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 1157746040
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:809e3acd6500b225640befb80ada0867ff0014057ed77395131fa24cf1e1b9a7
|
| 3 |
size 1157746040
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 588699796
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa4e30f5acb96185faec5aaae32a13f3c056961441f5cc5ce7862dcfde006d03
|
| 3 |
size 588699796
|
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 sha256:650079aad0f4b18cb833b2e9db06a769db0486ca9bf00a1498c4fc7ea4ffb01d
|
| 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 sha256:3709ad194ceda6ee92d3d2c8f2dd5203a40bedaa701af97b45dc02564222704e
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 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": 4.311,
|
| 1090 |
"eval_steps_per_second": 1.084,
|
| 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": 1.
|
| 1121 |
"train_batch_size": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.979677438735962,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.5161290322580645,
|
| 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": 4.311,
|
| 1090 |
"eval_steps_per_second": 1.084,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.3896774193548387,
|
| 1095 |
+
"grad_norm": 0.6236698031425476,
|
| 1096 |
+
"learning_rate": 2.597e-05,
|
| 1097 |
+
"loss": 2.7676,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.39225806451612905,
|
| 1102 |
+
"grad_norm": 0.6113293170928955,
|
| 1103 |
+
"learning_rate": 2.544e-05,
|
| 1104 |
+
"loss": 2.7639,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.39483870967741935,
|
| 1109 |
+
"grad_norm": 0.610192060470581,
|
| 1110 |
+
"learning_rate": 2.4909999999999997e-05,
|
| 1111 |
+
"loss": 2.5103,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.39741935483870966,
|
| 1116 |
+
"grad_norm": 0.6351131200790405,
|
| 1117 |
+
"learning_rate": 2.438e-05,
|
| 1118 |
+
"loss": 2.8813,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.4,
|
| 1123 |
+
"grad_norm": 0.6906495690345764,
|
| 1124 |
+
"learning_rate": 2.3849999999999997e-05,
|
| 1125 |
+
"loss": 2.8643,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.40258064516129033,
|
| 1130 |
+
"grad_norm": 0.7632659673690796,
|
| 1131 |
+
"learning_rate": 2.3319999999999997e-05,
|
| 1132 |
+
"loss": 2.8429,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.40516129032258064,
|
| 1137 |
+
"grad_norm": 0.6306165456771851,
|
| 1138 |
+
"learning_rate": 2.279e-05,
|
| 1139 |
+
"loss": 2.7581,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.40774193548387094,
|
| 1144 |
+
"grad_norm": 0.5983100533485413,
|
| 1145 |
+
"learning_rate": 2.2259999999999997e-05,
|
| 1146 |
+
"loss": 2.8474,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.4103225806451613,
|
| 1151 |
+
"grad_norm": 0.6067503094673157,
|
| 1152 |
+
"learning_rate": 2.173e-05,
|
| 1153 |
+
"loss": 2.8127,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.4129032258064516,
|
| 1158 |
+
"grad_norm": 0.5717953443527222,
|
| 1159 |
+
"learning_rate": 2.1199999999999997e-05,
|
| 1160 |
+
"loss": 2.7154,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.4154838709677419,
|
| 1165 |
+
"grad_norm": 0.6313890218734741,
|
| 1166 |
+
"learning_rate": 2.067e-05,
|
| 1167 |
+
"loss": 2.9207,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.4180645161290323,
|
| 1172 |
+
"grad_norm": 0.6323216557502747,
|
| 1173 |
+
"learning_rate": 2.014e-05,
|
| 1174 |
+
"loss": 3.0632,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.4206451612903226,
|
| 1179 |
+
"grad_norm": 0.5878114104270935,
|
| 1180 |
+
"learning_rate": 1.9609999999999997e-05,
|
| 1181 |
+
"loss": 2.6803,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.4232258064516129,
|
| 1186 |
+
"grad_norm": 0.6011391282081604,
|
| 1187 |
+
"learning_rate": 1.908e-05,
|
| 1188 |
+
"loss": 2.761,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.4258064516129032,
|
| 1193 |
+
"grad_norm": 0.6402645111083984,
|
| 1194 |
+
"learning_rate": 1.8549999999999997e-05,
|
| 1195 |
+
"loss": 2.8095,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.42838709677419357,
|
| 1200 |
+
"grad_norm": 0.6337774991989136,
|
| 1201 |
+
"learning_rate": 1.802e-05,
|
| 1202 |
+
"loss": 2.8637,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.4309677419354839,
|
| 1207 |
+
"grad_norm": 0.6133434772491455,
|
| 1208 |
+
"learning_rate": 1.749e-05,
|
| 1209 |
+
"loss": 2.7507,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.4335483870967742,
|
| 1214 |
+
"grad_norm": 0.6644814610481262,
|
| 1215 |
+
"learning_rate": 1.696e-05,
|
| 1216 |
+
"loss": 2.8863,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.43612903225806454,
|
| 1221 |
+
"grad_norm": 0.6810536980628967,
|
| 1222 |
+
"learning_rate": 1.643e-05,
|
| 1223 |
+
"loss": 3.0598,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.43870967741935485,
|
| 1228 |
+
"grad_norm": 0.644666850566864,
|
| 1229 |
+
"learning_rate": 1.5899999999999997e-05,
|
| 1230 |
+
"loss": 2.6853,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.44129032258064516,
|
| 1235 |
+
"grad_norm": 0.8024281859397888,
|
| 1236 |
+
"learning_rate": 1.537e-05,
|
| 1237 |
+
"loss": 3.0717,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.44387096774193546,
|
| 1242 |
+
"grad_norm": 0.7148249745368958,
|
| 1243 |
+
"learning_rate": 1.4839999999999999e-05,
|
| 1244 |
+
"loss": 2.8716,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.4464516129032258,
|
| 1249 |
+
"grad_norm": 0.6904494762420654,
|
| 1250 |
+
"learning_rate": 1.4309999999999999e-05,
|
| 1251 |
+
"loss": 2.8221,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.44903225806451613,
|
| 1256 |
+
"grad_norm": 0.7332553863525391,
|
| 1257 |
+
"learning_rate": 1.378e-05,
|
| 1258 |
+
"loss": 3.0164,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.45161290322580644,
|
| 1263 |
+
"grad_norm": 0.820591151714325,
|
| 1264 |
+
"learning_rate": 1.3249999999999999e-05,
|
| 1265 |
+
"loss": 3.0185,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.4541935483870968,
|
| 1270 |
+
"grad_norm": 0.7899701595306396,
|
| 1271 |
+
"learning_rate": 1.272e-05,
|
| 1272 |
+
"loss": 2.7191,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.4567741935483871,
|
| 1277 |
+
"grad_norm": 0.8323290944099426,
|
| 1278 |
+
"learning_rate": 1.219e-05,
|
| 1279 |
+
"loss": 3.1204,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.4593548387096774,
|
| 1284 |
+
"grad_norm": 0.8330437541007996,
|
| 1285 |
+
"learning_rate": 1.1659999999999998e-05,
|
| 1286 |
+
"loss": 3.191,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.4619354838709677,
|
| 1291 |
+
"grad_norm": 0.8948123455047607,
|
| 1292 |
+
"learning_rate": 1.1129999999999998e-05,
|
| 1293 |
+
"loss": 3.1088,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.4645161290322581,
|
| 1298 |
+
"grad_norm": 0.8483486175537109,
|
| 1299 |
+
"learning_rate": 1.0599999999999998e-05,
|
| 1300 |
+
"loss": 2.7368,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.4670967741935484,
|
| 1305 |
+
"grad_norm": 0.8846768140792847,
|
| 1306 |
+
"learning_rate": 1.007e-05,
|
| 1307 |
+
"loss": 2.8681,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.4696774193548387,
|
| 1312 |
+
"grad_norm": 0.9632049798965454,
|
| 1313 |
+
"learning_rate": 9.54e-06,
|
| 1314 |
+
"loss": 2.7557,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.472258064516129,
|
| 1319 |
+
"grad_norm": 0.9614686965942383,
|
| 1320 |
+
"learning_rate": 9.01e-06,
|
| 1321 |
+
"loss": 2.8339,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.47483870967741937,
|
| 1326 |
+
"grad_norm": 0.9410024285316467,
|
| 1327 |
+
"learning_rate": 8.48e-06,
|
| 1328 |
+
"loss": 2.8687,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.4774193548387097,
|
| 1333 |
+
"grad_norm": 1.2544703483581543,
|
| 1334 |
+
"learning_rate": 7.949999999999998e-06,
|
| 1335 |
+
"loss": 2.8427,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.48,
|
| 1340 |
+
"grad_norm": 1.054551124572754,
|
| 1341 |
+
"learning_rate": 7.419999999999999e-06,
|
| 1342 |
+
"loss": 3.0275,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.48258064516129034,
|
| 1347 |
+
"grad_norm": 0.9934067130088806,
|
| 1348 |
+
"learning_rate": 6.89e-06,
|
| 1349 |
+
"loss": 2.8259,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.48516129032258065,
|
| 1354 |
+
"grad_norm": 1.0902060270309448,
|
| 1355 |
+
"learning_rate": 6.36e-06,
|
| 1356 |
+
"loss": 2.925,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.48774193548387096,
|
| 1361 |
+
"grad_norm": 1.249941110610962,
|
| 1362 |
+
"learning_rate": 5.829999999999999e-06,
|
| 1363 |
+
"loss": 3.2027,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.49032258064516127,
|
| 1368 |
+
"grad_norm": 1.44179105758667,
|
| 1369 |
+
"learning_rate": 5.299999999999999e-06,
|
| 1370 |
+
"loss": 3.1991,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.49290322580645163,
|
| 1375 |
+
"grad_norm": 1.3627164363861084,
|
| 1376 |
+
"learning_rate": 4.77e-06,
|
| 1377 |
+
"loss": 3.0373,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.49548387096774194,
|
| 1382 |
+
"grad_norm": 1.419520378112793,
|
| 1383 |
+
"learning_rate": 4.24e-06,
|
| 1384 |
+
"loss": 3.1531,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.49806451612903224,
|
| 1389 |
+
"grad_norm": 1.5665879249572754,
|
| 1390 |
+
"learning_rate": 3.7099999999999996e-06,
|
| 1391 |
+
"loss": 3.0034,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.5006451612903225,
|
| 1396 |
+
"grad_norm": 1.668223261833191,
|
| 1397 |
+
"learning_rate": 3.18e-06,
|
| 1398 |
+
"loss": 2.8947,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.5032258064516129,
|
| 1403 |
+
"grad_norm": 2.2476518154144287,
|
| 1404 |
+
"learning_rate": 2.6499999999999996e-06,
|
| 1405 |
+
"loss": 3.6002,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.5058064516129033,
|
| 1410 |
+
"grad_norm": 2.826122760772705,
|
| 1411 |
+
"learning_rate": 2.12e-06,
|
| 1412 |
+
"loss": 3.2501,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.5083870967741936,
|
| 1417 |
+
"grad_norm": 2.145322561264038,
|
| 1418 |
+
"learning_rate": 1.59e-06,
|
| 1419 |
+
"loss": 3.3192,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.5109677419354839,
|
| 1424 |
+
"grad_norm": 3.014976978302002,
|
| 1425 |
+
"learning_rate": 1.06e-06,
|
| 1426 |
+
"loss": 3.1429,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.5135483870967742,
|
| 1431 |
+
"grad_norm": 3.8677399158477783,
|
| 1432 |
+
"learning_rate": 5.3e-07,
|
| 1433 |
+
"loss": 3.3806,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.5161290322580645,
|
| 1438 |
+
"grad_norm": 9.486526489257812,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 4.3408,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.5161290322580645,
|
| 1445 |
+
"eval_loss": 2.979677438735962,
|
| 1446 |
+
"eval_runtime": 38.3406,
|
| 1447 |
+
"eval_samples_per_second": 4.251,
|
| 1448 |
+
"eval_steps_per_second": 1.069,
|
| 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": 1.676900394199941e+17,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|