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 80013120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92ab93f7caaf979c12c219cf97f4c2efc50dd8a431c1d350c54566ef764275b9
|
| 3 |
size 80013120
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 41119636
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23198dd5b92e9eaecd1c2629a1de4b4f6bde6fc30e2c832c493615cf1ada7827
|
| 3 |
size 41119636
|
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 sha256:2d3f6ea981a04fd422934b12bbf4f4ea20c72deb42679ca8b997d16955f077a1
|
| 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:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 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": 26.551,
|
| 1090 |
"eval_steps_per_second": 13.275,
|
| 1091 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1092 |
}
|
| 1093 |
],
|
| 1094 |
"logging_steps": 1,
|
|
@@ -1103,12 +1461,12 @@
|
|
| 1103 |
"should_evaluate": false,
|
| 1104 |
"should_log": false,
|
| 1105 |
"should_save": true,
|
| 1106 |
-
"should_training_stop":
|
| 1107 |
},
|
| 1108 |
"attributes": {}
|
| 1109 |
}
|
| 1110 |
},
|
| 1111 |
-
"total_flos":
|
| 1112 |
"train_batch_size": 2,
|
| 1113 |
"trial_name": null,
|
| 1114 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.11379800853485064,
|
| 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": 26.551,
|
| 1090 |
"eval_steps_per_second": 13.275,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.08591749644381223,
|
| 1095 |
+
"grad_norm": 7.080511093139648,
|
| 1096 |
+
"learning_rate": 3.106465908814342e-05,
|
| 1097 |
+
"loss": 4.2857,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.08648648648648649,
|
| 1102 |
+
"grad_norm": 3.2187960147857666,
|
| 1103 |
+
"learning_rate": 2.9876321572751144e-05,
|
| 1104 |
+
"loss": 4.8182,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.08705547652916074,
|
| 1109 |
+
"grad_norm": 4.8124494552612305,
|
| 1110 |
+
"learning_rate": 2.87071551708603e-05,
|
| 1111 |
+
"loss": 6.0068,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.087624466571835,
|
| 1116 |
+
"grad_norm": 2.8262407779693604,
|
| 1117 |
+
"learning_rate": 2.7557479520891104e-05,
|
| 1118 |
+
"loss": 4.792,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.08819345661450925,
|
| 1123 |
+
"grad_norm": 2.923560857772827,
|
| 1124 |
+
"learning_rate": 2.6427608932686843e-05,
|
| 1125 |
+
"loss": 5.1326,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.0887624466571835,
|
| 1130 |
+
"grad_norm": 5.176588535308838,
|
| 1131 |
+
"learning_rate": 2.5317852301584643e-05,
|
| 1132 |
+
"loss": 4.5157,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.08933143669985776,
|
| 1137 |
+
"grad_norm": 3.6101057529449463,
|
| 1138 |
+
"learning_rate": 2.422851302396655e-05,
|
| 1139 |
+
"loss": 4.4102,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.089900426742532,
|
| 1144 |
+
"grad_norm": 3.444321632385254,
|
| 1145 |
+
"learning_rate": 2.315988891431412e-05,
|
| 1146 |
+
"loss": 4.6294,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.09046941678520626,
|
| 1151 |
+
"grad_norm": 4.463266849517822,
|
| 1152 |
+
"learning_rate": 2.2112272123788768e-05,
|
| 1153 |
+
"loss": 5.5477,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.09103840682788052,
|
| 1158 |
+
"grad_norm": 1.8937747478485107,
|
| 1159 |
+
"learning_rate": 2.1085949060360654e-05,
|
| 1160 |
+
"loss": 4.4425,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.09160739687055476,
|
| 1165 |
+
"grad_norm": 4.402875900268555,
|
| 1166 |
+
"learning_rate": 2.008120031050753e-05,
|
| 1167 |
+
"loss": 4.9106,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.09217638691322902,
|
| 1172 |
+
"grad_norm": 7.496870994567871,
|
| 1173 |
+
"learning_rate": 1.9098300562505266e-05,
|
| 1174 |
+
"loss": 5.9993,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.09274537695590328,
|
| 1179 |
+
"grad_norm": 3.5323891639709473,
|
| 1180 |
+
"learning_rate": 1.8137518531330767e-05,
|
| 1181 |
+
"loss": 3.4518,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.09331436699857752,
|
| 1186 |
+
"grad_norm": 2.1053411960601807,
|
| 1187 |
+
"learning_rate": 1.7199116885197995e-05,
|
| 1188 |
+
"loss": 7.2256,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.09388335704125178,
|
| 1193 |
+
"grad_norm": 4.349791526794434,
|
| 1194 |
+
"learning_rate": 1.6283352173747145e-05,
|
| 1195 |
+
"loss": 7.4584,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.09445234708392602,
|
| 1200 |
+
"grad_norm": 2.5480291843414307,
|
| 1201 |
+
"learning_rate": 1.5390474757906446e-05,
|
| 1202 |
+
"loss": 5.4292,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.09502133712660028,
|
| 1207 |
+
"grad_norm": 4.777122974395752,
|
| 1208 |
+
"learning_rate": 1.4520728741446089e-05,
|
| 1209 |
+
"loss": 4.4266,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.09559032716927454,
|
| 1214 |
+
"grad_norm": 4.1914896965026855,
|
| 1215 |
+
"learning_rate": 1.3674351904242611e-05,
|
| 1216 |
+
"loss": 5.1201,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.09615931721194879,
|
| 1221 |
+
"grad_norm": 3.859760284423828,
|
| 1222 |
+
"learning_rate": 1.2851575637272262e-05,
|
| 1223 |
+
"loss": 5.8536,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.09672830725462304,
|
| 1228 |
+
"grad_norm": 2.8088245391845703,
|
| 1229 |
+
"learning_rate": 1.2052624879351104e-05,
|
| 1230 |
+
"loss": 4.4732,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.0972972972972973,
|
| 1235 |
+
"grad_norm": 3.0024406909942627,
|
| 1236 |
+
"learning_rate": 1.1277718055638819e-05,
|
| 1237 |
+
"loss": 6.3882,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.09786628733997155,
|
| 1242 |
+
"grad_norm": 2.2800610065460205,
|
| 1243 |
+
"learning_rate": 1.0527067017923654e-05,
|
| 1244 |
+
"loss": 4.2305,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.0984352773826458,
|
| 1249 |
+
"grad_norm": 5.0042243003845215,
|
| 1250 |
+
"learning_rate": 9.80087698670411e-06,
|
| 1251 |
+
"loss": 5.2088,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.09900426742532005,
|
| 1256 |
+
"grad_norm": 3.1999149322509766,
|
| 1257 |
+
"learning_rate": 9.09934649508375e-06,
|
| 1258 |
+
"loss": 6.1894,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.09957325746799431,
|
| 1263 |
+
"grad_norm": 2.6670374870300293,
|
| 1264 |
+
"learning_rate": 8.422667334494249e-06,
|
| 1265 |
+
"loss": 6.6094,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.10014224751066857,
|
| 1270 |
+
"grad_norm": 3.14996075630188,
|
| 1271 |
+
"learning_rate": 7.771024502261526e-06,
|
| 1272 |
+
"loss": 5.5419,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.10071123755334281,
|
| 1277 |
+
"grad_norm": 3.2261385917663574,
|
| 1278 |
+
"learning_rate": 7.144596151029303e-06,
|
| 1279 |
+
"loss": 5.99,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.10128022759601707,
|
| 1284 |
+
"grad_norm": 3.104440927505493,
|
| 1285 |
+
"learning_rate": 6.543553540053926e-06,
|
| 1286 |
+
"loss": 5.852,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.10184921763869133,
|
| 1291 |
+
"grad_norm": 4.476421356201172,
|
| 1292 |
+
"learning_rate": 5.968060988383883e-06,
|
| 1293 |
+
"loss": 5.0951,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.10241820768136557,
|
| 1298 |
+
"grad_norm": 3.7444934844970703,
|
| 1299 |
+
"learning_rate": 5.418275829936537e-06,
|
| 1300 |
+
"loss": 5.4538,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.10298719772403983,
|
| 1305 |
+
"grad_norm": 2.4591422080993652,
|
| 1306 |
+
"learning_rate": 4.8943483704846475e-06,
|
| 1307 |
+
"loss": 5.6287,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.10355618776671409,
|
| 1312 |
+
"grad_norm": 4.3750176429748535,
|
| 1313 |
+
"learning_rate": 4.3964218465642355e-06,
|
| 1314 |
+
"loss": 6.177,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.10412517780938833,
|
| 1319 |
+
"grad_norm": 5.408864498138428,
|
| 1320 |
+
"learning_rate": 3.924632386315186e-06,
|
| 1321 |
+
"loss": 5.263,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.10469416785206259,
|
| 1326 |
+
"grad_norm": 4.513190746307373,
|
| 1327 |
+
"learning_rate": 3.4791089722651436e-06,
|
| 1328 |
+
"loss": 5.6333,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.10526315789473684,
|
| 1333 |
+
"grad_norm": 2.7678093910217285,
|
| 1334 |
+
"learning_rate": 3.059973406066963e-06,
|
| 1335 |
+
"loss": 4.9883,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.1058321479374111,
|
| 1340 |
+
"grad_norm": 8.396341323852539,
|
| 1341 |
+
"learning_rate": 2.667340275199426e-06,
|
| 1342 |
+
"loss": 4.9833,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.10640113798008535,
|
| 1347 |
+
"grad_norm": 3.3889670372009277,
|
| 1348 |
+
"learning_rate": 2.3013169216400733e-06,
|
| 1349 |
+
"loss": 5.6266,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.1069701280227596,
|
| 1354 |
+
"grad_norm": 2.7151944637298584,
|
| 1355 |
+
"learning_rate": 1.9620034125190644e-06,
|
| 1356 |
+
"loss": 5.215,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.10753911806543386,
|
| 1361 |
+
"grad_norm": 2.5354421138763428,
|
| 1362 |
+
"learning_rate": 1.6494925127617634e-06,
|
| 1363 |
+
"loss": 6.294,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.10810810810810811,
|
| 1368 |
+
"grad_norm": 4.257821559906006,
|
| 1369 |
+
"learning_rate": 1.3638696597277679e-06,
|
| 1370 |
+
"loss": 5.8779,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.10867709815078236,
|
| 1375 |
+
"grad_norm": 4.796931266784668,
|
| 1376 |
+
"learning_rate": 1.1052129398531507e-06,
|
| 1377 |
+
"loss": 5.5843,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.10924608819345662,
|
| 1382 |
+
"grad_norm": 5.218569278717041,
|
| 1383 |
+
"learning_rate": 8.735930673024806e-07,
|
| 1384 |
+
"loss": 4.0941,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.10981507823613086,
|
| 1389 |
+
"grad_norm": 5.072295665740967,
|
| 1390 |
+
"learning_rate": 6.690733646361857e-07,
|
| 1391 |
+
"loss": 5.5361,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.11038406827880512,
|
| 1396 |
+
"grad_norm": 4.800101280212402,
|
| 1397 |
+
"learning_rate": 4.917097454988584e-07,
|
| 1398 |
+
"loss": 6.2412,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.11095305832147938,
|
| 1403 |
+
"grad_norm": 5.073276996612549,
|
| 1404 |
+
"learning_rate": 3.415506993330153e-07,
|
| 1405 |
+
"loss": 4.265,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.11152204836415362,
|
| 1410 |
+
"grad_norm": 3.1230766773223877,
|
| 1411 |
+
"learning_rate": 2.1863727812254653e-07,
|
| 1412 |
+
"loss": 4.2952,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.11209103840682788,
|
| 1417 |
+
"grad_norm": 3.5099849700927734,
|
| 1418 |
+
"learning_rate": 1.230030851695263e-07,
|
| 1419 |
+
"loss": 5.3853,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.11266002844950214,
|
| 1424 |
+
"grad_norm": 4.778675556182861,
|
| 1425 |
+
"learning_rate": 5.467426590739511e-08,
|
| 1426 |
+
"loss": 5.4041,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.11322901849217638,
|
| 1431 |
+
"grad_norm": 5.886673927307129,
|
| 1432 |
+
"learning_rate": 1.3669500753099585e-08,
|
| 1433 |
+
"loss": 4.2501,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.11379800853485064,
|
| 1438 |
+
"grad_norm": 3.1427319049835205,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 4.7047,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.11379800853485064,
|
| 1445 |
+
"eval_loss": 1.374655842781067,
|
| 1446 |
+
"eval_runtime": 27.5583,
|
| 1447 |
+
"eval_samples_per_second": 26.852,
|
| 1448 |
+
"eval_steps_per_second": 13.426,
|
| 1449 |
+
"step": 200
|
| 1450 |
}
|
| 1451 |
],
|
| 1452 |
"logging_steps": 1,
|
|
|
|
| 1461 |
"should_evaluate": false,
|
| 1462 |
"should_log": false,
|
| 1463 |
"should_save": true,
|
| 1464 |
+
"should_training_stop": true
|
| 1465 |
},
|
| 1466 |
"attributes": {}
|
| 1467 |
}
|
| 1468 |
},
|
| 1469 |
+
"total_flos": 3.522135406411776e+16,
|
| 1470 |
"train_batch_size": 2,
|
| 1471 |
"trial_name": null,
|
| 1472 |
"trial_params": null
|