
+
"learning_rate": 2.6856274447727475e-06,
|
| 1293 |
+
"loss": 1.061,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.0034582464769114018,
|
| 1298 |
+
"grad_norm": 1.7341974973678589,
|
| 1299 |
+
"learning_rate": 2.4382241234714413e-06,
|
| 1300 |
+
"loss": 1.2628,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.003477458957338687,
|
| 1305 |
+
"grad_norm": 1.8596497774124146,
|
| 1306 |
+
"learning_rate": 2.2024567667180914e-06,
|
| 1307 |
+
"loss": 1.8631,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.0034966714377659726,
|
| 1312 |
+
"grad_norm": 1.7305415868759155,
|
| 1313 |
+
"learning_rate": 1.978389830953906e-06,
|
| 1314 |
+
"loss": 1.1139,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.0035158839181932584,
|
| 1319 |
+
"grad_norm": 1.690251350402832,
|
| 1320 |
+
"learning_rate": 1.7660845738418336e-06,
|
| 1321 |
+
"loss": 1.1278,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.003535096398620544,
|
| 1326 |
+
"grad_norm": 1.4446978569030762,
|
| 1327 |
+
"learning_rate": 1.5655990375193147e-06,
|
| 1328 |
+
"loss": 0.899,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.0035543088790478293,
|
| 1333 |
+
"grad_norm": 1.9374878406524658,
|
| 1334 |
+
"learning_rate": 1.3769880327301332e-06,
|
| 1335 |
+
"loss": 0.9448,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.003573521359475115,
|
| 1340 |
+
"grad_norm": 1.8252419233322144,
|
| 1341 |
+
"learning_rate": 1.2003031238397417e-06,
|
| 1342 |
+
"loss": 0.7858,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.0035927338399024005,
|
| 1347 |
+
"grad_norm": 2.349891424179077,
|
| 1348 |
+
"learning_rate": 1.035592614738033e-06,
|
| 1349 |
+
"loss": 1.245,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.0036119463203296864,
|
| 1354 |
+
"grad_norm": 1.9561939239501953,
|
| 1355 |
+
"learning_rate": 8.829015356335791e-07,
|
| 1356 |
+
"loss": 1.5753,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.003631158800756972,
|
| 1361 |
+
"grad_norm": 1.7813923358917236,
|
| 1362 |
+
"learning_rate": 7.422716307427936e-07,
|
| 1363 |
+
"loss": 1.5121,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.003650371281184257,
|
| 1368 |
+
"grad_norm": 2.0774621963500977,
|
| 1369 |
+
"learning_rate": 6.137413468774955e-07,
|
| 1370 |
+
"loss": 1.9692,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.003669583761611543,
|
| 1375 |
+
"grad_norm": 1.7934973239898682,
|
| 1376 |
+
"learning_rate": 4.973458229339179e-07,
|
| 1377 |
+
"loss": 1.7271,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.0036887962420388285,
|
| 1382 |
+
"grad_norm": 2.4085757732391357,
|
| 1383 |
+
"learning_rate": 3.9311688028611627e-07,
|
| 1384 |
+
"loss": 1.9639,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.003708008722466114,
|
| 1389 |
+
"grad_norm": 2.4580140113830566,
|
| 1390 |
+
"learning_rate": 3.010830140862836e-07,
|
| 1391 |
+
"loss": 1.2718,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.0037272212028933997,
|
| 1396 |
+
"grad_norm": 2.0989091396331787,
|
| 1397 |
+
"learning_rate": 2.2126938547448627e-07,
|
| 1398 |
+
"loss": 2.1295,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.003746433683320685,
|
| 1403 |
+
"grad_norm": 2.8977036476135254,
|
| 1404 |
+
"learning_rate": 1.536978146998569e-07,
|
| 1405 |
+
"loss": 2.605,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.0037656461637479706,
|
| 1410 |
+
"grad_norm": 2.9574570655822754,
|
| 1411 |
+
"learning_rate": 9.838677515514594e-08,
|
| 1412 |
+
"loss": 2.2732,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.0037848586441752564,
|
| 1417 |
+
"grad_norm": 3.1725268363952637,
|
| 1418 |
+
"learning_rate": 5.5351388326286834e-08,
|
| 1419 |
+
"loss": 2.3167,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.003804071124602542,
|
| 1424 |
+
"grad_norm": 3.776048421859741,
|
| 1425 |
+
"learning_rate": 2.4603419658327797e-08,
|
| 1426 |
+
"loss": 2.1604,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.0038232836050298273,
|
| 1431 |
+
"grad_norm": 3.629805088043213,
|
| 1432 |
+
"learning_rate": 6.151275338894813e-09,
|
| 1433 |
+
"loss": 2.3745,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.003842496085457113,
|
| 1438 |
+
"grad_norm": 3.931309461593628,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 2.6561,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.003842496085457113,
|
| 1445 |
+
"eval_loss": 1.8127896785736084,
|
| 1446 |
+
"eval_runtime": 3843.9208,
|
| 1447 |
+
"eval_samples_per_second": 22.805,
|
| 1448 |
+
"eval_steps_per_second": 5.701,
|
| 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": 1.1853173533075046e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|