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 60576160
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69768d5f457b28fd086bda0aed7689ae4b3146cb3fa854068bd4395aef9a738c
|
| 3 |
size 60576160
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 121216762
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f23118051076371559aa90b1ed20d554424bb47fff005917445ee0596d9d71e9
|
| 3 |
size 121216762
|
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 sha256:521c128066f618a1ede3a5d1c49d4acebcffa4cda5cb97f34fcc7d91e1477230
|
| 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": 8.
|
| 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": 144.651,
|
| 1090 |
"eval_steps_per_second": 72.325,
|
| 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": 8.815260887145996,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.03192338387869114,
|
| 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": 144.651,
|
| 1090 |
"eval_steps_per_second": 72.325,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.024102154828411812,
|
| 1095 |
+
"grad_norm": 2.0528664588928223,
|
| 1096 |
+
"learning_rate": 1.7197048550474643e-05,
|
| 1097 |
+
"loss": 9.2736,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.024261771747805267,
|
| 1102 |
+
"grad_norm": 2.0826079845428467,
|
| 1103 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 1104 |
+
"loss": 9.0889,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.024421388667198722,
|
| 1109 |
+
"grad_norm": 2.23173451423645,
|
| 1110 |
+
"learning_rate": 1.5900081996875083e-05,
|
| 1111 |
+
"loss": 9.0961,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.024581005586592177,
|
| 1116 |
+
"grad_norm": 1.9450350999832153,
|
| 1117 |
+
"learning_rate": 1.526708147705013e-05,
|
| 1118 |
+
"loss": 9.1019,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.024740622505985636,
|
| 1123 |
+
"grad_norm": 2.1064467430114746,
|
| 1124 |
+
"learning_rate": 1.4644660940672627e-05,
|
| 1125 |
+
"loss": 8.9931,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.02490023942537909,
|
| 1130 |
+
"grad_norm": 1.9277666807174683,
|
| 1131 |
+
"learning_rate": 1.4033009983067452e-05,
|
| 1132 |
+
"loss": 9.115,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.025059856344772546,
|
| 1137 |
+
"grad_norm": 1.4659113883972168,
|
| 1138 |
+
"learning_rate": 1.3432314919041478e-05,
|
| 1139 |
+
"loss": 9.0417,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.025219473264166,
|
| 1144 |
+
"grad_norm": 1.404615879058838,
|
| 1145 |
+
"learning_rate": 1.2842758726130283e-05,
|
| 1146 |
+
"loss": 9.0074,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.025379090183559456,
|
| 1151 |
+
"grad_norm": 1.1520626544952393,
|
| 1152 |
+
"learning_rate": 1.22645209888614e-05,
|
| 1153 |
+
"loss": 8.909,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.025538707102952914,
|
| 1158 |
+
"grad_norm": 1.211961269378662,
|
| 1159 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 1160 |
+
"loss": 8.9261,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.02569832402234637,
|
| 1165 |
+
"grad_norm": 1.0652966499328613,
|
| 1166 |
+
"learning_rate": 1.1142701927151456e-05,
|
| 1167 |
+
"loss": 8.9164,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.025857940941739824,
|
| 1172 |
+
"grad_norm": 1.0396746397018433,
|
| 1173 |
+
"learning_rate": 1.0599462319663905e-05,
|
| 1174 |
+
"loss": 8.9401,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.02601755786113328,
|
| 1179 |
+
"grad_norm": 1.0601286888122559,
|
| 1180 |
+
"learning_rate": 1.006822449763537e-05,
|
| 1181 |
+
"loss": 8.8261,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.026177174780526734,
|
| 1186 |
+
"grad_norm": 0.826156735420227,
|
| 1187 |
+
"learning_rate": 9.549150281252633e-06,
|
| 1188 |
+
"loss": 8.9257,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.026336791699920193,
|
| 1193 |
+
"grad_norm": 0.8957279920578003,
|
| 1194 |
+
"learning_rate": 9.042397785550405e-06,
|
| 1195 |
+
"loss": 8.8738,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.026496408619313648,
|
| 1200 |
+
"grad_norm": 0.8793820738792419,
|
| 1201 |
+
"learning_rate": 8.548121372247918e-06,
|
| 1202 |
+
"loss": 8.9119,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.026656025538707103,
|
| 1207 |
+
"grad_norm": 0.7437137961387634,
|
| 1208 |
+
"learning_rate": 8.066471602728803e-06,
|
| 1209 |
+
"loss": 9.0189,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.026815642458100558,
|
| 1214 |
+
"grad_norm": 0.8339880108833313,
|
| 1215 |
+
"learning_rate": 7.597595192178702e-06,
|
| 1216 |
+
"loss": 8.8991,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.026975259377494013,
|
| 1221 |
+
"grad_norm": 0.7902394533157349,
|
| 1222 |
+
"learning_rate": 7.1416349648943894e-06,
|
| 1223 |
+
"loss": 8.8982,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.02713487629688747,
|
| 1228 |
+
"grad_norm": 0.8195562362670898,
|
| 1229 |
+
"learning_rate": 6.698729810778065e-06,
|
| 1230 |
+
"loss": 8.7673,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.027294493216280927,
|
| 1235 |
+
"grad_norm": 0.7785468697547913,
|
| 1236 |
+
"learning_rate": 6.269014643030213e-06,
|
| 1237 |
+
"loss": 8.9051,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.027454110135674382,
|
| 1242 |
+
"grad_norm": 0.8220974206924438,
|
| 1243 |
+
"learning_rate": 5.852620357053651e-06,
|
| 1244 |
+
"loss": 8.8356,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.027613727055067837,
|
| 1249 |
+
"grad_norm": 0.7799994349479675,
|
| 1250 |
+
"learning_rate": 5.449673790581611e-06,
|
| 1251 |
+
"loss": 8.8642,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.027773343974461292,
|
| 1256 |
+
"grad_norm": 0.7996445298194885,
|
| 1257 |
+
"learning_rate": 5.060297685041659e-06,
|
| 1258 |
+
"loss": 8.8479,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.027932960893854747,
|
| 1263 |
+
"grad_norm": 0.9289652705192566,
|
| 1264 |
+
"learning_rate": 4.684610648167503e-06,
|
| 1265 |
+
"loss": 8.8279,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.028092577813248205,
|
| 1270 |
+
"grad_norm": 0.7999223470687866,
|
| 1271 |
+
"learning_rate": 4.322727117869951e-06,
|
| 1272 |
+
"loss": 8.7969,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.02825219473264166,
|
| 1277 |
+
"grad_norm": 0.9309490919113159,
|
| 1278 |
+
"learning_rate": 3.974757327377981e-06,
|
| 1279 |
+
"loss": 8.7552,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.028411811652035115,
|
| 1284 |
+
"grad_norm": 1.0407963991165161,
|
| 1285 |
+
"learning_rate": 3.6408072716606346e-06,
|
| 1286 |
+
"loss": 9.0681,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.02857142857142857,
|
| 1291 |
+
"grad_norm": 0.8138166069984436,
|
| 1292 |
+
"learning_rate": 3.3209786751399187e-06,
|
| 1293 |
+
"loss": 8.8665,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.028731045490822026,
|
| 1298 |
+
"grad_norm": 1.0900275707244873,
|
| 1299 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 1300 |
+
"loss": 8.5964,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.028890662410215484,
|
| 1305 |
+
"grad_norm": 0.8788620233535767,
|
| 1306 |
+
"learning_rate": 2.724071220034158e-06,
|
| 1307 |
+
"loss": 8.8323,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.02905027932960894,
|
| 1312 |
+
"grad_norm": 1.0682237148284912,
|
| 1313 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 1314 |
+
"loss": 8.7646,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.029209896249002394,
|
| 1319 |
+
"grad_norm": 0.9872691035270691,
|
| 1320 |
+
"learning_rate": 2.1847622018482283e-06,
|
| 1321 |
+
"loss": 8.656,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.02936951316839585,
|
| 1326 |
+
"grad_norm": 1.0506043434143066,
|
| 1327 |
+
"learning_rate": 1.9369152030840556e-06,
|
| 1328 |
+
"loss": 8.5878,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.029529130087789304,
|
| 1333 |
+
"grad_norm": 1.0583956241607666,
|
| 1334 |
+
"learning_rate": 1.70370868554659e-06,
|
| 1335 |
+
"loss": 8.6643,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.029688747007182763,
|
| 1340 |
+
"grad_norm": 1.1388531923294067,
|
| 1341 |
+
"learning_rate": 1.4852136862001764e-06,
|
| 1342 |
+
"loss": 8.595,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.029848363926576218,
|
| 1347 |
+
"grad_norm": 1.1205211877822876,
|
| 1348 |
+
"learning_rate": 1.2814967607382432e-06,
|
| 1349 |
+
"loss": 8.8281,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.030007980845969673,
|
| 1354 |
+
"grad_norm": 1.2090356349945068,
|
| 1355 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 1356 |
+
"loss": 8.7386,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.030167597765363128,
|
| 1361 |
+
"grad_norm": 1.282060146331787,
|
| 1362 |
+
"learning_rate": 9.186408276168013e-07,
|
| 1363 |
+
"loss": 8.7749,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.030327214684756583,
|
| 1368 |
+
"grad_norm": 1.6507028341293335,
|
| 1369 |
+
"learning_rate": 7.596123493895991e-07,
|
| 1370 |
+
"loss": 8.6737,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.03048683160415004,
|
| 1375 |
+
"grad_norm": 1.6307878494262695,
|
| 1376 |
+
"learning_rate": 6.15582970243117e-07,
|
| 1377 |
+
"loss": 8.7428,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.030646448523543496,
|
| 1382 |
+
"grad_norm": 1.6969655752182007,
|
| 1383 |
+
"learning_rate": 4.865965629214819e-07,
|
| 1384 |
+
"loss": 8.7698,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.03080606544293695,
|
| 1389 |
+
"grad_norm": 1.7107874155044556,
|
| 1390 |
+
"learning_rate": 3.7269241793390085e-07,
|
| 1391 |
+
"loss": 8.7961,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.030965682362330407,
|
| 1396 |
+
"grad_norm": 1.939238429069519,
|
| 1397 |
+
"learning_rate": 2.7390523158633554e-07,
|
| 1398 |
+
"loss": 8.6847,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.03112529928172386,
|
| 1403 |
+
"grad_norm": 2.0403974056243896,
|
| 1404 |
+
"learning_rate": 1.9026509541272275e-07,
|
| 1405 |
+
"loss": 8.7122,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.03128491620111732,
|
| 1410 |
+
"grad_norm": 2.102086067199707,
|
| 1411 |
+
"learning_rate": 1.2179748700879012e-07,
|
| 1412 |
+
"loss": 8.7029,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.03144453312051077,
|
| 1417 |
+
"grad_norm": 2.1964938640594482,
|
| 1418 |
+
"learning_rate": 6.852326227130834e-08,
|
| 1419 |
+
"loss": 8.6416,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.03160415003990423,
|
| 1424 |
+
"grad_norm": 2.626417398452759,
|
| 1425 |
+
"learning_rate": 3.04586490452119e-08,
|
| 1426 |
+
"loss": 8.7796,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.03176376695929769,
|
| 1431 |
+
"grad_norm": 3.056986093521118,
|
| 1432 |
+
"learning_rate": 7.615242180436522e-09,
|
| 1433 |
+
"loss": 8.4312,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.03192338387869114,
|
| 1438 |
+
"grad_norm": 4.446366310119629,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 8.5991,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.03192338387869114,
|
| 1445 |
+
"eval_loss": 8.815260887145996,
|
| 1446 |
+
"eval_runtime": 73.4833,
|
| 1447 |
+
"eval_samples_per_second": 143.597,
|
| 1448 |
+
"eval_steps_per_second": 71.799,
|
| 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": 9029012353449984.0,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|