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 113284112
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea082eac372fff81ac14bb4fdbac846c846ded09a07efb0ee3eda6522777e9ed
|
| 3 |
size 113284112
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 57846868
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcdbce684187f76d573e60d985e1e82ec35c97f99987c86317753d6f3ff7d22c
|
| 3 |
size 57846868
|
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 sha256:1363a368a375a84fcf4e1a2ab7099bc7f24ac0da08f6379d64fb69d0b2f211d8
|
| 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:a27b052646dcb561cbd68156c30bd466ce59bda64cf3c8eba9c3c1113af9827c
|
| 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": 35.078,
|
| 1090 |
"eval_steps_per_second": 8.777,
|
| 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": 2.997969388961792,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.2759572266298724,
|
| 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": 35.078,
|
| 1090 |
"eval_steps_per_second": 8.777,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.20834770610555364,
|
| 1095 |
+
"grad_norm": 3.158139228820801,
|
| 1096 |
+
"learning_rate": 4.995066821070679e-05,
|
| 1097 |
+
"loss": 3.6353,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.209727492238703,
|
| 1102 |
+
"grad_norm": 3.5997750759124756,
|
| 1103 |
+
"learning_rate": 4.980286753286195e-05,
|
| 1104 |
+
"loss": 3.5989,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.21110727837185236,
|
| 1109 |
+
"grad_norm": 3.574474334716797,
|
| 1110 |
+
"learning_rate": 4.9557181268217227e-05,
|
| 1111 |
+
"loss": 3.4982,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.21248706450500174,
|
| 1116 |
+
"grad_norm": 2.906959056854248,
|
| 1117 |
+
"learning_rate": 4.9214579028215776e-05,
|
| 1118 |
+
"loss": 3.3847,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.21386685063815108,
|
| 1123 |
+
"grad_norm": 2.554720640182495,
|
| 1124 |
+
"learning_rate": 4.877641290737884e-05,
|
| 1125 |
+
"loss": 3.3131,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.21524663677130046,
|
| 1130 |
+
"grad_norm": 2.099410057067871,
|
| 1131 |
+
"learning_rate": 4.8244412147206284e-05,
|
| 1132 |
+
"loss": 3.2781,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.2166264229044498,
|
| 1137 |
+
"grad_norm": 1.690164566040039,
|
| 1138 |
+
"learning_rate": 4.762067631165049e-05,
|
| 1139 |
+
"loss": 3.2736,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.21800620903759918,
|
| 1144 |
+
"grad_norm": 1.4456684589385986,
|
| 1145 |
+
"learning_rate": 4.690766700109659e-05,
|
| 1146 |
+
"loss": 3.1785,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.21938599517074853,
|
| 1151 |
+
"grad_norm": 1.255626916885376,
|
| 1152 |
+
"learning_rate": 4.610819813755038e-05,
|
| 1153 |
+
"loss": 2.9921,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.2207657813038979,
|
| 1158 |
+
"grad_norm": 1.102941870689392,
|
| 1159 |
+
"learning_rate": 4.522542485937369e-05,
|
| 1160 |
+
"loss": 3.2609,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.22214556743704725,
|
| 1165 |
+
"grad_norm": 1.0562005043029785,
|
| 1166 |
+
"learning_rate": 4.426283106939474e-05,
|
| 1167 |
+
"loss": 3.011,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.22352535357019662,
|
| 1172 |
+
"grad_norm": 1.1416147947311401,
|
| 1173 |
+
"learning_rate": 4.3224215685535294e-05,
|
| 1174 |
+
"loss": 2.9283,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.22490513970334597,
|
| 1179 |
+
"grad_norm": 1.1108524799346924,
|
| 1180 |
+
"learning_rate": 4.211367764821722e-05,
|
| 1181 |
+
"loss": 3.2749,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.22628492583649534,
|
| 1186 |
+
"grad_norm": 1.2051870822906494,
|
| 1187 |
+
"learning_rate": 4.093559974371725e-05,
|
| 1188 |
+
"loss": 3.0462,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.22766471196964472,
|
| 1193 |
+
"grad_norm": 1.1099305152893066,
|
| 1194 |
+
"learning_rate": 3.969463130731183e-05,
|
| 1195 |
+
"loss": 3.1848,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.22904449810279406,
|
| 1200 |
+
"grad_norm": 0.9574990272521973,
|
| 1201 |
+
"learning_rate": 3.8395669874474915e-05,
|
| 1202 |
+
"loss": 3.0329,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.23042428423594344,
|
| 1207 |
+
"grad_norm": 1.0350350141525269,
|
| 1208 |
+
"learning_rate": 3.704384185254288e-05,
|
| 1209 |
+
"loss": 2.9134,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.23180407036909279,
|
| 1214 |
+
"grad_norm": 0.8609461784362793,
|
| 1215 |
+
"learning_rate": 3.564448228912682e-05,
|
| 1216 |
+
"loss": 2.9771,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.23318385650224216,
|
| 1221 |
+
"grad_norm": 1.0324912071228027,
|
| 1222 |
+
"learning_rate": 3.4203113817116957e-05,
|
| 1223 |
+
"loss": 2.9351,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.2345636426353915,
|
| 1228 |
+
"grad_norm": 0.9436797499656677,
|
| 1229 |
+
"learning_rate": 3.272542485937369e-05,
|
| 1230 |
+
"loss": 2.9729,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.23594342876854088,
|
| 1235 |
+
"grad_norm": 0.931715726852417,
|
| 1236 |
+
"learning_rate": 3.121724717912138e-05,
|
| 1237 |
+
"loss": 3.2443,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.23732321490169023,
|
| 1242 |
+
"grad_norm": 0.9500223398208618,
|
| 1243 |
+
"learning_rate": 2.9684532864643122e-05,
|
| 1244 |
+
"loss": 2.9819,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.2387030010348396,
|
| 1249 |
+
"grad_norm": 0.875689685344696,
|
| 1250 |
+
"learning_rate": 2.8133330839107608e-05,
|
| 1251 |
+
"loss": 2.9361,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.24008278716798895,
|
| 1256 |
+
"grad_norm": 0.891899824142456,
|
| 1257 |
+
"learning_rate": 2.656976298823284e-05,
|
| 1258 |
+
"loss": 2.9722,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.24146257330113832,
|
| 1263 |
+
"grad_norm": 1.091869592666626,
|
| 1264 |
+
"learning_rate": 2.5e-05,
|
| 1265 |
+
"loss": 3.1387,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.2428423594342877,
|
| 1270 |
+
"grad_norm": 0.9385702013969421,
|
| 1271 |
+
"learning_rate": 2.3430237011767167e-05,
|
| 1272 |
+
"loss": 2.9316,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.24422214556743704,
|
| 1277 |
+
"grad_norm": 0.9347511529922485,
|
| 1278 |
+
"learning_rate": 2.186666916089239e-05,
|
| 1279 |
+
"loss": 2.9608,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.24560193170058642,
|
| 1284 |
+
"grad_norm": 0.9398484230041504,
|
| 1285 |
+
"learning_rate": 2.031546713535688e-05,
|
| 1286 |
+
"loss": 2.9103,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.24698171783373576,
|
| 1291 |
+
"grad_norm": 0.9190600514411926,
|
| 1292 |
+
"learning_rate": 1.8782752820878634e-05,
|
| 1293 |
+
"loss": 3.1082,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.24836150396688514,
|
| 1298 |
+
"grad_norm": 1.0726330280303955,
|
| 1299 |
+
"learning_rate": 1.7274575140626318e-05,
|
| 1300 |
+
"loss": 3.232,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.24974129010003449,
|
| 1305 |
+
"grad_norm": 0.964190661907196,
|
| 1306 |
+
"learning_rate": 1.5796886182883053e-05,
|
| 1307 |
+
"loss": 3.0588,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.25112107623318386,
|
| 1312 |
+
"grad_norm": 0.9404963850975037,
|
| 1313 |
+
"learning_rate": 1.4355517710873184e-05,
|
| 1314 |
+
"loss": 2.9696,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.25250086236633323,
|
| 1319 |
+
"grad_norm": 1.1561006307601929,
|
| 1320 |
+
"learning_rate": 1.2956158147457115e-05,
|
| 1321 |
+
"loss": 3.163,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.25388064849948255,
|
| 1326 |
+
"grad_norm": 1.0033360719680786,
|
| 1327 |
+
"learning_rate": 1.1604330125525079e-05,
|
| 1328 |
+
"loss": 2.8147,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.2552604346326319,
|
| 1333 |
+
"grad_norm": 1.0727239847183228,
|
| 1334 |
+
"learning_rate": 1.0305368692688174e-05,
|
| 1335 |
+
"loss": 3.1405,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.2566402207657813,
|
| 1340 |
+
"grad_norm": 1.106379747390747,
|
| 1341 |
+
"learning_rate": 9.064400256282757e-06,
|
| 1342 |
+
"loss": 3.0658,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.2580200068989307,
|
| 1347 |
+
"grad_norm": 0.97951740026474,
|
| 1348 |
+
"learning_rate": 7.886322351782783e-06,
|
| 1349 |
+
"loss": 3.1416,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.25939979303208005,
|
| 1354 |
+
"grad_norm": 1.2267470359802246,
|
| 1355 |
+
"learning_rate": 6.775784314464717e-06,
|
| 1356 |
+
"loss": 3.0927,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.26077957916522937,
|
| 1361 |
+
"grad_norm": 1.2311291694641113,
|
| 1362 |
+
"learning_rate": 5.737168930605272e-06,
|
| 1363 |
+
"loss": 2.9075,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.26215936529837874,
|
| 1368 |
+
"grad_norm": 1.1488878726959229,
|
| 1369 |
+
"learning_rate": 4.7745751406263165e-06,
|
| 1370 |
+
"loss": 3.0904,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.2635391514315281,
|
| 1375 |
+
"grad_norm": 1.127191424369812,
|
| 1376 |
+
"learning_rate": 3.891801862449629e-06,
|
| 1377 |
+
"loss": 3.0047,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.2649189375646775,
|
| 1382 |
+
"grad_norm": 1.446352481842041,
|
| 1383 |
+
"learning_rate": 3.092332998903416e-06,
|
| 1384 |
+
"loss": 2.971,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.2662987236978268,
|
| 1389 |
+
"grad_norm": 1.3929004669189453,
|
| 1390 |
+
"learning_rate": 2.379323688349516e-06,
|
| 1391 |
+
"loss": 3.026,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.2676785098309762,
|
| 1396 |
+
"grad_norm": 1.512418508529663,
|
| 1397 |
+
"learning_rate": 1.7555878527937164e-06,
|
| 1398 |
+
"loss": 2.9506,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.26905829596412556,
|
| 1403 |
+
"grad_norm": 1.65766441822052,
|
| 1404 |
+
"learning_rate": 1.2235870926211619e-06,
|
| 1405 |
+
"loss": 2.9575,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.27043808209727493,
|
| 1410 |
+
"grad_norm": 1.5741119384765625,
|
| 1411 |
+
"learning_rate": 7.854209717842231e-07,
|
| 1412 |
+
"loss": 2.9769,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.2718178682304243,
|
| 1417 |
+
"grad_norm": 1.678270697593689,
|
| 1418 |
+
"learning_rate": 4.4281873178278475e-07,
|
| 1419 |
+
"loss": 3.0054,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.2731976543635736,
|
| 1424 |
+
"grad_norm": 1.7038488388061523,
|
| 1425 |
+
"learning_rate": 1.9713246713805588e-07,
|
| 1426 |
+
"loss": 3.0776,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.274577440496723,
|
| 1431 |
+
"grad_norm": 2.050671100616455,
|
| 1432 |
+
"learning_rate": 4.9331789293211026e-08,
|
| 1433 |
+
"loss": 3.1415,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.2759572266298724,
|
| 1438 |
+
"grad_norm": 2.6361677646636963,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 3.1783,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.2759572266298724,
|
| 1445 |
+
"eval_loss": 2.997969388961792,
|
| 1446 |
+
"eval_runtime": 69.6597,
|
| 1447 |
+
"eval_samples_per_second": 35.056,
|
| 1448 |
+
"eval_steps_per_second": 8.771,
|
| 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": 1.055175217250304e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|