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 83945296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ca59f66b35a1e424297872e6cb304ce0e6de48e88f70b285a44797b35b63ed0
|
| 3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43122580
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40c437e7d8552db33803897da7a6f797bd6e86a3d49c3fe449835159bc199e95
|
| 3 |
size 43122580
|
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 sha256:6e39d3bd6aca35d9c2c4af115bc55fc6bc26ea5767dd3a367c3979f22ceabe3d
|
| 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": 32.117,
|
| 1090 |
"eval_steps_per_second": 16.074,
|
| 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": 0.08019246190858059,
|
| 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": 32.117,
|
| 1090 |
"eval_steps_per_second": 16.074,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.06054530874097835,
|
| 1095 |
+
"grad_norm": 1.6141358613967896,
|
| 1096 |
+
"learning_rate": 3.106465908814342e-05,
|
| 1097 |
+
"loss": 2.7322,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.06094627105052125,
|
| 1102 |
+
"grad_norm": 1.4215883016586304,
|
| 1103 |
+
"learning_rate": 2.9876321572751144e-05,
|
| 1104 |
+
"loss": 2.5039,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.06134723336006415,
|
| 1109 |
+
"grad_norm": 1.3733489513397217,
|
| 1110 |
+
"learning_rate": 2.87071551708603e-05,
|
| 1111 |
+
"loss": 2.4508,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.061748195669607056,
|
| 1116 |
+
"grad_norm": 1.566167950630188,
|
| 1117 |
+
"learning_rate": 2.7557479520891104e-05,
|
| 1118 |
+
"loss": 2.5605,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.06214915797914996,
|
| 1123 |
+
"grad_norm": 1.7038018703460693,
|
| 1124 |
+
"learning_rate": 2.6427608932686843e-05,
|
| 1125 |
+
"loss": 2.5898,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.06255012028869286,
|
| 1130 |
+
"grad_norm": 1.6522966623306274,
|
| 1131 |
+
"learning_rate": 2.5317852301584643e-05,
|
| 1132 |
+
"loss": 2.4836,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.06295108259823577,
|
| 1137 |
+
"grad_norm": 1.280804991722107,
|
| 1138 |
+
"learning_rate": 2.422851302396655e-05,
|
| 1139 |
+
"loss": 2.2322,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.06335204490777867,
|
| 1144 |
+
"grad_norm": 1.4104244709014893,
|
| 1145 |
+
"learning_rate": 2.315988891431412e-05,
|
| 1146 |
+
"loss": 2.7656,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.06375300721732158,
|
| 1151 |
+
"grad_norm": 1.5219942331314087,
|
| 1152 |
+
"learning_rate": 2.2112272123788768e-05,
|
| 1153 |
+
"loss": 2.5849,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.06415396952686447,
|
| 1158 |
+
"grad_norm": 1.7256830930709839,
|
| 1159 |
+
"learning_rate": 2.1085949060360654e-05,
|
| 1160 |
+
"loss": 2.7485,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.06455493183640738,
|
| 1165 |
+
"grad_norm": 1.437982201576233,
|
| 1166 |
+
"learning_rate": 2.008120031050753e-05,
|
| 1167 |
+
"loss": 2.5537,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.06495589414595028,
|
| 1172 |
+
"grad_norm": 1.7291004657745361,
|
| 1173 |
+
"learning_rate": 1.9098300562505266e-05,
|
| 1174 |
+
"loss": 2.7314,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.06535685645549319,
|
| 1179 |
+
"grad_norm": 1.7065455913543701,
|
| 1180 |
+
"learning_rate": 1.8137518531330767e-05,
|
| 1181 |
+
"loss": 2.8562,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.06575781876503609,
|
| 1186 |
+
"grad_norm": 1.5972216129302979,
|
| 1187 |
+
"learning_rate": 1.7199116885197995e-05,
|
| 1188 |
+
"loss": 2.7651,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.066158781074579,
|
| 1193 |
+
"grad_norm": 1.4370338916778564,
|
| 1194 |
+
"learning_rate": 1.6283352173747145e-05,
|
| 1195 |
+
"loss": 2.5583,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.06655974338412189,
|
| 1200 |
+
"grad_norm": 1.490268349647522,
|
| 1201 |
+
"learning_rate": 1.5390474757906446e-05,
|
| 1202 |
+
"loss": 2.4052,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.0669607056936648,
|
| 1207 |
+
"grad_norm": 1.5364216566085815,
|
| 1208 |
+
"learning_rate": 1.4520728741446089e-05,
|
| 1209 |
+
"loss": 2.4988,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.0673616680032077,
|
| 1214 |
+
"grad_norm": 1.3920948505401611,
|
| 1215 |
+
"learning_rate": 1.3674351904242611e-05,
|
| 1216 |
+
"loss": 2.4575,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.06776263031275061,
|
| 1221 |
+
"grad_norm": 1.3365832567214966,
|
| 1222 |
+
"learning_rate": 1.2851575637272262e-05,
|
| 1223 |
+
"loss": 2.5124,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.0681635926222935,
|
| 1228 |
+
"grad_norm": 1.4743620157241821,
|
| 1229 |
+
"learning_rate": 1.2052624879351104e-05,
|
| 1230 |
+
"loss": 2.5516,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.06856455493183641,
|
| 1235 |
+
"grad_norm": 1.3127464056015015,
|
| 1236 |
+
"learning_rate": 1.1277718055638819e-05,
|
| 1237 |
+
"loss": 2.554,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.06896551724137931,
|
| 1242 |
+
"grad_norm": 1.7853848934173584,
|
| 1243 |
+
"learning_rate": 1.0527067017923654e-05,
|
| 1244 |
+
"loss": 3.0233,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.06936647955092222,
|
| 1249 |
+
"grad_norm": 1.4360729455947876,
|
| 1250 |
+
"learning_rate": 9.80087698670411e-06,
|
| 1251 |
+
"loss": 2.5379,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.06976744186046512,
|
| 1256 |
+
"grad_norm": 1.7601673603057861,
|
| 1257 |
+
"learning_rate": 9.09934649508375e-06,
|
| 1258 |
+
"loss": 2.6231,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.07016840417000803,
|
| 1263 |
+
"grad_norm": 1.4633996486663818,
|
| 1264 |
+
"learning_rate": 8.422667334494249e-06,
|
| 1265 |
+
"loss": 2.4548,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.07056936647955092,
|
| 1270 |
+
"grad_norm": 1.5791006088256836,
|
| 1271 |
+
"learning_rate": 7.771024502261526e-06,
|
| 1272 |
+
"loss": 2.5061,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.07097032878909383,
|
| 1277 |
+
"grad_norm": 1.6427297592163086,
|
| 1278 |
+
"learning_rate": 7.144596151029303e-06,
|
| 1279 |
+
"loss": 2.7168,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.07137129109863673,
|
| 1284 |
+
"grad_norm": 1.7753262519836426,
|
| 1285 |
+
"learning_rate": 6.543553540053926e-06,
|
| 1286 |
+
"loss": 2.8722,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.07177225340817964,
|
| 1291 |
+
"grad_norm": 1.6255383491516113,
|
| 1292 |
+
"learning_rate": 5.968060988383883e-06,
|
| 1293 |
+
"loss": 2.7931,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.07217321571772253,
|
| 1298 |
+
"grad_norm": 1.5804318189620972,
|
| 1299 |
+
"learning_rate": 5.418275829936537e-06,
|
| 1300 |
+
"loss": 2.7363,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.07257417802726544,
|
| 1305 |
+
"grad_norm": 1.4814261198043823,
|
| 1306 |
+
"learning_rate": 4.8943483704846475e-06,
|
| 1307 |
+
"loss": 2.7161,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.07297514033680834,
|
| 1312 |
+
"grad_norm": 1.4553298950195312,
|
| 1313 |
+
"learning_rate": 4.3964218465642355e-06,
|
| 1314 |
+
"loss": 2.4494,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.07337610264635125,
|
| 1319 |
+
"grad_norm": 1.4600770473480225,
|
| 1320 |
+
"learning_rate": 3.924632386315186e-06,
|
| 1321 |
+
"loss": 2.5873,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.07377706495589414,
|
| 1326 |
+
"grad_norm": 1.434856653213501,
|
| 1327 |
+
"learning_rate": 3.4791089722651436e-06,
|
| 1328 |
+
"loss": 2.6847,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.07417802726543705,
|
| 1333 |
+
"grad_norm": 1.712814450263977,
|
| 1334 |
+
"learning_rate": 3.059973406066963e-06,
|
| 1335 |
+
"loss": 2.8479,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.07457898957497995,
|
| 1340 |
+
"grad_norm": 1.447488784790039,
|
| 1341 |
+
"learning_rate": 2.667340275199426e-06,
|
| 1342 |
+
"loss": 2.4426,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.07497995188452286,
|
| 1347 |
+
"grad_norm": 1.4372308254241943,
|
| 1348 |
+
"learning_rate": 2.3013169216400733e-06,
|
| 1349 |
+
"loss": 2.3632,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.07538091419406576,
|
| 1354 |
+
"grad_norm": 1.254798173904419,
|
| 1355 |
+
"learning_rate": 1.9620034125190644e-06,
|
| 1356 |
+
"loss": 2.3443,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.07578187650360867,
|
| 1361 |
+
"grad_norm": 1.4436801671981812,
|
| 1362 |
+
"learning_rate": 1.6494925127617634e-06,
|
| 1363 |
+
"loss": 2.4658,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.07618283881315156,
|
| 1368 |
+
"grad_norm": 1.5613583326339722,
|
| 1369 |
+
"learning_rate": 1.3638696597277679e-06,
|
| 1370 |
+
"loss": 2.489,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.07658380112269447,
|
| 1375 |
+
"grad_norm": 1.2076396942138672,
|
| 1376 |
+
"learning_rate": 1.1052129398531507e-06,
|
| 1377 |
+
"loss": 2.4914,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.07698476343223737,
|
| 1382 |
+
"grad_norm": 1.641299843788147,
|
| 1383 |
+
"learning_rate": 8.735930673024806e-07,
|
| 1384 |
+
"loss": 2.5859,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.07738572574178028,
|
| 1389 |
+
"grad_norm": 1.3305034637451172,
|
| 1390 |
+
"learning_rate": 6.690733646361857e-07,
|
| 1391 |
+
"loss": 2.3244,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.07778668805132317,
|
| 1396 |
+
"grad_norm": 1.4163548946380615,
|
| 1397 |
+
"learning_rate": 4.917097454988584e-07,
|
| 1398 |
+
"loss": 2.4282,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.07818765036086608,
|
| 1403 |
+
"grad_norm": 1.3471722602844238,
|
| 1404 |
+
"learning_rate": 3.415506993330153e-07,
|
| 1405 |
+
"loss": 2.388,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.07858861267040898,
|
| 1410 |
+
"grad_norm": 1.5998355150222778,
|
| 1411 |
+
"learning_rate": 2.1863727812254653e-07,
|
| 1412 |
+
"loss": 2.8515,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.07898957497995189,
|
| 1417 |
+
"grad_norm": 1.3900372982025146,
|
| 1418 |
+
"learning_rate": 1.230030851695263e-07,
|
| 1419 |
+
"loss": 2.4173,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.07939053728949479,
|
| 1424 |
+
"grad_norm": 1.9590660333633423,
|
| 1425 |
+
"learning_rate": 5.467426590739511e-08,
|
| 1426 |
+
"loss": 2.6594,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.0797914995990377,
|
| 1431 |
+
"grad_norm": 1.8619194030761719,
|
| 1432 |
+
"learning_rate": 1.3669500753099585e-08,
|
| 1433 |
+
"loss": 2.7384,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.08019246190858059,
|
| 1438 |
+
"grad_norm": 1.6162388324737549,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 2.6588,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.08019246190858059,
|
| 1445 |
+
"eval_loss": 2.537005662918091,
|
| 1446 |
+
"eval_runtime": 32.7979,
|
| 1447 |
+
"eval_samples_per_second": 32.045,
|
| 1448 |
+
"eval_steps_per_second": 16.038,
|
| 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": 3.69912849629184e+16,
|
| 1470 |
"train_batch_size": 2,
|
| 1471 |
"trial_name": null,
|
| 1472 |
"trial_params": null
|