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 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc2130b605b26e806afc2cf634df1c075a8e8bce334bd0d4b0003b459e2cfe42
|
| 3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1342555602
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c61af562ba42a74b0ed382b589265f4570551610b66d2bc41eaeed3701b8abea
|
| 3 |
size 1342555602
|
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 sha256:2a438d173ecfcc770702d943dae3703f537bd7d05115cfe9fcd81e8173b509ed
|
| 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:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
|
| 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": 11.888,
|
| 1090 |
"eval_steps_per_second": 5.952,
|
| 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": 1.671525478363037,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.45454545454545453,
|
| 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": 11.888,
|
| 1090 |
"eval_steps_per_second": 5.952,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.3431818181818182,
|
| 1095 |
+
"grad_norm": 0.8612778782844543,
|
| 1096 |
+
"learning_rate": 1.7197048550474643e-05,
|
| 1097 |
+
"loss": 1.807,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.34545454545454546,
|
| 1102 |
+
"grad_norm": 1.0314704179763794,
|
| 1103 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 1104 |
+
"loss": 2.0075,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.3477272727272727,
|
| 1109 |
+
"grad_norm": 0.9576540589332581,
|
| 1110 |
+
"learning_rate": 1.5900081996875083e-05,
|
| 1111 |
+
"loss": 1.8654,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.35,
|
| 1116 |
+
"grad_norm": 0.9733042120933533,
|
| 1117 |
+
"learning_rate": 1.526708147705013e-05,
|
| 1118 |
+
"loss": 1.6772,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.3522727272727273,
|
| 1123 |
+
"grad_norm": 0.9843775033950806,
|
| 1124 |
+
"learning_rate": 1.4644660940672627e-05,
|
| 1125 |
+
"loss": 1.8438,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.35454545454545455,
|
| 1130 |
+
"grad_norm": 0.9702544212341309,
|
| 1131 |
+
"learning_rate": 1.4033009983067452e-05,
|
| 1132 |
+
"loss": 1.8467,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.3568181818181818,
|
| 1137 |
+
"grad_norm": 0.9344901442527771,
|
| 1138 |
+
"learning_rate": 1.3432314919041478e-05,
|
| 1139 |
+
"loss": 1.7625,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.35909090909090907,
|
| 1144 |
+
"grad_norm": 0.8675273060798645,
|
| 1145 |
+
"learning_rate": 1.2842758726130283e-05,
|
| 1146 |
+
"loss": 1.6983,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.3613636363636364,
|
| 1151 |
+
"grad_norm": 0.8406621217727661,
|
| 1152 |
+
"learning_rate": 1.22645209888614e-05,
|
| 1153 |
+
"loss": 1.7905,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.36363636363636365,
|
| 1158 |
+
"grad_norm": 0.8631937503814697,
|
| 1159 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 1160 |
+
"loss": 1.7407,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.3659090909090909,
|
| 1165 |
+
"grad_norm": 0.8949780464172363,
|
| 1166 |
+
"learning_rate": 1.1142701927151456e-05,
|
| 1167 |
+
"loss": 1.7007,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.36818181818181817,
|
| 1172 |
+
"grad_norm": 0.8787016272544861,
|
| 1173 |
+
"learning_rate": 1.0599462319663905e-05,
|
| 1174 |
+
"loss": 1.7203,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.3704545454545455,
|
| 1179 |
+
"grad_norm": 0.9685916900634766,
|
| 1180 |
+
"learning_rate": 1.006822449763537e-05,
|
| 1181 |
+
"loss": 1.7624,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.37272727272727274,
|
| 1186 |
+
"grad_norm": 0.8896955847740173,
|
| 1187 |
+
"learning_rate": 9.549150281252633e-06,
|
| 1188 |
+
"loss": 1.7665,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.375,
|
| 1193 |
+
"grad_norm": 0.8174881935119629,
|
| 1194 |
+
"learning_rate": 9.042397785550405e-06,
|
| 1195 |
+
"loss": 1.6385,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.37727272727272726,
|
| 1200 |
+
"grad_norm": 0.844082772731781,
|
| 1201 |
+
"learning_rate": 8.548121372247918e-06,
|
| 1202 |
+
"loss": 1.585,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.3795454545454545,
|
| 1207 |
+
"grad_norm": 0.9889433979988098,
|
| 1208 |
+
"learning_rate": 8.066471602728803e-06,
|
| 1209 |
+
"loss": 1.5663,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.38181818181818183,
|
| 1214 |
+
"grad_norm": 1.087799310684204,
|
| 1215 |
+
"learning_rate": 7.597595192178702e-06,
|
| 1216 |
+
"loss": 1.4998,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.3840909090909091,
|
| 1221 |
+
"grad_norm": 0.9920996427536011,
|
| 1222 |
+
"learning_rate": 7.1416349648943894e-06,
|
| 1223 |
+
"loss": 1.6414,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.38636363636363635,
|
| 1228 |
+
"grad_norm": 0.9823297262191772,
|
| 1229 |
+
"learning_rate": 6.698729810778065e-06,
|
| 1230 |
+
"loss": 1.688,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.3886363636363636,
|
| 1235 |
+
"grad_norm": 1.0681322813034058,
|
| 1236 |
+
"learning_rate": 6.269014643030213e-06,
|
| 1237 |
+
"loss": 1.6283,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.39090909090909093,
|
| 1242 |
+
"grad_norm": 0.996666431427002,
|
| 1243 |
+
"learning_rate": 5.852620357053651e-06,
|
| 1244 |
+
"loss": 1.4533,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.3931818181818182,
|
| 1249 |
+
"grad_norm": 1.0531445741653442,
|
| 1250 |
+
"learning_rate": 5.449673790581611e-06,
|
| 1251 |
+
"loss": 1.6793,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.39545454545454545,
|
| 1256 |
+
"grad_norm": 1.1200153827667236,
|
| 1257 |
+
"learning_rate": 5.060297685041659e-06,
|
| 1258 |
+
"loss": 1.5885,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.3977272727272727,
|
| 1263 |
+
"grad_norm": 1.1026841402053833,
|
| 1264 |
+
"learning_rate": 4.684610648167503e-06,
|
| 1265 |
+
"loss": 1.4877,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.4,
|
| 1270 |
+
"grad_norm": 1.2321683168411255,
|
| 1271 |
+
"learning_rate": 4.322727117869951e-06,
|
| 1272 |
+
"loss": 1.7277,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.4022727272727273,
|
| 1277 |
+
"grad_norm": 1.1422961950302124,
|
| 1278 |
+
"learning_rate": 3.974757327377981e-06,
|
| 1279 |
+
"loss": 1.5716,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.40454545454545454,
|
| 1284 |
+
"grad_norm": 1.1938626766204834,
|
| 1285 |
+
"learning_rate": 3.6408072716606346e-06,
|
| 1286 |
+
"loss": 1.4974,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.4068181818181818,
|
| 1291 |
+
"grad_norm": 1.0967926979064941,
|
| 1292 |
+
"learning_rate": 3.3209786751399187e-06,
|
| 1293 |
+
"loss": 1.4771,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.4090909090909091,
|
| 1298 |
+
"grad_norm": 1.366172194480896,
|
| 1299 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 1300 |
+
"loss": 1.7274,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.4113636363636364,
|
| 1305 |
+
"grad_norm": 1.2525289058685303,
|
| 1306 |
+
"learning_rate": 2.724071220034158e-06,
|
| 1307 |
+
"loss": 1.4662,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.41363636363636364,
|
| 1312 |
+
"grad_norm": 1.4062180519104004,
|
| 1313 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 1314 |
+
"loss": 1.6317,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.4159090909090909,
|
| 1319 |
+
"grad_norm": 1.5819109678268433,
|
| 1320 |
+
"learning_rate": 2.1847622018482283e-06,
|
| 1321 |
+
"loss": 1.7772,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.41818181818181815,
|
| 1326 |
+
"grad_norm": 1.6406415700912476,
|
| 1327 |
+
"learning_rate": 1.9369152030840556e-06,
|
| 1328 |
+
"loss": 1.5917,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.42045454545454547,
|
| 1333 |
+
"grad_norm": 1.506263256072998,
|
| 1334 |
+
"learning_rate": 1.70370868554659e-06,
|
| 1335 |
+
"loss": 1.5047,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.42272727272727273,
|
| 1340 |
+
"grad_norm": 1.6531805992126465,
|
| 1341 |
+
"learning_rate": 1.4852136862001764e-06,
|
| 1342 |
+
"loss": 1.5347,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.425,
|
| 1347 |
+
"grad_norm": 1.6337155103683472,
|
| 1348 |
+
"learning_rate": 1.2814967607382432e-06,
|
| 1349 |
+
"loss": 1.3556,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.42727272727272725,
|
| 1354 |
+
"grad_norm": 1.7176258563995361,
|
| 1355 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 1356 |
+
"loss": 1.5636,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.42954545454545456,
|
| 1361 |
+
"grad_norm": 1.8075064420700073,
|
| 1362 |
+
"learning_rate": 9.186408276168013e-07,
|
| 1363 |
+
"loss": 1.4563,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.4318181818181818,
|
| 1368 |
+
"grad_norm": 1.7502872943878174,
|
| 1369 |
+
"learning_rate": 7.596123493895991e-07,
|
| 1370 |
+
"loss": 1.2788,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.4340909090909091,
|
| 1375 |
+
"grad_norm": 1.9488650560379028,
|
| 1376 |
+
"learning_rate": 6.15582970243117e-07,
|
| 1377 |
+
"loss": 1.3266,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.43636363636363634,
|
| 1382 |
+
"grad_norm": 2.198270320892334,
|
| 1383 |
+
"learning_rate": 4.865965629214819e-07,
|
| 1384 |
+
"loss": 1.4447,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.43863636363636366,
|
| 1389 |
+
"grad_norm": 2.048422336578369,
|
| 1390 |
+
"learning_rate": 3.7269241793390085e-07,
|
| 1391 |
+
"loss": 1.5203,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.4409090909090909,
|
| 1396 |
+
"grad_norm": 2.4291017055511475,
|
| 1397 |
+
"learning_rate": 2.7390523158633554e-07,
|
| 1398 |
+
"loss": 1.6495,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.4431818181818182,
|
| 1403 |
+
"grad_norm": 2.916109085083008,
|
| 1404 |
+
"learning_rate": 1.9026509541272275e-07,
|
| 1405 |
+
"loss": 1.7544,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.44545454545454544,
|
| 1410 |
+
"grad_norm": 3.0741372108459473,
|
| 1411 |
+
"learning_rate": 1.2179748700879012e-07,
|
| 1412 |
+
"loss": 1.8354,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.44772727272727275,
|
| 1417 |
+
"grad_norm": 3.8066229820251465,
|
| 1418 |
+
"learning_rate": 6.852326227130834e-08,
|
| 1419 |
+
"loss": 2.0545,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.45,
|
| 1424 |
+
"grad_norm": 4.246571063995361,
|
| 1425 |
+
"learning_rate": 3.04586490452119e-08,
|
| 1426 |
+
"loss": 2.0616,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.45227272727272727,
|
| 1431 |
+
"grad_norm": 6.185179710388184,
|
| 1432 |
+
"learning_rate": 7.615242180436522e-09,
|
| 1433 |
+
"loss": 1.8495,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.45454545454545453,
|
| 1438 |
+
"grad_norm": 7.912553310394287,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 2.5258,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.45454545454545453,
|
| 1445 |
+
"eval_loss": 1.671525478363037,
|
| 1446 |
+
"eval_runtime": 62.4768,
|
| 1447 |
+
"eval_samples_per_second": 11.86,
|
| 1448 |
+
"eval_steps_per_second": 5.938,
|
| 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": 3.0434261451197645e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|