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 755015736
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e138cc1f53ae15a03c2f4cb2eb57b58276d1ba401e2b7b6454560314f56ed511
|
| 3 |
size 755015736
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 383724628
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30a1d2c3d5529a388f7715e7859533c5061d082e65f0ee31dec6afc1b08507f1
|
| 3 |
size 383724628
|
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 sha256:336dda81b6dfbc99d433c90346258593946116fe986a20a81841691a558e8981
|
| 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 sha256:4f96196bd3544de2c28f6af356470f327df948539b0e3259c46b8a6786b633fd
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 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": 4.202,
|
| 1090 |
"eval_steps_per_second": 1.05,
|
| 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": 1.
|
| 1121 |
"train_batch_size": 4,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.405928611755371,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.11379800853485064,
|
| 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": 4.202,
|
| 1090 |
"eval_steps_per_second": 1.05,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.08591749644381223,
|
| 1095 |
+
"grad_norm": 0.7843250036239624,
|
| 1096 |
+
"learning_rate": 2.599578947368421e-05,
|
| 1097 |
+
"loss": 2.7679,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.08648648648648649,
|
| 1102 |
+
"grad_norm": 0.7846522331237793,
|
| 1103 |
+
"learning_rate": 2.5465263157894738e-05,
|
| 1104 |
+
"loss": 2.8495,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.08705547652916074,
|
| 1109 |
+
"grad_norm": 0.9606564044952393,
|
| 1110 |
+
"learning_rate": 2.493473684210526e-05,
|
| 1111 |
+
"loss": 3.2779,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.087624466571835,
|
| 1116 |
+
"grad_norm": 0.9346444010734558,
|
| 1117 |
+
"learning_rate": 2.440421052631579e-05,
|
| 1118 |
+
"loss": 3.0407,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.08819345661450925,
|
| 1123 |
+
"grad_norm": 0.9511997699737549,
|
| 1124 |
+
"learning_rate": 2.3873684210526313e-05,
|
| 1125 |
+
"loss": 2.9737,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.0887624466571835,
|
| 1130 |
+
"grad_norm": 0.8434960246086121,
|
| 1131 |
+
"learning_rate": 2.3343157894736843e-05,
|
| 1132 |
+
"loss": 3.0923,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.08933143669985776,
|
| 1137 |
+
"grad_norm": 0.879172146320343,
|
| 1138 |
+
"learning_rate": 2.281263157894737e-05,
|
| 1139 |
+
"loss": 2.9789,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.089900426742532,
|
| 1144 |
+
"grad_norm": 0.8454552292823792,
|
| 1145 |
+
"learning_rate": 2.2282105263157892e-05,
|
| 1146 |
+
"loss": 3.0846,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.09046941678520626,
|
| 1151 |
+
"grad_norm": 0.8216034770011902,
|
| 1152 |
+
"learning_rate": 2.175157894736842e-05,
|
| 1153 |
+
"loss": 3.3177,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.09103840682788052,
|
| 1158 |
+
"grad_norm": 0.7577628493309021,
|
| 1159 |
+
"learning_rate": 2.1221052631578944e-05,
|
| 1160 |
+
"loss": 3.1528,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.09160739687055476,
|
| 1165 |
+
"grad_norm": 0.7628657221794128,
|
| 1166 |
+
"learning_rate": 2.0690526315789474e-05,
|
| 1167 |
+
"loss": 2.8293,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.09217638691322902,
|
| 1172 |
+
"grad_norm": 0.7651684880256653,
|
| 1173 |
+
"learning_rate": 2.016e-05,
|
| 1174 |
+
"loss": 3.1117,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.09274537695590328,
|
| 1179 |
+
"grad_norm": 0.7415760159492493,
|
| 1180 |
+
"learning_rate": 1.9629473684210526e-05,
|
| 1181 |
+
"loss": 2.7282,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.09331436699857752,
|
| 1186 |
+
"grad_norm": 0.8385205864906311,
|
| 1187 |
+
"learning_rate": 1.9098947368421053e-05,
|
| 1188 |
+
"loss": 2.8437,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.09388335704125178,
|
| 1193 |
+
"grad_norm": 0.8416845202445984,
|
| 1194 |
+
"learning_rate": 1.856842105263158e-05,
|
| 1195 |
+
"loss": 2.8249,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.09445234708392602,
|
| 1200 |
+
"grad_norm": 0.7852922677993774,
|
| 1201 |
+
"learning_rate": 1.8037894736842105e-05,
|
| 1202 |
+
"loss": 2.8207,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.09502133712660028,
|
| 1207 |
+
"grad_norm": 0.7799615263938904,
|
| 1208 |
+
"learning_rate": 1.750736842105263e-05,
|
| 1209 |
+
"loss": 3.0993,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.09559032716927454,
|
| 1214 |
+
"grad_norm": 0.8300429582595825,
|
| 1215 |
+
"learning_rate": 1.6976842105263157e-05,
|
| 1216 |
+
"loss": 2.8778,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.09615931721194879,
|
| 1221 |
+
"grad_norm": 0.8431521654129028,
|
| 1222 |
+
"learning_rate": 1.6446315789473684e-05,
|
| 1223 |
+
"loss": 3.0726,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.09672830725462304,
|
| 1228 |
+
"grad_norm": 0.9213804602622986,
|
| 1229 |
+
"learning_rate": 1.591578947368421e-05,
|
| 1230 |
+
"loss": 2.9397,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.0972972972972973,
|
| 1235 |
+
"grad_norm": 0.8189807534217834,
|
| 1236 |
+
"learning_rate": 1.5385263157894736e-05,
|
| 1237 |
+
"loss": 3.004,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.09786628733997155,
|
| 1242 |
+
"grad_norm": 0.8088762760162354,
|
| 1243 |
+
"learning_rate": 1.485473684210526e-05,
|
| 1244 |
+
"loss": 2.9671,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.0984352773826458,
|
| 1249 |
+
"grad_norm": 0.7970319986343384,
|
| 1250 |
+
"learning_rate": 1.4324210526315789e-05,
|
| 1251 |
+
"loss": 3.0041,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.09900426742532005,
|
| 1256 |
+
"grad_norm": 0.8069632649421692,
|
| 1257 |
+
"learning_rate": 1.3793684210526316e-05,
|
| 1258 |
+
"loss": 2.9655,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.09957325746799431,
|
| 1263 |
+
"grad_norm": 0.8151662349700928,
|
| 1264 |
+
"learning_rate": 1.3263157894736841e-05,
|
| 1265 |
+
"loss": 2.8613,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.10014224751066857,
|
| 1270 |
+
"grad_norm": 0.9155776500701904,
|
| 1271 |
+
"learning_rate": 1.2732631578947369e-05,
|
| 1272 |
+
"loss": 2.8786,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.10071123755334281,
|
| 1277 |
+
"grad_norm": 0.7725786566734314,
|
| 1278 |
+
"learning_rate": 1.2202105263157895e-05,
|
| 1279 |
+
"loss": 2.7416,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.10128022759601707,
|
| 1284 |
+
"grad_norm": 0.8339952230453491,
|
| 1285 |
+
"learning_rate": 1.1671578947368421e-05,
|
| 1286 |
+
"loss": 2.7873,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.10184921763869133,
|
| 1291 |
+
"grad_norm": 0.8299411535263062,
|
| 1292 |
+
"learning_rate": 1.1141052631578946e-05,
|
| 1293 |
+
"loss": 2.7875,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.10241820768136557,
|
| 1298 |
+
"grad_norm": 0.9416133761405945,
|
| 1299 |
+
"learning_rate": 1.0610526315789472e-05,
|
| 1300 |
+
"loss": 2.9303,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.10298719772403983,
|
| 1305 |
+
"grad_norm": 0.8860821723937988,
|
| 1306 |
+
"learning_rate": 1.008e-05,
|
| 1307 |
+
"loss": 2.7522,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.10355618776671409,
|
| 1312 |
+
"grad_norm": 0.8492652773857117,
|
| 1313 |
+
"learning_rate": 9.549473684210526e-06,
|
| 1314 |
+
"loss": 2.7127,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.10412517780938833,
|
| 1319 |
+
"grad_norm": 0.8111841678619385,
|
| 1320 |
+
"learning_rate": 9.018947368421052e-06,
|
| 1321 |
+
"loss": 2.8087,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.10469416785206259,
|
| 1326 |
+
"grad_norm": 0.8741388916969299,
|
| 1327 |
+
"learning_rate": 8.488421052631579e-06,
|
| 1328 |
+
"loss": 2.9206,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.10526315789473684,
|
| 1333 |
+
"grad_norm": 1.0461604595184326,
|
| 1334 |
+
"learning_rate": 7.957894736842105e-06,
|
| 1335 |
+
"loss": 3.0844,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.1058321479374111,
|
| 1340 |
+
"grad_norm": 0.9712023138999939,
|
| 1341 |
+
"learning_rate": 7.42736842105263e-06,
|
| 1342 |
+
"loss": 3.0991,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.10640113798008535,
|
| 1347 |
+
"grad_norm": 0.9134138226509094,
|
| 1348 |
+
"learning_rate": 6.896842105263158e-06,
|
| 1349 |
+
"loss": 2.8668,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.1069701280227596,
|
| 1354 |
+
"grad_norm": 0.9476480484008789,
|
| 1355 |
+
"learning_rate": 6.3663157894736845e-06,
|
| 1356 |
+
"loss": 3.0572,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.10753911806543386,
|
| 1361 |
+
"grad_norm": 0.9557372331619263,
|
| 1362 |
+
"learning_rate": 5.835789473684211e-06,
|
| 1363 |
+
"loss": 3.0734,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.10810810810810811,
|
| 1368 |
+
"grad_norm": 1.0418270826339722,
|
| 1369 |
+
"learning_rate": 5.305263157894736e-06,
|
| 1370 |
+
"loss": 3.2696,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.10867709815078236,
|
| 1375 |
+
"grad_norm": 1.0057651996612549,
|
| 1376 |
+
"learning_rate": 4.774736842105263e-06,
|
| 1377 |
+
"loss": 3.0763,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.10924608819345662,
|
| 1382 |
+
"grad_norm": 0.937343180179596,
|
| 1383 |
+
"learning_rate": 4.244210526315789e-06,
|
| 1384 |
+
"loss": 2.7003,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.10981507823613086,
|
| 1389 |
+
"grad_norm": 0.965437114238739,
|
| 1390 |
+
"learning_rate": 3.713684210526315e-06,
|
| 1391 |
+
"loss": 2.4666,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.11038406827880512,
|
| 1396 |
+
"grad_norm": 0.9241202473640442,
|
| 1397 |
+
"learning_rate": 3.1831578947368422e-06,
|
| 1398 |
+
"loss": 1.7998,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.11095305832147938,
|
| 1403 |
+
"grad_norm": 0.9487320184707642,
|
| 1404 |
+
"learning_rate": 2.652631578947368e-06,
|
| 1405 |
+
"loss": 1.6532,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.11152204836415362,
|
| 1410 |
+
"grad_norm": 1.029417872428894,
|
| 1411 |
+
"learning_rate": 2.1221052631578947e-06,
|
| 1412 |
+
"loss": 1.8063,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.11209103840682788,
|
| 1417 |
+
"grad_norm": 1.0649429559707642,
|
| 1418 |
+
"learning_rate": 1.5915789473684211e-06,
|
| 1419 |
+
"loss": 1.7311,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.11266002844950214,
|
| 1424 |
+
"grad_norm": 1.1187015771865845,
|
| 1425 |
+
"learning_rate": 1.0610526315789473e-06,
|
| 1426 |
+
"loss": 1.806,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.11322901849217638,
|
| 1431 |
+
"grad_norm": 1.6845424175262451,
|
| 1432 |
+
"learning_rate": 5.305263157894737e-07,
|
| 1433 |
+
"loss": 2.2611,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.11379800853485064,
|
| 1438 |
+
"grad_norm": 2.280428886413574,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 2.5917,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.11379800853485064,
|
| 1445 |
+
"eval_loss": 1.405928611755371,
|
| 1446 |
+
"eval_runtime": 176.2442,
|
| 1447 |
+
"eval_samples_per_second": 4.199,
|
| 1448 |
+
"eval_steps_per_second": 1.05,
|
| 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": 1.967507103547392e+17,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|