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 sha256:6aaad16373dfc17708a23ff1f2417ed2d1a82e957f085ee4381fec4b8e861ec7
|
| 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 sha256:79373b7c16bf0ba39cd2adfc042cd8240ecdde5653c7ef610376424e2287d10e
|
| 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 sha256:1b4b90022d53598fd566bddfba693c467cc59dc940624293aa478ba470333635
|
| 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 sha256:9e88715aecefb3c679b14ad9a6c0d783f40f5607dfbd8da1da22291853501b59
|
| 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": 9.08,
|
| 1090 |
"eval_steps_per_second": 2.27,
|
| 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": 0.11699455231428146,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.3568242640499554,
|
| 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": 9.08,
|
| 1090 |
"eval_steps_per_second": 2.27,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.2694023193577163,
|
| 1095 |
+
"grad_norm": 6.377121925354004,
|
| 1096 |
+
"learning_rate": 2.622789473684211e-05,
|
| 1097 |
+
"loss": 0.6521,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.2711864406779661,
|
| 1102 |
+
"grad_norm": 3.229111671447754,
|
| 1103 |
+
"learning_rate": 2.5692631578947372e-05,
|
| 1104 |
+
"loss": 0.4173,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.2729705619982159,
|
| 1109 |
+
"grad_norm": 2.997849225997925,
|
| 1110 |
+
"learning_rate": 2.515736842105263e-05,
|
| 1111 |
+
"loss": 0.486,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.27475468331846564,
|
| 1116 |
+
"grad_norm": 5.414923191070557,
|
| 1117 |
+
"learning_rate": 2.4622105263157897e-05,
|
| 1118 |
+
"loss": 0.4984,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.27653880463871544,
|
| 1123 |
+
"grad_norm": 5.7754597663879395,
|
| 1124 |
+
"learning_rate": 2.408684210526316e-05,
|
| 1125 |
+
"loss": 0.4548,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.2783229259589652,
|
| 1130 |
+
"grad_norm": 3.613875389099121,
|
| 1131 |
+
"learning_rate": 2.355157894736842e-05,
|
| 1132 |
+
"loss": 0.3154,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.280107047279215,
|
| 1137 |
+
"grad_norm": 2.7714474201202393,
|
| 1138 |
+
"learning_rate": 2.3016315789473687e-05,
|
| 1139 |
+
"loss": 0.2716,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.2818911685994648,
|
| 1144 |
+
"grad_norm": 3.1848134994506836,
|
| 1145 |
+
"learning_rate": 2.248105263157895e-05,
|
| 1146 |
+
"loss": 0.1476,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.2836752899197145,
|
| 1151 |
+
"grad_norm": 1.7357780933380127,
|
| 1152 |
+
"learning_rate": 2.194578947368421e-05,
|
| 1153 |
+
"loss": 0.1349,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.2854594112399643,
|
| 1158 |
+
"grad_norm": 2.317922353744507,
|
| 1159 |
+
"learning_rate": 2.1410526315789474e-05,
|
| 1160 |
+
"loss": 0.0644,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.2872435325602141,
|
| 1165 |
+
"grad_norm": 1.9329112768173218,
|
| 1166 |
+
"learning_rate": 2.087526315789474e-05,
|
| 1167 |
+
"loss": 0.1022,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.28902765388046386,
|
| 1172 |
+
"grad_norm": 1.6571458578109741,
|
| 1173 |
+
"learning_rate": 2.0340000000000002e-05,
|
| 1174 |
+
"loss": 0.125,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.29081177520071366,
|
| 1179 |
+
"grad_norm": 3.2216265201568604,
|
| 1180 |
+
"learning_rate": 1.9804736842105264e-05,
|
| 1181 |
+
"loss": 0.3244,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.2925958965209634,
|
| 1186 |
+
"grad_norm": 3.2759523391723633,
|
| 1187 |
+
"learning_rate": 1.9269473684210526e-05,
|
| 1188 |
+
"loss": 0.2553,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.2943800178412132,
|
| 1193 |
+
"grad_norm": 3.061447858810425,
|
| 1194 |
+
"learning_rate": 1.873421052631579e-05,
|
| 1195 |
+
"loss": 0.1635,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.296164139161463,
|
| 1200 |
+
"grad_norm": 2.6589152812957764,
|
| 1201 |
+
"learning_rate": 1.8198947368421054e-05,
|
| 1202 |
+
"loss": 0.3699,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.29794826048171275,
|
| 1207 |
+
"grad_norm": 2.176741600036621,
|
| 1208 |
+
"learning_rate": 1.7663684210526317e-05,
|
| 1209 |
+
"loss": 0.2426,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.29973238180196254,
|
| 1214 |
+
"grad_norm": 3.4110331535339355,
|
| 1215 |
+
"learning_rate": 1.712842105263158e-05,
|
| 1216 |
+
"loss": 0.1751,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.3015165031222123,
|
| 1221 |
+
"grad_norm": 2.073974132537842,
|
| 1222 |
+
"learning_rate": 1.6593157894736845e-05,
|
| 1223 |
+
"loss": 0.1996,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.3033006244424621,
|
| 1228 |
+
"grad_norm": 2.374593496322632,
|
| 1229 |
+
"learning_rate": 1.6057894736842104e-05,
|
| 1230 |
+
"loss": 0.1299,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.3050847457627119,
|
| 1235 |
+
"grad_norm": 2.038259744644165,
|
| 1236 |
+
"learning_rate": 1.552263157894737e-05,
|
| 1237 |
+
"loss": 0.1029,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.3068688670829616,
|
| 1242 |
+
"grad_norm": 1.358562707901001,
|
| 1243 |
+
"learning_rate": 1.4987368421052632e-05,
|
| 1244 |
+
"loss": 0.1095,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.3086529884032114,
|
| 1249 |
+
"grad_norm": 2.7677323818206787,
|
| 1250 |
+
"learning_rate": 1.4452105263157896e-05,
|
| 1251 |
+
"loss": 0.2534,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.31043710972346117,
|
| 1256 |
+
"grad_norm": 3.26887845993042,
|
| 1257 |
+
"learning_rate": 1.391684210526316e-05,
|
| 1258 |
+
"loss": 0.2149,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.31222123104371097,
|
| 1263 |
+
"grad_norm": 2.62199330329895,
|
| 1264 |
+
"learning_rate": 1.338157894736842e-05,
|
| 1265 |
+
"loss": 0.2241,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.31400535236396077,
|
| 1270 |
+
"grad_norm": 1.790993571281433,
|
| 1271 |
+
"learning_rate": 1.2846315789473686e-05,
|
| 1272 |
+
"loss": 0.2005,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.3157894736842105,
|
| 1277 |
+
"grad_norm": 1.6840771436691284,
|
| 1278 |
+
"learning_rate": 1.2311052631578948e-05,
|
| 1279 |
+
"loss": 0.2001,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.3175735950044603,
|
| 1284 |
+
"grad_norm": 1.7056312561035156,
|
| 1285 |
+
"learning_rate": 1.177578947368421e-05,
|
| 1286 |
+
"loss": 0.1361,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.3193577163247101,
|
| 1291 |
+
"grad_norm": 1.952252984046936,
|
| 1292 |
+
"learning_rate": 1.1240526315789475e-05,
|
| 1293 |
+
"loss": 0.2078,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.32114183764495985,
|
| 1298 |
+
"grad_norm": 2.965940475463867,
|
| 1299 |
+
"learning_rate": 1.0705263157894737e-05,
|
| 1300 |
+
"loss": 0.2415,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.32292595896520965,
|
| 1305 |
+
"grad_norm": 2.9831676483154297,
|
| 1306 |
+
"learning_rate": 1.0170000000000001e-05,
|
| 1307 |
+
"loss": 0.2756,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.3247100802854594,
|
| 1312 |
+
"grad_norm": 4.729600429534912,
|
| 1313 |
+
"learning_rate": 9.634736842105263e-06,
|
| 1314 |
+
"loss": 0.4065,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.3264942016057092,
|
| 1319 |
+
"grad_norm": 2.4799299240112305,
|
| 1320 |
+
"learning_rate": 9.099473684210527e-06,
|
| 1321 |
+
"loss": 0.1518,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.328278322925959,
|
| 1326 |
+
"grad_norm": 1.6759108304977417,
|
| 1327 |
+
"learning_rate": 8.56421052631579e-06,
|
| 1328 |
+
"loss": 0.1324,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.33006244424620873,
|
| 1333 |
+
"grad_norm": 1.1743565797805786,
|
| 1334 |
+
"learning_rate": 8.028947368421052e-06,
|
| 1335 |
+
"loss": 0.0901,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.33184656556645853,
|
| 1340 |
+
"grad_norm": 3.570462465286255,
|
| 1341 |
+
"learning_rate": 7.493684210526316e-06,
|
| 1342 |
+
"loss": 0.1744,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.33363068688670827,
|
| 1347 |
+
"grad_norm": 2.275346517562866,
|
| 1348 |
+
"learning_rate": 6.95842105263158e-06,
|
| 1349 |
+
"loss": 0.1587,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.33541480820695807,
|
| 1354 |
+
"grad_norm": 1.610485315322876,
|
| 1355 |
+
"learning_rate": 6.423157894736843e-06,
|
| 1356 |
+
"loss": 0.1512,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.33719892952720787,
|
| 1361 |
+
"grad_norm": 2.2590842247009277,
|
| 1362 |
+
"learning_rate": 5.887894736842105e-06,
|
| 1363 |
+
"loss": 0.0993,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.3389830508474576,
|
| 1368 |
+
"grad_norm": 2.172537088394165,
|
| 1369 |
+
"learning_rate": 5.3526315789473684e-06,
|
| 1370 |
+
"loss": 0.1312,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.3407671721677074,
|
| 1375 |
+
"grad_norm": 1.2215029001235962,
|
| 1376 |
+
"learning_rate": 4.817368421052632e-06,
|
| 1377 |
+
"loss": 0.0668,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.34255129348795715,
|
| 1382 |
+
"grad_norm": 0.9878784418106079,
|
| 1383 |
+
"learning_rate": 4.282105263157895e-06,
|
| 1384 |
+
"loss": 0.0921,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.34433541480820695,
|
| 1389 |
+
"grad_norm": 1.8482226133346558,
|
| 1390 |
+
"learning_rate": 3.746842105263158e-06,
|
| 1391 |
+
"loss": 0.1168,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.34611953612845675,
|
| 1396 |
+
"grad_norm": 4.2362775802612305,
|
| 1397 |
+
"learning_rate": 3.2115789473684215e-06,
|
| 1398 |
+
"loss": 0.153,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.3479036574487065,
|
| 1403 |
+
"grad_norm": 3.5083532333374023,
|
| 1404 |
+
"learning_rate": 2.6763157894736842e-06,
|
| 1405 |
+
"loss": 0.2441,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.3496877787689563,
|
| 1410 |
+
"grad_norm": 2.575528144836426,
|
| 1411 |
+
"learning_rate": 2.1410526315789474e-06,
|
| 1412 |
+
"loss": 0.2789,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.3514719000892061,
|
| 1417 |
+
"grad_norm": 3.301903247833252,
|
| 1418 |
+
"learning_rate": 1.6057894736842107e-06,
|
| 1419 |
+
"loss": 0.1416,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.35325602140945583,
|
| 1424 |
+
"grad_norm": 2.226771354675293,
|
| 1425 |
+
"learning_rate": 1.0705263157894737e-06,
|
| 1426 |
+
"loss": 0.2886,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.35504014272970563,
|
| 1431 |
+
"grad_norm": 3.2611441612243652,
|
| 1432 |
+
"learning_rate": 5.352631578947368e-07,
|
| 1433 |
+
"loss": 0.4134,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.3568242640499554,
|
| 1438 |
+
"grad_norm": 6.527837753295898,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.6558,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.3568242640499554,
|
| 1445 |
+
"eval_loss": 0.11699455231428146,
|
| 1446 |
+
"eval_runtime": 25.9831,
|
| 1447 |
+
"eval_samples_per_second": 9.083,
|
| 1448 |
+
"eval_steps_per_second": 2.271,
|
| 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": 7.54256789372928e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|