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 1001465824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5733fd572a041502fd0f75b54fee4ddeec0a77d42518c275e38825d19812baa9
|
| 3 |
size 1001465824
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 509176980
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41c0d45e892b0c1ccd73d13415e605977578fc34d02e69d0d25733dfa68394d4
|
| 3 |
size 509176980
|
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 sha256:4cb8a67fd05d3419c045fb4224f49b4687799b59240231eb4e285b2a2ccff3c9
|
| 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 sha256:7df65c8f4b426598b0abc4173b1983dcf7411aee63ea4061d980eae7a1af2363
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 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": 1.623,
|
| 1090 |
"eval_steps_per_second": 0.409,
|
| 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": 0.10804670304059982,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.8403361344537815,
|
| 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": 1.623,
|
| 1090 |
"eval_steps_per_second": 0.409,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.634453781512605,
|
| 1095 |
+
"grad_norm": 0.9199975728988647,
|
| 1096 |
+
"learning_rate": 1.7085562498478883e-05,
|
| 1097 |
+
"loss": 0.0577,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.6386554621848739,
|
| 1102 |
+
"grad_norm": 0.38636523485183716,
|
| 1103 |
+
"learning_rate": 1.6431976865013128e-05,
|
| 1104 |
+
"loss": 0.039,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.6428571428571429,
|
| 1109 |
+
"grad_norm": 0.2471998631954193,
|
| 1110 |
+
"learning_rate": 1.5788935343973164e-05,
|
| 1111 |
+
"loss": 0.0295,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.6470588235294118,
|
| 1116 |
+
"grad_norm": 0.1585417538881302,
|
| 1117 |
+
"learning_rate": 1.5156613736490108e-05,
|
| 1118 |
+
"loss": 0.0266,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.6512605042016807,
|
| 1123 |
+
"grad_norm": 0.06748829782009125,
|
| 1124 |
+
"learning_rate": 1.4535184912977763e-05,
|
| 1125 |
+
"loss": 0.0251,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.6554621848739496,
|
| 1130 |
+
"grad_norm": 0.06747037917375565,
|
| 1131 |
+
"learning_rate": 1.3924818765871553e-05,
|
| 1132 |
+
"loss": 0.0306,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.6596638655462185,
|
| 1137 |
+
"grad_norm": 0.07344760745763779,
|
| 1138 |
+
"learning_rate": 1.3325682163181601e-05,
|
| 1139 |
+
"loss": 0.0268,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.6638655462184874,
|
| 1144 |
+
"grad_norm": 0.08845263719558716,
|
| 1145 |
+
"learning_rate": 1.2737938902872767e-05,
|
| 1146 |
+
"loss": 0.0297,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.6680672268907563,
|
| 1151 |
+
"grad_norm": 0.10601629316806793,
|
| 1152 |
+
"learning_rate": 1.2161749668083823e-05,
|
| 1153 |
+
"loss": 0.0277,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.6722689075630253,
|
| 1158 |
+
"grad_norm": 0.2715802788734436,
|
| 1159 |
+
"learning_rate": 1.159727198319836e-05,
|
| 1160 |
+
"loss": 0.0282,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.6764705882352942,
|
| 1165 |
+
"grad_norm": 0.06532086431980133,
|
| 1166 |
+
"learning_rate": 1.1044660170779142e-05,
|
| 1167 |
+
"loss": 0.0314,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.680672268907563,
|
| 1172 |
+
"grad_norm": 0.05947871133685112,
|
| 1173 |
+
"learning_rate": 1.0504065309377897e-05,
|
| 1174 |
+
"loss": 0.0366,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.6848739495798319,
|
| 1179 |
+
"grad_norm": 0.05421306937932968,
|
| 1180 |
+
"learning_rate": 9.97563519223192e-06,
|
| 1181 |
+
"loss": 0.0324,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.6890756302521008,
|
| 1186 |
+
"grad_norm": 0.056551430374383926,
|
| 1187 |
+
"learning_rate": 9.459514286858898e-06,
|
| 1188 |
+
"loss": 0.0326,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.6932773109243697,
|
| 1193 |
+
"grad_norm": 0.05368305742740631,
|
| 1194 |
+
"learning_rate": 8.95584369556093e-06,
|
| 1195 |
+
"loss": 0.0364,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.6974789915966386,
|
| 1200 |
+
"grad_norm": 0.05321598798036575,
|
| 1201 |
+
"learning_rate": 8.464761116848546e-06,
|
| 1202 |
+
"loss": 0.0368,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.7016806722689075,
|
| 1207 |
+
"grad_norm": 0.05156972259283066,
|
| 1208 |
+
"learning_rate": 7.986400807795349e-06,
|
| 1209 |
+
"loss": 0.0284,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.7058823529411765,
|
| 1214 |
+
"grad_norm": 0.04861694574356079,
|
| 1215 |
+
"learning_rate": 7.520893547333436e-06,
|
| 1216 |
+
"loss": 0.0319,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.7100840336134454,
|
| 1221 |
+
"grad_norm": 0.05087107792496681,
|
| 1222 |
+
"learning_rate": 7.068366600499744e-06,
|
| 1223 |
+
"loss": 0.0319,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.7142857142857143,
|
| 1228 |
+
"grad_norm": 0.045963507145643234,
|
| 1229 |
+
"learning_rate": 6.6289436836431076e-06,
|
| 1230 |
+
"loss": 0.0351,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.7184873949579832,
|
| 1235 |
+
"grad_norm": 0.0428263358771801,
|
| 1236 |
+
"learning_rate": 6.20274493060135e-06,
|
| 1237 |
+
"loss": 0.0327,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.7226890756302521,
|
| 1242 |
+
"grad_norm": 0.048912014812231064,
|
| 1243 |
+
"learning_rate": 5.789886859858009e-06,
|
| 1244 |
+
"loss": 0.0373,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.726890756302521,
|
| 1249 |
+
"grad_norm": 0.04380197450518608,
|
| 1250 |
+
"learning_rate": 5.3904823426872605e-06,
|
| 1251 |
+
"loss": 0.0398,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.7310924369747899,
|
| 1256 |
+
"grad_norm": 0.04742840304970741,
|
| 1257 |
+
"learning_rate": 5.004640572296062e-06,
|
| 1258 |
+
"loss": 0.0375,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.7352941176470589,
|
| 1263 |
+
"grad_norm": 0.04380054399371147,
|
| 1264 |
+
"learning_rate": 4.632467033971838e-06,
|
| 1265 |
+
"loss": 0.0413,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.7394957983193278,
|
| 1270 |
+
"grad_norm": 0.03939207270741463,
|
| 1271 |
+
"learning_rate": 4.274063476243839e-06,
|
| 1272 |
+
"loss": 0.0362,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.7436974789915967,
|
| 1277 |
+
"grad_norm": 0.04470328986644745,
|
| 1278 |
+
"learning_rate": 3.929527883066117e-06,
|
| 1279 |
+
"loss": 0.0517,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.7478991596638656,
|
| 1284 |
+
"grad_norm": 0.045310597866773605,
|
| 1285 |
+
"learning_rate": 3.5989544470296595e-06,
|
| 1286 |
+
"loss": 0.0505,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.7521008403361344,
|
| 1291 |
+
"grad_norm": 0.04871699959039688,
|
| 1292 |
+
"learning_rate": 3.282433543611136e-06,
|
| 1293 |
+
"loss": 0.0554,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.7563025210084033,
|
| 1298 |
+
"grad_norm": 0.050524331629276276,
|
| 1299 |
+
"learning_rate": 2.980051706465095e-06,
|
| 1300 |
+
"loss": 0.0583,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.7605042016806722,
|
| 1305 |
+
"grad_norm": 0.05556650459766388,
|
| 1306 |
+
"learning_rate": 2.691891603766556e-06,
|
| 1307 |
+
"loss": 0.0576,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.7647058823529411,
|
| 1312 |
+
"grad_norm": 0.06121022626757622,
|
| 1313 |
+
"learning_rate": 2.4180320156103298e-06,
|
| 1314 |
+
"loss": 0.0746,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.7689075630252101,
|
| 1319 |
+
"grad_norm": 0.06415616720914841,
|
| 1320 |
+
"learning_rate": 2.158547812473352e-06,
|
| 1321 |
+
"loss": 0.073,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.773109243697479,
|
| 1326 |
+
"grad_norm": 0.07119602710008621,
|
| 1327 |
+
"learning_rate": 1.9135099347458293e-06,
|
| 1328 |
+
"loss": 0.0778,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.7773109243697479,
|
| 1333 |
+
"grad_norm": 0.08688875287771225,
|
| 1334 |
+
"learning_rate": 1.6829853733368294e-06,
|
| 1335 |
+
"loss": 0.0791,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.7815126050420168,
|
| 1340 |
+
"grad_norm": 0.09698156267404556,
|
| 1341 |
+
"learning_rate": 1.4670371513596842e-06,
|
| 1342 |
+
"loss": 0.0907,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.7857142857142857,
|
| 1347 |
+
"grad_norm": 0.11040172725915909,
|
| 1348 |
+
"learning_rate": 1.2657243069020402e-06,
|
| 1349 |
+
"loss": 0.0904,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.7899159663865546,
|
| 1354 |
+
"grad_norm": 0.13165590167045593,
|
| 1355 |
+
"learning_rate": 1.0791018768854855e-06,
|
| 1356 |
+
"loss": 0.1196,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.7941176470588235,
|
| 1361 |
+
"grad_norm": 0.14704085886478424,
|
| 1362 |
+
"learning_rate": 9.072208820189698e-07,
|
| 1363 |
+
"loss": 0.1128,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.7983193277310925,
|
| 1368 |
+
"grad_norm": 0.16108661890029907,
|
| 1369 |
+
"learning_rate": 7.501283128502722e-07,
|
| 1370 |
+
"loss": 0.1301,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.8025210084033614,
|
| 1375 |
+
"grad_norm": 0.19200128316879272,
|
| 1376 |
+
"learning_rate": 6.07867116919233e-07,
|
| 1377 |
+
"loss": 0.1524,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.8067226890756303,
|
| 1382 |
+
"grad_norm": 0.20474770665168762,
|
| 1383 |
+
"learning_rate": 4.804761870163643e-07,
|
| 1384 |
+
"loss": 0.1627,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.8109243697478992,
|
| 1389 |
+
"grad_norm": 0.20066982507705688,
|
| 1390 |
+
"learning_rate": 3.6799035054990215e-07,
|
| 1391 |
+
"loss": 0.1791,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.8151260504201681,
|
| 1396 |
+
"grad_norm": 0.18784397840499878,
|
| 1397 |
+
"learning_rate": 2.704403600243721e-07,
|
| 1398 |
+
"loss": 0.2186,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.819327731092437,
|
| 1403 |
+
"grad_norm": 0.17218390107154846,
|
| 1404 |
+
"learning_rate": 1.878528846331584e-07,
|
| 1405 |
+
"loss": 0.2742,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.8235294117647058,
|
| 1410 |
+
"grad_norm": 0.17353031039237976,
|
| 1411 |
+
"learning_rate": 1.202505029674006e-07,
|
| 1412 |
+
"loss": 0.3294,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.8277310924369747,
|
| 1417 |
+
"grad_norm": 0.2161194235086441,
|
| 1418 |
+
"learning_rate": 6.765169684323947e-08,
|
| 1419 |
+
"loss": 0.428,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.8319327731092437,
|
| 1424 |
+
"grad_norm": 0.2484060823917389,
|
| 1425 |
+
"learning_rate": 3.007084624906731e-08,
|
| 1426 |
+
"loss": 0.6874,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.8361344537815126,
|
| 1431 |
+
"grad_norm": 0.3053840696811676,
|
| 1432 |
+
"learning_rate": 7.518225414204771e-09,
|
| 1433 |
+
"loss": 0.981,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.8403361344537815,
|
| 1438 |
+
"grad_norm": 0.340952605009079,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.0018,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.8403361344537815,
|
| 1445 |
+
"eval_loss": 0.10804670304059982,
|
| 1446 |
+
"eval_runtime": 226.7217,
|
| 1447 |
+
"eval_samples_per_second": 1.769,
|
| 1448 |
+
"eval_steps_per_second": 0.445,
|
| 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": 5.15206425870336e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|