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 78207176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17dd12ccc4edab5612b37b8279b9c38369e73abaecd142f86e6526c852b46400
|
| 3 |
size 78207176
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 40177764
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80d185261203b02163bf268d37dd9685680ec8577214859703dca23446c018de
|
| 3 |
size 40177764
|
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 sha256:88dbc236c500062b328da7c75fdeb7d199dd658d4e28f80b5279062b2466234b
|
| 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:ca62d85cf5423834480d3c20680f93b185c8e6574a8a14021d285e0b05c7449f
|
| 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": 1.
|
| 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": 64.297,
|
| 1090 |
"eval_steps_per_second": 16.074,
|
| 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": 0.15735851228237152,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 1.5344827586206895,
|
| 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": 64.297,
|
| 1090 |
"eval_steps_per_second": 16.074,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.1590038314176245,
|
| 1095 |
+
"grad_norm": 0.09190652519464493,
|
| 1096 |
+
"learning_rate": 9.319397726443026e-06,
|
| 1097 |
+
"loss": 0.08,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.1666666666666667,
|
| 1102 |
+
"grad_norm": 0.08560865372419357,
|
| 1103 |
+
"learning_rate": 8.962896471825342e-06,
|
| 1104 |
+
"loss": 0.1018,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 1.1743295019157087,
|
| 1109 |
+
"grad_norm": 0.09749860316514969,
|
| 1110 |
+
"learning_rate": 8.61214655125809e-06,
|
| 1111 |
+
"loss": 0.0997,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 1.181992337164751,
|
| 1116 |
+
"grad_norm": 0.0863884836435318,
|
| 1117 |
+
"learning_rate": 8.267243856267331e-06,
|
| 1118 |
+
"loss": 0.1043,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 1.1896551724137931,
|
| 1123 |
+
"grad_norm": 0.09674271196126938,
|
| 1124 |
+
"learning_rate": 7.928282679806052e-06,
|
| 1125 |
+
"loss": 0.0869,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.1973180076628354,
|
| 1130 |
+
"grad_norm": 0.09813065826892853,
|
| 1131 |
+
"learning_rate": 7.595355690475393e-06,
|
| 1132 |
+
"loss": 0.115,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.2049808429118773,
|
| 1137 |
+
"grad_norm": 0.11123661696910858,
|
| 1138 |
+
"learning_rate": 7.268553907189964e-06,
|
| 1139 |
+
"loss": 0.1153,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 1.2126436781609196,
|
| 1144 |
+
"grad_norm": 0.1099216416478157,
|
| 1145 |
+
"learning_rate": 6.947966674294236e-06,
|
| 1146 |
+
"loss": 0.1313,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 1.2203065134099618,
|
| 1151 |
+
"grad_norm": 0.12104592472314835,
|
| 1152 |
+
"learning_rate": 6.6336816371366305e-06,
|
| 1153 |
+
"loss": 0.175,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 1.2279693486590038,
|
| 1158 |
+
"grad_norm": 0.14585037529468536,
|
| 1159 |
+
"learning_rate": 6.325784718108196e-06,
|
| 1160 |
+
"loss": 0.1442,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 1.235632183908046,
|
| 1165 |
+
"grad_norm": 0.162072092294693,
|
| 1166 |
+
"learning_rate": 6.0243600931522595e-06,
|
| 1167 |
+
"loss": 0.1529,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 1.2432950191570882,
|
| 1172 |
+
"grad_norm": 0.22925086319446564,
|
| 1173 |
+
"learning_rate": 5.72949016875158e-06,
|
| 1174 |
+
"loss": 0.1984,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 1.2509578544061304,
|
| 1179 |
+
"grad_norm": 0.13616731762886047,
|
| 1180 |
+
"learning_rate": 5.44125555939923e-06,
|
| 1181 |
+
"loss": 0.2254,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 1.2586206896551724,
|
| 1186 |
+
"grad_norm": 0.14947763085365295,
|
| 1187 |
+
"learning_rate": 5.159735065559399e-06,
|
| 1188 |
+
"loss": 0.379,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 1.2662835249042146,
|
| 1193 |
+
"grad_norm": 0.10282624512910843,
|
| 1194 |
+
"learning_rate": 4.885005652124144e-06,
|
| 1195 |
+
"loss": 0.3126,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 1.2739463601532566,
|
| 1200 |
+
"grad_norm": 0.12892718613147736,
|
| 1201 |
+
"learning_rate": 4.617142427371934e-06,
|
| 1202 |
+
"loss": 0.4403,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 1.2816091954022988,
|
| 1207 |
+
"grad_norm": 0.09580893069505692,
|
| 1208 |
+
"learning_rate": 4.3562186224338265e-06,
|
| 1209 |
+
"loss": 0.2804,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 1.289272030651341,
|
| 1214 |
+
"grad_norm": 0.07744543999433517,
|
| 1215 |
+
"learning_rate": 4.102305571272783e-06,
|
| 1216 |
+
"loss": 0.2067,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 1.2969348659003832,
|
| 1221 |
+
"grad_norm": 0.08755867183208466,
|
| 1222 |
+
"learning_rate": 3.855472691181678e-06,
|
| 1223 |
+
"loss": 0.2504,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 1.3045977011494254,
|
| 1228 |
+
"grad_norm": 0.07829572260379791,
|
| 1229 |
+
"learning_rate": 3.615787463805331e-06,
|
| 1230 |
+
"loss": 0.1686,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 1.3122605363984674,
|
| 1235 |
+
"grad_norm": 0.06435937434434891,
|
| 1236 |
+
"learning_rate": 3.383315416691646e-06,
|
| 1237 |
+
"loss": 0.1323,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 1.3199233716475096,
|
| 1242 |
+
"grad_norm": 0.11443574726581573,
|
| 1243 |
+
"learning_rate": 3.158120105377096e-06,
|
| 1244 |
+
"loss": 0.1042,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 1.3275862068965516,
|
| 1249 |
+
"grad_norm": 0.0844988003373146,
|
| 1250 |
+
"learning_rate": 2.940263096011233e-06,
|
| 1251 |
+
"loss": 0.1191,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 1.3352490421455938,
|
| 1256 |
+
"grad_norm": 0.07520398497581482,
|
| 1257 |
+
"learning_rate": 2.729803948525125e-06,
|
| 1258 |
+
"loss": 0.0742,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 1.342911877394636,
|
| 1263 |
+
"grad_norm": 0.08877892047166824,
|
| 1264 |
+
"learning_rate": 2.526800200348275e-06,
|
| 1265 |
+
"loss": 0.1036,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 1.3505747126436782,
|
| 1270 |
+
"grad_norm": 0.09079942852258682,
|
| 1271 |
+
"learning_rate": 2.3313073506784575e-06,
|
| 1272 |
+
"loss": 0.1974,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 1.3582375478927204,
|
| 1277 |
+
"grad_norm": 0.06422315537929535,
|
| 1278 |
+
"learning_rate": 2.143378845308791e-06,
|
| 1279 |
+
"loss": 0.0846,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 1.3659003831417624,
|
| 1284 |
+
"grad_norm": 0.08929227292537689,
|
| 1285 |
+
"learning_rate": 1.9630660620161777e-06,
|
| 1286 |
+
"loss": 0.2096,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 1.3735632183908046,
|
| 1291 |
+
"grad_norm": 0.0649232268333435,
|
| 1292 |
+
"learning_rate": 1.790418296515165e-06,
|
| 1293 |
+
"loss": 0.0711,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 1.3812260536398466,
|
| 1298 |
+
"grad_norm": 0.06585374474525452,
|
| 1299 |
+
"learning_rate": 1.625482748980961e-06,
|
| 1300 |
+
"loss": 0.0756,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 1.3888888888888888,
|
| 1305 |
+
"grad_norm": 0.08487678319215775,
|
| 1306 |
+
"learning_rate": 1.4683045111453942e-06,
|
| 1307 |
+
"loss": 0.1589,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 1.396551724137931,
|
| 1312 |
+
"grad_norm": 0.08722589910030365,
|
| 1313 |
+
"learning_rate": 1.3189265539692707e-06,
|
| 1314 |
+
"loss": 0.0999,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 1.4042145593869733,
|
| 1319 |
+
"grad_norm": 0.066057488322258,
|
| 1320 |
+
"learning_rate": 1.1773897158945557e-06,
|
| 1321 |
+
"loss": 0.0952,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 1.4118773946360152,
|
| 1326 |
+
"grad_norm": 0.07314711809158325,
|
| 1327 |
+
"learning_rate": 1.0437326916795432e-06,
|
| 1328 |
+
"loss": 0.0918,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 1.4195402298850575,
|
| 1333 |
+
"grad_norm": 0.08497738838195801,
|
| 1334 |
+
"learning_rate": 9.179920218200888e-07,
|
| 1335 |
+
"loss": 0.0882,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 1.4272030651340997,
|
| 1340 |
+
"grad_norm": 0.08262482285499573,
|
| 1341 |
+
"learning_rate": 8.002020825598277e-07,
|
| 1342 |
+
"loss": 0.0782,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 1.4348659003831417,
|
| 1347 |
+
"grad_norm": 0.10725460946559906,
|
| 1348 |
+
"learning_rate": 6.90395076492022e-07,
|
| 1349 |
+
"loss": 0.1653,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 1.4425287356321839,
|
| 1354 |
+
"grad_norm": 0.0954778790473938,
|
| 1355 |
+
"learning_rate": 5.886010237557194e-07,
|
| 1356 |
+
"loss": 0.1031,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 1.450191570881226,
|
| 1361 |
+
"grad_norm": 0.08982761204242706,
|
| 1362 |
+
"learning_rate": 4.94847753828529e-07,
|
| 1363 |
+
"loss": 0.0956,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 1.4578544061302683,
|
| 1368 |
+
"grad_norm": 0.10045281052589417,
|
| 1369 |
+
"learning_rate": 4.091608979183303e-07,
|
| 1370 |
+
"loss": 0.1225,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 1.4655172413793103,
|
| 1375 |
+
"grad_norm": 0.11967014521360397,
|
| 1376 |
+
"learning_rate": 3.315638819559452e-07,
|
| 1377 |
+
"loss": 0.1291,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 1.4731800766283525,
|
| 1382 |
+
"grad_norm": 0.15871833264827728,
|
| 1383 |
+
"learning_rate": 2.6207792019074414e-07,
|
| 1384 |
+
"loss": 0.1136,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 1.4808429118773947,
|
| 1389 |
+
"grad_norm": 0.15147604048252106,
|
| 1390 |
+
"learning_rate": 2.0072200939085573e-07,
|
| 1391 |
+
"loss": 0.1825,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 1.4885057471264367,
|
| 1396 |
+
"grad_norm": 0.19062329828739166,
|
| 1397 |
+
"learning_rate": 1.475129236496575e-07,
|
| 1398 |
+
"loss": 0.176,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 1.496168582375479,
|
| 1403 |
+
"grad_norm": 0.10360642522573471,
|
| 1404 |
+
"learning_rate": 1.0246520979990459e-07,
|
| 1405 |
+
"loss": 0.2787,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 1.503831417624521,
|
| 1410 |
+
"grad_norm": 0.09995601326227188,
|
| 1411 |
+
"learning_rate": 6.559118343676396e-08,
|
| 1412 |
+
"loss": 0.2528,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 1.5114942528735633,
|
| 1417 |
+
"grad_norm": 0.11199713498353958,
|
| 1418 |
+
"learning_rate": 3.690092555085789e-08,
|
| 1419 |
+
"loss": 0.2772,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 1.5191570881226055,
|
| 1424 |
+
"grad_norm": 0.09361888468265533,
|
| 1425 |
+
"learning_rate": 1.640227977221853e-08,
|
| 1426 |
+
"loss": 0.2773,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 1.5268199233716475,
|
| 1431 |
+
"grad_norm": 0.09406208992004395,
|
| 1432 |
+
"learning_rate": 4.1008502259298755e-09,
|
| 1433 |
+
"loss": 0.2662,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 1.5344827586206895,
|
| 1438 |
+
"grad_norm": 0.10898585617542267,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.3079,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 1.5344827586206895,
|
| 1445 |
+
"eval_loss": 0.15735851228237152,
|
| 1446 |
+
"eval_runtime": 3.4239,
|
| 1447 |
+
"eval_samples_per_second": 64.254,
|
| 1448 |
+
"eval_steps_per_second": 16.064,
|
| 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": 7132227890577408.0,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|