Hugging Face's logo

aleegis10
/
328c7fca-9a6b-4269-9dfe-e170212caa1c

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
aleegis10 commited on
Commit
2dee002
·
verified ·
1 Parent(s): 8277958

Training in progress, step 177, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +193 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ebc7ceb7ecddfb1549aa9b294a9286e445e64173f4683b8813784644fdd26dc
3
  size 78207176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9af577030e0d1ea19f27a734808c67204f166a9b543ff58641fcbc7fa46563ab
3
  size 78207176
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a827d82c6fddd582c2adf8418ecc68bf15fb117024264fc77dd8d627381a3742
3
  size 40177764
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b56e2103eb728a4b8a9543b05b230a1b1907a6ffcf8e5dc21a6bf156e54a1af
3
  size 40177764
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4faab524ed8a4ede88fe4014f2fac1363e19754fcf08782cce5e759d4637ec17
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5cfbdfd476ba453801a7b0b549bc8952ec25e55308ff788915444832b54f51c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae143a1b3a6f3911d7de6f885a33334066ae6c29ef03002bdce21e41331f97e8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3920ee4a294e40209fd09294d2bc1408892fffa1eb0ce50b11d8a2f2e706c9ae
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.9148275852203369,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 2.542372881355932,
5
  "eval_steps": 50,
6
- "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1089,6 +1089,195 @@
1089
  "eval_samples_per_second": 69.125,
1090
  "eval_steps_per_second": 17.281,
1091
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1092
  }
1093
  ],
1094
  "logging_steps": 1,
@@ -1112,12 +1301,12 @@
1112
  "should_evaluate": false,
1113
  "should_log": false,
1114
  "should_save": true,
1115
- "should_training_stop": false
1116
  },
1117
  "attributes": {}
1118
  }
1119
  },
1120
- "total_flos": 3702083627778048.0,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
  "best_metric": 0.9148275852203369,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 3.0,
5
  "eval_steps": 50,
6
+ "global_step": 177,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1089
  "eval_samples_per_second": 69.125,
1090
  "eval_steps_per_second": 17.281,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 2.559322033898305,
1095
+ "grad_norm": 0.11883600056171417,
1096
+ "learning_rate": 5.86243717785463e-06,
1097
+ "loss": 0.0865,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 2.576271186440678,
1102
+ "grad_norm": 0.029807042330503464,
1103
+ "learning_rate": 5.428342404965076e-06,
1104
+ "loss": 0.0033,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 2.593220338983051,
1109
+ "grad_norm": 0.15622468292713165,
1110
+ "learning_rate": 5.010020576785174e-06,
1111
+ "loss": 0.1535,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 2.610169491525424,
1116
+ "grad_norm": 0.4695366322994232,
1117
+ "learning_rate": 4.607619728353818e-06,
1118
+ "loss": 1.2671,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 2.6271186440677967,
1123
+ "grad_norm": 0.7809627652168274,
1124
+ "learning_rate": 4.221282260619891e-06,
1125
+ "loss": 1.7782,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 2.6440677966101696,
1130
+ "grad_norm": 0.7714522480964661,
1131
+ "learning_rate": 3.851144890049535e-06,
1132
+ "loss": 2.0438,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 2.6610169491525424,
1137
+ "grad_norm": 0.9179351329803467,
1138
+ "learning_rate": 3.4973386002452535e-06,
1139
+ "loss": 2.2235,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 2.6779661016949152,
1144
+ "grad_norm": 0.8256776332855225,
1145
+ "learning_rate": 3.159988595593616e-06,
1146
+ "loss": 1.9886,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 2.694915254237288,
1151
+ "grad_norm": 0.9762132167816162,
1152
+ "learning_rate": 2.839214256958106e-06,
1153
+ "loss": 2.0266,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 2.711864406779661,
1158
+ "grad_norm": 1.1027181148529053,
1159
+ "learning_rate": 2.53512909943287e-06,
1160
+ "loss": 2.1582,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 2.7288135593220337,
1165
+ "grad_norm": 0.5595541000366211,
1166
+ "learning_rate": 2.2478407321721296e-06,
1167
+ "loss": 1.4767,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 2.7457627118644066,
1172
+ "grad_norm": 0.19766104221343994,
1173
+ "learning_rate": 1.977450820309684e-06,
1174
+ "loss": 0.2643,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 2.7627118644067794,
1179
+ "grad_norm": 0.2085597813129425,
1180
+ "learning_rate": 1.7240550489817653e-06,
1181
+ "loss": 0.2502,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 2.7796610169491527,
1186
+ "grad_norm": 0.2631925940513611,
1187
+ "learning_rate": 1.4877430894662036e-06,
1188
+ "loss": 0.4407,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 2.7966101694915255,
1193
+ "grad_norm": 0.1086735650897026,
1194
+ "learning_rate": 1.268598567449647e-06,
1195
+ "loss": 0.0985,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 2.8135593220338984,
1200
+ "grad_norm": 0.1114293783903122,
1201
+ "learning_rate": 1.0666990334342707e-06,
1202
+ "loss": 0.0853,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 2.830508474576271,
1207
+ "grad_norm": 0.20077882707118988,
1208
+ "learning_rate": 8.821159352943143e-07,
1209
+ "loss": 0.3038,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 2.847457627118644,
1214
+ "grad_norm": 0.5867683291435242,
1215
+ "learning_rate": 7.149145929922607e-07,
1216
+ "loss": 1.7456,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 2.864406779661017,
1221
+ "grad_norm": 0.8998249173164368,
1222
+ "learning_rate": 5.651541754634726e-07,
1223
+ "loss": 2.1784,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 2.8813559322033897,
1228
+ "grad_norm": 0.7912001609802246,
1229
+ "learning_rate": 4.3288767967760715e-07,
1230
+ "loss": 1.8512,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 2.898305084745763,
1235
+ "grad_norm": 0.7731630206108093,
1236
+ "learning_rate": 3.1816191188415166e-07,
1237
+ "loss": 2.1491,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 2.915254237288136,
1242
+ "grad_norm": 0.860531210899353,
1243
+ "learning_rate": 2.2101747104866788e-07,
1244
+ "loss": 1.8962,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 2.9322033898305087,
1249
+ "grad_norm": 0.9022953510284424,
1250
+ "learning_rate": 1.4148873448573408e-07,
1251
+ "loss": 2.2015,
1252
+ "step": 173
1253
+ },
1254
+ {
1255
+ "epoch": 2.9491525423728815,
1256
+ "grad_norm": 1.231516718864441,
1257
+ "learning_rate": 7.960384569353219e-08,
1258
+ "loss": 2.2436,
1259
+ "step": 174
1260
+ },
1261
+ {
1262
+ "epoch": 2.9661016949152543,
1263
+ "grad_norm": 0.2086687535047531,
1264
+ "learning_rate": 3.538470439448105e-08,
1265
+ "loss": 0.2974,
1266
+ "step": 175
1267
+ },
1268
+ {
1269
+ "epoch": 2.983050847457627,
1270
+ "grad_norm": 0.2978679835796356,
1271
+ "learning_rate": 8.846958785418968e-09,
1272
+ "loss": 0.6034,
1273
+ "step": 176
1274
+ },
1275
+ {
1276
+ "epoch": 3.0,
1277
+ "grad_norm": 0.9400612711906433,
1278
+ "learning_rate": 0.0,
1279
+ "loss": 2.0483,
1280
+ "step": 177
1281
  }
1282
  ],
1283
  "logging_steps": 1,
 
1301
  "should_evaluate": false,
1302
  "should_log": false,
1303
  "should_save": true,
1304
+ "should_training_stop": true
1305
  },
1306
  "attributes": {}
1307
  }
1308
  },
1309
+ "total_flos": 4366480939941888.0,
1310
  "train_batch_size": 8,
1311
  "trial_name": null,
1312
  "trial_params": null