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 335604696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:603bfcf28e944199abcb5323bcd1d788099a7ca7f3d5a6b0cd810d148ac7538a
|
| 3 |
size 335604696
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 170920084
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:815821e009137eecdbeea6312484c9b25e9d24d9475fa642f02086e0e6691559
|
| 3 |
size 170920084
|
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:f46055a58b9f99fc9d08a86bf20f570e5bee6fa690589a2ad37d4110d1e5ec63
|
| 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:a27b052646dcb561cbd68156c30bd466ce59bda64cf3c8eba9c3c1113af9827c
|
| 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": 8.38,
|
| 1090 |
"eval_steps_per_second": 2.095,
|
| 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": 0.5240768790245056,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.09488791365199857,
|
| 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": 8.38,
|
| 1090 |
"eval_steps_per_second": 2.095,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.07164037480725892,
|
| 1095 |
+
"grad_norm": 0.6407384276390076,
|
| 1096 |
+
"learning_rate": 4.995066821070679e-05,
|
| 1097 |
+
"loss": 0.5625,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.07211481437551892,
|
| 1102 |
+
"grad_norm": 0.6112384796142578,
|
| 1103 |
+
"learning_rate": 4.980286753286195e-05,
|
| 1104 |
+
"loss": 0.5653,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.07258925394377891,
|
| 1109 |
+
"grad_norm": 0.6031837463378906,
|
| 1110 |
+
"learning_rate": 4.9557181268217227e-05,
|
| 1111 |
+
"loss": 0.554,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.07306369351203891,
|
| 1116 |
+
"grad_norm": 0.6688528656959534,
|
| 1117 |
+
"learning_rate": 4.9214579028215776e-05,
|
| 1118 |
+
"loss": 0.5895,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.0735381330802989,
|
| 1123 |
+
"grad_norm": 0.7718383073806763,
|
| 1124 |
+
"learning_rate": 4.877641290737884e-05,
|
| 1125 |
+
"loss": 0.5888,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.07401257264855889,
|
| 1130 |
+
"grad_norm": 0.6664111614227295,
|
| 1131 |
+
"learning_rate": 4.8244412147206284e-05,
|
| 1132 |
+
"loss": 0.5952,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.07448701221681889,
|
| 1137 |
+
"grad_norm": 0.6297560334205627,
|
| 1138 |
+
"learning_rate": 4.762067631165049e-05,
|
| 1139 |
+
"loss": 0.5885,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.07496145178507888,
|
| 1144 |
+
"grad_norm": 0.6725597381591797,
|
| 1145 |
+
"learning_rate": 4.690766700109659e-05,
|
| 1146 |
+
"loss": 0.5825,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.07543589135333886,
|
| 1151 |
+
"grad_norm": 0.7031341195106506,
|
| 1152 |
+
"learning_rate": 4.610819813755038e-05,
|
| 1153 |
+
"loss": 0.5712,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.07591033092159886,
|
| 1158 |
+
"grad_norm": 0.6546705365180969,
|
| 1159 |
+
"learning_rate": 4.522542485937369e-05,
|
| 1160 |
+
"loss": 0.5406,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.07638477048985885,
|
| 1165 |
+
"grad_norm": 0.6717162132263184,
|
| 1166 |
+
"learning_rate": 4.426283106939474e-05,
|
| 1167 |
+
"loss": 0.5637,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.07685921005811884,
|
| 1172 |
+
"grad_norm": 0.7519511580467224,
|
| 1173 |
+
"learning_rate": 4.3224215685535294e-05,
|
| 1174 |
+
"loss": 0.5447,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.07733364962637884,
|
| 1179 |
+
"grad_norm": 1.100063443183899,
|
| 1180 |
+
"learning_rate": 4.211367764821722e-05,
|
| 1181 |
+
"loss": 0.5934,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.07780808919463883,
|
| 1186 |
+
"grad_norm": 1.2684733867645264,
|
| 1187 |
+
"learning_rate": 4.093559974371725e-05,
|
| 1188 |
+
"loss": 0.5837,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.07828252876289883,
|
| 1193 |
+
"grad_norm": 0.9038509726524353,
|
| 1194 |
+
"learning_rate": 3.969463130731183e-05,
|
| 1195 |
+
"loss": 0.5871,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.07875696833115882,
|
| 1200 |
+
"grad_norm": 0.7687073945999146,
|
| 1201 |
+
"learning_rate": 3.8395669874474915e-05,
|
| 1202 |
+
"loss": 0.5687,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.07923140789941881,
|
| 1207 |
+
"grad_norm": 0.7183095812797546,
|
| 1208 |
+
"learning_rate": 3.704384185254288e-05,
|
| 1209 |
+
"loss": 0.5445,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.07970584746767881,
|
| 1214 |
+
"grad_norm": 0.8233352303504944,
|
| 1215 |
+
"learning_rate": 3.564448228912682e-05,
|
| 1216 |
+
"loss": 0.6104,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.0801802870359388,
|
| 1221 |
+
"grad_norm": 0.8277663588523865,
|
| 1222 |
+
"learning_rate": 3.4203113817116957e-05,
|
| 1223 |
+
"loss": 0.5466,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.08065472660419878,
|
| 1228 |
+
"grad_norm": 0.8397349715232849,
|
| 1229 |
+
"learning_rate": 3.272542485937369e-05,
|
| 1230 |
+
"loss": 0.6032,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.08112916617245879,
|
| 1235 |
+
"grad_norm": 0.9372188448905945,
|
| 1236 |
+
"learning_rate": 3.121724717912138e-05,
|
| 1237 |
+
"loss": 0.582,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.08160360574071877,
|
| 1242 |
+
"grad_norm": 0.7972699999809265,
|
| 1243 |
+
"learning_rate": 2.9684532864643122e-05,
|
| 1244 |
+
"loss": 0.5705,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.08207804530897878,
|
| 1249 |
+
"grad_norm": 0.887993574142456,
|
| 1250 |
+
"learning_rate": 2.8133330839107608e-05,
|
| 1251 |
+
"loss": 0.5956,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.08255248487723876,
|
| 1256 |
+
"grad_norm": 0.9554271101951599,
|
| 1257 |
+
"learning_rate": 2.656976298823284e-05,
|
| 1258 |
+
"loss": 0.5826,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.08302692444549875,
|
| 1263 |
+
"grad_norm": 0.965546190738678,
|
| 1264 |
+
"learning_rate": 2.5e-05,
|
| 1265 |
+
"loss": 0.6667,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.08350136401375875,
|
| 1270 |
+
"grad_norm": 1.0202322006225586,
|
| 1271 |
+
"learning_rate": 2.3430237011767167e-05,
|
| 1272 |
+
"loss": 0.6359,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.08397580358201874,
|
| 1277 |
+
"grad_norm": 0.7853454351425171,
|
| 1278 |
+
"learning_rate": 2.186666916089239e-05,
|
| 1279 |
+
"loss": 0.5719,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.08445024315027873,
|
| 1284 |
+
"grad_norm": 0.8861081600189209,
|
| 1285 |
+
"learning_rate": 2.031546713535688e-05,
|
| 1286 |
+
"loss": 0.5466,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.08492468271853873,
|
| 1291 |
+
"grad_norm": 0.8035862445831299,
|
| 1292 |
+
"learning_rate": 1.8782752820878634e-05,
|
| 1293 |
+
"loss": 0.4791,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.08539912228679872,
|
| 1298 |
+
"grad_norm": 0.7730982303619385,
|
| 1299 |
+
"learning_rate": 1.7274575140626318e-05,
|
| 1300 |
+
"loss": 0.4957,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.0858735618550587,
|
| 1305 |
+
"grad_norm": 0.7126002907752991,
|
| 1306 |
+
"learning_rate": 1.5796886182883053e-05,
|
| 1307 |
+
"loss": 0.4602,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.08634800142331871,
|
| 1312 |
+
"grad_norm": 0.6563583016395569,
|
| 1313 |
+
"learning_rate": 1.4355517710873184e-05,
|
| 1314 |
+
"loss": 0.4697,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.0868224409915787,
|
| 1319 |
+
"grad_norm": 0.6551535129547119,
|
| 1320 |
+
"learning_rate": 1.2956158147457115e-05,
|
| 1321 |
+
"loss": 0.4977,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.0872968805598387,
|
| 1326 |
+
"grad_norm": 0.6339255571365356,
|
| 1327 |
+
"learning_rate": 1.1604330125525079e-05,
|
| 1328 |
+
"loss": 0.4551,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.08777132012809868,
|
| 1333 |
+
"grad_norm": 0.6310778856277466,
|
| 1334 |
+
"learning_rate": 1.0305368692688174e-05,
|
| 1335 |
+
"loss": 0.4624,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.08824575969635867,
|
| 1340 |
+
"grad_norm": 0.6144092679023743,
|
| 1341 |
+
"learning_rate": 9.064400256282757e-06,
|
| 1342 |
+
"loss": 0.4172,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.08872019926461867,
|
| 1347 |
+
"grad_norm": 0.6439892649650574,
|
| 1348 |
+
"learning_rate": 7.886322351782783e-06,
|
| 1349 |
+
"loss": 0.4743,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.08919463883287866,
|
| 1354 |
+
"grad_norm": 0.6598646640777588,
|
| 1355 |
+
"learning_rate": 6.775784314464717e-06,
|
| 1356 |
+
"loss": 0.4595,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.08966907840113865,
|
| 1361 |
+
"grad_norm": 0.6310641169548035,
|
| 1362 |
+
"learning_rate": 5.737168930605272e-06,
|
| 1363 |
+
"loss": 0.4651,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.09014351796939865,
|
| 1368 |
+
"grad_norm": 0.6230701208114624,
|
| 1369 |
+
"learning_rate": 4.7745751406263165e-06,
|
| 1370 |
+
"loss": 0.4454,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.09061795753765864,
|
| 1375 |
+
"grad_norm": 0.6929914951324463,
|
| 1376 |
+
"learning_rate": 3.891801862449629e-06,
|
| 1377 |
+
"loss": 0.462,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.09109239710591864,
|
| 1382 |
+
"grad_norm": 0.6001230478286743,
|
| 1383 |
+
"learning_rate": 3.092332998903416e-06,
|
| 1384 |
+
"loss": 0.4515,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.09156683667417863,
|
| 1389 |
+
"grad_norm": 0.6835476756095886,
|
| 1390 |
+
"learning_rate": 2.379323688349516e-06,
|
| 1391 |
+
"loss": 0.4995,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.09204127624243862,
|
| 1396 |
+
"grad_norm": 0.6249610185623169,
|
| 1397 |
+
"learning_rate": 1.7555878527937164e-06,
|
| 1398 |
+
"loss": 0.4568,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.09251571581069862,
|
| 1403 |
+
"grad_norm": 0.6171400547027588,
|
| 1404 |
+
"learning_rate": 1.2235870926211619e-06,
|
| 1405 |
+
"loss": 0.4729,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.0929901553789586,
|
| 1410 |
+
"grad_norm": 0.6366883516311646,
|
| 1411 |
+
"learning_rate": 7.854209717842231e-07,
|
| 1412 |
+
"loss": 0.4457,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.0934645949472186,
|
| 1417 |
+
"grad_norm": 0.6031494736671448,
|
| 1418 |
+
"learning_rate": 4.4281873178278475e-07,
|
| 1419 |
+
"loss": 0.4652,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.0939390345154786,
|
| 1424 |
+
"grad_norm": 0.6091623306274414,
|
| 1425 |
+
"learning_rate": 1.9713246713805588e-07,
|
| 1426 |
+
"loss": 0.4665,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.09441347408373858,
|
| 1431 |
+
"grad_norm": 0.5706689953804016,
|
| 1432 |
+
"learning_rate": 4.9331789293211026e-08,
|
| 1433 |
+
"loss": 0.4282,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.09488791365199857,
|
| 1438 |
+
"grad_norm": 0.761282205581665,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.4888,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.09488791365199857,
|
| 1445 |
+
"eval_loss": 0.5240768790245056,
|
| 1446 |
+
"eval_runtime": 848.4751,
|
| 1447 |
+
"eval_samples_per_second": 8.368,
|
| 1448 |
+
"eval_steps_per_second": 2.092,
|
| 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": 9.522823421881221e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|