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 100690288
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:efe115045ce3098b83208817be7b15f964e225849b3314c1641e3ca466a8d88c
|
| 3 |
size 100690288
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 51344890
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcd9a4c591c4c6ff5e718585f3e79dfcd8b19bd364e519fc9fc4ae06512c890b
|
| 3 |
size 51344890
|
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 sha256:8480a633bfcfa8c2d9fa818f135247c817e0614341bd17a78321f03a1149f95b
|
| 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 sha256:2eca4a3affde04f8094d886307f00c561b3e3a77570955ff1177732e06fbab0c
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 3.
|
| 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": 22.759,
|
| 1090 |
"eval_steps_per_second": 5.714,
|
| 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": 3.2126824855804443,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.35842293906810035,
|
| 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": 22.759,
|
| 1090 |
"eval_steps_per_second": 5.714,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.27060931899641577,
|
| 1095 |
+
"grad_norm": 3.4328715801239014,
|
| 1096 |
+
"learning_rate": 2.6021578947368423e-05,
|
| 1097 |
+
"loss": 6.4233,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.2724014336917563,
|
| 1102 |
+
"grad_norm": 3.84840989112854,
|
| 1103 |
+
"learning_rate": 2.5490526315789475e-05,
|
| 1104 |
+
"loss": 6.5303,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.27419354838709675,
|
| 1109 |
+
"grad_norm": 4.179206848144531,
|
| 1110 |
+
"learning_rate": 2.4959473684210524e-05,
|
| 1111 |
+
"loss": 6.3638,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.27598566308243727,
|
| 1116 |
+
"grad_norm": 4.336339473724365,
|
| 1117 |
+
"learning_rate": 2.442842105263158e-05,
|
| 1118 |
+
"loss": 6.4631,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.2777777777777778,
|
| 1123 |
+
"grad_norm": 4.317768573760986,
|
| 1124 |
+
"learning_rate": 2.389736842105263e-05,
|
| 1125 |
+
"loss": 6.4562,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.27956989247311825,
|
| 1130 |
+
"grad_norm": 3.927757740020752,
|
| 1131 |
+
"learning_rate": 2.3366315789473685e-05,
|
| 1132 |
+
"loss": 6.3095,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.28136200716845877,
|
| 1137 |
+
"grad_norm": 4.185893535614014,
|
| 1138 |
+
"learning_rate": 2.2835263157894738e-05,
|
| 1139 |
+
"loss": 6.3723,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.2831541218637993,
|
| 1144 |
+
"grad_norm": 3.7943179607391357,
|
| 1145 |
+
"learning_rate": 2.230421052631579e-05,
|
| 1146 |
+
"loss": 6.3678,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.2849462365591398,
|
| 1151 |
+
"grad_norm": 3.7967092990875244,
|
| 1152 |
+
"learning_rate": 2.1773157894736843e-05,
|
| 1153 |
+
"loss": 6.4141,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.2867383512544803,
|
| 1158 |
+
"grad_norm": 3.7188453674316406,
|
| 1159 |
+
"learning_rate": 2.1242105263157895e-05,
|
| 1160 |
+
"loss": 6.0975,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.2885304659498208,
|
| 1165 |
+
"grad_norm": 3.597055673599243,
|
| 1166 |
+
"learning_rate": 2.0711052631578947e-05,
|
| 1167 |
+
"loss": 6.2374,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.2903225806451613,
|
| 1172 |
+
"grad_norm": 3.9644243717193604,
|
| 1173 |
+
"learning_rate": 2.018e-05,
|
| 1174 |
+
"loss": 6.4148,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.2921146953405018,
|
| 1179 |
+
"grad_norm": 3.8214528560638428,
|
| 1180 |
+
"learning_rate": 1.9648947368421052e-05,
|
| 1181 |
+
"loss": 6.7674,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.2939068100358423,
|
| 1186 |
+
"grad_norm": 4.147940158843994,
|
| 1187 |
+
"learning_rate": 1.9117894736842105e-05,
|
| 1188 |
+
"loss": 6.1552,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.2956989247311828,
|
| 1193 |
+
"grad_norm": 3.685476303100586,
|
| 1194 |
+
"learning_rate": 1.8586842105263157e-05,
|
| 1195 |
+
"loss": 6.6526,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.2974910394265233,
|
| 1200 |
+
"grad_norm": 3.927133560180664,
|
| 1201 |
+
"learning_rate": 1.805578947368421e-05,
|
| 1202 |
+
"loss": 6.4206,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.2992831541218638,
|
| 1207 |
+
"grad_norm": 3.8087570667266846,
|
| 1208 |
+
"learning_rate": 1.7524736842105266e-05,
|
| 1209 |
+
"loss": 5.7276,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.3010752688172043,
|
| 1214 |
+
"grad_norm": 3.9403533935546875,
|
| 1215 |
+
"learning_rate": 1.6993684210526315e-05,
|
| 1216 |
+
"loss": 6.2683,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.30286738351254483,
|
| 1221 |
+
"grad_norm": 4.542222023010254,
|
| 1222 |
+
"learning_rate": 1.646263157894737e-05,
|
| 1223 |
+
"loss": 6.7371,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.3046594982078853,
|
| 1228 |
+
"grad_norm": 4.154723167419434,
|
| 1229 |
+
"learning_rate": 1.593157894736842e-05,
|
| 1230 |
+
"loss": 6.3052,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.3064516129032258,
|
| 1235 |
+
"grad_norm": 4.047012805938721,
|
| 1236 |
+
"learning_rate": 1.5400526315789475e-05,
|
| 1237 |
+
"loss": 6.2573,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.30824372759856633,
|
| 1242 |
+
"grad_norm": 3.9153900146484375,
|
| 1243 |
+
"learning_rate": 1.4869473684210524e-05,
|
| 1244 |
+
"loss": 6.2081,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.3100358422939068,
|
| 1249 |
+
"grad_norm": 4.141908645629883,
|
| 1250 |
+
"learning_rate": 1.4338421052631579e-05,
|
| 1251 |
+
"loss": 6.3796,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.3118279569892473,
|
| 1256 |
+
"grad_norm": 4.091080188751221,
|
| 1257 |
+
"learning_rate": 1.3807368421052633e-05,
|
| 1258 |
+
"loss": 6.4765,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.31362007168458783,
|
| 1263 |
+
"grad_norm": 4.347208499908447,
|
| 1264 |
+
"learning_rate": 1.3276315789473684e-05,
|
| 1265 |
+
"loss": 6.2807,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.3154121863799283,
|
| 1270 |
+
"grad_norm": 3.9828412532806396,
|
| 1271 |
+
"learning_rate": 1.2745263157894738e-05,
|
| 1272 |
+
"loss": 5.8736,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.3172043010752688,
|
| 1277 |
+
"grad_norm": 4.449699878692627,
|
| 1278 |
+
"learning_rate": 1.221421052631579e-05,
|
| 1279 |
+
"loss": 6.8993,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.31899641577060933,
|
| 1284 |
+
"grad_norm": 4.073231220245361,
|
| 1285 |
+
"learning_rate": 1.1683157894736843e-05,
|
| 1286 |
+
"loss": 6.0161,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.3207885304659498,
|
| 1291 |
+
"grad_norm": 3.944138526916504,
|
| 1292 |
+
"learning_rate": 1.1152105263157895e-05,
|
| 1293 |
+
"loss": 6.4192,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.3225806451612903,
|
| 1298 |
+
"grad_norm": 4.515273094177246,
|
| 1299 |
+
"learning_rate": 1.0621052631578948e-05,
|
| 1300 |
+
"loss": 6.8505,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.32437275985663083,
|
| 1305 |
+
"grad_norm": 4.274086952209473,
|
| 1306 |
+
"learning_rate": 1.009e-05,
|
| 1307 |
+
"loss": 6.6451,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.32616487455197135,
|
| 1312 |
+
"grad_norm": 4.1749114990234375,
|
| 1313 |
+
"learning_rate": 9.558947368421052e-06,
|
| 1314 |
+
"loss": 6.1817,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.3279569892473118,
|
| 1319 |
+
"grad_norm": 4.580990314483643,
|
| 1320 |
+
"learning_rate": 9.027894736842105e-06,
|
| 1321 |
+
"loss": 6.6129,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.32974910394265233,
|
| 1326 |
+
"grad_norm": 4.359395503997803,
|
| 1327 |
+
"learning_rate": 8.496842105263157e-06,
|
| 1328 |
+
"loss": 6.2116,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.33154121863799285,
|
| 1333 |
+
"grad_norm": 4.21564245223999,
|
| 1334 |
+
"learning_rate": 7.96578947368421e-06,
|
| 1335 |
+
"loss": 6.1489,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.3333333333333333,
|
| 1340 |
+
"grad_norm": 4.635838508605957,
|
| 1341 |
+
"learning_rate": 7.434736842105262e-06,
|
| 1342 |
+
"loss": 6.2616,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.33512544802867383,
|
| 1347 |
+
"grad_norm": 4.36469841003418,
|
| 1348 |
+
"learning_rate": 6.903684210526316e-06,
|
| 1349 |
+
"loss": 6.8617,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.33691756272401435,
|
| 1354 |
+
"grad_norm": 4.288735389709473,
|
| 1355 |
+
"learning_rate": 6.372631578947369e-06,
|
| 1356 |
+
"loss": 6.4591,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.3387096774193548,
|
| 1361 |
+
"grad_norm": 4.40194845199585,
|
| 1362 |
+
"learning_rate": 5.841578947368421e-06,
|
| 1363 |
+
"loss": 6.7289,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.34050179211469533,
|
| 1368 |
+
"grad_norm": 4.413331508636475,
|
| 1369 |
+
"learning_rate": 5.310526315789474e-06,
|
| 1370 |
+
"loss": 6.6116,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.34229390681003585,
|
| 1375 |
+
"grad_norm": 4.823085784912109,
|
| 1376 |
+
"learning_rate": 4.779473684210526e-06,
|
| 1377 |
+
"loss": 6.35,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.34408602150537637,
|
| 1382 |
+
"grad_norm": 5.074087142944336,
|
| 1383 |
+
"learning_rate": 4.248421052631579e-06,
|
| 1384 |
+
"loss": 6.8554,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.34587813620071683,
|
| 1389 |
+
"grad_norm": 4.536152362823486,
|
| 1390 |
+
"learning_rate": 3.717368421052631e-06,
|
| 1391 |
+
"loss": 6.1555,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.34767025089605735,
|
| 1396 |
+
"grad_norm": 4.731776714324951,
|
| 1397 |
+
"learning_rate": 3.1863157894736844e-06,
|
| 1398 |
+
"loss": 6.5222,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.34946236559139787,
|
| 1403 |
+
"grad_norm": 4.665464401245117,
|
| 1404 |
+
"learning_rate": 2.655263157894737e-06,
|
| 1405 |
+
"loss": 6.4625,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.35125448028673834,
|
| 1410 |
+
"grad_norm": 5.292746067047119,
|
| 1411 |
+
"learning_rate": 2.1242105263157893e-06,
|
| 1412 |
+
"loss": 6.6233,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.35304659498207885,
|
| 1417 |
+
"grad_norm": 5.008660793304443,
|
| 1418 |
+
"learning_rate": 1.5931578947368422e-06,
|
| 1419 |
+
"loss": 6.4388,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.3548387096774194,
|
| 1424 |
+
"grad_norm": 5.119359493255615,
|
| 1425 |
+
"learning_rate": 1.0621052631578947e-06,
|
| 1426 |
+
"loss": 6.3227,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.35663082437275984,
|
| 1431 |
+
"grad_norm": 5.395398139953613,
|
| 1432 |
+
"learning_rate": 5.310526315789473e-07,
|
| 1433 |
+
"loss": 6.3648,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.35842293906810035,
|
| 1438 |
+
"grad_norm": 6.391620635986328,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 6.0084,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.35842293906810035,
|
| 1445 |
+
"eval_loss": 3.2126824855804443,
|
| 1446 |
+
"eval_runtime": 10.1929,
|
| 1447 |
+
"eval_samples_per_second": 23.055,
|
| 1448 |
+
"eval_steps_per_second": 5.788,
|
| 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": 3219252471398400.0,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|