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 289452128
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c223ee757ded049d10a9381d56fed8bbe5665e6e8de89726f94f95c17ecfa00
|
| 3 |
size 289452128
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 147359892
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fff7a0b1849b2dbfa32527158d2511790180b1bb53cb96f6b4ed1bf75173390
|
| 3 |
size 147359892
|
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 sha256:209e8026ca4cc844398b8092c5a87cc1cb5929231006e3fa2f916275948e0a8f
|
| 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:e1748c065d82adf475a51dba0ff56fd123a17810f07662718ca6d5704be8f9bd
|
| 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": 22.127,
|
| 1090 |
"eval_steps_per_second": 5.547,
|
| 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": 1.5823931694030762,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.11293054771315642,
|
| 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": 22.127,
|
| 1090 |
"eval_steps_per_second": 5.547,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.08526256352343309,
|
| 1095 |
+
"grad_norm": 0.3272818326950073,
|
| 1096 |
+
"learning_rate": 2.6124736842105265e-05,
|
| 1097 |
+
"loss": 1.4871,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.08582721626199886,
|
| 1102 |
+
"grad_norm": 0.32894277572631836,
|
| 1103 |
+
"learning_rate": 2.5591578947368422e-05,
|
| 1104 |
+
"loss": 1.7465,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.08639186900056466,
|
| 1109 |
+
"grad_norm": 0.34903210401535034,
|
| 1110 |
+
"learning_rate": 2.5058421052631576e-05,
|
| 1111 |
+
"loss": 2.1659,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.08695652173913043,
|
| 1116 |
+
"grad_norm": 0.309485524892807,
|
| 1117 |
+
"learning_rate": 2.4525263157894737e-05,
|
| 1118 |
+
"loss": 0.9477,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.08752117447769622,
|
| 1123 |
+
"grad_norm": 0.3330695927143097,
|
| 1124 |
+
"learning_rate": 2.3992105263157894e-05,
|
| 1125 |
+
"loss": 1.5259,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.088085827216262,
|
| 1130 |
+
"grad_norm": 0.3170928657054901,
|
| 1131 |
+
"learning_rate": 2.345894736842105e-05,
|
| 1132 |
+
"loss": 2.1571,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.08865047995482778,
|
| 1137 |
+
"grad_norm": 0.44350671768188477,
|
| 1138 |
+
"learning_rate": 2.292578947368421e-05,
|
| 1139 |
+
"loss": 1.7132,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.08921513269339357,
|
| 1144 |
+
"grad_norm": 0.3251064419746399,
|
| 1145 |
+
"learning_rate": 2.2392631578947366e-05,
|
| 1146 |
+
"loss": 1.7776,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.08977978543195934,
|
| 1151 |
+
"grad_norm": 0.4512995183467865,
|
| 1152 |
+
"learning_rate": 2.1859473684210527e-05,
|
| 1153 |
+
"loss": 1.6642,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.09034443817052512,
|
| 1158 |
+
"grad_norm": 0.9298767447471619,
|
| 1159 |
+
"learning_rate": 2.132631578947368e-05,
|
| 1160 |
+
"loss": 1.8871,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.09090909090909091,
|
| 1165 |
+
"grad_norm": 0.39221644401550293,
|
| 1166 |
+
"learning_rate": 2.0793157894736842e-05,
|
| 1167 |
+
"loss": 1.6345,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.09147374364765669,
|
| 1172 |
+
"grad_norm": 0.4242939054965973,
|
| 1173 |
+
"learning_rate": 2.026e-05,
|
| 1174 |
+
"loss": 1.5644,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.09203839638622248,
|
| 1179 |
+
"grad_norm": 0.39541876316070557,
|
| 1180 |
+
"learning_rate": 1.9726842105263157e-05,
|
| 1181 |
+
"loss": 2.0449,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.09260304912478826,
|
| 1186 |
+
"grad_norm": 0.49802130460739136,
|
| 1187 |
+
"learning_rate": 1.9193684210526314e-05,
|
| 1188 |
+
"loss": 1.7162,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.09316770186335403,
|
| 1193 |
+
"grad_norm": 0.38496336340904236,
|
| 1194 |
+
"learning_rate": 1.866052631578947e-05,
|
| 1195 |
+
"loss": 2.2872,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.09373235460191982,
|
| 1200 |
+
"grad_norm": 0.5159594416618347,
|
| 1201 |
+
"learning_rate": 1.8127368421052632e-05,
|
| 1202 |
+
"loss": 1.8203,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.0942970073404856,
|
| 1207 |
+
"grad_norm": 0.7461097836494446,
|
| 1208 |
+
"learning_rate": 1.759421052631579e-05,
|
| 1209 |
+
"loss": 2.0484,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.09486166007905138,
|
| 1214 |
+
"grad_norm": 0.4127659797668457,
|
| 1215 |
+
"learning_rate": 1.7061052631578947e-05,
|
| 1216 |
+
"loss": 1.8052,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.09542631281761717,
|
| 1221 |
+
"grad_norm": 0.4347990155220032,
|
| 1222 |
+
"learning_rate": 1.6527894736842104e-05,
|
| 1223 |
+
"loss": 1.7951,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.09599096555618294,
|
| 1228 |
+
"grad_norm": 0.4800684154033661,
|
| 1229 |
+
"learning_rate": 1.599473684210526e-05,
|
| 1230 |
+
"loss": 1.5261,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.09655561829474874,
|
| 1235 |
+
"grad_norm": 0.3702009320259094,
|
| 1236 |
+
"learning_rate": 1.546157894736842e-05,
|
| 1237 |
+
"loss": 2.0826,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.09712027103331451,
|
| 1242 |
+
"grad_norm": 0.6166195273399353,
|
| 1243 |
+
"learning_rate": 1.4928421052631576e-05,
|
| 1244 |
+
"loss": 1.437,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.09768492377188029,
|
| 1249 |
+
"grad_norm": 0.5393872857093811,
|
| 1250 |
+
"learning_rate": 1.4395263157894735e-05,
|
| 1251 |
+
"loss": 2.0329,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.09824957651044608,
|
| 1256 |
+
"grad_norm": 0.3947698771953583,
|
| 1257 |
+
"learning_rate": 1.3862105263157895e-05,
|
| 1258 |
+
"loss": 1.9888,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.09881422924901186,
|
| 1263 |
+
"grad_norm": 0.5108495354652405,
|
| 1264 |
+
"learning_rate": 1.3328947368421052e-05,
|
| 1265 |
+
"loss": 1.6187,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.09937888198757763,
|
| 1270 |
+
"grad_norm": 0.42177772521972656,
|
| 1271 |
+
"learning_rate": 1.2795789473684211e-05,
|
| 1272 |
+
"loss": 1.752,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.09994353472614342,
|
| 1277 |
+
"grad_norm": 0.4926985800266266,
|
| 1278 |
+
"learning_rate": 1.2262631578947368e-05,
|
| 1279 |
+
"loss": 2.1683,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.1005081874647092,
|
| 1284 |
+
"grad_norm": 0.46454355120658875,
|
| 1285 |
+
"learning_rate": 1.1729473684210526e-05,
|
| 1286 |
+
"loss": 1.4214,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.10107284020327499,
|
| 1291 |
+
"grad_norm": 0.4612448811531067,
|
| 1292 |
+
"learning_rate": 1.1196315789473683e-05,
|
| 1293 |
+
"loss": 1.7107,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.10163749294184077,
|
| 1298 |
+
"grad_norm": 0.5232647657394409,
|
| 1299 |
+
"learning_rate": 1.066315789473684e-05,
|
| 1300 |
+
"loss": 2.0586,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.10220214568040654,
|
| 1305 |
+
"grad_norm": 0.5285339951515198,
|
| 1306 |
+
"learning_rate": 1.013e-05,
|
| 1307 |
+
"loss": 1.5791,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.10276679841897234,
|
| 1312 |
+
"grad_norm": 0.46414557099342346,
|
| 1313 |
+
"learning_rate": 9.596842105263157e-06,
|
| 1314 |
+
"loss": 1.7391,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.10333145115753811,
|
| 1319 |
+
"grad_norm": 0.5057702660560608,
|
| 1320 |
+
"learning_rate": 9.063684210526316e-06,
|
| 1321 |
+
"loss": 1.7127,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.1038961038961039,
|
| 1326 |
+
"grad_norm": 0.5308021903038025,
|
| 1327 |
+
"learning_rate": 8.530526315789473e-06,
|
| 1328 |
+
"loss": 1.691,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.10446075663466968,
|
| 1333 |
+
"grad_norm": 0.6663089394569397,
|
| 1334 |
+
"learning_rate": 7.99736842105263e-06,
|
| 1335 |
+
"loss": 1.403,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.10502540937323546,
|
| 1340 |
+
"grad_norm": 0.601261556148529,
|
| 1341 |
+
"learning_rate": 7.464210526315788e-06,
|
| 1342 |
+
"loss": 1.5466,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.10559006211180125,
|
| 1347 |
+
"grad_norm": 0.563347578048706,
|
| 1348 |
+
"learning_rate": 6.931052631578947e-06,
|
| 1349 |
+
"loss": 1.389,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.10615471485036702,
|
| 1354 |
+
"grad_norm": 0.6577058434486389,
|
| 1355 |
+
"learning_rate": 6.3978947368421055e-06,
|
| 1356 |
+
"loss": 2.0848,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.1067193675889328,
|
| 1361 |
+
"grad_norm": 1.0290292501449585,
|
| 1362 |
+
"learning_rate": 5.864736842105263e-06,
|
| 1363 |
+
"loss": 1.715,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.10728402032749859,
|
| 1368 |
+
"grad_norm": 1.501333475112915,
|
| 1369 |
+
"learning_rate": 5.33157894736842e-06,
|
| 1370 |
+
"loss": 1.8911,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.10784867306606437,
|
| 1375 |
+
"grad_norm": 0.7974535226821899,
|
| 1376 |
+
"learning_rate": 4.7984210526315785e-06,
|
| 1377 |
+
"loss": 1.6194,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.10841332580463016,
|
| 1382 |
+
"grad_norm": 0.6893588304519653,
|
| 1383 |
+
"learning_rate": 4.265263157894737e-06,
|
| 1384 |
+
"loss": 2.0794,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.10897797854319594,
|
| 1389 |
+
"grad_norm": 0.7431008815765381,
|
| 1390 |
+
"learning_rate": 3.732105263157894e-06,
|
| 1391 |
+
"loss": 1.2137,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.10954263128176171,
|
| 1396 |
+
"grad_norm": 0.8880150318145752,
|
| 1397 |
+
"learning_rate": 3.1989473684210527e-06,
|
| 1398 |
+
"loss": 1.3514,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.1101072840203275,
|
| 1403 |
+
"grad_norm": 1.2837520837783813,
|
| 1404 |
+
"learning_rate": 2.66578947368421e-06,
|
| 1405 |
+
"loss": 1.6779,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.11067193675889328,
|
| 1410 |
+
"grad_norm": 1.7506012916564941,
|
| 1411 |
+
"learning_rate": 2.1326315789473684e-06,
|
| 1412 |
+
"loss": 0.9495,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.11123658949745906,
|
| 1417 |
+
"grad_norm": 1.3716044425964355,
|
| 1418 |
+
"learning_rate": 1.5994736842105264e-06,
|
| 1419 |
+
"loss": 1.1218,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.11180124223602485,
|
| 1424 |
+
"grad_norm": 1.528428077697754,
|
| 1425 |
+
"learning_rate": 1.0663157894736842e-06,
|
| 1426 |
+
"loss": 0.9545,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.11236589497459062,
|
| 1431 |
+
"grad_norm": 1.5911756753921509,
|
| 1432 |
+
"learning_rate": 5.331578947368421e-07,
|
| 1433 |
+
"loss": 1.27,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.11293054771315642,
|
| 1438 |
+
"grad_norm": 2.935549259185791,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 2.7936,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.11293054771315642,
|
| 1445 |
+
"eval_loss": 1.5823931694030762,
|
| 1446 |
+
"eval_runtime": 33.5466,
|
| 1447 |
+
"eval_samples_per_second": 22.238,
|
| 1448 |
+
"eval_steps_per_second": 5.574,
|
| 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": 1.675201553104896e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|