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 1163996488
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:957fbc70285ecf6cef92499eb209a1bcd0447c947d20c1c032fd35676ad035ad
|
| 3 |
size 1163996488
|
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:f0089cd35ee2f0e917439400ce9ea883d6e87b88f31a251b1ec36a7b7ce236ca
|
| 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 sha256:5b907b37a5243703a7153e6180084d50d88016d5fd99beffbee3d491b70b8bf5
|
| 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": 11.229,
|
| 1090 |
"eval_steps_per_second": 2.83,
|
| 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": 1.010448932647705,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.22870211549456831,
|
| 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": 11.229,
|
| 1090 |
"eval_steps_per_second": 2.83,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.1726700971983991,
|
| 1095 |
+
"grad_norm": 0.1942352056503296,
|
| 1096 |
+
"learning_rate": 2.6253684210526317e-05,
|
| 1097 |
+
"loss": 0.7878,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.17381360777587193,
|
| 1102 |
+
"grad_norm": 0.24811097979545593,
|
| 1103 |
+
"learning_rate": 2.5717894736842106e-05,
|
| 1104 |
+
"loss": 1.1611,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.17495711835334476,
|
| 1109 |
+
"grad_norm": 0.24453826248645782,
|
| 1110 |
+
"learning_rate": 2.518210526315789e-05,
|
| 1111 |
+
"loss": 0.9794,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.1761006289308176,
|
| 1116 |
+
"grad_norm": 0.23959362506866455,
|
| 1117 |
+
"learning_rate": 2.4646315789473683e-05,
|
| 1118 |
+
"loss": 1.1261,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.17724413950829046,
|
| 1123 |
+
"grad_norm": 0.24163787066936493,
|
| 1124 |
+
"learning_rate": 2.411052631578947e-05,
|
| 1125 |
+
"loss": 1.017,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.1783876500857633,
|
| 1130 |
+
"grad_norm": 0.25836434960365295,
|
| 1131 |
+
"learning_rate": 2.357473684210526e-05,
|
| 1132 |
+
"loss": 1.2222,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.17953116066323613,
|
| 1137 |
+
"grad_norm": 0.27292728424072266,
|
| 1138 |
+
"learning_rate": 2.3038947368421052e-05,
|
| 1139 |
+
"loss": 1.1383,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.180674671240709,
|
| 1144 |
+
"grad_norm": 0.25207802653312683,
|
| 1145 |
+
"learning_rate": 2.250315789473684e-05,
|
| 1146 |
+
"loss": 1.1166,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.18181818181818182,
|
| 1151 |
+
"grad_norm": 0.25218677520751953,
|
| 1152 |
+
"learning_rate": 2.196736842105263e-05,
|
| 1153 |
+
"loss": 1.1572,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.18296169239565466,
|
| 1158 |
+
"grad_norm": 0.256805956363678,
|
| 1159 |
+
"learning_rate": 2.1431578947368418e-05,
|
| 1160 |
+
"loss": 1.1692,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.1841052029731275,
|
| 1165 |
+
"grad_norm": 0.25223690271377563,
|
| 1166 |
+
"learning_rate": 2.089578947368421e-05,
|
| 1167 |
+
"loss": 1.0468,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.18524871355060035,
|
| 1172 |
+
"grad_norm": 0.2556026875972748,
|
| 1173 |
+
"learning_rate": 2.036e-05,
|
| 1174 |
+
"loss": 1.0576,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.1863922241280732,
|
| 1179 |
+
"grad_norm": 0.25864240527153015,
|
| 1180 |
+
"learning_rate": 1.9824210526315787e-05,
|
| 1181 |
+
"loss": 1.0228,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.18753573470554602,
|
| 1186 |
+
"grad_norm": 0.37401801347732544,
|
| 1187 |
+
"learning_rate": 1.928842105263158e-05,
|
| 1188 |
+
"loss": 1.2331,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.18867924528301888,
|
| 1193 |
+
"grad_norm": 0.2586139440536499,
|
| 1194 |
+
"learning_rate": 1.8752631578947367e-05,
|
| 1195 |
+
"loss": 1.1819,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.18982275586049172,
|
| 1200 |
+
"grad_norm": 0.28469181060791016,
|
| 1201 |
+
"learning_rate": 1.8216842105263156e-05,
|
| 1202 |
+
"loss": 1.1134,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.19096626643796455,
|
| 1207 |
+
"grad_norm": 0.2891313135623932,
|
| 1208 |
+
"learning_rate": 1.7681052631578948e-05,
|
| 1209 |
+
"loss": 1.1394,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.19210977701543738,
|
| 1214 |
+
"grad_norm": 0.2869350016117096,
|
| 1215 |
+
"learning_rate": 1.7145263157894736e-05,
|
| 1216 |
+
"loss": 1.2324,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.19325328759291024,
|
| 1221 |
+
"grad_norm": 0.2780541479587555,
|
| 1222 |
+
"learning_rate": 1.6609473684210525e-05,
|
| 1223 |
+
"loss": 1.0539,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.19439679817038308,
|
| 1228 |
+
"grad_norm": 0.3022194802761078,
|
| 1229 |
+
"learning_rate": 1.6073684210526313e-05,
|
| 1230 |
+
"loss": 1.0295,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.1955403087478559,
|
| 1235 |
+
"grad_norm": 0.28873467445373535,
|
| 1236 |
+
"learning_rate": 1.5537894736842105e-05,
|
| 1237 |
+
"loss": 0.8893,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.19668381932532875,
|
| 1242 |
+
"grad_norm": 0.30483803153038025,
|
| 1243 |
+
"learning_rate": 1.5002105263157892e-05,
|
| 1244 |
+
"loss": 1.1619,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.1978273299028016,
|
| 1249 |
+
"grad_norm": 0.30440232157707214,
|
| 1250 |
+
"learning_rate": 1.4466315789473684e-05,
|
| 1251 |
+
"loss": 0.965,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.19897084048027444,
|
| 1256 |
+
"grad_norm": 0.687065601348877,
|
| 1257 |
+
"learning_rate": 1.3930526315789474e-05,
|
| 1258 |
+
"loss": 1.1708,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.20011435105774728,
|
| 1263 |
+
"grad_norm": 0.33709561824798584,
|
| 1264 |
+
"learning_rate": 1.3394736842105261e-05,
|
| 1265 |
+
"loss": 1.1682,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.20125786163522014,
|
| 1270 |
+
"grad_norm": 0.3644546866416931,
|
| 1271 |
+
"learning_rate": 1.2858947368421053e-05,
|
| 1272 |
+
"loss": 1.017,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.20240137221269297,
|
| 1277 |
+
"grad_norm": 0.27532678842544556,
|
| 1278 |
+
"learning_rate": 1.2323157894736842e-05,
|
| 1279 |
+
"loss": 0.7339,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.2035448827901658,
|
| 1284 |
+
"grad_norm": 0.30165594816207886,
|
| 1285 |
+
"learning_rate": 1.178736842105263e-05,
|
| 1286 |
+
"loss": 0.8808,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.20468839336763864,
|
| 1291 |
+
"grad_norm": 0.2191629558801651,
|
| 1292 |
+
"learning_rate": 1.125157894736842e-05,
|
| 1293 |
+
"loss": 0.6094,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.2058319039451115,
|
| 1298 |
+
"grad_norm": 0.3130112886428833,
|
| 1299 |
+
"learning_rate": 1.0715789473684209e-05,
|
| 1300 |
+
"loss": 0.9785,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.20697541452258433,
|
| 1305 |
+
"grad_norm": 0.3028048872947693,
|
| 1306 |
+
"learning_rate": 1.018e-05,
|
| 1307 |
+
"loss": 0.8878,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.20811892510005717,
|
| 1312 |
+
"grad_norm": 0.311773419380188,
|
| 1313 |
+
"learning_rate": 9.64421052631579e-06,
|
| 1314 |
+
"loss": 1.0961,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.20926243567753003,
|
| 1319 |
+
"grad_norm": 0.2816356122493744,
|
| 1320 |
+
"learning_rate": 9.108421052631578e-06,
|
| 1321 |
+
"loss": 1.1126,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.21040594625500286,
|
| 1326 |
+
"grad_norm": 0.28161346912384033,
|
| 1327 |
+
"learning_rate": 8.572631578947368e-06,
|
| 1328 |
+
"loss": 1.3081,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.2115494568324757,
|
| 1333 |
+
"grad_norm": 0.30611908435821533,
|
| 1334 |
+
"learning_rate": 8.036842105263157e-06,
|
| 1335 |
+
"loss": 1.0617,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.21269296740994853,
|
| 1340 |
+
"grad_norm": 0.36937642097473145,
|
| 1341 |
+
"learning_rate": 7.501052631578946e-06,
|
| 1342 |
+
"loss": 0.9797,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.2138364779874214,
|
| 1347 |
+
"grad_norm": 0.29416340589523315,
|
| 1348 |
+
"learning_rate": 6.965263157894737e-06,
|
| 1349 |
+
"loss": 0.9259,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.21497998856489423,
|
| 1354 |
+
"grad_norm": 0.2920408844947815,
|
| 1355 |
+
"learning_rate": 6.4294736842105265e-06,
|
| 1356 |
+
"loss": 0.62,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.21612349914236706,
|
| 1361 |
+
"grad_norm": 0.30948537588119507,
|
| 1362 |
+
"learning_rate": 5.893684210526315e-06,
|
| 1363 |
+
"loss": 1.0818,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.21726700971983992,
|
| 1368 |
+
"grad_norm": 0.28673791885375977,
|
| 1369 |
+
"learning_rate": 5.3578947368421044e-06,
|
| 1370 |
+
"loss": 0.9172,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.21841052029731275,
|
| 1375 |
+
"grad_norm": 0.30014482140541077,
|
| 1376 |
+
"learning_rate": 4.822105263157895e-06,
|
| 1377 |
+
"loss": 0.9343,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.2195540308747856,
|
| 1382 |
+
"grad_norm": 0.30985647439956665,
|
| 1383 |
+
"learning_rate": 4.286315789473684e-06,
|
| 1384 |
+
"loss": 0.901,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.22069754145225842,
|
| 1389 |
+
"grad_norm": 0.29817381501197815,
|
| 1390 |
+
"learning_rate": 3.750526315789473e-06,
|
| 1391 |
+
"loss": 0.9511,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.22184105202973128,
|
| 1396 |
+
"grad_norm": 0.37334078550338745,
|
| 1397 |
+
"learning_rate": 3.2147368421052633e-06,
|
| 1398 |
+
"loss": 0.9329,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.22298456260720412,
|
| 1403 |
+
"grad_norm": 0.4006776511669159,
|
| 1404 |
+
"learning_rate": 2.6789473684210522e-06,
|
| 1405 |
+
"loss": 1.0734,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.22412807318467695,
|
| 1410 |
+
"grad_norm": 0.5243512392044067,
|
| 1411 |
+
"learning_rate": 2.143157894736842e-06,
|
| 1412 |
+
"loss": 0.7941,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.2252715837621498,
|
| 1417 |
+
"grad_norm": 0.8219733834266663,
|
| 1418 |
+
"learning_rate": 1.6073684210526316e-06,
|
| 1419 |
+
"loss": 0.7681,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.22641509433962265,
|
| 1424 |
+
"grad_norm": 0.8885450959205627,
|
| 1425 |
+
"learning_rate": 1.071578947368421e-06,
|
| 1426 |
+
"loss": 0.8465,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.22755860491709548,
|
| 1431 |
+
"grad_norm": 1.3124046325683594,
|
| 1432 |
+
"learning_rate": 5.357894736842105e-07,
|
| 1433 |
+
"loss": 0.6274,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.22870211549456831,
|
| 1438 |
+
"grad_norm": 1.9900838136672974,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.6783,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.22870211549456831,
|
| 1445 |
+
"eval_loss": 1.010448932647705,
|
| 1446 |
+
"eval_runtime": 32.855,
|
| 1447 |
+
"eval_samples_per_second": 11.231,
|
| 1448 |
+
"eval_steps_per_second": 2.831,
|
| 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": 1.1791525936417997e+17,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|