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 871457448
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:daded2ea81e1c246e495e0bfcb9ac38035c1b4f3c8fe5cef5ccb5bf57edd6da3
|
| 3 |
size 871457448
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 443280340
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1200e7188d980e034eef13ee53467ae4fbfaf7d955fb6879339de3bdbc929bf8
|
| 3 |
size 443280340
|
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 sha256:2c795ecc565271ef96d79e0256ef074f709506941a2513cc2908808c7323e441
|
| 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": 7.481,
|
| 1090 |
"eval_steps_per_second": 1.872,
|
| 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": 1.1331982612609863,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.03266372693124286,
|
| 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": 7.481,
|
| 1090 |
"eval_steps_per_second": 1.872,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.024661113833088357,
|
| 1095 |
+
"grad_norm": 0.5295467972755432,
|
| 1096 |
+
"learning_rate": 2.5841052631578947e-05,
|
| 1097 |
+
"loss": 0.9102,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.02482443246774457,
|
| 1102 |
+
"grad_norm": 0.42944419384002686,
|
| 1103 |
+
"learning_rate": 2.5313684210526316e-05,
|
| 1104 |
+
"loss": 0.7221,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.024987751102400785,
|
| 1109 |
+
"grad_norm": 0.4469304084777832,
|
| 1110 |
+
"learning_rate": 2.4786315789473682e-05,
|
| 1111 |
+
"loss": 0.7679,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.025151069737056997,
|
| 1116 |
+
"grad_norm": 0.6193202137947083,
|
| 1117 |
+
"learning_rate": 2.425894736842105e-05,
|
| 1118 |
+
"loss": 0.9083,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.025314388371713212,
|
| 1123 |
+
"grad_norm": 0.5847591161727905,
|
| 1124 |
+
"learning_rate": 2.373157894736842e-05,
|
| 1125 |
+
"loss": 0.72,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.025477707006369428,
|
| 1130 |
+
"grad_norm": 0.5906417965888977,
|
| 1131 |
+
"learning_rate": 2.3204210526315788e-05,
|
| 1132 |
+
"loss": 0.9138,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.02564102564102564,
|
| 1137 |
+
"grad_norm": 0.4926919639110565,
|
| 1138 |
+
"learning_rate": 2.2676842105263157e-05,
|
| 1139 |
+
"loss": 0.9187,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.025804344275681856,
|
| 1144 |
+
"grad_norm": 0.5422658920288086,
|
| 1145 |
+
"learning_rate": 2.2149473684210526e-05,
|
| 1146 |
+
"loss": 1.0084,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.02596766291033807,
|
| 1151 |
+
"grad_norm": 0.5664920210838318,
|
| 1152 |
+
"learning_rate": 2.1622105263157895e-05,
|
| 1153 |
+
"loss": 0.9221,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.026130981544994283,
|
| 1158 |
+
"grad_norm": 0.5593885779380798,
|
| 1159 |
+
"learning_rate": 2.109473684210526e-05,
|
| 1160 |
+
"loss": 0.8757,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.0262943001796505,
|
| 1165 |
+
"grad_norm": 0.6178870797157288,
|
| 1166 |
+
"learning_rate": 2.0567368421052632e-05,
|
| 1167 |
+
"loss": 1.0018,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.02645761881430671,
|
| 1172 |
+
"grad_norm": 0.5820048451423645,
|
| 1173 |
+
"learning_rate": 2.004e-05,
|
| 1174 |
+
"loss": 0.8186,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.026620937448962927,
|
| 1179 |
+
"grad_norm": 0.606930673122406,
|
| 1180 |
+
"learning_rate": 1.9512631578947367e-05,
|
| 1181 |
+
"loss": 0.915,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.026784256083619142,
|
| 1186 |
+
"grad_norm": 0.5813213586807251,
|
| 1187 |
+
"learning_rate": 1.8985263157894736e-05,
|
| 1188 |
+
"loss": 0.8943,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.026947574718275354,
|
| 1193 |
+
"grad_norm": 0.7827402949333191,
|
| 1194 |
+
"learning_rate": 1.8457894736842104e-05,
|
| 1195 |
+
"loss": 0.6757,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.02711089335293157,
|
| 1200 |
+
"grad_norm": 0.7083070874214172,
|
| 1201 |
+
"learning_rate": 1.7930526315789473e-05,
|
| 1202 |
+
"loss": 0.797,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.027274211987587785,
|
| 1207 |
+
"grad_norm": 0.6508756875991821,
|
| 1208 |
+
"learning_rate": 1.7403157894736842e-05,
|
| 1209 |
+
"loss": 0.98,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.027437530622243998,
|
| 1214 |
+
"grad_norm": 0.681760847568512,
|
| 1215 |
+
"learning_rate": 1.687578947368421e-05,
|
| 1216 |
+
"loss": 0.8936,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.027600849256900213,
|
| 1221 |
+
"grad_norm": 0.7164104580879211,
|
| 1222 |
+
"learning_rate": 1.634842105263158e-05,
|
| 1223 |
+
"loss": 0.866,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.027764167891556425,
|
| 1228 |
+
"grad_norm": 0.8126941919326782,
|
| 1229 |
+
"learning_rate": 1.5821052631578945e-05,
|
| 1230 |
+
"loss": 0.8797,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.02792748652621264,
|
| 1235 |
+
"grad_norm": 0.7941915988922119,
|
| 1236 |
+
"learning_rate": 1.5293684210526314e-05,
|
| 1237 |
+
"loss": 1.0358,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.028090805160868856,
|
| 1242 |
+
"grad_norm": 0.9106842875480652,
|
| 1243 |
+
"learning_rate": 1.4766315789473683e-05,
|
| 1244 |
+
"loss": 1.0669,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.02825412379552507,
|
| 1249 |
+
"grad_norm": 0.9008748531341553,
|
| 1250 |
+
"learning_rate": 1.4238947368421052e-05,
|
| 1251 |
+
"loss": 1.0582,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.028417442430181284,
|
| 1256 |
+
"grad_norm": 0.916495144367218,
|
| 1257 |
+
"learning_rate": 1.3711578947368422e-05,
|
| 1258 |
+
"loss": 0.7787,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.0285807610648375,
|
| 1263 |
+
"grad_norm": 0.9486830234527588,
|
| 1264 |
+
"learning_rate": 1.3184210526315788e-05,
|
| 1265 |
+
"loss": 0.9648,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.02874407969949371,
|
| 1270 |
+
"grad_norm": 0.975587785243988,
|
| 1271 |
+
"learning_rate": 1.2656842105263158e-05,
|
| 1272 |
+
"loss": 0.9214,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.028907398334149927,
|
| 1277 |
+
"grad_norm": 1.2781733274459839,
|
| 1278 |
+
"learning_rate": 1.2129473684210525e-05,
|
| 1279 |
+
"loss": 1.2543,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.02907071696880614,
|
| 1284 |
+
"grad_norm": 1.1123965978622437,
|
| 1285 |
+
"learning_rate": 1.1602105263157894e-05,
|
| 1286 |
+
"loss": 0.9457,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.029234035603462355,
|
| 1291 |
+
"grad_norm": 1.0323660373687744,
|
| 1292 |
+
"learning_rate": 1.1074736842105263e-05,
|
| 1293 |
+
"loss": 0.8505,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.02939735423811857,
|
| 1298 |
+
"grad_norm": 1.3954451084136963,
|
| 1299 |
+
"learning_rate": 1.054736842105263e-05,
|
| 1300 |
+
"loss": 1.1639,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.029560672872774783,
|
| 1305 |
+
"grad_norm": 1.4453262090682983,
|
| 1306 |
+
"learning_rate": 1.002e-05,
|
| 1307 |
+
"loss": 1.1046,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.029723991507430998,
|
| 1312 |
+
"grad_norm": 1.371714472770691,
|
| 1313 |
+
"learning_rate": 9.492631578947368e-06,
|
| 1314 |
+
"loss": 1.1104,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.029887310142087214,
|
| 1319 |
+
"grad_norm": 1.7723652124404907,
|
| 1320 |
+
"learning_rate": 8.965263157894737e-06,
|
| 1321 |
+
"loss": 1.1258,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.030050628776743426,
|
| 1326 |
+
"grad_norm": 1.6344342231750488,
|
| 1327 |
+
"learning_rate": 8.437894736842105e-06,
|
| 1328 |
+
"loss": 1.1028,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.03021394741139964,
|
| 1333 |
+
"grad_norm": 2.0994627475738525,
|
| 1334 |
+
"learning_rate": 7.910526315789473e-06,
|
| 1335 |
+
"loss": 1.0568,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.030377266046055854,
|
| 1340 |
+
"grad_norm": 2.0363705158233643,
|
| 1341 |
+
"learning_rate": 7.383157894736841e-06,
|
| 1342 |
+
"loss": 1.5804,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.03054058468071207,
|
| 1347 |
+
"grad_norm": 2.4229798316955566,
|
| 1348 |
+
"learning_rate": 6.855789473684211e-06,
|
| 1349 |
+
"loss": 1.1893,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.030703903315368285,
|
| 1354 |
+
"grad_norm": 3.015899181365967,
|
| 1355 |
+
"learning_rate": 6.328421052631579e-06,
|
| 1356 |
+
"loss": 1.2766,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.030867221950024497,
|
| 1361 |
+
"grad_norm": 2.2767412662506104,
|
| 1362 |
+
"learning_rate": 5.801052631578947e-06,
|
| 1363 |
+
"loss": 1.22,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.031030540584680712,
|
| 1368 |
+
"grad_norm": 3.660109758377075,
|
| 1369 |
+
"learning_rate": 5.273684210526315e-06,
|
| 1370 |
+
"loss": 1.2292,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.031193859219336928,
|
| 1375 |
+
"grad_norm": 4.029131889343262,
|
| 1376 |
+
"learning_rate": 4.746315789473684e-06,
|
| 1377 |
+
"loss": 1.7373,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.03135717785399314,
|
| 1382 |
+
"grad_norm": 3.336766242980957,
|
| 1383 |
+
"learning_rate": 4.218947368421053e-06,
|
| 1384 |
+
"loss": 1.44,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.03152049648864935,
|
| 1389 |
+
"grad_norm": 3.1067514419555664,
|
| 1390 |
+
"learning_rate": 3.6915789473684207e-06,
|
| 1391 |
+
"loss": 1.512,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.03168381512330557,
|
| 1396 |
+
"grad_norm": 3.971158981323242,
|
| 1397 |
+
"learning_rate": 3.1642105263157895e-06,
|
| 1398 |
+
"loss": 1.5966,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.03184713375796178,
|
| 1403 |
+
"grad_norm": 2.507552146911621,
|
| 1404 |
+
"learning_rate": 2.6368421052631575e-06,
|
| 1405 |
+
"loss": 1.0217,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.032010452392617995,
|
| 1410 |
+
"grad_norm": 3.831817865371704,
|
| 1411 |
+
"learning_rate": 2.1094736842105264e-06,
|
| 1412 |
+
"loss": 0.9842,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.032173771027274214,
|
| 1417 |
+
"grad_norm": 5.005215167999268,
|
| 1418 |
+
"learning_rate": 1.5821052631578948e-06,
|
| 1419 |
+
"loss": 2.8562,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.03233708966193043,
|
| 1424 |
+
"grad_norm": 4.721521377563477,
|
| 1425 |
+
"learning_rate": 1.0547368421052632e-06,
|
| 1426 |
+
"loss": 2.4518,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.03250040829658664,
|
| 1431 |
+
"grad_norm": 5.0478363037109375,
|
| 1432 |
+
"learning_rate": 5.273684210526316e-07,
|
| 1433 |
+
"loss": 2.0353,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.03266372693124286,
|
| 1438 |
+
"grad_norm": 6.368497371673584,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.6937,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.03266372693124286,
|
| 1445 |
+
"eval_loss": 1.1331982612609863,
|
| 1446 |
+
"eval_runtime": 344.2422,
|
| 1447 |
+
"eval_samples_per_second": 7.489,
|
| 1448 |
+
"eval_steps_per_second": 1.874,
|
| 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": 8.65769979075625e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|