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 12589528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e484f46d0648448a4a3fb51b6dfd3725340e8b511fed8c2bfefc132004a2fd0
|
| 3 |
size 12589528
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6448570
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10feff8d7863b7e5e778121b4563472fe1dac72828382ad73fdf3ca271b0595f
|
| 3 |
size 6448570
|
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 sha256:7a393f7f6135a2e075bf721eb2007891d2963440bf507ca27371a805bc18f7c1
|
| 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":
|
| 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": 285.77,
|
| 1090 |
"eval_steps_per_second": 71.443,
|
| 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": 16.426185607910156,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.07982438635002993,
|
| 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": 285.77,
|
| 1090 |
"eval_steps_per_second": 71.443,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.0602674116942726,
|
| 1095 |
+
"grad_norm": 12100.32421875,
|
| 1096 |
+
"learning_rate": 1.553232954407171e-05,
|
| 1097 |
+
"loss": 46.1682,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.06066653362602275,
|
| 1102 |
+
"grad_norm": 17816.08984375,
|
| 1103 |
+
"learning_rate": 1.4938160786375572e-05,
|
| 1104 |
+
"loss": 48.948,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.0610656555577729,
|
| 1109 |
+
"grad_norm": 38728.3046875,
|
| 1110 |
+
"learning_rate": 1.435357758543015e-05,
|
| 1111 |
+
"loss": 54.0206,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.06146477748952305,
|
| 1116 |
+
"grad_norm": 34616.15234375,
|
| 1117 |
+
"learning_rate": 1.3778739760445552e-05,
|
| 1118 |
+
"loss": 54.2833,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.0618638994212732,
|
| 1123 |
+
"grad_norm": 27462.8984375,
|
| 1124 |
+
"learning_rate": 1.3213804466343421e-05,
|
| 1125 |
+
"loss": 57.2774,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.06226302135302335,
|
| 1130 |
+
"grad_norm": 23525.93359375,
|
| 1131 |
+
"learning_rate": 1.2658926150792322e-05,
|
| 1132 |
+
"loss": 57.5012,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.0626621432847735,
|
| 1137 |
+
"grad_norm": 27339.947265625,
|
| 1138 |
+
"learning_rate": 1.2114256511983274e-05,
|
| 1139 |
+
"loss": 55.4658,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.06306126521652365,
|
| 1144 |
+
"grad_norm": 16805.66015625,
|
| 1145 |
+
"learning_rate": 1.157994445715706e-05,
|
| 1146 |
+
"loss": 56.5597,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.0634603871482738,
|
| 1151 |
+
"grad_norm": 25625.26953125,
|
| 1152 |
+
"learning_rate": 1.1056136061894384e-05,
|
| 1153 |
+
"loss": 52.3354,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.06385950908002394,
|
| 1158 |
+
"grad_norm": 89494.90625,
|
| 1159 |
+
"learning_rate": 1.0542974530180327e-05,
|
| 1160 |
+
"loss": 60.3594,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.06425863101177409,
|
| 1165 |
+
"grad_norm": 28573.064453125,
|
| 1166 |
+
"learning_rate": 1.0040600155253765e-05,
|
| 1167 |
+
"loss": 50.8484,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.06465775294352424,
|
| 1172 |
+
"grad_norm": 54717.48046875,
|
| 1173 |
+
"learning_rate": 9.549150281252633e-06,
|
| 1174 |
+
"loss": 57.2542,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.0650568748752744,
|
| 1179 |
+
"grad_norm": 179563.671875,
|
| 1180 |
+
"learning_rate": 9.068759265665384e-06,
|
| 1181 |
+
"loss": 51.5404,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.06545599680702455,
|
| 1186 |
+
"grad_norm": 44480.33203125,
|
| 1187 |
+
"learning_rate": 8.599558442598998e-06,
|
| 1188 |
+
"loss": 61.301,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.0658551187387747,
|
| 1193 |
+
"grad_norm": 50463.93359375,
|
| 1194 |
+
"learning_rate": 8.141676086873572e-06,
|
| 1195 |
+
"loss": 55.3502,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.06625424067052485,
|
| 1200 |
+
"grad_norm": 20146.619140625,
|
| 1201 |
+
"learning_rate": 7.695237378953223e-06,
|
| 1202 |
+
"loss": 55.6622,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.066653362602275,
|
| 1207 |
+
"grad_norm": 77468.3359375,
|
| 1208 |
+
"learning_rate": 7.260364370723044e-06,
|
| 1209 |
+
"loss": 61.5627,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.06705248453402514,
|
| 1214 |
+
"grad_norm": 65669.296875,
|
| 1215 |
+
"learning_rate": 6.837175952121306e-06,
|
| 1216 |
+
"loss": 60.0044,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.06745160646577529,
|
| 1221 |
+
"grad_norm": 100907.78125,
|
| 1222 |
+
"learning_rate": 6.425787818636131e-06,
|
| 1223 |
+
"loss": 56.207,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.06785072839752544,
|
| 1228 |
+
"grad_norm": 189922.9375,
|
| 1229 |
+
"learning_rate": 6.026312439675552e-06,
|
| 1230 |
+
"loss": 59.0817,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.0682498503292756,
|
| 1235 |
+
"grad_norm": 64130.74609375,
|
| 1236 |
+
"learning_rate": 5.6388590278194096e-06,
|
| 1237 |
+
"loss": 59.6253,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.06864897226102575,
|
| 1242 |
+
"grad_norm": 56074.6328125,
|
| 1243 |
+
"learning_rate": 5.263533508961827e-06,
|
| 1244 |
+
"loss": 56.2686,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.0690480941927759,
|
| 1249 |
+
"grad_norm": 58847.08984375,
|
| 1250 |
+
"learning_rate": 4.900438493352055e-06,
|
| 1251 |
+
"loss": 64.4589,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.06944721612452605,
|
| 1256 |
+
"grad_norm": 39088.37890625,
|
| 1257 |
+
"learning_rate": 4.549673247541875e-06,
|
| 1258 |
+
"loss": 49.3413,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.06984633805627619,
|
| 1263 |
+
"grad_norm": 71529.453125,
|
| 1264 |
+
"learning_rate": 4.2113336672471245e-06,
|
| 1265 |
+
"loss": 69.4396,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.07024545998802634,
|
| 1270 |
+
"grad_norm": 82603.328125,
|
| 1271 |
+
"learning_rate": 3.885512251130763e-06,
|
| 1272 |
+
"loss": 66.9742,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.07064458191977649,
|
| 1277 |
+
"grad_norm": 63139.46484375,
|
| 1278 |
+
"learning_rate": 3.5722980755146517e-06,
|
| 1279 |
+
"loss": 62.6972,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.07104370385152664,
|
| 1284 |
+
"grad_norm": 60760.25,
|
| 1285 |
+
"learning_rate": 3.271776770026963e-06,
|
| 1286 |
+
"loss": 75.4641,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.07144282578327679,
|
| 1291 |
+
"grad_norm": 57640.85546875,
|
| 1292 |
+
"learning_rate": 2.9840304941919415e-06,
|
| 1293 |
+
"loss": 61.6008,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.07184194771502694,
|
| 1298 |
+
"grad_norm": 54318.703125,
|
| 1299 |
+
"learning_rate": 2.7091379149682685e-06,
|
| 1300 |
+
"loss": 66.0331,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.0722410696467771,
|
| 1305 |
+
"grad_norm": 148162.5,
|
| 1306 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 1307 |
+
"loss": 85.2826,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.07264019157852725,
|
| 1312 |
+
"grad_norm": 75190.171875,
|
| 1313 |
+
"learning_rate": 2.1982109232821178e-06,
|
| 1314 |
+
"loss": 70.0884,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.07303931351027738,
|
| 1319 |
+
"grad_norm": 121845.421875,
|
| 1320 |
+
"learning_rate": 1.962316193157593e-06,
|
| 1321 |
+
"loss": 67.787,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.07343843544202754,
|
| 1326 |
+
"grad_norm": 80806.6640625,
|
| 1327 |
+
"learning_rate": 1.7395544861325718e-06,
|
| 1328 |
+
"loss": 66.3449,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.07383755737377769,
|
| 1333 |
+
"grad_norm": 145304.078125,
|
| 1334 |
+
"learning_rate": 1.5299867030334814e-06,
|
| 1335 |
+
"loss": 71.2909,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.07423667930552784,
|
| 1340 |
+
"grad_norm": 71253.890625,
|
| 1341 |
+
"learning_rate": 1.333670137599713e-06,
|
| 1342 |
+
"loss": 73.8471,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.07463580123727799,
|
| 1347 |
+
"grad_norm": 123051.7265625,
|
| 1348 |
+
"learning_rate": 1.1506584608200367e-06,
|
| 1349 |
+
"loss": 70.9921,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.07503492316902814,
|
| 1354 |
+
"grad_norm": 240493.984375,
|
| 1355 |
+
"learning_rate": 9.810017062595322e-07,
|
| 1356 |
+
"loss": 71.6231,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.0754340451007783,
|
| 1361 |
+
"grad_norm": 113903.9296875,
|
| 1362 |
+
"learning_rate": 8.247462563808817e-07,
|
| 1363 |
+
"loss": 76.6697,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.07583316703252843,
|
| 1368 |
+
"grad_norm": 64319.34375,
|
| 1369 |
+
"learning_rate": 6.819348298638839e-07,
|
| 1370 |
+
"loss": 84.118,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.07623228896427858,
|
| 1375 |
+
"grad_norm": 79210.8828125,
|
| 1376 |
+
"learning_rate": 5.526064699265753e-07,
|
| 1377 |
+
"loss": 81.1656,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.07663141089602873,
|
| 1382 |
+
"grad_norm": 109979.9375,
|
| 1383 |
+
"learning_rate": 4.367965336512403e-07,
|
| 1384 |
+
"loss": 68.1978,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.07703053282777889,
|
| 1389 |
+
"grad_norm": 123544.0,
|
| 1390 |
+
"learning_rate": 3.3453668231809286e-07,
|
| 1391 |
+
"loss": 57.9494,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.07742965475952904,
|
| 1396 |
+
"grad_norm": 51323.3515625,
|
| 1397 |
+
"learning_rate": 2.458548727494292e-07,
|
| 1398 |
+
"loss": 64.8058,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.07782877669127919,
|
| 1403 |
+
"grad_norm": 65579.828125,
|
| 1404 |
+
"learning_rate": 1.7077534966650766e-07,
|
| 1405 |
+
"loss": 79.9243,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.07822789862302934,
|
| 1410 |
+
"grad_norm": 133177.75,
|
| 1411 |
+
"learning_rate": 1.0931863906127327e-07,
|
| 1412 |
+
"loss": 75.3729,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.07862702055477949,
|
| 1417 |
+
"grad_norm": 90115.7265625,
|
| 1418 |
+
"learning_rate": 6.150154258476315e-08,
|
| 1419 |
+
"loss": 86.5352,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.07902614248652963,
|
| 1424 |
+
"grad_norm": 145049.390625,
|
| 1425 |
+
"learning_rate": 2.7337132953697554e-08,
|
| 1426 |
+
"loss": 93.1018,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.07942526441827978,
|
| 1431 |
+
"grad_norm": 85661.875,
|
| 1432 |
+
"learning_rate": 6.834750376549792e-09,
|
| 1433 |
+
"loss": 86.8992,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.07982438635002993,
|
| 1438 |
+
"grad_norm": 61471.18359375,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 137.2803,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.07982438635002993,
|
| 1445 |
+
"eval_loss": 16.426185607910156,
|
| 1446 |
+
"eval_runtime": 14.799,
|
| 1447 |
+
"eval_samples_per_second": 285.155,
|
| 1448 |
+
"eval_steps_per_second": 71.289,
|
| 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": 1887280167911424.0,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|