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 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0869115c501bcc249f26737ff19caabdb054887e793f2e35f97f89d8ac942c33
|
| 3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 341314196
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64ef611e0ad01235a4ef62dd4f9e2a57cef167b530d2a0c9b326853038d0b913
|
| 3 |
size 341314196
|
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:ccfa543f8bb5dbb36ff648782427c63c8919f2d0a8e556bd1213b9e49ca0307f
|
| 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:c09a3e270daa077e38bac4ad605b0e6c9b43938bcf49dc3d62c3671f11248c14
|
| 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": 12.522,
|
| 1090 |
"eval_steps_per_second": 3.13,
|
| 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": 0.36728447675704956,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.1568627450980392,
|
| 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": 12.522,
|
| 1090 |
"eval_steps_per_second": 3.13,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.11843137254901961,
|
| 1095 |
+
"grad_norm": 3.1740787029266357,
|
| 1096 |
+
"learning_rate": 1.397909658966454e-05,
|
| 1097 |
+
"loss": 3.2078,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.1192156862745098,
|
| 1102 |
+
"grad_norm": 2.5368189811706543,
|
| 1103 |
+
"learning_rate": 1.3444344707738015e-05,
|
| 1104 |
+
"loss": 1.736,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.12,
|
| 1109 |
+
"grad_norm": 2.4591469764709473,
|
| 1110 |
+
"learning_rate": 1.2918219826887136e-05,
|
| 1111 |
+
"loss": 1.6981,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.1207843137254902,
|
| 1116 |
+
"grad_norm": 2.356226921081543,
|
| 1117 |
+
"learning_rate": 1.2400865784400998e-05,
|
| 1118 |
+
"loss": 1.3207,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.12156862745098039,
|
| 1123 |
+
"grad_norm": 2.378990888595581,
|
| 1124 |
+
"learning_rate": 1.189242401970908e-05,
|
| 1125 |
+
"loss": 1.3112,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.1223529411764706,
|
| 1130 |
+
"grad_norm": 2.623610734939575,
|
| 1131 |
+
"learning_rate": 1.139303353571309e-05,
|
| 1132 |
+
"loss": 1.2035,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.12313725490196079,
|
| 1137 |
+
"grad_norm": 2.538539409637451,
|
| 1138 |
+
"learning_rate": 1.0902830860784946e-05,
|
| 1139 |
+
"loss": 1.1537,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.12392156862745098,
|
| 1144 |
+
"grad_norm": 2.950873613357544,
|
| 1145 |
+
"learning_rate": 1.0421950011441355e-05,
|
| 1146 |
+
"loss": 1.091,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.12470588235294118,
|
| 1151 |
+
"grad_norm": 3.1460249423980713,
|
| 1152 |
+
"learning_rate": 9.950522455704946e-06,
|
| 1153 |
+
"loss": 1.4024,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.12549019607843137,
|
| 1158 |
+
"grad_norm": 3.339446544647217,
|
| 1159 |
+
"learning_rate": 9.488677077162294e-06,
|
| 1160 |
+
"loss": 1.3126,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.12627450980392158,
|
| 1165 |
+
"grad_norm": 3.6245152950286865,
|
| 1166 |
+
"learning_rate": 9.03654013972839e-06,
|
| 1167 |
+
"loss": 1.4356,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.12705882352941175,
|
| 1172 |
+
"grad_norm": 3.8416507244110107,
|
| 1173 |
+
"learning_rate": 8.59423525312737e-06,
|
| 1174 |
+
"loss": 1.3236,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.12784313725490196,
|
| 1179 |
+
"grad_norm": 4.071051120758057,
|
| 1180 |
+
"learning_rate": 8.161883339098845e-06,
|
| 1181 |
+
"loss": 1.4993,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.12862745098039216,
|
| 1186 |
+
"grad_norm": 4.043711185455322,
|
| 1187 |
+
"learning_rate": 7.739602598339099e-06,
|
| 1188 |
+
"loss": 1.6008,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.12941176470588237,
|
| 1193 |
+
"grad_norm": 3.690749168395996,
|
| 1194 |
+
"learning_rate": 7.327508478186216e-06,
|
| 1195 |
+
"loss": 1.1721,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.13019607843137254,
|
| 1200 |
+
"grad_norm": 3.896296262741089,
|
| 1201 |
+
"learning_rate": 6.925713641057902e-06,
|
| 1202 |
+
"loss": 1.2947,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.13098039215686275,
|
| 1207 |
+
"grad_norm": 3.99424409866333,
|
| 1208 |
+
"learning_rate": 6.53432793365074e-06,
|
| 1209 |
+
"loss": 1.28,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.13176470588235295,
|
| 1214 |
+
"grad_norm": 4.055082321166992,
|
| 1215 |
+
"learning_rate": 6.153458356909174e-06,
|
| 1216 |
+
"loss": 1.0857,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.13254901960784313,
|
| 1221 |
+
"grad_norm": 4.159709930419922,
|
| 1222 |
+
"learning_rate": 5.783209036772518e-06,
|
| 1223 |
+
"loss": 1.1397,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.13333333333333333,
|
| 1228 |
+
"grad_norm": 4.578479290008545,
|
| 1229 |
+
"learning_rate": 5.423681195707997e-06,
|
| 1230 |
+
"loss": 1.4361,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.13411764705882354,
|
| 1235 |
+
"grad_norm": 5.518746376037598,
|
| 1236 |
+
"learning_rate": 5.074973125037469e-06,
|
| 1237 |
+
"loss": 1.8645,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.1349019607843137,
|
| 1242 |
+
"grad_norm": 4.65179967880249,
|
| 1243 |
+
"learning_rate": 4.737180158065644e-06,
|
| 1244 |
+
"loss": 1.2877,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.13568627450980392,
|
| 1249 |
+
"grad_norm": 4.779722213745117,
|
| 1250 |
+
"learning_rate": 4.41039464401685e-06,
|
| 1251 |
+
"loss": 1.2109,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.13647058823529412,
|
| 1256 |
+
"grad_norm": 4.066786289215088,
|
| 1257 |
+
"learning_rate": 4.094705922787687e-06,
|
| 1258 |
+
"loss": 1.1928,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.13725490196078433,
|
| 1263 |
+
"grad_norm": 4.523605823516846,
|
| 1264 |
+
"learning_rate": 3.7902003005224126e-06,
|
| 1265 |
+
"loss": 1.1624,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.1380392156862745,
|
| 1270 |
+
"grad_norm": 5.148304462432861,
|
| 1271 |
+
"learning_rate": 3.4969610260176865e-06,
|
| 1272 |
+
"loss": 1.0653,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.1388235294117647,
|
| 1277 |
+
"grad_norm": 3.7846312522888184,
|
| 1278 |
+
"learning_rate": 3.2150682679631867e-06,
|
| 1279 |
+
"loss": 0.6153,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.1396078431372549,
|
| 1284 |
+
"grad_norm": 4.997846603393555,
|
| 1285 |
+
"learning_rate": 2.9445990930242668e-06,
|
| 1286 |
+
"loss": 0.9906,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.1403921568627451,
|
| 1291 |
+
"grad_norm": 4.470591068267822,
|
| 1292 |
+
"learning_rate": 2.6856274447727475e-06,
|
| 1293 |
+
"loss": 0.9009,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.1411764705882353,
|
| 1298 |
+
"grad_norm": 4.197781085968018,
|
| 1299 |
+
"learning_rate": 2.4382241234714413e-06,
|
| 1300 |
+
"loss": 0.7853,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.1419607843137255,
|
| 1305 |
+
"grad_norm": 5.868466854095459,
|
| 1306 |
+
"learning_rate": 2.2024567667180914e-06,
|
| 1307 |
+
"loss": 1.2172,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.14274509803921567,
|
| 1312 |
+
"grad_norm": 7.754011154174805,
|
| 1313 |
+
"learning_rate": 1.978389830953906e-06,
|
| 1314 |
+
"loss": 1.363,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.14352941176470588,
|
| 1319 |
+
"grad_norm": 4.4714884757995605,
|
| 1320 |
+
"learning_rate": 1.7660845738418336e-06,
|
| 1321 |
+
"loss": 0.8215,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.14431372549019608,
|
| 1326 |
+
"grad_norm": 5.938106536865234,
|
| 1327 |
+
"learning_rate": 1.5655990375193147e-06,
|
| 1328 |
+
"loss": 1.4177,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.1450980392156863,
|
| 1333 |
+
"grad_norm": 6.424489498138428,
|
| 1334 |
+
"learning_rate": 1.3769880327301332e-06,
|
| 1335 |
+
"loss": 1.4252,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.14588235294117646,
|
| 1340 |
+
"grad_norm": 4.783531188964844,
|
| 1341 |
+
"learning_rate": 1.2003031238397417e-06,
|
| 1342 |
+
"loss": 0.8835,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.14666666666666667,
|
| 1347 |
+
"grad_norm": 7.15680456161499,
|
| 1348 |
+
"learning_rate": 1.035592614738033e-06,
|
| 1349 |
+
"loss": 1.6154,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.14745098039215687,
|
| 1354 |
+
"grad_norm": 7.671852111816406,
|
| 1355 |
+
"learning_rate": 8.829015356335791e-07,
|
| 1356 |
+
"loss": 1.4224,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.14823529411764705,
|
| 1361 |
+
"grad_norm": 8.599688529968262,
|
| 1362 |
+
"learning_rate": 7.422716307427936e-07,
|
| 1363 |
+
"loss": 1.8422,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.14901960784313725,
|
| 1368 |
+
"grad_norm": 9.633552551269531,
|
| 1369 |
+
"learning_rate": 6.137413468774955e-07,
|
| 1370 |
+
"loss": 1.9472,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.14980392156862746,
|
| 1375 |
+
"grad_norm": 7.004188060760498,
|
| 1376 |
+
"learning_rate": 4.973458229339179e-07,
|
| 1377 |
+
"loss": 1.5712,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.15058823529411763,
|
| 1382 |
+
"grad_norm": 8.92959976196289,
|
| 1383 |
+
"learning_rate": 3.9311688028611627e-07,
|
| 1384 |
+
"loss": 1.8607,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.15137254901960784,
|
| 1389 |
+
"grad_norm": 11.083267211914062,
|
| 1390 |
+
"learning_rate": 3.010830140862836e-07,
|
| 1391 |
+
"loss": 1.9006,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.15215686274509804,
|
| 1396 |
+
"grad_norm": 8.419087409973145,
|
| 1397 |
+
"learning_rate": 2.2126938547448627e-07,
|
| 1398 |
+
"loss": 1.9129,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.15294117647058825,
|
| 1403 |
+
"grad_norm": 19.231441497802734,
|
| 1404 |
+
"learning_rate": 1.536978146998569e-07,
|
| 1405 |
+
"loss": 2.5608,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.15372549019607842,
|
| 1410 |
+
"grad_norm": 9.949979782104492,
|
| 1411 |
+
"learning_rate": 9.838677515514594e-08,
|
| 1412 |
+
"loss": 1.9126,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.15450980392156863,
|
| 1417 |
+
"grad_norm": 13.315712928771973,
|
| 1418 |
+
"learning_rate": 5.5351388326286834e-08,
|
| 1419 |
+
"loss": 2.0499,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.15529411764705883,
|
| 1424 |
+
"grad_norm": 14.174652099609375,
|
| 1425 |
+
"learning_rate": 2.4603419658327797e-08,
|
| 1426 |
+
"loss": 2.4591,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.156078431372549,
|
| 1431 |
+
"grad_norm": 15.293482780456543,
|
| 1432 |
+
"learning_rate": 6.151275338894813e-09,
|
| 1433 |
+
"loss": 2.6328,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.1568627450980392,
|
| 1438 |
+
"grad_norm": 13.656365394592285,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 1.9934,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.1568627450980392,
|
| 1445 |
+
"eval_loss": 0.36728447675704956,
|
| 1446 |
+
"eval_runtime": 172.0542,
|
| 1447 |
+
"eval_samples_per_second": 12.484,
|
| 1448 |
+
"eval_steps_per_second": 3.121,
|
| 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": 3.030141694503813e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|