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 295488936
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3bd854e32931a03871efe47b703d705d235c16112352c920e5566e12155f35c6
|
| 3 |
size 295488936
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 591203178
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b084498ca2bff2cb21b8b8a1b9ef6ee4c5019ede28d92927211dccc86b7588f
|
| 3 |
size 591203178
|
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:eda3dea0cdf0feb4317651292698559d84c1ff2174abd86e54d75ecb5a75cc95
|
| 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:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
|
| 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": 28.132,
|
| 1090 |
"eval_steps_per_second": 14.082,
|
| 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": 3.3320932388305664,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.37261294829995345,
|
| 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": 28.132,
|
| 1090 |
"eval_steps_per_second": 14.082,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.2813227759664648,
|
| 1095 |
+
"grad_norm": 1.0994431972503662,
|
| 1096 |
+
"learning_rate": 1.7197048550474643e-05,
|
| 1097 |
+
"loss": 2.7072,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.2831858407079646,
|
| 1102 |
+
"grad_norm": 1.0657951831817627,
|
| 1103 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 1104 |
+
"loss": 3.1659,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.2850489054494644,
|
| 1109 |
+
"grad_norm": 1.3122929334640503,
|
| 1110 |
+
"learning_rate": 1.5900081996875083e-05,
|
| 1111 |
+
"loss": 3.1423,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.28691197019096415,
|
| 1116 |
+
"grad_norm": 1.0391207933425903,
|
| 1117 |
+
"learning_rate": 1.526708147705013e-05,
|
| 1118 |
+
"loss": 2.8446,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.2887750349324639,
|
| 1123 |
+
"grad_norm": 1.1318707466125488,
|
| 1124 |
+
"learning_rate": 1.4644660940672627e-05,
|
| 1125 |
+
"loss": 3.1408,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.29063809967396365,
|
| 1130 |
+
"grad_norm": 1.162157416343689,
|
| 1131 |
+
"learning_rate": 1.4033009983067452e-05,
|
| 1132 |
+
"loss": 2.852,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.2925011644154634,
|
| 1137 |
+
"grad_norm": 1.4153108596801758,
|
| 1138 |
+
"learning_rate": 1.3432314919041478e-05,
|
| 1139 |
+
"loss": 3.2088,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.2943642291569632,
|
| 1144 |
+
"grad_norm": 1.2663054466247559,
|
| 1145 |
+
"learning_rate": 1.2842758726130283e-05,
|
| 1146 |
+
"loss": 3.3267,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.296227293898463,
|
| 1151 |
+
"grad_norm": 1.0257394313812256,
|
| 1152 |
+
"learning_rate": 1.22645209888614e-05,
|
| 1153 |
+
"loss": 3.1659,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.29809035863996275,
|
| 1158 |
+
"grad_norm": 1.4004676342010498,
|
| 1159 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 1160 |
+
"loss": 3.1246,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.2999534233814625,
|
| 1165 |
+
"grad_norm": 1.103905439376831,
|
| 1166 |
+
"learning_rate": 1.1142701927151456e-05,
|
| 1167 |
+
"loss": 3.2662,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.30181648812296225,
|
| 1172 |
+
"grad_norm": 1.0684690475463867,
|
| 1173 |
+
"learning_rate": 1.0599462319663905e-05,
|
| 1174 |
+
"loss": 3.0609,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.303679552864462,
|
| 1179 |
+
"grad_norm": 1.1447290182113647,
|
| 1180 |
+
"learning_rate": 1.006822449763537e-05,
|
| 1181 |
+
"loss": 2.9505,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.3055426176059618,
|
| 1186 |
+
"grad_norm": 1.2237478494644165,
|
| 1187 |
+
"learning_rate": 9.549150281252633e-06,
|
| 1188 |
+
"loss": 3.2494,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.3074056823474616,
|
| 1193 |
+
"grad_norm": 1.0637820959091187,
|
| 1194 |
+
"learning_rate": 9.042397785550405e-06,
|
| 1195 |
+
"loss": 2.9076,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.30926874708896135,
|
| 1200 |
+
"grad_norm": 1.2343932390213013,
|
| 1201 |
+
"learning_rate": 8.548121372247918e-06,
|
| 1202 |
+
"loss": 3.3097,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.3111318118304611,
|
| 1207 |
+
"grad_norm": 1.0267237424850464,
|
| 1208 |
+
"learning_rate": 8.066471602728803e-06,
|
| 1209 |
+
"loss": 2.92,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.3129948765719609,
|
| 1214 |
+
"grad_norm": 1.1801772117614746,
|
| 1215 |
+
"learning_rate": 7.597595192178702e-06,
|
| 1216 |
+
"loss": 3.0281,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.3148579413134606,
|
| 1221 |
+
"grad_norm": 1.3864883184432983,
|
| 1222 |
+
"learning_rate": 7.1416349648943894e-06,
|
| 1223 |
+
"loss": 3.2964,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.3167210060549604,
|
| 1228 |
+
"grad_norm": 1.212416410446167,
|
| 1229 |
+
"learning_rate": 6.698729810778065e-06,
|
| 1230 |
+
"loss": 3.1213,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.3185840707964602,
|
| 1235 |
+
"grad_norm": 1.1211936473846436,
|
| 1236 |
+
"learning_rate": 6.269014643030213e-06,
|
| 1237 |
+
"loss": 2.8045,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.32044713553795995,
|
| 1242 |
+
"grad_norm": 1.1482990980148315,
|
| 1243 |
+
"learning_rate": 5.852620357053651e-06,
|
| 1244 |
+
"loss": 3.0468,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.3223102002794597,
|
| 1249 |
+
"grad_norm": 1.3345028162002563,
|
| 1250 |
+
"learning_rate": 5.449673790581611e-06,
|
| 1251 |
+
"loss": 2.9481,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.3241732650209595,
|
| 1256 |
+
"grad_norm": 1.0090028047561646,
|
| 1257 |
+
"learning_rate": 5.060297685041659e-06,
|
| 1258 |
+
"loss": 3.0541,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.3260363297624592,
|
| 1263 |
+
"grad_norm": 1.2291425466537476,
|
| 1264 |
+
"learning_rate": 4.684610648167503e-06,
|
| 1265 |
+
"loss": 3.4524,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.327899394503959,
|
| 1270 |
+
"grad_norm": 1.4188092947006226,
|
| 1271 |
+
"learning_rate": 4.322727117869951e-06,
|
| 1272 |
+
"loss": 3.387,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.32976245924545877,
|
| 1277 |
+
"grad_norm": 1.2818740606307983,
|
| 1278 |
+
"learning_rate": 3.974757327377981e-06,
|
| 1279 |
+
"loss": 3.5364,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.33162552398695855,
|
| 1284 |
+
"grad_norm": 1.3271952867507935,
|
| 1285 |
+
"learning_rate": 3.6408072716606346e-06,
|
| 1286 |
+
"loss": 3.1821,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.3334885887284583,
|
| 1291 |
+
"grad_norm": 1.2895276546478271,
|
| 1292 |
+
"learning_rate": 3.3209786751399187e-06,
|
| 1293 |
+
"loss": 3.0432,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.3353516534699581,
|
| 1298 |
+
"grad_norm": 1.2879928350448608,
|
| 1299 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 1300 |
+
"loss": 3.367,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.3372147182114579,
|
| 1305 |
+
"grad_norm": 1.3287880420684814,
|
| 1306 |
+
"learning_rate": 2.724071220034158e-06,
|
| 1307 |
+
"loss": 3.2295,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.3390777829529576,
|
| 1312 |
+
"grad_norm": 1.314154863357544,
|
| 1313 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 1314 |
+
"loss": 3.3232,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.34094084769445737,
|
| 1319 |
+
"grad_norm": 1.3569366931915283,
|
| 1320 |
+
"learning_rate": 2.1847622018482283e-06,
|
| 1321 |
+
"loss": 2.9797,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.34280391243595715,
|
| 1326 |
+
"grad_norm": 1.5291014909744263,
|
| 1327 |
+
"learning_rate": 1.9369152030840556e-06,
|
| 1328 |
+
"loss": 3.2835,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.3446669771774569,
|
| 1333 |
+
"grad_norm": 1.3267407417297363,
|
| 1334 |
+
"learning_rate": 1.70370868554659e-06,
|
| 1335 |
+
"loss": 3.1526,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.3465300419189567,
|
| 1340 |
+
"grad_norm": 1.36220383644104,
|
| 1341 |
+
"learning_rate": 1.4852136862001764e-06,
|
| 1342 |
+
"loss": 3.7465,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.3483931066604565,
|
| 1347 |
+
"grad_norm": 1.2978960275650024,
|
| 1348 |
+
"learning_rate": 1.2814967607382432e-06,
|
| 1349 |
+
"loss": 3.7277,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.3502561714019562,
|
| 1354 |
+
"grad_norm": 1.3940683603286743,
|
| 1355 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 1356 |
+
"loss": 3.4685,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.35211923614345597,
|
| 1361 |
+
"grad_norm": 1.4953304529190063,
|
| 1362 |
+
"learning_rate": 9.186408276168013e-07,
|
| 1363 |
+
"loss": 3.5472,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.35398230088495575,
|
| 1368 |
+
"grad_norm": 1.4648510217666626,
|
| 1369 |
+
"learning_rate": 7.596123493895991e-07,
|
| 1370 |
+
"loss": 3.3383,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.3558453656264555,
|
| 1375 |
+
"grad_norm": 1.5643545389175415,
|
| 1376 |
+
"learning_rate": 6.15582970243117e-07,
|
| 1377 |
+
"loss": 3.4377,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.3577084303679553,
|
| 1382 |
+
"grad_norm": 1.4430068731307983,
|
| 1383 |
+
"learning_rate": 4.865965629214819e-07,
|
| 1384 |
+
"loss": 3.6607,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.3595714951094551,
|
| 1389 |
+
"grad_norm": 1.5247834920883179,
|
| 1390 |
+
"learning_rate": 3.7269241793390085e-07,
|
| 1391 |
+
"loss": 3.8584,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.3614345598509548,
|
| 1396 |
+
"grad_norm": 1.5962194204330444,
|
| 1397 |
+
"learning_rate": 2.7390523158633554e-07,
|
| 1398 |
+
"loss": 3.6967,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.36329762459245457,
|
| 1403 |
+
"grad_norm": 3.414898633956909,
|
| 1404 |
+
"learning_rate": 1.9026509541272275e-07,
|
| 1405 |
+
"loss": 3.7934,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.36516068933395435,
|
| 1410 |
+
"grad_norm": 1.7514005899429321,
|
| 1411 |
+
"learning_rate": 1.2179748700879012e-07,
|
| 1412 |
+
"loss": 3.9039,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.3670237540754541,
|
| 1417 |
+
"grad_norm": 1.91195809841156,
|
| 1418 |
+
"learning_rate": 6.852326227130834e-08,
|
| 1419 |
+
"loss": 3.604,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.3688868188169539,
|
| 1424 |
+
"grad_norm": 2.1014304161071777,
|
| 1425 |
+
"learning_rate": 3.04586490452119e-08,
|
| 1426 |
+
"loss": 3.6654,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.3707498835584537,
|
| 1431 |
+
"grad_norm": 2.118112564086914,
|
| 1432 |
+
"learning_rate": 7.615242180436522e-09,
|
| 1433 |
+
"loss": 3.8243,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.37261294829995345,
|
| 1438 |
+
"grad_norm": 3.0300862789154053,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 3.6882,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.37261294829995345,
|
| 1445 |
+
"eval_loss": 3.3320932388305664,
|
| 1446 |
+
"eval_runtime": 32.1296,
|
| 1447 |
+
"eval_samples_per_second": 28.167,
|
| 1448 |
+
"eval_steps_per_second": 14.099,
|
| 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": 5.4428946137088e+16,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|