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:ae9ec60f16edfd89f42f68519072b89ba19fabb31d731736f32b67c6bcd94fb3
|
| 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:c3c0e2d12fb3923641bfd867761ce1a654edd2c4355e624db6926c058d9f1af1
|
| 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:fee0353af67f64bbe6ef9ed7ab40fb3815f458ff8ea74533429be88b75734378
|
| 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:a3e88ef6a2716260516e17223973d6a3b0a4c88bf12c72ed47e80e6f2a6782fd
|
| 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": 6.06,
|
| 1090 |
"eval_steps_per_second": 1.515,
|
| 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": 0.00452503003180027,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.007590564927794751,
|
| 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": 6.06,
|
| 1090 |
"eval_steps_per_second": 1.515,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.005730876520485037,
|
| 1095 |
+
"grad_norm": 0.1738223284482956,
|
| 1096 |
+
"learning_rate": 2.589263157894737e-05,
|
| 1097 |
+
"loss": 0.0216,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.005768829345124011,
|
| 1102 |
+
"grad_norm": 0.07341416925191879,
|
| 1103 |
+
"learning_rate": 2.536421052631579e-05,
|
| 1104 |
+
"loss": 0.0026,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.005806782169762985,
|
| 1109 |
+
"grad_norm": 0.18592970073223114,
|
| 1110 |
+
"learning_rate": 2.483578947368421e-05,
|
| 1111 |
+
"loss": 0.0166,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.005844734994401958,
|
| 1116 |
+
"grad_norm": 0.22769445180892944,
|
| 1117 |
+
"learning_rate": 2.430736842105263e-05,
|
| 1118 |
+
"loss": 0.002,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.0058826878190409325,
|
| 1123 |
+
"grad_norm": 0.15929220616817474,
|
| 1124 |
+
"learning_rate": 2.3778947368421052e-05,
|
| 1125 |
+
"loss": 0.0081,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.005920640643679906,
|
| 1130 |
+
"grad_norm": 0.6884347796440125,
|
| 1131 |
+
"learning_rate": 2.3250526315789473e-05,
|
| 1132 |
+
"loss": 0.0261,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.005958593468318879,
|
| 1137 |
+
"grad_norm": 0.01688176579773426,
|
| 1138 |
+
"learning_rate": 2.2722105263157894e-05,
|
| 1139 |
+
"loss": 0.0008,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.0059965462929578535,
|
| 1144 |
+
"grad_norm": 0.12140548229217529,
|
| 1145 |
+
"learning_rate": 2.2193684210526316e-05,
|
| 1146 |
+
"loss": 0.0023,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.006034499117596827,
|
| 1151 |
+
"grad_norm": 0.393767386674881,
|
| 1152 |
+
"learning_rate": 2.1665263157894737e-05,
|
| 1153 |
+
"loss": 0.0198,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.006072451942235801,
|
| 1158 |
+
"grad_norm": 0.03978809714317322,
|
| 1159 |
+
"learning_rate": 2.1136842105263158e-05,
|
| 1160 |
+
"loss": 0.0023,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.0061104047668747745,
|
| 1165 |
+
"grad_norm": 0.023572852835059166,
|
| 1166 |
+
"learning_rate": 2.060842105263158e-05,
|
| 1167 |
+
"loss": 0.0008,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.006148357591513749,
|
| 1172 |
+
"grad_norm": 0.04517120495438576,
|
| 1173 |
+
"learning_rate": 2.008e-05,
|
| 1174 |
+
"loss": 0.0022,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.006186310416152722,
|
| 1179 |
+
"grad_norm": 0.24617835879325867,
|
| 1180 |
+
"learning_rate": 1.9551578947368422e-05,
|
| 1181 |
+
"loss": 0.0219,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.006224263240791696,
|
| 1186 |
+
"grad_norm": 0.12453620135784149,
|
| 1187 |
+
"learning_rate": 1.9023157894736843e-05,
|
| 1188 |
+
"loss": 0.0077,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.00626221606543067,
|
| 1193 |
+
"grad_norm": 0.0945534035563469,
|
| 1194 |
+
"learning_rate": 1.849473684210526e-05,
|
| 1195 |
+
"loss": 0.0041,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.006300168890069643,
|
| 1200 |
+
"grad_norm": 0.20276235044002533,
|
| 1201 |
+
"learning_rate": 1.7966315789473686e-05,
|
| 1202 |
+
"loss": 0.0096,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.006338121714708617,
|
| 1207 |
+
"grad_norm": 0.46055176854133606,
|
| 1208 |
+
"learning_rate": 1.7437894736842107e-05,
|
| 1209 |
+
"loss": 0.048,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.006376074539347591,
|
| 1214 |
+
"grad_norm": 0.09639254957437515,
|
| 1215 |
+
"learning_rate": 1.6909473684210525e-05,
|
| 1216 |
+
"loss": 0.006,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.006414027363986565,
|
| 1221 |
+
"grad_norm": 0.6072278022766113,
|
| 1222 |
+
"learning_rate": 1.638105263157895e-05,
|
| 1223 |
+
"loss": 0.0378,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.006451980188625538,
|
| 1228 |
+
"grad_norm": 0.13296294212341309,
|
| 1229 |
+
"learning_rate": 1.5852631578947368e-05,
|
| 1230 |
+
"loss": 0.0027,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.0064899330132645126,
|
| 1235 |
+
"grad_norm": 0.012549227103590965,
|
| 1236 |
+
"learning_rate": 1.532421052631579e-05,
|
| 1237 |
+
"loss": 0.0006,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.006527885837903486,
|
| 1242 |
+
"grad_norm": 0.021954134106636047,
|
| 1243 |
+
"learning_rate": 1.4795789473684209e-05,
|
| 1244 |
+
"loss": 0.0011,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.006565838662542459,
|
| 1249 |
+
"grad_norm": 0.29627010226249695,
|
| 1250 |
+
"learning_rate": 1.4267368421052632e-05,
|
| 1251 |
+
"loss": 0.0105,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.0066037914871814336,
|
| 1256 |
+
"grad_norm": 0.005537001416087151,
|
| 1257 |
+
"learning_rate": 1.3738947368421053e-05,
|
| 1258 |
+
"loss": 0.0003,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.006641744311820407,
|
| 1263 |
+
"grad_norm": 0.19363458454608917,
|
| 1264 |
+
"learning_rate": 1.3210526315789473e-05,
|
| 1265 |
+
"loss": 0.008,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.006679697136459381,
|
| 1270 |
+
"grad_norm": 0.0236789733171463,
|
| 1271 |
+
"learning_rate": 1.2682105263157896e-05,
|
| 1272 |
+
"loss": 0.001,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.0067176499610983546,
|
| 1277 |
+
"grad_norm": 0.020757243037223816,
|
| 1278 |
+
"learning_rate": 1.2153684210526315e-05,
|
| 1279 |
+
"loss": 0.0011,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.006755602785737329,
|
| 1284 |
+
"grad_norm": 0.07720403373241425,
|
| 1285 |
+
"learning_rate": 1.1625263157894737e-05,
|
| 1286 |
+
"loss": 0.0023,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.006793555610376302,
|
| 1291 |
+
"grad_norm": 0.01530242059379816,
|
| 1292 |
+
"learning_rate": 1.1096842105263158e-05,
|
| 1293 |
+
"loss": 0.0009,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.006831508435015276,
|
| 1298 |
+
"grad_norm": 0.012970831245183945,
|
| 1299 |
+
"learning_rate": 1.0568421052631579e-05,
|
| 1300 |
+
"loss": 0.0005,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.00686946125965425,
|
| 1305 |
+
"grad_norm": 0.13305489718914032,
|
| 1306 |
+
"learning_rate": 1.004e-05,
|
| 1307 |
+
"loss": 0.004,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.006907414084293223,
|
| 1312 |
+
"grad_norm": 0.012722056359052658,
|
| 1313 |
+
"learning_rate": 9.511578947368422e-06,
|
| 1314 |
+
"loss": 0.0006,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.006945366908932197,
|
| 1319 |
+
"grad_norm": 0.008336643688380718,
|
| 1320 |
+
"learning_rate": 8.983157894736843e-06,
|
| 1321 |
+
"loss": 0.0005,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.006983319733571171,
|
| 1326 |
+
"grad_norm": 0.036989495158195496,
|
| 1327 |
+
"learning_rate": 8.454736842105263e-06,
|
| 1328 |
+
"loss": 0.0012,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.007021272558210145,
|
| 1333 |
+
"grad_norm": 0.22104616463184357,
|
| 1334 |
+
"learning_rate": 7.926315789473684e-06,
|
| 1335 |
+
"loss": 0.0103,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.007059225382849118,
|
| 1340 |
+
"grad_norm": 0.027394304051995277,
|
| 1341 |
+
"learning_rate": 7.397894736842104e-06,
|
| 1342 |
+
"loss": 0.001,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.007097178207488093,
|
| 1347 |
+
"grad_norm": 0.08365759998559952,
|
| 1348 |
+
"learning_rate": 6.8694736842105265e-06,
|
| 1349 |
+
"loss": 0.0024,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.007135131032127066,
|
| 1354 |
+
"grad_norm": 0.035681914538145065,
|
| 1355 |
+
"learning_rate": 6.341052631578948e-06,
|
| 1356 |
+
"loss": 0.0019,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.007173083856766039,
|
| 1361 |
+
"grad_norm": 0.02156599797308445,
|
| 1362 |
+
"learning_rate": 5.812631578947368e-06,
|
| 1363 |
+
"loss": 0.0008,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.007211036681405014,
|
| 1368 |
+
"grad_norm": 0.01591232419013977,
|
| 1369 |
+
"learning_rate": 5.2842105263157896e-06,
|
| 1370 |
+
"loss": 0.0006,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.007248989506043987,
|
| 1375 |
+
"grad_norm": 0.04397885501384735,
|
| 1376 |
+
"learning_rate": 4.755789473684211e-06,
|
| 1377 |
+
"loss": 0.0013,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.007286942330682961,
|
| 1382 |
+
"grad_norm": 0.024483874440193176,
|
| 1383 |
+
"learning_rate": 4.227368421052631e-06,
|
| 1384 |
+
"loss": 0.001,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.007324895155321935,
|
| 1389 |
+
"grad_norm": 0.002727488288655877,
|
| 1390 |
+
"learning_rate": 3.698947368421052e-06,
|
| 1391 |
+
"loss": 0.0001,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.007362847979960909,
|
| 1396 |
+
"grad_norm": 0.014970963820815086,
|
| 1397 |
+
"learning_rate": 3.170526315789474e-06,
|
| 1398 |
+
"loss": 0.0006,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.007400800804599882,
|
| 1403 |
+
"grad_norm": 0.04240657016634941,
|
| 1404 |
+
"learning_rate": 2.6421052631578948e-06,
|
| 1405 |
+
"loss": 0.0015,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.007438753629238856,
|
| 1410 |
+
"grad_norm": 0.8572260737419128,
|
| 1411 |
+
"learning_rate": 2.1136842105263157e-06,
|
| 1412 |
+
"loss": 0.1317,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.00747670645387783,
|
| 1417 |
+
"grad_norm": 0.14317569136619568,
|
| 1418 |
+
"learning_rate": 1.585263157894737e-06,
|
| 1419 |
+
"loss": 0.0045,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.007514659278516803,
|
| 1424 |
+
"grad_norm": 0.20292750000953674,
|
| 1425 |
+
"learning_rate": 1.0568421052631578e-06,
|
| 1426 |
+
"loss": 0.0066,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.0075526121031557775,
|
| 1431 |
+
"grad_norm": 0.05312797799706459,
|
| 1432 |
+
"learning_rate": 5.284210526315789e-07,
|
| 1433 |
+
"loss": 0.0017,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.007590564927794751,
|
| 1438 |
+
"grad_norm": 0.11282480508089066,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.003,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.007590564927794751,
|
| 1445 |
+
"eval_loss": 0.00452503003180027,
|
| 1446 |
+
"eval_runtime": 1815.3286,
|
| 1447 |
+
"eval_samples_per_second": 6.112,
|
| 1448 |
+
"eval_steps_per_second": 1.528,
|
| 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": 1.2912436734590976e+17,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|