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 985240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2e0b72fe2f0c4321a8d936437e0cf30977a6eb4ff6915ae8ee13101f6d9c1de
|
| 3 |
size 985240
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 520860
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aca4c113273d4f26d7d6540b20edc9c6a3e7c30bbd91996dd1d9533c8bc09ef4
|
| 3 |
size 520860
|
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 sha256:4b4f794a92fa2b9f16fda328afadd716e28907db970d48c60a97f93197611bd7
|
| 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 sha256:2eca4a3affde04f8094d886307f00c561b3e3a77570955ff1177732e06fbab0c
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 10.
|
| 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": 59.498,
|
| 1090 |
"eval_steps_per_second": 14.882,
|
| 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": 10.55037784576416,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.020064205457463884,
|
| 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": 59.498,
|
| 1090 |
"eval_steps_per_second": 14.882,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.015148475120385233,
|
| 1095 |
+
"grad_norm": 0.8424636721611023,
|
| 1096 |
+
"learning_rate": 2.6021578947368423e-05,
|
| 1097 |
+
"loss": 20.936,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.015248796147672551,
|
| 1102 |
+
"grad_norm": 0.5448256731033325,
|
| 1103 |
+
"learning_rate": 2.5490526315789475e-05,
|
| 1104 |
+
"loss": 21.1742,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.015349117174959872,
|
| 1109 |
+
"grad_norm": 0.6612237095832825,
|
| 1110 |
+
"learning_rate": 2.4959473684210524e-05,
|
| 1111 |
+
"loss": 21.0709,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.01544943820224719,
|
| 1116 |
+
"grad_norm": 0.550390899181366,
|
| 1117 |
+
"learning_rate": 2.442842105263158e-05,
|
| 1118 |
+
"loss": 20.8933,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.015549759229534511,
|
| 1123 |
+
"grad_norm": 0.6066597700119019,
|
| 1124 |
+
"learning_rate": 2.389736842105263e-05,
|
| 1125 |
+
"loss": 20.9679,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.01565008025682183,
|
| 1130 |
+
"grad_norm": 0.595045804977417,
|
| 1131 |
+
"learning_rate": 2.3366315789473685e-05,
|
| 1132 |
+
"loss": 21.0887,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.01575040128410915,
|
| 1137 |
+
"grad_norm": 0.6363713145256042,
|
| 1138 |
+
"learning_rate": 2.2835263157894738e-05,
|
| 1139 |
+
"loss": 21.3898,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.01585072231139647,
|
| 1144 |
+
"grad_norm": 0.5982836484909058,
|
| 1145 |
+
"learning_rate": 2.230421052631579e-05,
|
| 1146 |
+
"loss": 21.1671,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.015951043338683787,
|
| 1151 |
+
"grad_norm": 0.7963234782218933,
|
| 1152 |
+
"learning_rate": 2.1773157894736843e-05,
|
| 1153 |
+
"loss": 20.9716,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.016051364365971106,
|
| 1158 |
+
"grad_norm": 0.647216796875,
|
| 1159 |
+
"learning_rate": 2.1242105263157895e-05,
|
| 1160 |
+
"loss": 21.1608,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.016151685393258428,
|
| 1165 |
+
"grad_norm": 0.5022075772285461,
|
| 1166 |
+
"learning_rate": 2.0711052631578947e-05,
|
| 1167 |
+
"loss": 21.1819,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.016252006420545747,
|
| 1172 |
+
"grad_norm": 0.5094108581542969,
|
| 1173 |
+
"learning_rate": 2.018e-05,
|
| 1174 |
+
"loss": 21.1568,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.016352327447833066,
|
| 1179 |
+
"grad_norm": 0.5434950590133667,
|
| 1180 |
+
"learning_rate": 1.9648947368421052e-05,
|
| 1181 |
+
"loss": 20.9586,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.016452648475120384,
|
| 1186 |
+
"grad_norm": 0.6874385476112366,
|
| 1187 |
+
"learning_rate": 1.9117894736842105e-05,
|
| 1188 |
+
"loss": 21.0375,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.016552969502407703,
|
| 1193 |
+
"grad_norm": 0.49630945920944214,
|
| 1194 |
+
"learning_rate": 1.8586842105263157e-05,
|
| 1195 |
+
"loss": 21.0352,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.016653290529695025,
|
| 1200 |
+
"grad_norm": 0.6111531257629395,
|
| 1201 |
+
"learning_rate": 1.805578947368421e-05,
|
| 1202 |
+
"loss": 21.2822,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.016753611556982344,
|
| 1207 |
+
"grad_norm": 0.5392615795135498,
|
| 1208 |
+
"learning_rate": 1.7524736842105266e-05,
|
| 1209 |
+
"loss": 21.1524,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.016853932584269662,
|
| 1214 |
+
"grad_norm": 0.5594942569732666,
|
| 1215 |
+
"learning_rate": 1.6993684210526315e-05,
|
| 1216 |
+
"loss": 21.1931,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.01695425361155698,
|
| 1221 |
+
"grad_norm": 0.5756310224533081,
|
| 1222 |
+
"learning_rate": 1.646263157894737e-05,
|
| 1223 |
+
"loss": 21.2089,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.017054574638844303,
|
| 1228 |
+
"grad_norm": 0.783043622970581,
|
| 1229 |
+
"learning_rate": 1.593157894736842e-05,
|
| 1230 |
+
"loss": 20.8715,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.017154895666131622,
|
| 1235 |
+
"grad_norm": 0.4898316562175751,
|
| 1236 |
+
"learning_rate": 1.5400526315789475e-05,
|
| 1237 |
+
"loss": 21.1136,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.01725521669341894,
|
| 1242 |
+
"grad_norm": 0.6354514360427856,
|
| 1243 |
+
"learning_rate": 1.4869473684210524e-05,
|
| 1244 |
+
"loss": 21.089,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.01735553772070626,
|
| 1249 |
+
"grad_norm": 0.6032927632331848,
|
| 1250 |
+
"learning_rate": 1.4338421052631579e-05,
|
| 1251 |
+
"loss": 21.0936,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.017455858747993578,
|
| 1256 |
+
"grad_norm": 0.6571072936058044,
|
| 1257 |
+
"learning_rate": 1.3807368421052633e-05,
|
| 1258 |
+
"loss": 20.9723,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.0175561797752809,
|
| 1263 |
+
"grad_norm": 0.5904538035392761,
|
| 1264 |
+
"learning_rate": 1.3276315789473684e-05,
|
| 1265 |
+
"loss": 21.287,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.01765650080256822,
|
| 1270 |
+
"grad_norm": 0.5847862362861633,
|
| 1271 |
+
"learning_rate": 1.2745263157894738e-05,
|
| 1272 |
+
"loss": 21.1966,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.017756821829855537,
|
| 1277 |
+
"grad_norm": 0.5706862211227417,
|
| 1278 |
+
"learning_rate": 1.221421052631579e-05,
|
| 1279 |
+
"loss": 20.9706,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.017857142857142856,
|
| 1284 |
+
"grad_norm": 0.5410795211791992,
|
| 1285 |
+
"learning_rate": 1.1683157894736843e-05,
|
| 1286 |
+
"loss": 21.2563,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.01795746388443018,
|
| 1291 |
+
"grad_norm": 0.5394900441169739,
|
| 1292 |
+
"learning_rate": 1.1152105263157895e-05,
|
| 1293 |
+
"loss": 20.9992,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.018057784911717497,
|
| 1298 |
+
"grad_norm": 0.45912498235702515,
|
| 1299 |
+
"learning_rate": 1.0621052631578948e-05,
|
| 1300 |
+
"loss": 21.2137,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.018158105939004816,
|
| 1305 |
+
"grad_norm": 0.5860676765441895,
|
| 1306 |
+
"learning_rate": 1.009e-05,
|
| 1307 |
+
"loss": 21.1744,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.018258426966292134,
|
| 1312 |
+
"grad_norm": 0.7394751310348511,
|
| 1313 |
+
"learning_rate": 9.558947368421052e-06,
|
| 1314 |
+
"loss": 20.9416,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.018358747993579453,
|
| 1319 |
+
"grad_norm": 0.6703020334243774,
|
| 1320 |
+
"learning_rate": 9.027894736842105e-06,
|
| 1321 |
+
"loss": 20.9801,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.018459069020866775,
|
| 1326 |
+
"grad_norm": 0.5259845852851868,
|
| 1327 |
+
"learning_rate": 8.496842105263157e-06,
|
| 1328 |
+
"loss": 21.0672,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.018559390048154094,
|
| 1333 |
+
"grad_norm": 0.47938376665115356,
|
| 1334 |
+
"learning_rate": 7.96578947368421e-06,
|
| 1335 |
+
"loss": 21.0379,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.018659711075441412,
|
| 1340 |
+
"grad_norm": 0.6665632128715515,
|
| 1341 |
+
"learning_rate": 7.434736842105262e-06,
|
| 1342 |
+
"loss": 21.3934,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.01876003210272873,
|
| 1347 |
+
"grad_norm": 0.6356412172317505,
|
| 1348 |
+
"learning_rate": 6.903684210526316e-06,
|
| 1349 |
+
"loss": 21.3995,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.01886035313001605,
|
| 1354 |
+
"grad_norm": 0.5531170964241028,
|
| 1355 |
+
"learning_rate": 6.372631578947369e-06,
|
| 1356 |
+
"loss": 21.177,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.018960674157303372,
|
| 1361 |
+
"grad_norm": 0.5264145731925964,
|
| 1362 |
+
"learning_rate": 5.841578947368421e-06,
|
| 1363 |
+
"loss": 21.2467,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.01906099518459069,
|
| 1368 |
+
"grad_norm": 0.5184823870658875,
|
| 1369 |
+
"learning_rate": 5.310526315789474e-06,
|
| 1370 |
+
"loss": 21.0768,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.01916131621187801,
|
| 1375 |
+
"grad_norm": 0.601334810256958,
|
| 1376 |
+
"learning_rate": 4.779473684210526e-06,
|
| 1377 |
+
"loss": 21.0318,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.019261637239165328,
|
| 1382 |
+
"grad_norm": 0.6639525890350342,
|
| 1383 |
+
"learning_rate": 4.248421052631579e-06,
|
| 1384 |
+
"loss": 20.9996,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.01936195826645265,
|
| 1389 |
+
"grad_norm": 0.47377097606658936,
|
| 1390 |
+
"learning_rate": 3.717368421052631e-06,
|
| 1391 |
+
"loss": 21.0164,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.01946227929373997,
|
| 1396 |
+
"grad_norm": 0.6908702254295349,
|
| 1397 |
+
"learning_rate": 3.1863157894736844e-06,
|
| 1398 |
+
"loss": 20.9247,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.019562600321027288,
|
| 1403 |
+
"grad_norm": 0.5369330048561096,
|
| 1404 |
+
"learning_rate": 2.655263157894737e-06,
|
| 1405 |
+
"loss": 21.3861,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.019662921348314606,
|
| 1410 |
+
"grad_norm": 0.6818935871124268,
|
| 1411 |
+
"learning_rate": 2.1242105263157893e-06,
|
| 1412 |
+
"loss": 21.0936,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.019763242375601925,
|
| 1417 |
+
"grad_norm": 0.6107151508331299,
|
| 1418 |
+
"learning_rate": 1.5931578947368422e-06,
|
| 1419 |
+
"loss": 21.0526,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.019863563402889247,
|
| 1424 |
+
"grad_norm": 0.6597663760185242,
|
| 1425 |
+
"learning_rate": 1.0621052631578947e-06,
|
| 1426 |
+
"loss": 21.1064,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.019963884430176566,
|
| 1431 |
+
"grad_norm": 0.6686668992042542,
|
| 1432 |
+
"learning_rate": 5.310526315789473e-07,
|
| 1433 |
+
"loss": 21.0729,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.020064205457463884,
|
| 1438 |
+
"grad_norm": 0.7321626543998718,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 21.4709,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.020064205457463884,
|
| 1445 |
+
"eval_loss": 10.55037784576416,
|
| 1446 |
+
"eval_runtime": 70.588,
|
| 1447 |
+
"eval_samples_per_second": 59.472,
|
| 1448 |
+
"eval_steps_per_second": 14.875,
|
| 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": 11943700070400.0,
|
| 1479 |
"train_batch_size": 4,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|