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 639691872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3bf0784eff6ef207dcf81247f4b13dbc3535c71445a56dcd0d9aa6b86f15bb0
|
| 3 |
size 639691872
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 325339796
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:084d9551da2d31c36e832b6718ed99fc5eb7c8158f32594366161a5af4e6b490
|
| 3 |
size 325339796
|
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:cbaa49b9aac57396fb70fa3deaa5fece67e5e8bebb3857e5382d74ed81e912c3
|
| 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 sha256:4f96196bd3544de2c28f6af356470f327df948539b0e3259c46b8a6786b633fd
|
| 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": 7.835,
|
| 1090 |
"eval_steps_per_second": 1.996,
|
| 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": 0.7936509251594543,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.5376344086021505,
|
| 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": 7.835,
|
| 1090 |
"eval_steps_per_second": 1.996,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.40591397849462363,
|
| 1095 |
+
"grad_norm": 2.3321237564086914,
|
| 1096 |
+
"learning_rate": 2.599578947368421e-05,
|
| 1097 |
+
"loss": 3.6574,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.40860215053763443,
|
| 1102 |
+
"grad_norm": 2.897630214691162,
|
| 1103 |
+
"learning_rate": 2.5465263157894738e-05,
|
| 1104 |
+
"loss": 2.9582,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.4112903225806452,
|
| 1109 |
+
"grad_norm": 2.3918817043304443,
|
| 1110 |
+
"learning_rate": 2.493473684210526e-05,
|
| 1111 |
+
"loss": 2.7901,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.41397849462365593,
|
| 1116 |
+
"grad_norm": 2.5373759269714355,
|
| 1117 |
+
"learning_rate": 2.440421052631579e-05,
|
| 1118 |
+
"loss": 3.1311,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.4166666666666667,
|
| 1123 |
+
"grad_norm": 2.5285072326660156,
|
| 1124 |
+
"learning_rate": 2.3873684210526313e-05,
|
| 1125 |
+
"loss": 2.5189,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.41935483870967744,
|
| 1130 |
+
"grad_norm": 2.504533052444458,
|
| 1131 |
+
"learning_rate": 2.3343157894736843e-05,
|
| 1132 |
+
"loss": 3.2569,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.4220430107526882,
|
| 1137 |
+
"grad_norm": 2.3029768466949463,
|
| 1138 |
+
"learning_rate": 2.281263157894737e-05,
|
| 1139 |
+
"loss": 2.6988,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.42473118279569894,
|
| 1144 |
+
"grad_norm": 2.2616817951202393,
|
| 1145 |
+
"learning_rate": 2.2282105263157892e-05,
|
| 1146 |
+
"loss": 2.3272,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.4274193548387097,
|
| 1151 |
+
"grad_norm": 2.2895076274871826,
|
| 1152 |
+
"learning_rate": 2.175157894736842e-05,
|
| 1153 |
+
"loss": 2.3862,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.43010752688172044,
|
| 1158 |
+
"grad_norm": 1.9649949073791504,
|
| 1159 |
+
"learning_rate": 2.1221052631578944e-05,
|
| 1160 |
+
"loss": 2.1478,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.4327956989247312,
|
| 1165 |
+
"grad_norm": 2.0496561527252197,
|
| 1166 |
+
"learning_rate": 2.0690526315789474e-05,
|
| 1167 |
+
"loss": 1.3665,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.43548387096774194,
|
| 1172 |
+
"grad_norm": 2.4721364974975586,
|
| 1173 |
+
"learning_rate": 2.016e-05,
|
| 1174 |
+
"loss": 3.1437,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.4381720430107527,
|
| 1179 |
+
"grad_norm": 2.5533034801483154,
|
| 1180 |
+
"learning_rate": 1.9629473684210526e-05,
|
| 1181 |
+
"loss": 2.2656,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.44086021505376344,
|
| 1186 |
+
"grad_norm": 1.7975753545761108,
|
| 1187 |
+
"learning_rate": 1.9098947368421053e-05,
|
| 1188 |
+
"loss": 1.4366,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.4435483870967742,
|
| 1193 |
+
"grad_norm": 2.068775177001953,
|
| 1194 |
+
"learning_rate": 1.856842105263158e-05,
|
| 1195 |
+
"loss": 1.3049,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.44623655913978494,
|
| 1200 |
+
"grad_norm": 2.0522570610046387,
|
| 1201 |
+
"learning_rate": 1.8037894736842105e-05,
|
| 1202 |
+
"loss": 1.8766,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.4489247311827957,
|
| 1207 |
+
"grad_norm": 1.8050427436828613,
|
| 1208 |
+
"learning_rate": 1.750736842105263e-05,
|
| 1209 |
+
"loss": 1.501,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.45161290322580644,
|
| 1214 |
+
"grad_norm": 2.184504508972168,
|
| 1215 |
+
"learning_rate": 1.6976842105263157e-05,
|
| 1216 |
+
"loss": 1.7882,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.4543010752688172,
|
| 1221 |
+
"grad_norm": 1.4424117803573608,
|
| 1222 |
+
"learning_rate": 1.6446315789473684e-05,
|
| 1223 |
+
"loss": 0.6933,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.45698924731182794,
|
| 1228 |
+
"grad_norm": 2.0629289150238037,
|
| 1229 |
+
"learning_rate": 1.591578947368421e-05,
|
| 1230 |
+
"loss": 1.1983,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.4596774193548387,
|
| 1235 |
+
"grad_norm": 2.0509307384490967,
|
| 1236 |
+
"learning_rate": 1.5385263157894736e-05,
|
| 1237 |
+
"loss": 1.709,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.46236559139784944,
|
| 1242 |
+
"grad_norm": 1.423912525177002,
|
| 1243 |
+
"learning_rate": 1.485473684210526e-05,
|
| 1244 |
+
"loss": 0.6537,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.4650537634408602,
|
| 1249 |
+
"grad_norm": 2.0477561950683594,
|
| 1250 |
+
"learning_rate": 1.4324210526315789e-05,
|
| 1251 |
+
"loss": 0.791,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.46774193548387094,
|
| 1256 |
+
"grad_norm": 2.9739744663238525,
|
| 1257 |
+
"learning_rate": 1.3793684210526316e-05,
|
| 1258 |
+
"loss": 1.7767,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.47043010752688175,
|
| 1263 |
+
"grad_norm": 2.3965930938720703,
|
| 1264 |
+
"learning_rate": 1.3263157894736841e-05,
|
| 1265 |
+
"loss": 1.8458,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.4731182795698925,
|
| 1270 |
+
"grad_norm": 2.0706305503845215,
|
| 1271 |
+
"learning_rate": 1.2732631578947369e-05,
|
| 1272 |
+
"loss": 0.8644,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.47580645161290325,
|
| 1277 |
+
"grad_norm": 1.389144778251648,
|
| 1278 |
+
"learning_rate": 1.2202105263157895e-05,
|
| 1279 |
+
"loss": 0.5712,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.478494623655914,
|
| 1284 |
+
"grad_norm": 2.4105353355407715,
|
| 1285 |
+
"learning_rate": 1.1671578947368421e-05,
|
| 1286 |
+
"loss": 1.7319,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.48118279569892475,
|
| 1291 |
+
"grad_norm": 1.4054794311523438,
|
| 1292 |
+
"learning_rate": 1.1141052631578946e-05,
|
| 1293 |
+
"loss": 0.594,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.4838709677419355,
|
| 1298 |
+
"grad_norm": 1.2603883743286133,
|
| 1299 |
+
"learning_rate": 1.0610526315789472e-05,
|
| 1300 |
+
"loss": 0.521,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.48655913978494625,
|
| 1305 |
+
"grad_norm": 2.3499302864074707,
|
| 1306 |
+
"learning_rate": 1.008e-05,
|
| 1307 |
+
"loss": 1.2467,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.489247311827957,
|
| 1312 |
+
"grad_norm": 1.8965387344360352,
|
| 1313 |
+
"learning_rate": 9.549473684210526e-06,
|
| 1314 |
+
"loss": 1.0413,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.49193548387096775,
|
| 1319 |
+
"grad_norm": 1.9322240352630615,
|
| 1320 |
+
"learning_rate": 9.018947368421052e-06,
|
| 1321 |
+
"loss": 1.1569,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.4946236559139785,
|
| 1326 |
+
"grad_norm": 2.103156089782715,
|
| 1327 |
+
"learning_rate": 8.488421052631579e-06,
|
| 1328 |
+
"loss": 1.1426,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.49731182795698925,
|
| 1333 |
+
"grad_norm": 1.795997142791748,
|
| 1334 |
+
"learning_rate": 7.957894736842105e-06,
|
| 1335 |
+
"loss": 1.1144,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.5,
|
| 1340 |
+
"grad_norm": 2.546483278274536,
|
| 1341 |
+
"learning_rate": 7.42736842105263e-06,
|
| 1342 |
+
"loss": 1.2147,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.5026881720430108,
|
| 1347 |
+
"grad_norm": 2.0869460105895996,
|
| 1348 |
+
"learning_rate": 6.896842105263158e-06,
|
| 1349 |
+
"loss": 1.4491,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.5053763440860215,
|
| 1354 |
+
"grad_norm": 2.946209192276001,
|
| 1355 |
+
"learning_rate": 6.3663157894736845e-06,
|
| 1356 |
+
"loss": 1.5029,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.5080645161290323,
|
| 1361 |
+
"grad_norm": 1.2845457792282104,
|
| 1362 |
+
"learning_rate": 5.835789473684211e-06,
|
| 1363 |
+
"loss": 0.5538,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.510752688172043,
|
| 1368 |
+
"grad_norm": 1.6108278036117554,
|
| 1369 |
+
"learning_rate": 5.305263157894736e-06,
|
| 1370 |
+
"loss": 0.5395,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.5134408602150538,
|
| 1375 |
+
"grad_norm": 2.4547786712646484,
|
| 1376 |
+
"learning_rate": 4.774736842105263e-06,
|
| 1377 |
+
"loss": 0.7314,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.5161290322580645,
|
| 1382 |
+
"grad_norm": 4.319262981414795,
|
| 1383 |
+
"learning_rate": 4.244210526315789e-06,
|
| 1384 |
+
"loss": 2.1648,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.5188172043010753,
|
| 1389 |
+
"grad_norm": 1.8788155317306519,
|
| 1390 |
+
"learning_rate": 3.713684210526315e-06,
|
| 1391 |
+
"loss": 0.9098,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.521505376344086,
|
| 1396 |
+
"grad_norm": 2.349867820739746,
|
| 1397 |
+
"learning_rate": 3.1831578947368422e-06,
|
| 1398 |
+
"loss": 1.2202,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.5241935483870968,
|
| 1403 |
+
"grad_norm": 2.8968505859375,
|
| 1404 |
+
"learning_rate": 2.652631578947368e-06,
|
| 1405 |
+
"loss": 1.8995,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.5268817204301075,
|
| 1410 |
+
"grad_norm": 4.167923927307129,
|
| 1411 |
+
"learning_rate": 2.1221052631578947e-06,
|
| 1412 |
+
"loss": 2.6088,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.5295698924731183,
|
| 1417 |
+
"grad_norm": 4.212091445922852,
|
| 1418 |
+
"learning_rate": 1.5915789473684211e-06,
|
| 1419 |
+
"loss": 1.8908,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.532258064516129,
|
| 1424 |
+
"grad_norm": 1.670013666152954,
|
| 1425 |
+
"learning_rate": 1.0610526315789473e-06,
|
| 1426 |
+
"loss": 0.529,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.5349462365591398,
|
| 1431 |
+
"grad_norm": 2.4547181129455566,
|
| 1432 |
+
"learning_rate": 5.305263157894737e-07,
|
| 1433 |
+
"loss": 0.7957,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.5376344086021505,
|
| 1438 |
+
"grad_norm": 2.100339651107788,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 0.3624,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.5376344086021505,
|
| 1445 |
+
"eval_loss": 0.7936509251594543,
|
| 1446 |
+
"eval_runtime": 20.0443,
|
| 1447 |
+
"eval_samples_per_second": 7.833,
|
| 1448 |
+
"eval_steps_per_second": 1.996,
|
| 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": 6.65254329581568e+16,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|