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 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:708c798d1ac1eb1587970713ca88b8f251db861dbb29e101a10b4a6a97eb4e14
|
| 3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 341314196
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80695967c7294a869e72f8feea1e80b63efda1d546374ee9b82103037a892bbe
|
| 3 |
size 341314196
|
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 sha256:00d2508e3aa2a7256203a06140520161452c7874056d11c270d8a0f8a70c287f
|
| 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 sha256:3e90d1a9917ccbc9819e77d754e81c093aaa1bcc13b46bc6c7bb4bcae17159bb
|
| 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": 7.778,
|
| 1090 |
"eval_steps_per_second": 1.945,
|
| 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": 2.710070848464966,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.06210215804999224,
|
| 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": 7.778,
|
| 1090 |
"eval_steps_per_second": 1.945,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.04688712932774414,
|
| 1095 |
+
"grad_norm": 8.627881050109863,
|
| 1096 |
+
"learning_rate": 2.586684210526316e-05,
|
| 1097 |
+
"loss": 5.0342,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.0471976401179941,
|
| 1102 |
+
"grad_norm": 3.0994157791137695,
|
| 1103 |
+
"learning_rate": 2.5338947368421054e-05,
|
| 1104 |
+
"loss": 5.6128,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.04750815090824406,
|
| 1109 |
+
"grad_norm": 7.781631946563721,
|
| 1110 |
+
"learning_rate": 2.4811052631578945e-05,
|
| 1111 |
+
"loss": 5.6382,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.047818661698494025,
|
| 1116 |
+
"grad_norm": 8.706255912780762,
|
| 1117 |
+
"learning_rate": 2.428315789473684e-05,
|
| 1118 |
+
"loss": 5.369,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.04812917248874398,
|
| 1123 |
+
"grad_norm": 10.600417137145996,
|
| 1124 |
+
"learning_rate": 2.3755263157894736e-05,
|
| 1125 |
+
"loss": 5.1998,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.04843968327899394,
|
| 1130 |
+
"grad_norm": 3.304457664489746,
|
| 1131 |
+
"learning_rate": 2.322736842105263e-05,
|
| 1132 |
+
"loss": 5.8636,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.048750194069243906,
|
| 1137 |
+
"grad_norm": 3.3973822593688965,
|
| 1138 |
+
"learning_rate": 2.2699473684210526e-05,
|
| 1139 |
+
"loss": 5.9097,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.04906070485949387,
|
| 1144 |
+
"grad_norm": 6.2585039138793945,
|
| 1145 |
+
"learning_rate": 2.217157894736842e-05,
|
| 1146 |
+
"loss": 6.0155,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.04937121564974383,
|
| 1151 |
+
"grad_norm": 4.313554286956787,
|
| 1152 |
+
"learning_rate": 2.1643684210526316e-05,
|
| 1153 |
+
"loss": 5.977,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.04968172643999379,
|
| 1158 |
+
"grad_norm": 6.310354232788086,
|
| 1159 |
+
"learning_rate": 2.1115789473684208e-05,
|
| 1160 |
+
"loss": 5.8565,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.04999223723024375,
|
| 1165 |
+
"grad_norm": 18.50254249572754,
|
| 1166 |
+
"learning_rate": 2.0587894736842106e-05,
|
| 1167 |
+
"loss": 5.9798,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.05030274802049371,
|
| 1172 |
+
"grad_norm": 11.727089881896973,
|
| 1173 |
+
"learning_rate": 2.006e-05,
|
| 1174 |
+
"loss": 6.3748,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.050613258810743675,
|
| 1179 |
+
"grad_norm": 4.172285556793213,
|
| 1180 |
+
"learning_rate": 1.9532105263157893e-05,
|
| 1181 |
+
"loss": 6.3266,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.05092376960099364,
|
| 1186 |
+
"grad_norm": 3.4230823516845703,
|
| 1187 |
+
"learning_rate": 1.900421052631579e-05,
|
| 1188 |
+
"loss": 5.8562,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.05123428039124359,
|
| 1193 |
+
"grad_norm": 3.503084421157837,
|
| 1194 |
+
"learning_rate": 1.8476315789473683e-05,
|
| 1195 |
+
"loss": 5.3421,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.051544791181493556,
|
| 1200 |
+
"grad_norm": 3.9270567893981934,
|
| 1201 |
+
"learning_rate": 1.7948421052631578e-05,
|
| 1202 |
+
"loss": 5.8137,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.05185530197174352,
|
| 1207 |
+
"grad_norm": 5.9435882568359375,
|
| 1208 |
+
"learning_rate": 1.7420526315789473e-05,
|
| 1209 |
+
"loss": 5.5091,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.05216581276199348,
|
| 1214 |
+
"grad_norm": 3.307124137878418,
|
| 1215 |
+
"learning_rate": 1.6892631578947368e-05,
|
| 1216 |
+
"loss": 6.1505,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.052476323552243444,
|
| 1221 |
+
"grad_norm": 3.08250093460083,
|
| 1222 |
+
"learning_rate": 1.6364736842105263e-05,
|
| 1223 |
+
"loss": 5.857,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.0527868343424934,
|
| 1228 |
+
"grad_norm": 3.2450950145721436,
|
| 1229 |
+
"learning_rate": 1.5836842105263158e-05,
|
| 1230 |
+
"loss": 5.7891,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.05309734513274336,
|
| 1235 |
+
"grad_norm": 3.96562123298645,
|
| 1236 |
+
"learning_rate": 1.5308947368421053e-05,
|
| 1237 |
+
"loss": 5.5198,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.053407855922993325,
|
| 1242 |
+
"grad_norm": 3.0473573207855225,
|
| 1243 |
+
"learning_rate": 1.4781052631578945e-05,
|
| 1244 |
+
"loss": 5.7508,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.05371836671324329,
|
| 1249 |
+
"grad_norm": 6.961787223815918,
|
| 1250 |
+
"learning_rate": 1.4253157894736842e-05,
|
| 1251 |
+
"loss": 5.6795,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.05402887750349324,
|
| 1256 |
+
"grad_norm": 3.1459827423095703,
|
| 1257 |
+
"learning_rate": 1.3725263157894737e-05,
|
| 1258 |
+
"loss": 5.4152,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.054339388293743206,
|
| 1263 |
+
"grad_norm": 4.134361267089844,
|
| 1264 |
+
"learning_rate": 1.319736842105263e-05,
|
| 1265 |
+
"loss": 5.8967,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.05464989908399317,
|
| 1270 |
+
"grad_norm": 8.840166091918945,
|
| 1271 |
+
"learning_rate": 1.2669473684210527e-05,
|
| 1272 |
+
"loss": 5.2314,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.05496040987424313,
|
| 1277 |
+
"grad_norm": 3.1707940101623535,
|
| 1278 |
+
"learning_rate": 1.214157894736842e-05,
|
| 1279 |
+
"loss": 5.8824,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.055270920664493094,
|
| 1284 |
+
"grad_norm": 2.967905044555664,
|
| 1285 |
+
"learning_rate": 1.1613684210526315e-05,
|
| 1286 |
+
"loss": 5.9145,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.05558143145474305,
|
| 1291 |
+
"grad_norm": 4.332707405090332,
|
| 1292 |
+
"learning_rate": 1.108578947368421e-05,
|
| 1293 |
+
"loss": 5.7882,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.05589194224499301,
|
| 1298 |
+
"grad_norm": 3.2459423542022705,
|
| 1299 |
+
"learning_rate": 1.0557894736842104e-05,
|
| 1300 |
+
"loss": 5.0901,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.056202453035242975,
|
| 1305 |
+
"grad_norm": 2.94150710105896,
|
| 1306 |
+
"learning_rate": 1.003e-05,
|
| 1307 |
+
"loss": 5.3414,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.05651296382549294,
|
| 1312 |
+
"grad_norm": 5.878596305847168,
|
| 1313 |
+
"learning_rate": 9.502105263157896e-06,
|
| 1314 |
+
"loss": 4.6183,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.0568234746157429,
|
| 1319 |
+
"grad_norm": 4.656161308288574,
|
| 1320 |
+
"learning_rate": 8.974210526315789e-06,
|
| 1321 |
+
"loss": 5.2575,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.057133985405992856,
|
| 1326 |
+
"grad_norm": 3.8339030742645264,
|
| 1327 |
+
"learning_rate": 8.446315789473684e-06,
|
| 1328 |
+
"loss": 5.2496,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.05744449619624282,
|
| 1333 |
+
"grad_norm": 4.35939884185791,
|
| 1334 |
+
"learning_rate": 7.918421052631579e-06,
|
| 1335 |
+
"loss": 5.0508,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.05775500698649278,
|
| 1340 |
+
"grad_norm": 4.872880935668945,
|
| 1341 |
+
"learning_rate": 7.3905263157894725e-06,
|
| 1342 |
+
"loss": 5.2661,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.058065517776742744,
|
| 1347 |
+
"grad_norm": 3.8898978233337402,
|
| 1348 |
+
"learning_rate": 6.862631578947368e-06,
|
| 1349 |
+
"loss": 5.0692,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.058376028566992706,
|
| 1354 |
+
"grad_norm": 9.882028579711914,
|
| 1355 |
+
"learning_rate": 6.3347368421052634e-06,
|
| 1356 |
+
"loss": 5.5958,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.05868653935724266,
|
| 1361 |
+
"grad_norm": 6.079442024230957,
|
| 1362 |
+
"learning_rate": 5.806842105263158e-06,
|
| 1363 |
+
"loss": 5.6492,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.058997050147492625,
|
| 1368 |
+
"grad_norm": 5.305960655212402,
|
| 1369 |
+
"learning_rate": 5.278947368421052e-06,
|
| 1370 |
+
"loss": 5.9404,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.05930756093774259,
|
| 1375 |
+
"grad_norm": 9.125515937805176,
|
| 1376 |
+
"learning_rate": 4.751052631578948e-06,
|
| 1377 |
+
"loss": 5.1715,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.05961807172799255,
|
| 1382 |
+
"grad_norm": 13.075247764587402,
|
| 1383 |
+
"learning_rate": 4.223157894736842e-06,
|
| 1384 |
+
"loss": 5.723,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.059928582518242506,
|
| 1389 |
+
"grad_norm": 11.328529357910156,
|
| 1390 |
+
"learning_rate": 3.6952631578947362e-06,
|
| 1391 |
+
"loss": 5.354,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.06023909330849247,
|
| 1396 |
+
"grad_norm": 7.932187080383301,
|
| 1397 |
+
"learning_rate": 3.1673684210526317e-06,
|
| 1398 |
+
"loss": 4.9868,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.06054960409874243,
|
| 1403 |
+
"grad_norm": 4.846871852874756,
|
| 1404 |
+
"learning_rate": 2.639473684210526e-06,
|
| 1405 |
+
"loss": 5.9433,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.06086011488899239,
|
| 1410 |
+
"grad_norm": 7.914638519287109,
|
| 1411 |
+
"learning_rate": 2.111578947368421e-06,
|
| 1412 |
+
"loss": 5.3406,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.061170625679242356,
|
| 1417 |
+
"grad_norm": 11.115379333496094,
|
| 1418 |
+
"learning_rate": 1.5836842105263159e-06,
|
| 1419 |
+
"loss": 4.7257,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.06148113646949231,
|
| 1424 |
+
"grad_norm": 12.03275203704834,
|
| 1425 |
+
"learning_rate": 1.0557894736842105e-06,
|
| 1426 |
+
"loss": 3.4278,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.061791647259742274,
|
| 1431 |
+
"grad_norm": 8.894533157348633,
|
| 1432 |
+
"learning_rate": 5.278947368421053e-07,
|
| 1433 |
+
"loss": 3.2262,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.06210215804999224,
|
| 1438 |
+
"grad_norm": 5.871228218078613,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 4.6102,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.06210215804999224,
|
| 1445 |
+
"eval_loss": 2.710070848464966,
|
| 1446 |
+
"eval_runtime": 174.2701,
|
| 1447 |
+
"eval_samples_per_second": 7.781,
|
| 1448 |
+
"eval_steps_per_second": 1.945,
|
| 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": 8.78275028016169e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|