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 sha256:5be9b0d1f7049376c6ac9281f99999da158491e09a823b28d2cc2ffa41cc793c
|
| 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:b40dfb4665cbdcabc7db941f8f0cbc3c699cf1a3c3fe2cc4b01de89606fda463
|
| 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 sha256:0566559177883c4194a08d8779faaa6d6b1ff550d28e94c7ac54029287fd8bc0
|
| 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:d703f9adb617aa1ec13556a7b7482c741f765121a5a04f3cafdcfbce6ed485ee
|
| 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": 19.779,
|
| 1090 |
"eval_steps_per_second": 4.965,
|
| 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": 1.630453109741211,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.11366865586814436,
|
| 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": 19.779,
|
| 1090 |
"eval_steps_per_second": 4.965,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.08581983518044899,
|
| 1095 |
+
"grad_norm": 0.33179932832717896,
|
| 1096 |
+
"learning_rate": 2.6253684210526317e-05,
|
| 1097 |
+
"loss": 1.7188,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.08638817845978972,
|
| 1102 |
+
"grad_norm": 0.32185089588165283,
|
| 1103 |
+
"learning_rate": 2.5717894736842106e-05,
|
| 1104 |
+
"loss": 1.6621,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.08695652173913043,
|
| 1109 |
+
"grad_norm": 0.35517582297325134,
|
| 1110 |
+
"learning_rate": 2.518210526315789e-05,
|
| 1111 |
+
"loss": 1.5507,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.08752486501847116,
|
| 1116 |
+
"grad_norm": 0.43270987272262573,
|
| 1117 |
+
"learning_rate": 2.4646315789473683e-05,
|
| 1118 |
+
"loss": 1.7868,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.08809320829781188,
|
| 1123 |
+
"grad_norm": 0.4225779175758362,
|
| 1124 |
+
"learning_rate": 2.411052631578947e-05,
|
| 1125 |
+
"loss": 1.5988,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.0886615515771526,
|
| 1130 |
+
"grad_norm": 0.4306216537952423,
|
| 1131 |
+
"learning_rate": 2.357473684210526e-05,
|
| 1132 |
+
"loss": 1.6786,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.08922989485649332,
|
| 1137 |
+
"grad_norm": 0.44885534048080444,
|
| 1138 |
+
"learning_rate": 2.3038947368421052e-05,
|
| 1139 |
+
"loss": 1.5094,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.08979823813583404,
|
| 1144 |
+
"grad_norm": 0.5068619251251221,
|
| 1145 |
+
"learning_rate": 2.250315789473684e-05,
|
| 1146 |
+
"loss": 1.6784,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.09036658141517477,
|
| 1151 |
+
"grad_norm": 0.4916083514690399,
|
| 1152 |
+
"learning_rate": 2.196736842105263e-05,
|
| 1153 |
+
"loss": 1.65,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.09093492469451549,
|
| 1158 |
+
"grad_norm": 0.5132988095283508,
|
| 1159 |
+
"learning_rate": 2.1431578947368418e-05,
|
| 1160 |
+
"loss": 1.6544,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.0915032679738562,
|
| 1165 |
+
"grad_norm": 0.5349146127700806,
|
| 1166 |
+
"learning_rate": 2.089578947368421e-05,
|
| 1167 |
+
"loss": 1.6086,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.09207161125319693,
|
| 1172 |
+
"grad_norm": 0.5187984704971313,
|
| 1173 |
+
"learning_rate": 2.036e-05,
|
| 1174 |
+
"loss": 1.3669,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.09263995453253765,
|
| 1179 |
+
"grad_norm": 0.5901036262512207,
|
| 1180 |
+
"learning_rate": 1.9824210526315787e-05,
|
| 1181 |
+
"loss": 1.7017,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.09320829781187838,
|
| 1186 |
+
"grad_norm": 0.5522847175598145,
|
| 1187 |
+
"learning_rate": 1.928842105263158e-05,
|
| 1188 |
+
"loss": 1.4784,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.0937766410912191,
|
| 1193 |
+
"grad_norm": 0.6255651116371155,
|
| 1194 |
+
"learning_rate": 1.8752631578947367e-05,
|
| 1195 |
+
"loss": 1.7601,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.09434498437055981,
|
| 1200 |
+
"grad_norm": 0.586127519607544,
|
| 1201 |
+
"learning_rate": 1.8216842105263156e-05,
|
| 1202 |
+
"loss": 1.6422,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.09491332764990054,
|
| 1207 |
+
"grad_norm": 0.6434412598609924,
|
| 1208 |
+
"learning_rate": 1.7681052631578948e-05,
|
| 1209 |
+
"loss": 1.6697,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.09548167092924126,
|
| 1214 |
+
"grad_norm": 0.5888460278511047,
|
| 1215 |
+
"learning_rate": 1.7145263157894736e-05,
|
| 1216 |
+
"loss": 1.4801,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.09605001420858199,
|
| 1221 |
+
"grad_norm": 0.6054426431655884,
|
| 1222 |
+
"learning_rate": 1.6609473684210525e-05,
|
| 1223 |
+
"loss": 1.6244,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.0966183574879227,
|
| 1228 |
+
"grad_norm": 0.7235743999481201,
|
| 1229 |
+
"learning_rate": 1.6073684210526313e-05,
|
| 1230 |
+
"loss": 1.7011,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.09718670076726342,
|
| 1235 |
+
"grad_norm": 0.6796721816062927,
|
| 1236 |
+
"learning_rate": 1.5537894736842105e-05,
|
| 1237 |
+
"loss": 1.5895,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.09775504404660415,
|
| 1242 |
+
"grad_norm": 0.6769363284111023,
|
| 1243 |
+
"learning_rate": 1.5002105263157892e-05,
|
| 1244 |
+
"loss": 1.4874,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.09832338732594487,
|
| 1249 |
+
"grad_norm": 0.6305172443389893,
|
| 1250 |
+
"learning_rate": 1.4466315789473684e-05,
|
| 1251 |
+
"loss": 1.3513,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.0988917306052856,
|
| 1256 |
+
"grad_norm": 0.7441319823265076,
|
| 1257 |
+
"learning_rate": 1.3930526315789474e-05,
|
| 1258 |
+
"loss": 1.4042,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.09946007388462631,
|
| 1263 |
+
"grad_norm": 0.7381362318992615,
|
| 1264 |
+
"learning_rate": 1.3394736842105261e-05,
|
| 1265 |
+
"loss": 1.3791,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.10002841716396704,
|
| 1270 |
+
"grad_norm": 0.816709041595459,
|
| 1271 |
+
"learning_rate": 1.2858947368421053e-05,
|
| 1272 |
+
"loss": 1.6178,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.10059676044330776,
|
| 1277 |
+
"grad_norm": 0.7869638800621033,
|
| 1278 |
+
"learning_rate": 1.2323157894736842e-05,
|
| 1279 |
+
"loss": 1.3603,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.10116510372264848,
|
| 1284 |
+
"grad_norm": 0.9357262253761292,
|
| 1285 |
+
"learning_rate": 1.178736842105263e-05,
|
| 1286 |
+
"loss": 1.5296,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.1017334470019892,
|
| 1291 |
+
"grad_norm": 0.8037711381912231,
|
| 1292 |
+
"learning_rate": 1.125157894736842e-05,
|
| 1293 |
+
"loss": 1.4484,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.10230179028132992,
|
| 1298 |
+
"grad_norm": 0.9005003571510315,
|
| 1299 |
+
"learning_rate": 1.0715789473684209e-05,
|
| 1300 |
+
"loss": 1.4668,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.10287013356067065,
|
| 1305 |
+
"grad_norm": 0.9204942584037781,
|
| 1306 |
+
"learning_rate": 1.018e-05,
|
| 1307 |
+
"loss": 1.6658,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.10343847684001137,
|
| 1312 |
+
"grad_norm": 1.056218147277832,
|
| 1313 |
+
"learning_rate": 9.64421052631579e-06,
|
| 1314 |
+
"loss": 1.7106,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.10400682011935208,
|
| 1319 |
+
"grad_norm": 1.1173593997955322,
|
| 1320 |
+
"learning_rate": 9.108421052631578e-06,
|
| 1321 |
+
"loss": 1.7539,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.10457516339869281,
|
| 1326 |
+
"grad_norm": 1.0534868240356445,
|
| 1327 |
+
"learning_rate": 8.572631578947368e-06,
|
| 1328 |
+
"loss": 1.3405,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.10514350667803353,
|
| 1333 |
+
"grad_norm": 0.9765002131462097,
|
| 1334 |
+
"learning_rate": 8.036842105263157e-06,
|
| 1335 |
+
"loss": 1.5626,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.10571184995737426,
|
| 1340 |
+
"grad_norm": 1.197899341583252,
|
| 1341 |
+
"learning_rate": 7.501052631578946e-06,
|
| 1342 |
+
"loss": 1.596,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.10628019323671498,
|
| 1347 |
+
"grad_norm": 1.2872265577316284,
|
| 1348 |
+
"learning_rate": 6.965263157894737e-06,
|
| 1349 |
+
"loss": 1.5636,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.10684853651605569,
|
| 1354 |
+
"grad_norm": 1.211369276046753,
|
| 1355 |
+
"learning_rate": 6.4294736842105265e-06,
|
| 1356 |
+
"loss": 1.6695,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.10741687979539642,
|
| 1361 |
+
"grad_norm": 1.3407747745513916,
|
| 1362 |
+
"learning_rate": 5.893684210526315e-06,
|
| 1363 |
+
"loss": 1.675,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.10798522307473714,
|
| 1368 |
+
"grad_norm": 1.2818570137023926,
|
| 1369 |
+
"learning_rate": 5.3578947368421044e-06,
|
| 1370 |
+
"loss": 1.496,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.10855356635407787,
|
| 1375 |
+
"grad_norm": 1.1480392217636108,
|
| 1376 |
+
"learning_rate": 4.822105263157895e-06,
|
| 1377 |
+
"loss": 1.5432,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.10912190963341858,
|
| 1382 |
+
"grad_norm": 1.3711426258087158,
|
| 1383 |
+
"learning_rate": 4.286315789473684e-06,
|
| 1384 |
+
"loss": 1.4977,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.1096902529127593,
|
| 1389 |
+
"grad_norm": 1.4758083820343018,
|
| 1390 |
+
"learning_rate": 3.750526315789473e-06,
|
| 1391 |
+
"loss": 1.0595,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.11025859619210003,
|
| 1396 |
+
"grad_norm": 1.748803734779358,
|
| 1397 |
+
"learning_rate": 3.2147368421052633e-06,
|
| 1398 |
+
"loss": 1.5774,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.11082693947144075,
|
| 1403 |
+
"grad_norm": 1.7619532346725464,
|
| 1404 |
+
"learning_rate": 2.6789473684210522e-06,
|
| 1405 |
+
"loss": 1.5964,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.11139528275078148,
|
| 1410 |
+
"grad_norm": 1.7181921005249023,
|
| 1411 |
+
"learning_rate": 2.143157894736842e-06,
|
| 1412 |
+
"loss": 1.1225,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.11196362603012219,
|
| 1417 |
+
"grad_norm": 1.7596096992492676,
|
| 1418 |
+
"learning_rate": 1.6073684210526316e-06,
|
| 1419 |
+
"loss": 1.6769,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.11253196930946291,
|
| 1424 |
+
"grad_norm": 2.1839563846588135,
|
| 1425 |
+
"learning_rate": 1.071578947368421e-06,
|
| 1426 |
+
"loss": 1.4875,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.11310031258880364,
|
| 1431 |
+
"grad_norm": 2.683014154434204,
|
| 1432 |
+
"learning_rate": 5.357894736842105e-07,
|
| 1433 |
+
"loss": 2.4549,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.11366865586814436,
|
| 1438 |
+
"grad_norm": 3.496476888656616,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 2.27,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.11366865586814436,
|
| 1445 |
+
"eval_loss": 1.630453109741211,
|
| 1446 |
+
"eval_runtime": 37.4531,
|
| 1447 |
+
"eval_samples_per_second": 19.785,
|
| 1448 |
+
"eval_steps_per_second": 4.966,
|
| 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": 6.835422040267162e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|