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 sha256:12707e96557505dd699d17f38237182244feb00e9fd65b89534e340f20761209
|
| 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 sha256:38a484858e2a32808f18258819b85b8338e3fca481c350a85638c311c37f8317
|
| 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 sha256:337b59f0599868f1843a93909844f5322464009bc4610df56e24c8b93760811a
|
| 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:a3e88ef6a2716260516e17223973d6a3b0a4c88bf12c72ed47e80e6f2a6782fd
|
| 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": 8.626,
|
| 1090 |
"eval_steps_per_second": 2.159,
|
| 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": 1.453239917755127,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.08469193309337286,
|
| 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": 8.626,
|
| 1090 |
"eval_steps_per_second": 2.159,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.06394240948549651,
|
| 1095 |
+
"grad_norm": 0.7069029808044434,
|
| 1096 |
+
"learning_rate": 2.589263157894737e-05,
|
| 1097 |
+
"loss": 1.456,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.06436586915096337,
|
| 1102 |
+
"grad_norm": 0.6979643106460571,
|
| 1103 |
+
"learning_rate": 2.536421052631579e-05,
|
| 1104 |
+
"loss": 1.5482,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.06478932881643024,
|
| 1109 |
+
"grad_norm": 0.6391246318817139,
|
| 1110 |
+
"learning_rate": 2.483578947368421e-05,
|
| 1111 |
+
"loss": 1.4531,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.0652127884818971,
|
| 1116 |
+
"grad_norm": 0.668799102306366,
|
| 1117 |
+
"learning_rate": 2.430736842105263e-05,
|
| 1118 |
+
"loss": 1.4061,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.06563624814736396,
|
| 1123 |
+
"grad_norm": 0.6925205588340759,
|
| 1124 |
+
"learning_rate": 2.3778947368421052e-05,
|
| 1125 |
+
"loss": 1.5347,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.06605970781283083,
|
| 1130 |
+
"grad_norm": 0.6499634385108948,
|
| 1131 |
+
"learning_rate": 2.3250526315789473e-05,
|
| 1132 |
+
"loss": 1.5263,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.06648316747829769,
|
| 1137 |
+
"grad_norm": 0.6788086891174316,
|
| 1138 |
+
"learning_rate": 2.2722105263157894e-05,
|
| 1139 |
+
"loss": 1.4443,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.06690662714376455,
|
| 1144 |
+
"grad_norm": 0.7310974597930908,
|
| 1145 |
+
"learning_rate": 2.2193684210526316e-05,
|
| 1146 |
+
"loss": 1.4608,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.06733008680923142,
|
| 1151 |
+
"grad_norm": 0.675195574760437,
|
| 1152 |
+
"learning_rate": 2.1665263157894737e-05,
|
| 1153 |
+
"loss": 1.4124,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.06775354647469828,
|
| 1158 |
+
"grad_norm": 0.6866019368171692,
|
| 1159 |
+
"learning_rate": 2.1136842105263158e-05,
|
| 1160 |
+
"loss": 1.5076,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.06817700614016516,
|
| 1165 |
+
"grad_norm": 0.7151133418083191,
|
| 1166 |
+
"learning_rate": 2.060842105263158e-05,
|
| 1167 |
+
"loss": 1.3475,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.06860046580563202,
|
| 1172 |
+
"grad_norm": 0.6821713447570801,
|
| 1173 |
+
"learning_rate": 2.008e-05,
|
| 1174 |
+
"loss": 1.4513,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.06902392547109888,
|
| 1179 |
+
"grad_norm": 0.727641761302948,
|
| 1180 |
+
"learning_rate": 1.9551578947368422e-05,
|
| 1181 |
+
"loss": 1.437,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.06944738513656575,
|
| 1186 |
+
"grad_norm": 0.7269579172134399,
|
| 1187 |
+
"learning_rate": 1.9023157894736843e-05,
|
| 1188 |
+
"loss": 1.3762,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.06987084480203261,
|
| 1193 |
+
"grad_norm": 0.7100383043289185,
|
| 1194 |
+
"learning_rate": 1.849473684210526e-05,
|
| 1195 |
+
"loss": 1.3778,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.07029430446749947,
|
| 1200 |
+
"grad_norm": 0.7104079127311707,
|
| 1201 |
+
"learning_rate": 1.7966315789473686e-05,
|
| 1202 |
+
"loss": 1.3684,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.07071776413296633,
|
| 1207 |
+
"grad_norm": 0.7646909952163696,
|
| 1208 |
+
"learning_rate": 1.7437894736842107e-05,
|
| 1209 |
+
"loss": 1.4429,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.0711412237984332,
|
| 1214 |
+
"grad_norm": 0.7604168057441711,
|
| 1215 |
+
"learning_rate": 1.6909473684210525e-05,
|
| 1216 |
+
"loss": 1.4071,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.07156468346390006,
|
| 1221 |
+
"grad_norm": 0.7554246783256531,
|
| 1222 |
+
"learning_rate": 1.638105263157895e-05,
|
| 1223 |
+
"loss": 1.4778,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.07198814312936692,
|
| 1228 |
+
"grad_norm": 0.8014541864395142,
|
| 1229 |
+
"learning_rate": 1.5852631578947368e-05,
|
| 1230 |
+
"loss": 1.331,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.07241160279483379,
|
| 1235 |
+
"grad_norm": 0.7670878767967224,
|
| 1236 |
+
"learning_rate": 1.532421052631579e-05,
|
| 1237 |
+
"loss": 1.366,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.07283506246030065,
|
| 1242 |
+
"grad_norm": 0.7677123546600342,
|
| 1243 |
+
"learning_rate": 1.4795789473684209e-05,
|
| 1244 |
+
"loss": 1.2327,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.07325852212576751,
|
| 1249 |
+
"grad_norm": 0.7552341818809509,
|
| 1250 |
+
"learning_rate": 1.4267368421052632e-05,
|
| 1251 |
+
"loss": 1.3134,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.07368198179123439,
|
| 1256 |
+
"grad_norm": 0.827423095703125,
|
| 1257 |
+
"learning_rate": 1.3738947368421053e-05,
|
| 1258 |
+
"loss": 1.3989,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.07410544145670125,
|
| 1263 |
+
"grad_norm": 0.8643474578857422,
|
| 1264 |
+
"learning_rate": 1.3210526315789473e-05,
|
| 1265 |
+
"loss": 1.3781,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.07452890112216812,
|
| 1270 |
+
"grad_norm": 0.8241193890571594,
|
| 1271 |
+
"learning_rate": 1.2682105263157896e-05,
|
| 1272 |
+
"loss": 1.4126,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.07495236078763498,
|
| 1277 |
+
"grad_norm": 0.8594452738761902,
|
| 1278 |
+
"learning_rate": 1.2153684210526315e-05,
|
| 1279 |
+
"loss": 1.458,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.07537582045310184,
|
| 1284 |
+
"grad_norm": 0.8998329043388367,
|
| 1285 |
+
"learning_rate": 1.1625263157894737e-05,
|
| 1286 |
+
"loss": 1.4351,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.07579928011856871,
|
| 1291 |
+
"grad_norm": 0.8990980386734009,
|
| 1292 |
+
"learning_rate": 1.1096842105263158e-05,
|
| 1293 |
+
"loss": 1.4393,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.07622273978403557,
|
| 1298 |
+
"grad_norm": 0.8009428381919861,
|
| 1299 |
+
"learning_rate": 1.0568421052631579e-05,
|
| 1300 |
+
"loss": 1.2632,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.07664619944950243,
|
| 1305 |
+
"grad_norm": 1.099630355834961,
|
| 1306 |
+
"learning_rate": 1.004e-05,
|
| 1307 |
+
"loss": 1.582,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.0770696591149693,
|
| 1312 |
+
"grad_norm": 1.0162990093231201,
|
| 1313 |
+
"learning_rate": 9.511578947368422e-06,
|
| 1314 |
+
"loss": 1.364,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.07749311878043616,
|
| 1319 |
+
"grad_norm": 0.9093153476715088,
|
| 1320 |
+
"learning_rate": 8.983157894736843e-06,
|
| 1321 |
+
"loss": 1.3898,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.07791657844590302,
|
| 1326 |
+
"grad_norm": 1.0030639171600342,
|
| 1327 |
+
"learning_rate": 8.454736842105263e-06,
|
| 1328 |
+
"loss": 1.2831,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.07834003811136989,
|
| 1333 |
+
"grad_norm": 0.959372341632843,
|
| 1334 |
+
"learning_rate": 7.926315789473684e-06,
|
| 1335 |
+
"loss": 1.4891,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.07876349777683675,
|
| 1340 |
+
"grad_norm": 0.99298495054245,
|
| 1341 |
+
"learning_rate": 7.397894736842104e-06,
|
| 1342 |
+
"loss": 1.2753,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.07918695744230363,
|
| 1347 |
+
"grad_norm": 0.9265472888946533,
|
| 1348 |
+
"learning_rate": 6.8694736842105265e-06,
|
| 1349 |
+
"loss": 1.2293,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.07961041710777049,
|
| 1354 |
+
"grad_norm": 1.0850491523742676,
|
| 1355 |
+
"learning_rate": 6.341052631578948e-06,
|
| 1356 |
+
"loss": 1.3636,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.08003387677323735,
|
| 1361 |
+
"grad_norm": 1.0030916929244995,
|
| 1362 |
+
"learning_rate": 5.812631578947368e-06,
|
| 1363 |
+
"loss": 1.4687,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.08045733643870422,
|
| 1368 |
+
"grad_norm": 1.0106968879699707,
|
| 1369 |
+
"learning_rate": 5.2842105263157896e-06,
|
| 1370 |
+
"loss": 1.396,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.08088079610417108,
|
| 1375 |
+
"grad_norm": 1.021835207939148,
|
| 1376 |
+
"learning_rate": 4.755789473684211e-06,
|
| 1377 |
+
"loss": 1.274,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.08130425576963794,
|
| 1382 |
+
"grad_norm": 1.0136542320251465,
|
| 1383 |
+
"learning_rate": 4.227368421052631e-06,
|
| 1384 |
+
"loss": 1.553,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.0817277154351048,
|
| 1389 |
+
"grad_norm": 1.1040548086166382,
|
| 1390 |
+
"learning_rate": 3.698947368421052e-06,
|
| 1391 |
+
"loss": 1.5085,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.08215117510057167,
|
| 1396 |
+
"grad_norm": 1.238360047340393,
|
| 1397 |
+
"learning_rate": 3.170526315789474e-06,
|
| 1398 |
+
"loss": 1.5387,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.08257463476603853,
|
| 1403 |
+
"grad_norm": 1.2721796035766602,
|
| 1404 |
+
"learning_rate": 2.6421052631578948e-06,
|
| 1405 |
+
"loss": 1.3972,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.0829980944315054,
|
| 1410 |
+
"grad_norm": 1.4735435247421265,
|
| 1411 |
+
"learning_rate": 2.1136842105263157e-06,
|
| 1412 |
+
"loss": 1.9482,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.08342155409697226,
|
| 1417 |
+
"grad_norm": 1.433443546295166,
|
| 1418 |
+
"learning_rate": 1.585263157894737e-06,
|
| 1419 |
+
"loss": 1.7534,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.08384501376243912,
|
| 1424 |
+
"grad_norm": 1.7169157266616821,
|
| 1425 |
+
"learning_rate": 1.0568421052631578e-06,
|
| 1426 |
+
"loss": 1.542,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.084268473427906,
|
| 1431 |
+
"grad_norm": 2.0519940853118896,
|
| 1432 |
+
"learning_rate": 5.284210526315789e-07,
|
| 1433 |
+
"loss": 1.5499,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.08469193309337286,
|
| 1438 |
+
"grad_norm": 3.5967867374420166,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.6132,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.08469193309337286,
|
| 1445 |
+
"eval_loss": 1.453239917755127,
|
| 1446 |
+
"eval_runtime": 115.0821,
|
| 1447 |
+
"eval_samples_per_second": 8.646,
|
| 1448 |
+
"eval_steps_per_second": 2.164,
|
| 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": 7.674562831869542e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|