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 479005064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f27b98f6cf0f23eab77e3d54b5a7f589dce996ac161e0893df2660837e38ed6a
|
| 3 |
size 479005064
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 958299770
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:620c1fdc3c9b39083b8f370f6580946a66b53e2567231209749bc2443392a45d
|
| 3 |
size 958299770
|
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 sha256:01d13d0ea722ac4b27a5252dde4d9e2a0755a70348289e0361a2b12030351906
|
| 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": 0.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 2.
|
| 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": 18.832,
|
| 1090 |
"eval_steps_per_second": 9.495,
|
| 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": 0.02226005494594574,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 2.840989399293286,
|
| 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": 18.832,
|
| 1090 |
"eval_steps_per_second": 9.495,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 2.148409893992933,
|
| 1095 |
+
"grad_norm": 0.12965770065784454,
|
| 1096 |
+
"learning_rate": 1.7197048550474643e-05,
|
| 1097 |
+
"loss": 0.0034,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 2.1625441696113072,
|
| 1102 |
+
"grad_norm": 0.06591859459877014,
|
| 1103 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 1104 |
+
"loss": 0.0023,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 2.176678445229682,
|
| 1109 |
+
"grad_norm": 0.05958675220608711,
|
| 1110 |
+
"learning_rate": 1.5900081996875083e-05,
|
| 1111 |
+
"loss": 0.0021,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 2.1908127208480566,
|
| 1116 |
+
"grad_norm": 0.863341748714447,
|
| 1117 |
+
"learning_rate": 1.526708147705013e-05,
|
| 1118 |
+
"loss": 0.0085,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 2.204946996466431,
|
| 1123 |
+
"grad_norm": 0.31874069571495056,
|
| 1124 |
+
"learning_rate": 1.4644660940672627e-05,
|
| 1125 |
+
"loss": 0.0094,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 2.2190812720848054,
|
| 1130 |
+
"grad_norm": 0.22433172166347504,
|
| 1131 |
+
"learning_rate": 1.4033009983067452e-05,
|
| 1132 |
+
"loss": 0.0084,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 2.23321554770318,
|
| 1137 |
+
"grad_norm": 0.03787798061966896,
|
| 1138 |
+
"learning_rate": 1.3432314919041478e-05,
|
| 1139 |
+
"loss": 0.0014,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 2.2473498233215548,
|
| 1144 |
+
"grad_norm": 0.09445440024137497,
|
| 1145 |
+
"learning_rate": 1.2842758726130283e-05,
|
| 1146 |
+
"loss": 0.0028,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 2.2614840989399294,
|
| 1151 |
+
"grad_norm": 1.9811441898345947,
|
| 1152 |
+
"learning_rate": 1.22645209888614e-05,
|
| 1153 |
+
"loss": 0.0709,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 2.275618374558304,
|
| 1158 |
+
"grad_norm": 0.33604347705841064,
|
| 1159 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 1160 |
+
"loss": 0.0134,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 2.2897526501766783,
|
| 1165 |
+
"grad_norm": 0.4111025035381317,
|
| 1166 |
+
"learning_rate": 1.1142701927151456e-05,
|
| 1167 |
+
"loss": 0.0376,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 2.303886925795053,
|
| 1172 |
+
"grad_norm": 0.5210508108139038,
|
| 1173 |
+
"learning_rate": 1.0599462319663905e-05,
|
| 1174 |
+
"loss": 0.0372,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 2.3180212014134276,
|
| 1179 |
+
"grad_norm": 0.09174925088882446,
|
| 1180 |
+
"learning_rate": 1.006822449763537e-05,
|
| 1181 |
+
"loss": 0.0026,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 2.3321554770318023,
|
| 1186 |
+
"grad_norm": 0.04885992035269737,
|
| 1187 |
+
"learning_rate": 9.549150281252633e-06,
|
| 1188 |
+
"loss": 0.0016,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 2.3462897526501765,
|
| 1193 |
+
"grad_norm": 0.0838780626654625,
|
| 1194 |
+
"learning_rate": 9.042397785550405e-06,
|
| 1195 |
+
"loss": 0.0028,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 2.360424028268551,
|
| 1200 |
+
"grad_norm": 0.06478317826986313,
|
| 1201 |
+
"learning_rate": 8.548121372247918e-06,
|
| 1202 |
+
"loss": 0.0021,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 2.374558303886926,
|
| 1207 |
+
"grad_norm": 0.09824801236391068,
|
| 1208 |
+
"learning_rate": 8.066471602728803e-06,
|
| 1209 |
+
"loss": 0.0026,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 2.3886925795053005,
|
| 1214 |
+
"grad_norm": 0.06248147413134575,
|
| 1215 |
+
"learning_rate": 7.597595192178702e-06,
|
| 1216 |
+
"loss": 0.0018,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 2.402826855123675,
|
| 1221 |
+
"grad_norm": 0.1567322015762329,
|
| 1222 |
+
"learning_rate": 7.1416349648943894e-06,
|
| 1223 |
+
"loss": 0.0062,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 2.4169611307420493,
|
| 1228 |
+
"grad_norm": 0.28212109208106995,
|
| 1229 |
+
"learning_rate": 6.698729810778065e-06,
|
| 1230 |
+
"loss": 0.0068,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 2.431095406360424,
|
| 1235 |
+
"grad_norm": 0.11935470998287201,
|
| 1236 |
+
"learning_rate": 6.269014643030213e-06,
|
| 1237 |
+
"loss": 0.0023,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 2.4452296819787986,
|
| 1242 |
+
"grad_norm": 0.15177536010742188,
|
| 1243 |
+
"learning_rate": 5.852620357053651e-06,
|
| 1244 |
+
"loss": 0.0026,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 2.4593639575971733,
|
| 1249 |
+
"grad_norm": 0.22410543262958527,
|
| 1250 |
+
"learning_rate": 5.449673790581611e-06,
|
| 1251 |
+
"loss": 0.0029,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 2.4734982332155475,
|
| 1256 |
+
"grad_norm": 0.2390422374010086,
|
| 1257 |
+
"learning_rate": 5.060297685041659e-06,
|
| 1258 |
+
"loss": 0.0027,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 2.487632508833922,
|
| 1263 |
+
"grad_norm": 0.3170912563800812,
|
| 1264 |
+
"learning_rate": 4.684610648167503e-06,
|
| 1265 |
+
"loss": 0.0106,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 2.501766784452297,
|
| 1270 |
+
"grad_norm": 0.2848634421825409,
|
| 1271 |
+
"learning_rate": 4.322727117869951e-06,
|
| 1272 |
+
"loss": 0.0198,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 2.5159010600706715,
|
| 1277 |
+
"grad_norm": 0.3001430630683899,
|
| 1278 |
+
"learning_rate": 3.974757327377981e-06,
|
| 1279 |
+
"loss": 0.0082,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 2.530035335689046,
|
| 1284 |
+
"grad_norm": 0.15458659827709198,
|
| 1285 |
+
"learning_rate": 3.6408072716606346e-06,
|
| 1286 |
+
"loss": 0.0055,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 2.5441696113074204,
|
| 1291 |
+
"grad_norm": 0.19815073907375336,
|
| 1292 |
+
"learning_rate": 3.3209786751399187e-06,
|
| 1293 |
+
"loss": 0.0108,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 2.558303886925795,
|
| 1298 |
+
"grad_norm": 0.06913748383522034,
|
| 1299 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 1300 |
+
"loss": 0.0024,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 2.5724381625441697,
|
| 1305 |
+
"grad_norm": 0.6175816059112549,
|
| 1306 |
+
"learning_rate": 2.724071220034158e-06,
|
| 1307 |
+
"loss": 0.017,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 2.586572438162544,
|
| 1312 |
+
"grad_norm": 0.17493540048599243,
|
| 1313 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 1314 |
+
"loss": 0.0062,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 2.6007067137809186,
|
| 1319 |
+
"grad_norm": 0.030856192111968994,
|
| 1320 |
+
"learning_rate": 2.1847622018482283e-06,
|
| 1321 |
+
"loss": 0.0011,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 2.614840989399293,
|
| 1326 |
+
"grad_norm": 0.1881757527589798,
|
| 1327 |
+
"learning_rate": 1.9369152030840556e-06,
|
| 1328 |
+
"loss": 0.0075,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 2.628975265017668,
|
| 1333 |
+
"grad_norm": 0.03700214624404907,
|
| 1334 |
+
"learning_rate": 1.70370868554659e-06,
|
| 1335 |
+
"loss": 0.0014,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 2.6431095406360425,
|
| 1340 |
+
"grad_norm": 0.1864822953939438,
|
| 1341 |
+
"learning_rate": 1.4852136862001764e-06,
|
| 1342 |
+
"loss": 0.0089,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 2.657243816254417,
|
| 1347 |
+
"grad_norm": 0.07615940272808075,
|
| 1348 |
+
"learning_rate": 1.2814967607382432e-06,
|
| 1349 |
+
"loss": 0.0026,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 2.6713780918727914,
|
| 1354 |
+
"grad_norm": 0.04182976111769676,
|
| 1355 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 1356 |
+
"loss": 0.0014,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 2.685512367491166,
|
| 1361 |
+
"grad_norm": 0.11160821467638016,
|
| 1362 |
+
"learning_rate": 9.186408276168013e-07,
|
| 1363 |
+
"loss": 0.0019,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 2.6996466431095407,
|
| 1368 |
+
"grad_norm": 0.030893972143530846,
|
| 1369 |
+
"learning_rate": 7.596123493895991e-07,
|
| 1370 |
+
"loss": 0.0012,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 2.713780918727915,
|
| 1375 |
+
"grad_norm": 0.03732634335756302,
|
| 1376 |
+
"learning_rate": 6.15582970243117e-07,
|
| 1377 |
+
"loss": 0.0012,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 2.7279151943462896,
|
| 1382 |
+
"grad_norm": 0.1454208493232727,
|
| 1383 |
+
"learning_rate": 4.865965629214819e-07,
|
| 1384 |
+
"loss": 0.01,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 2.7420494699646643,
|
| 1389 |
+
"grad_norm": 0.11776148527860641,
|
| 1390 |
+
"learning_rate": 3.7269241793390085e-07,
|
| 1391 |
+
"loss": 0.0078,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 2.756183745583039,
|
| 1396 |
+
"grad_norm": 0.1260043829679489,
|
| 1397 |
+
"learning_rate": 2.7390523158633554e-07,
|
| 1398 |
+
"loss": 0.0033,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 2.7703180212014136,
|
| 1403 |
+
"grad_norm": 0.5196786522865295,
|
| 1404 |
+
"learning_rate": 1.9026509541272275e-07,
|
| 1405 |
+
"loss": 0.0244,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 2.7844522968197882,
|
| 1410 |
+
"grad_norm": 0.4225069284439087,
|
| 1411 |
+
"learning_rate": 1.2179748700879012e-07,
|
| 1412 |
+
"loss": 0.0241,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 2.7985865724381624,
|
| 1417 |
+
"grad_norm": 0.1836262196302414,
|
| 1418 |
+
"learning_rate": 6.852326227130834e-08,
|
| 1419 |
+
"loss": 0.0072,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 2.812720848056537,
|
| 1424 |
+
"grad_norm": 0.04496635124087334,
|
| 1425 |
+
"learning_rate": 3.04586490452119e-08,
|
| 1426 |
+
"loss": 0.0018,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 2.8268551236749118,
|
| 1431 |
+
"grad_norm": 0.3070247769355774,
|
| 1432 |
+
"learning_rate": 7.615242180436522e-09,
|
| 1433 |
+
"loss": 0.0095,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 2.840989399293286,
|
| 1438 |
+
"grad_norm": 0.13280314207077026,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.0015,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 2.840989399293286,
|
| 1445 |
+
"eval_loss": 0.02226005494594574,
|
| 1446 |
+
"eval_runtime": 6.3135,
|
| 1447 |
+
"eval_samples_per_second": 18.848,
|
| 1448 |
+
"eval_steps_per_second": 9.503,
|
| 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": 1.138166870310912e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|