brixeus commited on
Commit
c58cf0a
·
verified ·
1 Parent(s): ec31765

Training in progress, step 173, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47bf45895ca89ba2bd944e2e91074ffd9657ac2873c40cd93ee1317db7c0b151
3
  size 389074464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85d702d723b9a5b7b3e99590a82b5ffccf4bd8aca85f13d79be8a3d9b70bac55
3
  size 389074464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7cef557681bd8ef09914a6e014611029a5afbbe31bccf496208366a459ff61e
3
  size 198011252
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35c92803e89358dcfbad4c80b8e33d9c786af5a6e4dd554ca1b2c3bd4c502981
3
  size 198011252
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e79c861973f996d9daa7e558d03a8fd4c6fca4e164ce3e3069898269f9da138
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b1532ac5d2ef52963000f6588a6ae192ac1f74632cc9fa160113ecce398e5f6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cb01d4f0da8d959e9ca5a4773566e24c639c6b8f18e1285757275e715c7b05f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13cea8c13b7ff143621afe3809a9208b72f31395569d02b28f3b5848f77c0a7e
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 1.3433974981307983,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 2.606060606060606,
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 +1089,167 @@
1089
  "eval_samples_per_second": 20.955,
1090
  "eval_steps_per_second": 5.401,
1091
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1092
  }
1093
  ],
1094
  "logging_steps": 1,
@@ -1112,12 +1273,12 @@
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": 8.886296965545984e+16,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null
 
1
  {
2
  "best_metric": 1.3433974981307983,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 3.0086580086580086,
5
  "eval_steps": 50,
6
+ "global_step": 173,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1089
  "eval_samples_per_second": 20.955,
1090
  "eval_steps_per_second": 5.401,
1091
  "step": 150
1092
+ },
1093
+ {
1094
+ "epoch": 2.6233766233766236,
1095
+ "grad_norm": 0.5399381518363953,
1096
+ "learning_rate": 4.427853541662091e-06,
1097
+ "loss": 0.9998,
1098
+ "step": 151
1099
+ },
1100
+ {
1101
+ "epoch": 2.6406926406926408,
1102
+ "grad_norm": 0.5969071388244629,
1103
+ "learning_rate": 4.039859192235779e-06,
1104
+ "loss": 1.0212,
1105
+ "step": 152
1106
+ },
1107
+ {
1108
+ "epoch": 2.658008658008658,
1109
+ "grad_norm": 0.6443363428115845,
1110
+ "learning_rate": 3.668937158903901e-06,
1111
+ "loss": 0.9932,
1112
+ "step": 153
1113
+ },
1114
+ {
1115
+ "epoch": 2.675324675324675,
1116
+ "grad_norm": 0.6645355820655823,
1117
+ "learning_rate": 3.315225224059809e-06,
1118
+ "loss": 0.8225,
1119
+ "step": 154
1120
+ },
1121
+ {
1122
+ "epoch": 2.6926406926406927,
1123
+ "grad_norm": 0.7571910619735718,
1124
+ "learning_rate": 2.9788547772478416e-06,
1125
+ "loss": 0.8601,
1126
+ "step": 155
1127
+ },
1128
+ {
1129
+ "epoch": 2.70995670995671,
1130
+ "grad_norm": 0.8637107610702515,
1131
+ "learning_rate": 2.6599507663574384e-06,
1132
+ "loss": 0.7328,
1133
+ "step": 156
1134
+ },
1135
+ {
1136
+ "epoch": 2.7272727272727275,
1137
+ "grad_norm": 1.1502426862716675,
1138
+ "learning_rate": 2.3586316512101416e-06,
1139
+ "loss": 0.5778,
1140
+ "step": 157
1141
+ },
1142
+ {
1143
+ "epoch": 2.7445887445887447,
1144
+ "grad_norm": 0.34329354763031006,
1145
+ "learning_rate": 2.0750093595565733e-06,
1146
+ "loss": 0.9435,
1147
+ "step": 158
1148
+ },
1149
+ {
1150
+ "epoch": 2.761904761904762,
1151
+ "grad_norm": 0.3949293792247772,
1152
+ "learning_rate": 1.8091892454998594e-06,
1153
+ "loss": 1.0729,
1154
+ "step": 159
1155
+ },
1156
+ {
1157
+ "epoch": 2.779220779220779,
1158
+ "grad_norm": 0.4253315329551697,
1159
+ "learning_rate": 1.5612700503608968e-06,
1160
+ "loss": 1.1036,
1161
+ "step": 160
1162
+ },
1163
+ {
1164
+ "epoch": 2.7965367965367967,
1165
+ "grad_norm": 0.44031408429145813,
1166
+ "learning_rate": 1.33134386599994e-06,
1167
+ "loss": 1.0359,
1168
+ "step": 161
1169
+ },
1170
+ {
1171
+ "epoch": 2.813852813852814,
1172
+ "grad_norm": 0.44300365447998047,
1173
+ "learning_rate": 1.1194961006082972e-06,
1174
+ "loss": 0.9898,
1175
+ "step": 162
1176
+ },
1177
+ {
1178
+ "epoch": 2.8311688311688314,
1179
+ "grad_norm": 0.5027110576629639,
1180
+ "learning_rate": 9.258054469825972e-07,
1181
+ "loss": 1.0841,
1182
+ "step": 163
1183
+ },
1184
+ {
1185
+ "epoch": 2.8484848484848486,
1186
+ "grad_norm": 0.5065575838088989,
1187
+ "learning_rate": 7.503438532937168e-07,
1188
+ "loss": 0.9727,
1189
+ "step": 164
1190
+ },
1191
+ {
1192
+ "epoch": 2.865800865800866,
1193
+ "grad_norm": 0.5497288107872009,
1194
+ "learning_rate": 5.931764963608866e-07,
1195
+ "loss": 1.0719,
1196
+ "step": 165
1197
+ },
1198
+ {
1199
+ "epoch": 2.883116883116883,
1200
+ "grad_norm": 0.6146700978279114,
1201
+ "learning_rate": 4.543617574412184e-07,
1202
+ "loss": 1.0167,
1203
+ "step": 166
1204
+ },
1205
+ {
1206
+ "epoch": 2.9004329004329006,
1207
+ "grad_norm": 0.7063661813735962,
1208
+ "learning_rate": 3.339512005434309e-07,
1209
+ "loss": 1.1252,
1210
+ "step": 167
1211
+ },
1212
+ {
1213
+ "epoch": 2.9177489177489178,
1214
+ "grad_norm": 0.7030811905860901,
1215
+ "learning_rate": 2.319895532739369e-07,
1216
+ "loss": 0.9099,
1217
+ "step": 168
1218
+ },
1219
+ {
1220
+ "epoch": 2.935064935064935,
1221
+ "grad_norm": 0.7505781650543213,
1222
+ "learning_rate": 1.4851469022234e-07,
1223
+ "loss": 0.8802,
1224
+ "step": 169
1225
+ },
1226
+ {
1227
+ "epoch": 2.9523809523809526,
1228
+ "grad_norm": 0.8609737157821655,
1229
+ "learning_rate": 8.355761889260461e-08,
1230
+ "loss": 0.7878,
1231
+ "step": 170
1232
+ },
1233
+ {
1234
+ "epoch": 2.9696969696969697,
1235
+ "grad_norm": 1.2666159868240356,
1236
+ "learning_rate": 3.7142468185014104e-08,
1237
+ "loss": 0.6123,
1238
+ "step": 171
1239
+ },
1240
+ {
1241
+ "epoch": 2.987012987012987,
1242
+ "grad_norm": 0.41616591811180115,
1243
+ "learning_rate": 9.286479433257e-09,
1244
+ "loss": 0.9539,
1245
+ "step": 172
1246
+ },
1247
+ {
1248
+ "epoch": 3.0086580086580086,
1249
+ "grad_norm": 1.1707029342651367,
1250
+ "learning_rate": 0.0,
1251
+ "loss": 1.3226,
1252
+ "step": 173
1253
  }
1254
  ],
1255
  "logging_steps": 1,
 
1273
  "should_evaluate": false,
1274
  "should_log": false,
1275
  "should_save": true,
1276
+ "should_training_stop": true
1277
  },
1278
  "attributes": {}
1279
  }
1280
  },
1281
+ "total_flos": 1.0262239721501491e+17,
1282
  "train_batch_size": 8,
1283
  "trial_name": null,
1284
  "trial_params": null