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 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2856c3e43c3c513c2f50a8bb057d64f8c19b6b8592b0e748fdb1eafeee2a22e
|
| 3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 341314196
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d4029a6945840d6fb8ef37d9d491408338f92fc4a017932e558a9beb6fea671
|
| 3 |
size 341314196
|
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 sha256:5c0e255dfebdd91dd2b1c69bd937fb9195ff7ce72d2f04a7060f01cbb1f36194
|
| 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:c09a3e270daa077e38bac4ad605b0e6c9b43938bcf49dc3d62c3671f11248c14
|
| 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": 13.187,
|
| 1090 |
"eval_steps_per_second": 3.307,
|
| 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": 2.
|
| 1121 |
"train_batch_size": 8,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.4122912585735321,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
| 4 |
+
"epoch": 0.36579789666209417,
|
| 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": 13.187,
|
| 1090 |
"eval_steps_per_second": 3.307,
|
| 1091 |
"step": 150
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.2761774119798811,
|
| 1095 |
+
"grad_norm": 3.2242889404296875,
|
| 1096 |
+
"learning_rate": 1.397909658966454e-05,
|
| 1097 |
+
"loss": 3.3733,
|
| 1098 |
+
"step": 151
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.2780064014631916,
|
| 1102 |
+
"grad_norm": 5.670266151428223,
|
| 1103 |
+
"learning_rate": 1.3444344707738015e-05,
|
| 1104 |
+
"loss": 2.1266,
|
| 1105 |
+
"step": 152
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.27983539094650206,
|
| 1109 |
+
"grad_norm": 5.771026134490967,
|
| 1110 |
+
"learning_rate": 1.2918219826887136e-05,
|
| 1111 |
+
"loss": 2.1279,
|
| 1112 |
+
"step": 153
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.2816643804298125,
|
| 1116 |
+
"grad_norm": 4.846254348754883,
|
| 1117 |
+
"learning_rate": 1.2400865784400998e-05,
|
| 1118 |
+
"loss": 1.8303,
|
| 1119 |
+
"step": 154
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.283493369913123,
|
| 1123 |
+
"grad_norm": 3.5640859603881836,
|
| 1124 |
+
"learning_rate": 1.189242401970908e-05,
|
| 1125 |
+
"loss": 1.933,
|
| 1126 |
+
"step": 155
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.28532235939643347,
|
| 1130 |
+
"grad_norm": 3.4007530212402344,
|
| 1131 |
+
"learning_rate": 1.139303353571309e-05,
|
| 1132 |
+
"loss": 1.925,
|
| 1133 |
+
"step": 156
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.2871513488797439,
|
| 1137 |
+
"grad_norm": 2.8827219009399414,
|
| 1138 |
+
"learning_rate": 1.0902830860784946e-05,
|
| 1139 |
+
"loss": 1.8919,
|
| 1140 |
+
"step": 157
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.2889803383630544,
|
| 1144 |
+
"grad_norm": 2.5703036785125732,
|
| 1145 |
+
"learning_rate": 1.0421950011441355e-05,
|
| 1146 |
+
"loss": 1.6536,
|
| 1147 |
+
"step": 158
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.2908093278463649,
|
| 1151 |
+
"grad_norm": 3.159573793411255,
|
| 1152 |
+
"learning_rate": 9.950522455704946e-06,
|
| 1153 |
+
"loss": 1.8493,
|
| 1154 |
+
"step": 159
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.2926383173296754,
|
| 1158 |
+
"grad_norm": 2.5821759700775146,
|
| 1159 |
+
"learning_rate": 9.488677077162294e-06,
|
| 1160 |
+
"loss": 1.6803,
|
| 1161 |
+
"step": 160
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.29446730681298583,
|
| 1165 |
+
"grad_norm": 3.1302449703216553,
|
| 1166 |
+
"learning_rate": 9.03654013972839e-06,
|
| 1167 |
+
"loss": 1.7169,
|
| 1168 |
+
"step": 161
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.2962962962962963,
|
| 1172 |
+
"grad_norm": 2.8759653568267822,
|
| 1173 |
+
"learning_rate": 8.59423525312737e-06,
|
| 1174 |
+
"loss": 1.7755,
|
| 1175 |
+
"step": 162
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.2981252857796068,
|
| 1179 |
+
"grad_norm": 2.5034046173095703,
|
| 1180 |
+
"learning_rate": 8.161883339098845e-06,
|
| 1181 |
+
"loss": 1.629,
|
| 1182 |
+
"step": 163
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.29995427526291724,
|
| 1186 |
+
"grad_norm": 2.7628417015075684,
|
| 1187 |
+
"learning_rate": 7.739602598339099e-06,
|
| 1188 |
+
"loss": 1.6435,
|
| 1189 |
+
"step": 164
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.3017832647462277,
|
| 1193 |
+
"grad_norm": 2.9850990772247314,
|
| 1194 |
+
"learning_rate": 7.327508478186216e-06,
|
| 1195 |
+
"loss": 1.5329,
|
| 1196 |
+
"step": 165
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.3036122542295382,
|
| 1200 |
+
"grad_norm": 2.9146676063537598,
|
| 1201 |
+
"learning_rate": 6.925713641057902e-06,
|
| 1202 |
+
"loss": 1.5871,
|
| 1203 |
+
"step": 166
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.30544124371284864,
|
| 1207 |
+
"grad_norm": 2.9478302001953125,
|
| 1208 |
+
"learning_rate": 6.53432793365074e-06,
|
| 1209 |
+
"loss": 2.038,
|
| 1210 |
+
"step": 167
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.30727023319615915,
|
| 1214 |
+
"grad_norm": 2.645951509475708,
|
| 1215 |
+
"learning_rate": 6.153458356909174e-06,
|
| 1216 |
+
"loss": 1.5005,
|
| 1217 |
+
"step": 168
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.3090992226794696,
|
| 1221 |
+
"grad_norm": 3.275236129760742,
|
| 1222 |
+
"learning_rate": 5.783209036772518e-06,
|
| 1223 |
+
"loss": 1.5978,
|
| 1224 |
+
"step": 169
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.31092821216278005,
|
| 1228 |
+
"grad_norm": 3.1929399967193604,
|
| 1229 |
+
"learning_rate": 5.423681195707997e-06,
|
| 1230 |
+
"loss": 1.612,
|
| 1231 |
+
"step": 170
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.31275720164609055,
|
| 1235 |
+
"grad_norm": 2.6903254985809326,
|
| 1236 |
+
"learning_rate": 5.074973125037469e-06,
|
| 1237 |
+
"loss": 1.4468,
|
| 1238 |
+
"step": 171
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.314586191129401,
|
| 1242 |
+
"grad_norm": 2.8064029216766357,
|
| 1243 |
+
"learning_rate": 4.737180158065644e-06,
|
| 1244 |
+
"loss": 1.332,
|
| 1245 |
+
"step": 172
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.31641518061271146,
|
| 1249 |
+
"grad_norm": 3.1456053256988525,
|
| 1250 |
+
"learning_rate": 4.41039464401685e-06,
|
| 1251 |
+
"loss": 1.2924,
|
| 1252 |
+
"step": 173
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.31824417009602196,
|
| 1256 |
+
"grad_norm": 2.8055481910705566,
|
| 1257 |
+
"learning_rate": 4.094705922787687e-06,
|
| 1258 |
+
"loss": 1.5403,
|
| 1259 |
+
"step": 174
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.3200731595793324,
|
| 1263 |
+
"grad_norm": 3.6348037719726562,
|
| 1264 |
+
"learning_rate": 3.7902003005224126e-06,
|
| 1265 |
+
"loss": 1.7584,
|
| 1266 |
+
"step": 175
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.3219021490626429,
|
| 1270 |
+
"grad_norm": 3.2643659114837646,
|
| 1271 |
+
"learning_rate": 3.4969610260176865e-06,
|
| 1272 |
+
"loss": 1.601,
|
| 1273 |
+
"step": 176
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.32373113854595337,
|
| 1277 |
+
"grad_norm": 3.0372745990753174,
|
| 1278 |
+
"learning_rate": 3.2150682679631867e-06,
|
| 1279 |
+
"loss": 1.7298,
|
| 1280 |
+
"step": 177
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.3255601280292638,
|
| 1284 |
+
"grad_norm": 2.9586946964263916,
|
| 1285 |
+
"learning_rate": 2.9445990930242668e-06,
|
| 1286 |
+
"loss": 1.5171,
|
| 1287 |
+
"step": 178
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.3273891175125743,
|
| 1291 |
+
"grad_norm": 3.363837718963623,
|
| 1292 |
+
"learning_rate": 2.6856274447727475e-06,
|
| 1293 |
+
"loss": 1.4689,
|
| 1294 |
+
"step": 179
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.3292181069958848,
|
| 1298 |
+
"grad_norm": 2.9554202556610107,
|
| 1299 |
+
"learning_rate": 2.4382241234714413e-06,
|
| 1300 |
+
"loss": 1.3872,
|
| 1301 |
+
"step": 180
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.3310470964791952,
|
| 1305 |
+
"grad_norm": 2.9872653484344482,
|
| 1306 |
+
"learning_rate": 2.2024567667180914e-06,
|
| 1307 |
+
"loss": 1.346,
|
| 1308 |
+
"step": 181
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.33287608596250573,
|
| 1312 |
+
"grad_norm": 3.0197293758392334,
|
| 1313 |
+
"learning_rate": 1.978389830953906e-06,
|
| 1314 |
+
"loss": 1.387,
|
| 1315 |
+
"step": 182
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.3347050754458162,
|
| 1319 |
+
"grad_norm": 3.4662463665008545,
|
| 1320 |
+
"learning_rate": 1.7660845738418336e-06,
|
| 1321 |
+
"loss": 1.307,
|
| 1322 |
+
"step": 183
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.33653406492912663,
|
| 1326 |
+
"grad_norm": 2.93145751953125,
|
| 1327 |
+
"learning_rate": 1.5655990375193147e-06,
|
| 1328 |
+
"loss": 1.4363,
|
| 1329 |
+
"step": 184
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.33836305441243714,
|
| 1333 |
+
"grad_norm": 4.212636947631836,
|
| 1334 |
+
"learning_rate": 1.3769880327301332e-06,
|
| 1335 |
+
"loss": 1.6964,
|
| 1336 |
+
"step": 185
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.3401920438957476,
|
| 1340 |
+
"grad_norm": 3.6545448303222656,
|
| 1341 |
+
"learning_rate": 1.2003031238397417e-06,
|
| 1342 |
+
"loss": 1.3713,
|
| 1343 |
+
"step": 186
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.3420210333790581,
|
| 1347 |
+
"grad_norm": 3.6628952026367188,
|
| 1348 |
+
"learning_rate": 1.035592614738033e-06,
|
| 1349 |
+
"loss": 1.5177,
|
| 1350 |
+
"step": 187
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.34385002286236854,
|
| 1354 |
+
"grad_norm": 3.4088120460510254,
|
| 1355 |
+
"learning_rate": 8.829015356335791e-07,
|
| 1356 |
+
"loss": 1.4526,
|
| 1357 |
+
"step": 188
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.345679012345679,
|
| 1361 |
+
"grad_norm": 3.7372164726257324,
|
| 1362 |
+
"learning_rate": 7.422716307427936e-07,
|
| 1363 |
+
"loss": 1.5256,
|
| 1364 |
+
"step": 189
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.3475080018289895,
|
| 1368 |
+
"grad_norm": 4.675724506378174,
|
| 1369 |
+
"learning_rate": 6.137413468774955e-07,
|
| 1370 |
+
"loss": 1.6158,
|
| 1371 |
+
"step": 190
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.34933699131229995,
|
| 1375 |
+
"grad_norm": 4.1608476638793945,
|
| 1376 |
+
"learning_rate": 4.973458229339179e-07,
|
| 1377 |
+
"loss": 1.3692,
|
| 1378 |
+
"step": 191
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.3511659807956104,
|
| 1382 |
+
"grad_norm": 5.226892471313477,
|
| 1383 |
+
"learning_rate": 3.9311688028611627e-07,
|
| 1384 |
+
"loss": 1.5964,
|
| 1385 |
+
"step": 192
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.3529949702789209,
|
| 1389 |
+
"grad_norm": 5.3858866691589355,
|
| 1390 |
+
"learning_rate": 3.010830140862836e-07,
|
| 1391 |
+
"loss": 1.586,
|
| 1392 |
+
"step": 193
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.35482395976223136,
|
| 1396 |
+
"grad_norm": 7.010944366455078,
|
| 1397 |
+
"learning_rate": 2.2126938547448627e-07,
|
| 1398 |
+
"loss": 1.8911,
|
| 1399 |
+
"step": 194
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.35665294924554186,
|
| 1403 |
+
"grad_norm": 5.510322570800781,
|
| 1404 |
+
"learning_rate": 1.536978146998569e-07,
|
| 1405 |
+
"loss": 1.6378,
|
| 1406 |
+
"step": 195
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.3584819387288523,
|
| 1410 |
+
"grad_norm": 6.095245361328125,
|
| 1411 |
+
"learning_rate": 9.838677515514594e-08,
|
| 1412 |
+
"loss": 1.3781,
|
| 1413 |
+
"step": 196
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.36031092821216276,
|
| 1417 |
+
"grad_norm": 7.126282215118408,
|
| 1418 |
+
"learning_rate": 5.5351388326286834e-08,
|
| 1419 |
+
"loss": 1.5673,
|
| 1420 |
+
"step": 197
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.36213991769547327,
|
| 1424 |
+
"grad_norm": 10.43659782409668,
|
| 1425 |
+
"learning_rate": 2.4603419658327797e-08,
|
| 1426 |
+
"loss": 1.7628,
|
| 1427 |
+
"step": 198
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.3639689071787837,
|
| 1431 |
+
"grad_norm": 10.773320198059082,
|
| 1432 |
+
"learning_rate": 6.151275338894813e-09,
|
| 1433 |
+
"loss": 2.0201,
|
| 1434 |
+
"step": 199
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.36579789666209417,
|
| 1438 |
+
"grad_norm": 14.928093910217285,
|
| 1439 |
+
"learning_rate": 0.0,
|
| 1440 |
+
"loss": 2.1034,
|
| 1441 |
+
"step": 200
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.36579789666209417,
|
| 1445 |
+
"eval_loss": 0.4122912585735321,
|
| 1446 |
+
"eval_runtime": 70.0827,
|
| 1447 |
+
"eval_samples_per_second": 13.142,
|
| 1448 |
+
"eval_steps_per_second": 3.296,
|
| 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": 2.9156617249357824e+17,
|
| 1479 |
"train_batch_size": 8,
|
| 1480 |
"trial_name": null,
|
| 1481 |
"trial_params": null
|