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 201353800
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c8972abe9a71ea8432999ee2059aeaefb0081c5426aae5f97d47c8db86ab930
|
| 3 |
size 201353800
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 102462970
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:938b5fa3a467b688ea7b7c5133e893c97a7ff43ee97aa57c7764d459fbe57167
|
| 3 |
size 102462970
|
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:bfb6c4d15023b7f825314115ec967db308a5e76c09b6d9ab6b0f43eb8cd472ab
|
| 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 sha256:3709ad194ceda6ee92d3d2c8f2dd5203a40bedaa701af97b45dc02564222704e
|
| 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": 17.612,
|
| 1090 |
"eval_steps_per_second": 4.405,
|
| 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": 0.8893836140632629,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.015716474794703547,
|
| 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": 17.612,
|
| 1090 |
"eval_steps_per_second": 4.405,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.011865938470001178,
|
| 1095 |
+
"grad_norm": 1.8181077241897583,
|
| 1096 |
+
"learning_rate": 2.597e-05,
|
| 1097 |
+
"loss": 1.7493,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.011944520843974696,
|
| 1102 |
+
"grad_norm": 2.076934576034546,
|
| 1103 |
+
"learning_rate": 2.544e-05,
|
| 1104 |
+
"loss": 1.7957,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.012023103217948214,
|
| 1109 |
+
"grad_norm": 2.1660921573638916,
|
| 1110 |
+
"learning_rate": 2.4909999999999997e-05,
|
| 1111 |
+
"loss": 1.5835,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.012101685591921731,
|
| 1116 |
+
"grad_norm": 1.9632174968719482,
|
| 1117 |
+
"learning_rate": 2.438e-05,
|
| 1118 |
+
"loss": 1.5994,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.012180267965895249,
|
| 1123 |
+
"grad_norm": 2.900998115539551,
|
| 1124 |
+
"learning_rate": 2.3849999999999997e-05,
|
| 1125 |
+
"loss": 2.1993,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.012258850339868767,
|
| 1130 |
+
"grad_norm": 2.372654914855957,
|
| 1131 |
+
"learning_rate": 2.3319999999999997e-05,
|
| 1132 |
+
"loss": 1.7,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.012337432713842285,
|
| 1137 |
+
"grad_norm": 2.6485414505004883,
|
| 1138 |
+
"learning_rate": 2.279e-05,
|
| 1139 |
+
"loss": 1.5784,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.012416015087815802,
|
| 1144 |
+
"grad_norm": 2.039062738418579,
|
| 1145 |
+
"learning_rate": 2.2259999999999997e-05,
|
| 1146 |
+
"loss": 1.7178,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.01249459746178932,
|
| 1151 |
+
"grad_norm": 2.2866334915161133,
|
| 1152 |
+
"learning_rate": 2.173e-05,
|
| 1153 |
+
"loss": 1.7329,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.012573179835762838,
|
| 1158 |
+
"grad_norm": 2.146287202835083,
|
| 1159 |
+
"learning_rate": 2.1199999999999997e-05,
|
| 1160 |
+
"loss": 1.8941,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.012651762209736355,
|
| 1165 |
+
"grad_norm": 2.0105912685394287,
|
| 1166 |
+
"learning_rate": 2.067e-05,
|
| 1167 |
+
"loss": 1.446,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.012730344583709873,
|
| 1172 |
+
"grad_norm": 2.406883716583252,
|
| 1173 |
+
"learning_rate": 2.014e-05,
|
| 1174 |
+
"loss": 1.9801,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.012808926957683391,
|
| 1179 |
+
"grad_norm": 2.3333377838134766,
|
| 1180 |
+
"learning_rate": 1.9609999999999997e-05,
|
| 1181 |
+
"loss": 1.7974,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.012887509331656909,
|
| 1186 |
+
"grad_norm": 2.1827352046966553,
|
| 1187 |
+
"learning_rate": 1.908e-05,
|
| 1188 |
+
"loss": 1.4272,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.012966091705630426,
|
| 1193 |
+
"grad_norm": 2.277249574661255,
|
| 1194 |
+
"learning_rate": 1.8549999999999997e-05,
|
| 1195 |
+
"loss": 1.7542,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.013044674079603944,
|
| 1200 |
+
"grad_norm": 2.420073986053467,
|
| 1201 |
+
"learning_rate": 1.802e-05,
|
| 1202 |
+
"loss": 1.791,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.013123256453577462,
|
| 1207 |
+
"grad_norm": 2.2049803733825684,
|
| 1208 |
+
"learning_rate": 1.749e-05,
|
| 1209 |
+
"loss": 1.6978,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.01320183882755098,
|
| 1214 |
+
"grad_norm": 2.5003433227539062,
|
| 1215 |
+
"learning_rate": 1.696e-05,
|
| 1216 |
+
"loss": 1.7995,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.013280421201524497,
|
| 1221 |
+
"grad_norm": 2.038902997970581,
|
| 1222 |
+
"learning_rate": 1.643e-05,
|
| 1223 |
+
"loss": 1.8227,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.013359003575498015,
|
| 1228 |
+
"grad_norm": 2.4974002838134766,
|
| 1229 |
+
"learning_rate": 1.5899999999999997e-05,
|
| 1230 |
+
"loss": 1.7088,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.013437585949471533,
|
| 1235 |
+
"grad_norm": 2.4527053833007812,
|
| 1236 |
+
"learning_rate": 1.537e-05,
|
| 1237 |
+
"loss": 1.909,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.01351616832344505,
|
| 1242 |
+
"grad_norm": 2.499253273010254,
|
| 1243 |
+
"learning_rate": 1.4839999999999999e-05,
|
| 1244 |
+
"loss": 1.5983,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.013594750697418568,
|
| 1249 |
+
"grad_norm": 2.979060411453247,
|
| 1250 |
+
"learning_rate": 1.4309999999999999e-05,
|
| 1251 |
+
"loss": 2.1447,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.013673333071392086,
|
| 1256 |
+
"grad_norm": 2.4462897777557373,
|
| 1257 |
+
"learning_rate": 1.378e-05,
|
| 1258 |
+
"loss": 2.0196,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.013751915445365604,
|
| 1263 |
+
"grad_norm": 2.631182909011841,
|
| 1264 |
+
"learning_rate": 1.3249999999999999e-05,
|
| 1265 |
+
"loss": 1.8259,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.013830497819339121,
|
| 1270 |
+
"grad_norm": 2.4574482440948486,
|
| 1271 |
+
"learning_rate": 1.272e-05,
|
| 1272 |
+
"loss": 1.8608,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.01390908019331264,
|
| 1277 |
+
"grad_norm": 2.9573817253112793,
|
| 1278 |
+
"learning_rate": 1.219e-05,
|
| 1279 |
+
"loss": 2.0493,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.013987662567286157,
|
| 1284 |
+
"grad_norm": 2.3067586421966553,
|
| 1285 |
+
"learning_rate": 1.1659999999999998e-05,
|
| 1286 |
+
"loss": 1.6649,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.014066244941259675,
|
| 1291 |
+
"grad_norm": 2.3453915119171143,
|
| 1292 |
+
"learning_rate": 1.1129999999999998e-05,
|
| 1293 |
+
"loss": 1.8298,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.014144827315233192,
|
| 1298 |
+
"grad_norm": 2.4115869998931885,
|
| 1299 |
+
"learning_rate": 1.0599999999999998e-05,
|
| 1300 |
+
"loss": 1.8186,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.01422340968920671,
|
| 1305 |
+
"grad_norm": 3.03613018989563,
|
| 1306 |
+
"learning_rate": 1.007e-05,
|
| 1307 |
+
"loss": 1.6435,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.014301992063180228,
|
| 1312 |
+
"grad_norm": 2.7698209285736084,
|
| 1313 |
+
"learning_rate": 9.54e-06,
|
| 1314 |
+
"loss": 2.1196,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.014380574437153746,
|
| 1319 |
+
"grad_norm": 3.2634527683258057,
|
| 1320 |
+
"learning_rate": 9.01e-06,
|
| 1321 |
+
"loss": 1.914,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.014459156811127263,
|
| 1326 |
+
"grad_norm": 2.814863443374634,
|
| 1327 |
+
"learning_rate": 8.48e-06,
|
| 1328 |
+
"loss": 1.9775,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.014537739185100781,
|
| 1333 |
+
"grad_norm": 2.700026750564575,
|
| 1334 |
+
"learning_rate": 7.949999999999998e-06,
|
| 1335 |
+
"loss": 1.8949,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.014616321559074299,
|
| 1340 |
+
"grad_norm": 2.699542999267578,
|
| 1341 |
+
"learning_rate": 7.419999999999999e-06,
|
| 1342 |
+
"loss": 1.9938,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.014694903933047817,
|
| 1347 |
+
"grad_norm": 2.8317461013793945,
|
| 1348 |
+
"learning_rate": 6.89e-06,
|
| 1349 |
+
"loss": 1.9413,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.014773486307021334,
|
| 1354 |
+
"grad_norm": 2.5641987323760986,
|
| 1355 |
+
"learning_rate": 6.36e-06,
|
| 1356 |
+
"loss": 1.7367,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.014852068680994852,
|
| 1361 |
+
"grad_norm": 2.798137903213501,
|
| 1362 |
+
"learning_rate": 5.829999999999999e-06,
|
| 1363 |
+
"loss": 1.896,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.01493065105496837,
|
| 1368 |
+
"grad_norm": 2.7922170162200928,
|
| 1369 |
+
"learning_rate": 5.299999999999999e-06,
|
| 1370 |
+
"loss": 1.9496,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.015009233428941888,
|
| 1375 |
+
"grad_norm": 3.278426170349121,
|
| 1376 |
+
"learning_rate": 4.77e-06,
|
| 1377 |
+
"loss": 1.742,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.015087815802915405,
|
| 1382 |
+
"grad_norm": 2.9624500274658203,
|
| 1383 |
+
"learning_rate": 4.24e-06,
|
| 1384 |
+
"loss": 2.2221,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.015166398176888923,
|
| 1389 |
+
"grad_norm": 3.408240556716919,
|
| 1390 |
+
"learning_rate": 3.7099999999999996e-06,
|
| 1391 |
+
"loss": 1.879,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.01524498055086244,
|
| 1396 |
+
"grad_norm": 2.60992169380188,
|
| 1397 |
+
"learning_rate": 3.18e-06,
|
| 1398 |
+
"loss": 1.9405,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.015323562924835958,
|
| 1403 |
+
"grad_norm": 2.4439897537231445,
|
| 1404 |
+
"learning_rate": 2.6499999999999996e-06,
|
| 1405 |
+
"loss": 1.3485,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.015402145298809476,
|
| 1410 |
+
"grad_norm": 3.6060919761657715,
|
| 1411 |
+
"learning_rate": 2.12e-06,
|
| 1412 |
+
"loss": 2.2208,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.015480727672782994,
|
| 1417 |
+
"grad_norm": 3.201261281967163,
|
| 1418 |
+
"learning_rate": 1.59e-06,
|
| 1419 |
+
"loss": 1.9352,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.015559310046756512,
|
| 1424 |
+
"grad_norm": 3.102384328842163,
|
| 1425 |
+
"learning_rate": 1.06e-06,
|
| 1426 |
+
"loss": 1.9048,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.01563789242073003,
|
| 1431 |
+
"grad_norm": 3.2906687259674072,
|
| 1432 |
+
"learning_rate": 5.3e-07,
|
| 1433 |
+
"loss": 1.9021,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.015716474794703547,
|
| 1438 |
+
"grad_norm": 2.7191827297210693,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.5233,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.015716474794703547,
|
| 1445 |
+
"eval_loss": 0.8893836140632629,
|
| 1446 |
+
"eval_runtime": 304.9343,
|
| 1447 |
+
"eval_samples_per_second": 17.571,
|
| 1448 |
+
"eval_steps_per_second": 4.394,
|
| 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": 1.23758274674688e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|