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 645975704
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:62e4063f18b6a6178483461ee3c2c73b90591492fa88dc2f94a22288e985ffed
|
| 3 |
size 645975704
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 328468404
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9a870e252e4b14a1edbcc34c0c46cf9b8122fd5aebb6fd8558f055f3af7002b
|
| 3 |
size 328468404
|
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:ff7ee8dd05f27a3abd346bf717c3803b7ce75a6d25a638ee8eb730382e74fa6c
|
| 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": 7.781,
|
| 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": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.2598340511322021,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.24242424242424243,
|
| 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": 7.781,
|
| 1090 |
"eval_steps_per_second": 1.945,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.18303030303030304,
|
| 1095 |
+
"grad_norm": 0.7512244582176208,
|
| 1096 |
+
"learning_rate": 2.589263157894737e-05,
|
| 1097 |
+
"loss": 1.1194,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.18424242424242424,
|
| 1102 |
+
"grad_norm": 0.6910035610198975,
|
| 1103 |
+
"learning_rate": 2.536421052631579e-05,
|
| 1104 |
+
"loss": 0.841,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.18545454545454546,
|
| 1109 |
+
"grad_norm": 0.6037281155586243,
|
| 1110 |
+
"learning_rate": 2.483578947368421e-05,
|
| 1111 |
+
"loss": 0.6601,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.18666666666666668,
|
| 1116 |
+
"grad_norm": 0.5088821053504944,
|
| 1117 |
+
"learning_rate": 2.430736842105263e-05,
|
| 1118 |
+
"loss": 0.5358,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.18787878787878787,
|
| 1123 |
+
"grad_norm": 0.5077603459358215,
|
| 1124 |
+
"learning_rate": 2.3778947368421052e-05,
|
| 1125 |
+
"loss": 0.7446,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.1890909090909091,
|
| 1130 |
+
"grad_norm": 0.5302112102508545,
|
| 1131 |
+
"learning_rate": 2.3250526315789473e-05,
|
| 1132 |
+
"loss": 1.1613,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.1903030303030303,
|
| 1137 |
+
"grad_norm": 0.5649320483207703,
|
| 1138 |
+
"learning_rate": 2.2722105263157894e-05,
|
| 1139 |
+
"loss": 1.0012,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.19151515151515153,
|
| 1144 |
+
"grad_norm": 0.6187170147895813,
|
| 1145 |
+
"learning_rate": 2.2193684210526316e-05,
|
| 1146 |
+
"loss": 1.3781,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.19272727272727272,
|
| 1151 |
+
"grad_norm": 0.6741657853126526,
|
| 1152 |
+
"learning_rate": 2.1665263157894737e-05,
|
| 1153 |
+
"loss": 1.6947,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.19393939393939394,
|
| 1158 |
+
"grad_norm": 0.6700957417488098,
|
| 1159 |
+
"learning_rate": 2.1136842105263158e-05,
|
| 1160 |
+
"loss": 1.5328,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.19515151515151516,
|
| 1165 |
+
"grad_norm": 0.6595975160598755,
|
| 1166 |
+
"learning_rate": 2.060842105263158e-05,
|
| 1167 |
+
"loss": 1.392,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.19636363636363635,
|
| 1172 |
+
"grad_norm": 0.6863796710968018,
|
| 1173 |
+
"learning_rate": 2.008e-05,
|
| 1174 |
+
"loss": 1.3632,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.19757575757575757,
|
| 1179 |
+
"grad_norm": 0.7188916206359863,
|
| 1180 |
+
"learning_rate": 1.9551578947368422e-05,
|
| 1181 |
+
"loss": 1.2785,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.1987878787878788,
|
| 1186 |
+
"grad_norm": 0.7107079029083252,
|
| 1187 |
+
"learning_rate": 1.9023157894736843e-05,
|
| 1188 |
+
"loss": 1.5611,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.2,
|
| 1193 |
+
"grad_norm": 0.6337575316429138,
|
| 1194 |
+
"learning_rate": 1.849473684210526e-05,
|
| 1195 |
+
"loss": 1.1853,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.2012121212121212,
|
| 1200 |
+
"grad_norm": 0.6911616921424866,
|
| 1201 |
+
"learning_rate": 1.7966315789473686e-05,
|
| 1202 |
+
"loss": 1.4622,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.20242424242424242,
|
| 1207 |
+
"grad_norm": 0.6982558965682983,
|
| 1208 |
+
"learning_rate": 1.7437894736842107e-05,
|
| 1209 |
+
"loss": 1.2948,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.20363636363636364,
|
| 1214 |
+
"grad_norm": 0.6696563959121704,
|
| 1215 |
+
"learning_rate": 1.6909473684210525e-05,
|
| 1216 |
+
"loss": 1.343,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.20484848484848484,
|
| 1221 |
+
"grad_norm": 0.7335880398750305,
|
| 1222 |
+
"learning_rate": 1.638105263157895e-05,
|
| 1223 |
+
"loss": 1.5349,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.20606060606060606,
|
| 1228 |
+
"grad_norm": 0.723656177520752,
|
| 1229 |
+
"learning_rate": 1.5852631578947368e-05,
|
| 1230 |
+
"loss": 1.4002,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.20727272727272728,
|
| 1235 |
+
"grad_norm": 0.6852018237113953,
|
| 1236 |
+
"learning_rate": 1.532421052631579e-05,
|
| 1237 |
+
"loss": 1.2488,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.2084848484848485,
|
| 1242 |
+
"grad_norm": 0.7025154829025269,
|
| 1243 |
+
"learning_rate": 1.4795789473684209e-05,
|
| 1244 |
+
"loss": 1.3095,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.2096969696969697,
|
| 1249 |
+
"grad_norm": 0.7221577763557434,
|
| 1250 |
+
"learning_rate": 1.4267368421052632e-05,
|
| 1251 |
+
"loss": 1.2877,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.2109090909090909,
|
| 1256 |
+
"grad_norm": 0.7556721568107605,
|
| 1257 |
+
"learning_rate": 1.3738947368421053e-05,
|
| 1258 |
+
"loss": 1.4599,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.21212121212121213,
|
| 1263 |
+
"grad_norm": 0.7644419074058533,
|
| 1264 |
+
"learning_rate": 1.3210526315789473e-05,
|
| 1265 |
+
"loss": 1.4277,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.21333333333333335,
|
| 1270 |
+
"grad_norm": 0.7054294347763062,
|
| 1271 |
+
"learning_rate": 1.2682105263157896e-05,
|
| 1272 |
+
"loss": 1.4005,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.21454545454545454,
|
| 1277 |
+
"grad_norm": 0.6766452193260193,
|
| 1278 |
+
"learning_rate": 1.2153684210526315e-05,
|
| 1279 |
+
"loss": 1.2719,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.21575757575757576,
|
| 1284 |
+
"grad_norm": 0.7791915535926819,
|
| 1285 |
+
"learning_rate": 1.1625263157894737e-05,
|
| 1286 |
+
"loss": 1.4941,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.21696969696969698,
|
| 1291 |
+
"grad_norm": 0.7130074501037598,
|
| 1292 |
+
"learning_rate": 1.1096842105263158e-05,
|
| 1293 |
+
"loss": 1.3949,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.21818181818181817,
|
| 1298 |
+
"grad_norm": 0.7784357070922852,
|
| 1299 |
+
"learning_rate": 1.0568421052631579e-05,
|
| 1300 |
+
"loss": 1.5148,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.2193939393939394,
|
| 1305 |
+
"grad_norm": 0.7201549410820007,
|
| 1306 |
+
"learning_rate": 1.004e-05,
|
| 1307 |
+
"loss": 1.4644,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.2206060606060606,
|
| 1312 |
+
"grad_norm": 0.7416413426399231,
|
| 1313 |
+
"learning_rate": 9.511578947368422e-06,
|
| 1314 |
+
"loss": 1.3207,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.22181818181818183,
|
| 1319 |
+
"grad_norm": 0.6673482656478882,
|
| 1320 |
+
"learning_rate": 8.983157894736843e-06,
|
| 1321 |
+
"loss": 1.1482,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.22303030303030302,
|
| 1326 |
+
"grad_norm": 0.7707516551017761,
|
| 1327 |
+
"learning_rate": 8.454736842105263e-06,
|
| 1328 |
+
"loss": 1.3214,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.22424242424242424,
|
| 1333 |
+
"grad_norm": 0.7703214883804321,
|
| 1334 |
+
"learning_rate": 7.926315789473684e-06,
|
| 1335 |
+
"loss": 1.2984,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.22545454545454546,
|
| 1340 |
+
"grad_norm": 0.7766819000244141,
|
| 1341 |
+
"learning_rate": 7.397894736842104e-06,
|
| 1342 |
+
"loss": 1.3543,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.22666666666666666,
|
| 1347 |
+
"grad_norm": 0.691303014755249,
|
| 1348 |
+
"learning_rate": 6.8694736842105265e-06,
|
| 1349 |
+
"loss": 1.1357,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.22787878787878788,
|
| 1354 |
+
"grad_norm": 0.7542006969451904,
|
| 1355 |
+
"learning_rate": 6.341052631578948e-06,
|
| 1356 |
+
"loss": 1.3234,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.2290909090909091,
|
| 1361 |
+
"grad_norm": 0.7104735970497131,
|
| 1362 |
+
"learning_rate": 5.812631578947368e-06,
|
| 1363 |
+
"loss": 1.1579,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.23030303030303031,
|
| 1368 |
+
"grad_norm": 0.76435786485672,
|
| 1369 |
+
"learning_rate": 5.2842105263157896e-06,
|
| 1370 |
+
"loss": 1.2767,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.2315151515151515,
|
| 1375 |
+
"grad_norm": 0.7492122650146484,
|
| 1376 |
+
"learning_rate": 4.755789473684211e-06,
|
| 1377 |
+
"loss": 1.1998,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.23272727272727273,
|
| 1382 |
+
"grad_norm": 0.7435194253921509,
|
| 1383 |
+
"learning_rate": 4.227368421052631e-06,
|
| 1384 |
+
"loss": 1.2984,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.23393939393939395,
|
| 1389 |
+
"grad_norm": 0.793138861656189,
|
| 1390 |
+
"learning_rate": 3.698947368421052e-06,
|
| 1391 |
+
"loss": 1.4859,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.23515151515151514,
|
| 1396 |
+
"grad_norm": 0.7767377495765686,
|
| 1397 |
+
"learning_rate": 3.170526315789474e-06,
|
| 1398 |
+
"loss": 1.1898,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.23636363636363636,
|
| 1403 |
+
"grad_norm": 0.823668360710144,
|
| 1404 |
+
"learning_rate": 2.6421052631578948e-06,
|
| 1405 |
+
"loss": 1.5071,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.23757575757575758,
|
| 1410 |
+
"grad_norm": 0.7883502840995789,
|
| 1411 |
+
"learning_rate": 2.1136842105263157e-06,
|
| 1412 |
+
"loss": 1.2577,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.2387878787878788,
|
| 1417 |
+
"grad_norm": 0.8267744183540344,
|
| 1418 |
+
"learning_rate": 1.585263157894737e-06,
|
| 1419 |
+
"loss": 1.3081,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.24,
|
| 1424 |
+
"grad_norm": 0.8881554007530212,
|
| 1425 |
+
"learning_rate": 1.0568421052631578e-06,
|
| 1426 |
+
"loss": 1.3647,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.2412121212121212,
|
| 1431 |
+
"grad_norm": 0.8271504640579224,
|
| 1432 |
+
"learning_rate": 5.284210526315789e-07,
|
| 1433 |
+
"loss": 1.1263,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.24242424242424243,
|
| 1438 |
+
"grad_norm": 0.80052250623703,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.8633,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.24242424242424243,
|
| 1445 |
+
"eval_loss": 1.2598340511322021,
|
| 1446 |
+
"eval_runtime": 43.893,
|
| 1447 |
+
"eval_samples_per_second": 7.928,
|
| 1448 |
+
"eval_steps_per_second": 1.982,
|
| 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": 7.82038776938496e+16,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|