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 522227376
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db6527b92998eb4d97dd8557188c97c3bc38aaaf6b2fb98c8ae47b4010f9044d
|
| 3 |
size 522227376
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 265476436
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8af17623d3dd2edd153ed0eb4854180aa2d9a74c124355e2f897be02df9df7b
|
| 3 |
size 265476436
|
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 sha256:94778b2c0a4fafa19b9b9664a360321d3d7bcf837bddaa94e0390eb59a308100
|
| 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:c47edf82128c3f034f21204d4b9ce5c76cd3269748ce31061b148a0a389d049d
|
| 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": 9.995,
|
| 1090 |
"eval_steps_per_second": 2.499,
|
| 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": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.867233395576477,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.016857010409203926,
|
| 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": 9.995,
|
| 1090 |
"eval_steps_per_second": 2.499,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.012727042858948965,
|
| 1095 |
+
"grad_norm": 1.444331407546997,
|
| 1096 |
+
"learning_rate": 2.5944210526315793e-05,
|
| 1097 |
+
"loss": 3.8494,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.012811327910994985,
|
| 1102 |
+
"grad_norm": 1.4190081357955933,
|
| 1103 |
+
"learning_rate": 2.5414736842105266e-05,
|
| 1104 |
+
"loss": 3.6972,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.012895612963041005,
|
| 1109 |
+
"grad_norm": 1.3863047361373901,
|
| 1110 |
+
"learning_rate": 2.4885263157894737e-05,
|
| 1111 |
+
"loss": 3.593,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.012979898015087024,
|
| 1116 |
+
"grad_norm": 1.3513926267623901,
|
| 1117 |
+
"learning_rate": 2.4355789473684214e-05,
|
| 1118 |
+
"loss": 3.436,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.013064183067133044,
|
| 1123 |
+
"grad_norm": 1.2380362749099731,
|
| 1124 |
+
"learning_rate": 2.3826315789473684e-05,
|
| 1125 |
+
"loss": 3.2587,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.013148468119179064,
|
| 1130 |
+
"grad_norm": 1.4090365171432495,
|
| 1131 |
+
"learning_rate": 2.3296842105263158e-05,
|
| 1132 |
+
"loss": 3.367,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.013232753171225083,
|
| 1137 |
+
"grad_norm": 1.2374507188796997,
|
| 1138 |
+
"learning_rate": 2.2767368421052635e-05,
|
| 1139 |
+
"loss": 3.4684,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.013317038223271103,
|
| 1144 |
+
"grad_norm": 1.3896780014038086,
|
| 1145 |
+
"learning_rate": 2.2237894736842105e-05,
|
| 1146 |
+
"loss": 3.9113,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.013401323275317123,
|
| 1151 |
+
"grad_norm": 1.332416296005249,
|
| 1152 |
+
"learning_rate": 2.170842105263158e-05,
|
| 1153 |
+
"loss": 3.7664,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.013485608327363141,
|
| 1158 |
+
"grad_norm": 1.4905543327331543,
|
| 1159 |
+
"learning_rate": 2.1178947368421053e-05,
|
| 1160 |
+
"loss": 4.2563,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.013569893379409162,
|
| 1165 |
+
"grad_norm": 1.4605516195297241,
|
| 1166 |
+
"learning_rate": 2.0649473684210527e-05,
|
| 1167 |
+
"loss": 3.8242,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.013654178431455182,
|
| 1172 |
+
"grad_norm": 1.4748574495315552,
|
| 1173 |
+
"learning_rate": 2.0120000000000004e-05,
|
| 1174 |
+
"loss": 4.0375,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.0137384634835012,
|
| 1179 |
+
"grad_norm": 1.5476000308990479,
|
| 1180 |
+
"learning_rate": 1.9590526315789474e-05,
|
| 1181 |
+
"loss": 3.7669,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.01382274853554722,
|
| 1186 |
+
"grad_norm": 1.3919553756713867,
|
| 1187 |
+
"learning_rate": 1.9061052631578948e-05,
|
| 1188 |
+
"loss": 3.3237,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.01390703358759324,
|
| 1193 |
+
"grad_norm": 1.464743971824646,
|
| 1194 |
+
"learning_rate": 1.8531578947368422e-05,
|
| 1195 |
+
"loss": 3.8191,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.01399131863963926,
|
| 1200 |
+
"grad_norm": 1.5848177671432495,
|
| 1201 |
+
"learning_rate": 1.8002105263157896e-05,
|
| 1202 |
+
"loss": 3.9749,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.01407560369168528,
|
| 1207 |
+
"grad_norm": 1.6681814193725586,
|
| 1208 |
+
"learning_rate": 1.747263157894737e-05,
|
| 1209 |
+
"loss": 4.2865,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.0141598887437313,
|
| 1214 |
+
"grad_norm": 1.6060197353363037,
|
| 1215 |
+
"learning_rate": 1.6943157894736843e-05,
|
| 1216 |
+
"loss": 3.3702,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.01424417379577732,
|
| 1221 |
+
"grad_norm": 1.5922913551330566,
|
| 1222 |
+
"learning_rate": 1.6413684210526317e-05,
|
| 1223 |
+
"loss": 3.9925,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.014328458847823338,
|
| 1228 |
+
"grad_norm": 1.6466814279556274,
|
| 1229 |
+
"learning_rate": 1.588421052631579e-05,
|
| 1230 |
+
"loss": 3.4887,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.014412743899869358,
|
| 1235 |
+
"grad_norm": 1.7543516159057617,
|
| 1236 |
+
"learning_rate": 1.5354736842105264e-05,
|
| 1237 |
+
"loss": 4.0886,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.014497028951915378,
|
| 1242 |
+
"grad_norm": 1.7576175928115845,
|
| 1243 |
+
"learning_rate": 1.4825263157894736e-05,
|
| 1244 |
+
"loss": 3.769,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.014581314003961397,
|
| 1249 |
+
"grad_norm": 1.6161974668502808,
|
| 1250 |
+
"learning_rate": 1.4295789473684212e-05,
|
| 1251 |
+
"loss": 3.7848,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.014665599056007417,
|
| 1256 |
+
"grad_norm": 1.7880433797836304,
|
| 1257 |
+
"learning_rate": 1.3766315789473686e-05,
|
| 1258 |
+
"loss": 3.5251,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.014749884108053437,
|
| 1263 |
+
"grad_norm": 1.7841137647628784,
|
| 1264 |
+
"learning_rate": 1.3236842105263158e-05,
|
| 1265 |
+
"loss": 3.9346,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.014834169160099456,
|
| 1270 |
+
"grad_norm": 1.919546365737915,
|
| 1271 |
+
"learning_rate": 1.2707368421052633e-05,
|
| 1272 |
+
"loss": 4.1778,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.014918454212145476,
|
| 1277 |
+
"grad_norm": 1.8676812648773193,
|
| 1278 |
+
"learning_rate": 1.2177894736842107e-05,
|
| 1279 |
+
"loss": 3.8695,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.015002739264191496,
|
| 1284 |
+
"grad_norm": 1.832812786102295,
|
| 1285 |
+
"learning_rate": 1.1648421052631579e-05,
|
| 1286 |
+
"loss": 4.0394,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.015087024316237515,
|
| 1291 |
+
"grad_norm": 2.0502195358276367,
|
| 1292 |
+
"learning_rate": 1.1118947368421053e-05,
|
| 1293 |
+
"loss": 3.9268,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.015171309368283535,
|
| 1298 |
+
"grad_norm": 2.0106148719787598,
|
| 1299 |
+
"learning_rate": 1.0589473684210526e-05,
|
| 1300 |
+
"loss": 4.2192,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.015255594420329555,
|
| 1305 |
+
"grad_norm": 2.064776659011841,
|
| 1306 |
+
"learning_rate": 1.0060000000000002e-05,
|
| 1307 |
+
"loss": 3.9229,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.015339879472375573,
|
| 1312 |
+
"grad_norm": 2.251138687133789,
|
| 1313 |
+
"learning_rate": 9.530526315789474e-06,
|
| 1314 |
+
"loss": 3.9887,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.015424164524421594,
|
| 1319 |
+
"grad_norm": 2.255735397338867,
|
| 1320 |
+
"learning_rate": 9.001052631578948e-06,
|
| 1321 |
+
"loss": 4.02,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.015508449576467614,
|
| 1326 |
+
"grad_norm": 2.071152687072754,
|
| 1327 |
+
"learning_rate": 8.471578947368422e-06,
|
| 1328 |
+
"loss": 3.7057,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.015592734628513634,
|
| 1333 |
+
"grad_norm": 2.0596232414245605,
|
| 1334 |
+
"learning_rate": 7.942105263157895e-06,
|
| 1335 |
+
"loss": 3.7983,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.015677019680559654,
|
| 1340 |
+
"grad_norm": 2.190840721130371,
|
| 1341 |
+
"learning_rate": 7.412631578947368e-06,
|
| 1342 |
+
"loss": 3.9793,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.01576130473260567,
|
| 1347 |
+
"grad_norm": 2.3367197513580322,
|
| 1348 |
+
"learning_rate": 6.883157894736843e-06,
|
| 1349 |
+
"loss": 4.3535,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.01584558978465169,
|
| 1354 |
+
"grad_norm": 2.380443811416626,
|
| 1355 |
+
"learning_rate": 6.3536842105263166e-06,
|
| 1356 |
+
"loss": 3.8499,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.01592987483669771,
|
| 1361 |
+
"grad_norm": 2.041156530380249,
|
| 1362 |
+
"learning_rate": 5.8242105263157895e-06,
|
| 1363 |
+
"loss": 3.6364,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.01601415988874373,
|
| 1368 |
+
"grad_norm": 2.2828075885772705,
|
| 1369 |
+
"learning_rate": 5.294736842105263e-06,
|
| 1370 |
+
"loss": 4.0151,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.01609844494078975,
|
| 1375 |
+
"grad_norm": 2.1917965412139893,
|
| 1376 |
+
"learning_rate": 4.765263157894737e-06,
|
| 1377 |
+
"loss": 3.9636,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.016182729992835772,
|
| 1382 |
+
"grad_norm": 2.317061424255371,
|
| 1383 |
+
"learning_rate": 4.235789473684211e-06,
|
| 1384 |
+
"loss": 3.4895,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.01626701504488179,
|
| 1389 |
+
"grad_norm": 2.4780666828155518,
|
| 1390 |
+
"learning_rate": 3.706315789473684e-06,
|
| 1391 |
+
"loss": 3.2654,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.01635130009692781,
|
| 1396 |
+
"grad_norm": 2.7359607219696045,
|
| 1397 |
+
"learning_rate": 3.1768421052631583e-06,
|
| 1398 |
+
"loss": 3.6544,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.01643558514897383,
|
| 1403 |
+
"grad_norm": 2.5973706245422363,
|
| 1404 |
+
"learning_rate": 2.6473684210526316e-06,
|
| 1405 |
+
"loss": 3.615,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.01651987020101985,
|
| 1410 |
+
"grad_norm": 2.7825827598571777,
|
| 1411 |
+
"learning_rate": 2.1178947368421054e-06,
|
| 1412 |
+
"loss": 3.2319,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.01660415525306587,
|
| 1417 |
+
"grad_norm": 2.764317750930786,
|
| 1418 |
+
"learning_rate": 1.5884210526315791e-06,
|
| 1419 |
+
"loss": 3.2517,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.01668844030511189,
|
| 1424 |
+
"grad_norm": 2.831258535385132,
|
| 1425 |
+
"learning_rate": 1.0589473684210527e-06,
|
| 1426 |
+
"loss": 2.949,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.01677272535715791,
|
| 1431 |
+
"grad_norm": 3.2517249584198,
|
| 1432 |
+
"learning_rate": 5.294736842105263e-07,
|
| 1433 |
+
"loss": 3.4868,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.016857010409203926,
|
| 1438 |
+
"grad_norm": 4.0189619064331055,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 3.4463,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.016857010409203926,
|
| 1445 |
+
"eval_loss": 1.867233395576477,
|
| 1446 |
+
"eval_runtime": 498.9005,
|
| 1447 |
+
"eval_samples_per_second": 10.014,
|
| 1448 |
+
"eval_steps_per_second": 2.504,
|
| 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": 6.6422040428544e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|