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 101752088
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66c60c98657ed502fa2c1016b9ce5deef402bbf258bdfa6dd9b8020496dc75a0
|
| 3 |
size 101752088
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 203713238
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41c579475daf74857706e0dae085b8f2a787058662f7eb347521ab8cc25f5785
|
| 3 |
size 203713238
|
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:e6e59430d4b4b811794d683d76e428dbc806a60f2c322382193b90622a497076
|
| 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:fe157715eb8e05b3bab2a7f2fafac33705dc4a1a9dd7f6d860c3a7f9597d78bb
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1113,6 +1113,372 @@
|
|
| 1113 |
"eval_samples_per_second": 10.95,
|
| 1114 |
"eval_steps_per_second": 1.533,
|
| 1115 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1116 |
}
|
| 1117 |
],
|
| 1118 |
"logging_steps": 1,
|
|
@@ -1136,12 +1502,12 @@
|
|
| 1136 |
"should_evaluate": false,
|
| 1137 |
"should_log": false,
|
| 1138 |
"should_save": true,
|
| 1139 |
-
"should_training_stop":
|
| 1140 |
},
|
| 1141 |
"attributes": {}
|
| 1142 |
}
|
| 1143 |
},
|
| 1144 |
-
"total_flos": 1.
|
| 1145 |
"train_batch_size": 8,
|
| 1146 |
"trial_name": null,
|
| 1147 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.4329843521118164,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.028667670035117897,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 200,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1113 |
"eval_samples_per_second": 10.95,
|
| 1114 |
"eval_steps_per_second": 1.533,
|
| 1115 |
"step": 150
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.021644090876514012,
|
| 1119 |
+
"grad_norm": 0.42068323493003845,
|
| 1120 |
+
"learning_rate": 4.659698863221513e-05,
|
| 1121 |
+
"loss": 2.343,
|
| 1122 |
+
"step": 151
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.0217874292266896,
|
| 1126 |
+
"grad_norm": 0.436985045671463,
|
| 1127 |
+
"learning_rate": 4.481448235912671e-05,
|
| 1128 |
+
"loss": 2.3775,
|
| 1129 |
+
"step": 152
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.02193076757686519,
|
| 1133 |
+
"grad_norm": 0.43744659423828125,
|
| 1134 |
+
"learning_rate": 4.306073275629044e-05,
|
| 1135 |
+
"loss": 2.366,
|
| 1136 |
+
"step": 153
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.02207410592704078,
|
| 1140 |
+
"grad_norm": 0.42853182554244995,
|
| 1141 |
+
"learning_rate": 4.133621928133665e-05,
|
| 1142 |
+
"loss": 2.3583,
|
| 1143 |
+
"step": 154
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.02221744427721637,
|
| 1147 |
+
"grad_norm": 0.43902191519737244,
|
| 1148 |
+
"learning_rate": 3.964141339903026e-05,
|
| 1149 |
+
"loss": 2.3905,
|
| 1150 |
+
"step": 155
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.022360782627391957,
|
| 1154 |
+
"grad_norm": 0.46048280596733093,
|
| 1155 |
+
"learning_rate": 3.797677845237696e-05,
|
| 1156 |
+
"loss": 2.4043,
|
| 1157 |
+
"step": 156
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.022504120977567547,
|
| 1161 |
+
"grad_norm": 0.3899269998073578,
|
| 1162 |
+
"learning_rate": 3.634276953594982e-05,
|
| 1163 |
+
"loss": 2.3547,
|
| 1164 |
+
"step": 157
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.022647459327743136,
|
| 1168 |
+
"grad_norm": 0.37371909618377686,
|
| 1169 |
+
"learning_rate": 3.473983337147118e-05,
|
| 1170 |
+
"loss": 2.3287,
|
| 1171 |
+
"step": 158
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.022790797677918726,
|
| 1175 |
+
"grad_norm": 0.404742956161499,
|
| 1176 |
+
"learning_rate": 3.316840818568315e-05,
|
| 1177 |
+
"loss": 2.3772,
|
| 1178 |
+
"step": 159
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.022934136028094316,
|
| 1182 |
+
"grad_norm": 0.38302767276763916,
|
| 1183 |
+
"learning_rate": 3.162892359054098e-05,
|
| 1184 |
+
"loss": 2.3533,
|
| 1185 |
+
"step": 160
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.023077474378269906,
|
| 1189 |
+
"grad_norm": 0.3811044991016388,
|
| 1190 |
+
"learning_rate": 3.0121800465761293e-05,
|
| 1191 |
+
"loss": 2.3194,
|
| 1192 |
+
"step": 161
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.023220812728445495,
|
| 1196 |
+
"grad_norm": 0.5596585869789124,
|
| 1197 |
+
"learning_rate": 2.8647450843757897e-05,
|
| 1198 |
+
"loss": 2.4266,
|
| 1199 |
+
"step": 162
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.023364151078621085,
|
| 1203 |
+
"grad_norm": 0.5400771498680115,
|
| 1204 |
+
"learning_rate": 2.7206277796996144e-05,
|
| 1205 |
+
"loss": 2.3642,
|
| 1206 |
+
"step": 163
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.023507489428796675,
|
| 1210 |
+
"grad_norm": 0.4592722952365875,
|
| 1211 |
+
"learning_rate": 2.5798675327796993e-05,
|
| 1212 |
+
"loss": 2.327,
|
| 1213 |
+
"step": 164
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.023650827778972264,
|
| 1217 |
+
"grad_norm": 0.47848427295684814,
|
| 1218 |
+
"learning_rate": 2.4425028260620715e-05,
|
| 1219 |
+
"loss": 2.4503,
|
| 1220 |
+
"step": 165
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.023794166129147854,
|
| 1224 |
+
"grad_norm": 0.45060548186302185,
|
| 1225 |
+
"learning_rate": 2.3085712136859668e-05,
|
| 1226 |
+
"loss": 2.3749,
|
| 1227 |
+
"step": 166
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.023937504479323444,
|
| 1231 |
+
"grad_norm": 0.4228126108646393,
|
| 1232 |
+
"learning_rate": 2.178109311216913e-05,
|
| 1233 |
+
"loss": 2.4633,
|
| 1234 |
+
"step": 167
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.024080842829499034,
|
| 1238 |
+
"grad_norm": 0.5396104454994202,
|
| 1239 |
+
"learning_rate": 2.0511527856363912e-05,
|
| 1240 |
+
"loss": 2.4974,
|
| 1241 |
+
"step": 168
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.024224181179674623,
|
| 1245 |
+
"grad_norm": 0.47498688101768494,
|
| 1246 |
+
"learning_rate": 1.927736345590839e-05,
|
| 1247 |
+
"loss": 2.5275,
|
| 1248 |
+
"step": 169
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.024367519529850213,
|
| 1252 |
+
"grad_norm": 0.5508636832237244,
|
| 1253 |
+
"learning_rate": 1.8078937319026654e-05,
|
| 1254 |
+
"loss": 2.4751,
|
| 1255 |
+
"step": 170
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.0245108578800258,
|
| 1259 |
+
"grad_norm": 0.4817218780517578,
|
| 1260 |
+
"learning_rate": 1.6916577083458228e-05,
|
| 1261 |
+
"loss": 2.5245,
|
| 1262 |
+
"step": 171
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.02465419623020139,
|
| 1266 |
+
"grad_norm": 0.4276881217956543,
|
| 1267 |
+
"learning_rate": 1.579060052688548e-05,
|
| 1268 |
+
"loss": 2.403,
|
| 1269 |
+
"step": 172
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.02479753458037698,
|
| 1273 |
+
"grad_norm": 0.4423224627971649,
|
| 1274 |
+
"learning_rate": 1.4701315480056164e-05,
|
| 1275 |
+
"loss": 2.4871,
|
| 1276 |
+
"step": 173
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.02494087293055257,
|
| 1280 |
+
"grad_norm": 0.4730720818042755,
|
| 1281 |
+
"learning_rate": 1.3649019742625623e-05,
|
| 1282 |
+
"loss": 2.4419,
|
| 1283 |
+
"step": 174
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.025084211280728158,
|
| 1287 |
+
"grad_norm": 0.4102948009967804,
|
| 1288 |
+
"learning_rate": 1.2634001001741373e-05,
|
| 1289 |
+
"loss": 2.3216,
|
| 1290 |
+
"step": 175
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.025084211280728158,
|
| 1294 |
+
"eval_loss": 2.4315061569213867,
|
| 1295 |
+
"eval_runtime": 4.5667,
|
| 1296 |
+
"eval_samples_per_second": 10.949,
|
| 1297 |
+
"eval_steps_per_second": 1.533,
|
| 1298 |
+
"step": 175
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.025227549630903748,
|
| 1302 |
+
"grad_norm": 0.43688416481018066,
|
| 1303 |
+
"learning_rate": 1.1656536753392287e-05,
|
| 1304 |
+
"loss": 2.3618,
|
| 1305 |
+
"step": 176
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.025370887981079338,
|
| 1309 |
+
"grad_norm": 0.4183753728866577,
|
| 1310 |
+
"learning_rate": 1.0716894226543953e-05,
|
| 1311 |
+
"loss": 2.4004,
|
| 1312 |
+
"step": 177
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.025514226331254927,
|
| 1316 |
+
"grad_norm": 0.3798510432243347,
|
| 1317 |
+
"learning_rate": 9.815330310080887e-06,
|
| 1318 |
+
"loss": 2.3351,
|
| 1319 |
+
"step": 178
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.025657564681430517,
|
| 1323 |
+
"grad_norm": 0.4367026090621948,
|
| 1324 |
+
"learning_rate": 8.952091482575824e-06,
|
| 1325 |
+
"loss": 2.339,
|
| 1326 |
+
"step": 179
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.025800903031606107,
|
| 1330 |
+
"grad_norm": 0.43516334891319275,
|
| 1331 |
+
"learning_rate": 8.127413744904804e-06,
|
| 1332 |
+
"loss": 2.3865,
|
| 1333 |
+
"step": 180
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.025944241381781696,
|
| 1337 |
+
"grad_norm": 0.39649835228919983,
|
| 1338 |
+
"learning_rate": 7.34152255572697e-06,
|
| 1339 |
+
"loss": 2.4152,
|
| 1340 |
+
"step": 181
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.026087579731957286,
|
| 1344 |
+
"grad_norm": 0.4496510326862335,
|
| 1345 |
+
"learning_rate": 6.594632769846353e-06,
|
| 1346 |
+
"loss": 2.4076,
|
| 1347 |
+
"step": 182
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.026230918082132876,
|
| 1351 |
+
"grad_norm": 0.36271652579307556,
|
| 1352 |
+
"learning_rate": 5.886948579472778e-06,
|
| 1353 |
+
"loss": 2.349,
|
| 1354 |
+
"step": 183
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.026374256432308466,
|
| 1358 |
+
"grad_norm": 0.43088510632514954,
|
| 1359 |
+
"learning_rate": 5.218663458397715e-06,
|
| 1360 |
+
"loss": 2.412,
|
| 1361 |
+
"step": 184
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.026517594782484055,
|
| 1365 |
+
"grad_norm": 0.4110885262489319,
|
| 1366 |
+
"learning_rate": 4.589960109100444e-06,
|
| 1367 |
+
"loss": 2.3669,
|
| 1368 |
+
"step": 185
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.02666093313265964,
|
| 1372 |
+
"grad_norm": 0.44089290499687195,
|
| 1373 |
+
"learning_rate": 4.001010412799138e-06,
|
| 1374 |
+
"loss": 2.3644,
|
| 1375 |
+
"step": 186
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.02680427148283523,
|
| 1379 |
+
"grad_norm": 0.46191123127937317,
|
| 1380 |
+
"learning_rate": 3.451975382460109e-06,
|
| 1381 |
+
"loss": 2.4576,
|
| 1382 |
+
"step": 187
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.02694760983301082,
|
| 1386 |
+
"grad_norm": 0.43181681632995605,
|
| 1387 |
+
"learning_rate": 2.9430051187785962e-06,
|
| 1388 |
+
"loss": 2.3365,
|
| 1389 |
+
"step": 188
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.02709094818318641,
|
| 1393 |
+
"grad_norm": 0.5321618914604187,
|
| 1394 |
+
"learning_rate": 2.4742387691426445e-06,
|
| 1395 |
+
"loss": 2.3837,
|
| 1396 |
+
"step": 189
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.027234286533362,
|
| 1400 |
+
"grad_norm": 0.4526923894882202,
|
| 1401 |
+
"learning_rate": 2.0458044895916513e-06,
|
| 1402 |
+
"loss": 2.3506,
|
| 1403 |
+
"step": 190
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.02737762488353759,
|
| 1407 |
+
"grad_norm": 0.42679014801979065,
|
| 1408 |
+
"learning_rate": 1.6578194097797258e-06,
|
| 1409 |
+
"loss": 2.4344,
|
| 1410 |
+
"step": 191
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.02752096323371318,
|
| 1414 |
+
"grad_norm": 0.5031974911689758,
|
| 1415 |
+
"learning_rate": 1.3103896009537207e-06,
|
| 1416 |
+
"loss": 2.3758,
|
| 1417 |
+
"step": 192
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.02766430158388877,
|
| 1421 |
+
"grad_norm": 0.4715871214866638,
|
| 1422 |
+
"learning_rate": 1.0036100469542786e-06,
|
| 1423 |
+
"loss": 2.4062,
|
| 1424 |
+
"step": 193
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.02780763993406436,
|
| 1428 |
+
"grad_norm": 0.5107702612876892,
|
| 1429 |
+
"learning_rate": 7.375646182482875e-07,
|
| 1430 |
+
"loss": 2.4455,
|
| 1431 |
+
"step": 194
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.02795097828423995,
|
| 1435 |
+
"grad_norm": 0.44611087441444397,
|
| 1436 |
+
"learning_rate": 5.123260489995229e-07,
|
| 1437 |
+
"loss": 2.456,
|
| 1438 |
+
"step": 195
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.02809431663441554,
|
| 1442 |
+
"grad_norm": 0.4629242718219757,
|
| 1443 |
+
"learning_rate": 3.2795591718381975e-07,
|
| 1444 |
+
"loss": 2.3595,
|
| 1445 |
+
"step": 196
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.02823765498459113,
|
| 1449 |
+
"grad_norm": 0.4822857975959778,
|
| 1450 |
+
"learning_rate": 1.8450462775428942e-07,
|
| 1451 |
+
"loss": 2.4289,
|
| 1452 |
+
"step": 197
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.028380993334766718,
|
| 1456 |
+
"grad_norm": 0.4529360234737396,
|
| 1457 |
+
"learning_rate": 8.201139886109264e-08,
|
| 1458 |
+
"loss": 2.3392,
|
| 1459 |
+
"step": 198
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.028524331684942308,
|
| 1463 |
+
"grad_norm": 0.43792641162872314,
|
| 1464 |
+
"learning_rate": 2.0504251129649374e-08,
|
| 1465 |
+
"loss": 2.4626,
|
| 1466 |
+
"step": 199
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.028667670035117897,
|
| 1470 |
+
"grad_norm": 0.4136735796928406,
|
| 1471 |
+
"learning_rate": 0.0,
|
| 1472 |
+
"loss": 2.35,
|
| 1473 |
+
"step": 200
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.028667670035117897,
|
| 1477 |
+
"eval_loss": 2.4329843521118164,
|
| 1478 |
+
"eval_runtime": 4.566,
|
| 1479 |
+
"eval_samples_per_second": 10.95,
|
| 1480 |
+
"eval_steps_per_second": 1.533,
|
| 1481 |
+
"step": 200
|
| 1482 |
}
|
| 1483 |
],
|
| 1484 |
"logging_steps": 1,
|
|
|
|
| 1502 |
"should_evaluate": false,
|
| 1503 |
"should_log": false,
|
| 1504 |
"should_save": true,
|
| 1505 |
+
"should_training_stop": true
|
| 1506 |
},
|
| 1507 |
"attributes": {}
|
| 1508 |
}
|
| 1509 |
},
|
| 1510 |
+
"total_flos": 1.39939410345984e+17,
|
| 1511 |
"train_batch_size": 8,
|
| 1512 |
"trial_name": null,
|
| 1513 |
"trial_params": null
|