Hugging Face's logo

HealthTeam
/
mt5-small-finetuned-MultiHead-230207-finetuned-MultiHead-230210-finetuned-MultiHead-230214

Text2Text Generation
Transformers
PyTorch
TensorBoard
mt5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
HealthTeam commited on
Commit
ea0d69b
•
1 Parent(s): c42e4ed

Training in progress, step 99432

Browse files
Files changed (7) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +135 -3
  6. pytorch_model.bin +1 -1
  7. runs/Feb14_18-29-07_39730b194efc/events.out.tfevents.1676399391.39730b194efc.3664.0 +2 -2
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3167961b3eb97426f7187fd3899c213ef8e1929e8cfc18d3507c4b0dda5efcfd
3
  size 2401461637
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e99160596deaf1a941f401564fa9f387da61ce4fcbd3c8be41a5796b4d9c8fcb
3
  size 2401461637
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41ea2dbc0e7a213968965fd9cad858083c988e3c6021026300ebbce433d9cb8e
3
  size 1200739717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95a868f38e06c1d0679daaf4d5510e7ff02a3e67b90ee3a4b468a09643d77131
3
  size 1200739717
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:744e00579a1b935cd582e5adfe8d2dc8f6f8923224f5a97f68c8eaac321cce8d
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:049a8b27323a9ab88596ec47eb567e57317d171edf3ddee0d967d13cf176058a
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30aab5f6e1de88caa8ca66b22088d8788034d605b12a0733b6608052eb1f2bb8
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f57334800401c750c6751652d2fefd75968842550a273b6662abb88233eab71
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.629615304513403,
5
- "global_step": 88384,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -1080,11 +1080,143 @@
1080
  "learning_rate": 2.5453968442870885e-06,
1081
  "loss": 2.3949,
1082
  "step": 88000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1083
  }
1084
  ],
1085
  "max_steps": 100833,
1086
  "num_train_epochs": 3,
1087
- "total_flos": 2.3795073312148685e+17,
1088
  "trial_name": null,
1089
  "trial_params": null
1090
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.9583172175775787,
5
+ "global_step": 99432,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
1080
  "learning_rate": 2.5453968442870885e-06,
1081
  "loss": 2.3949,
1082
  "step": 88000
1083
+ },
1084
+ {
1085
+ "epoch": 2.63,
1086
+ "learning_rate": 2.446222962720538e-06,
1087
+ "loss": 2.3923,
1088
+ "step": 88500
1089
+ },
1090
+ {
1091
+ "epoch": 2.65,
1092
+ "learning_rate": 2.3470490811539874e-06,
1093
+ "loss": 2.3844,
1094
+ "step": 89000
1095
+ },
1096
+ {
1097
+ "epoch": 2.66,
1098
+ "learning_rate": 2.247875199587437e-06,
1099
+ "loss": 2.3928,
1100
+ "step": 89500
1101
+ },
1102
+ {
1103
+ "epoch": 2.68,
1104
+ "learning_rate": 2.1487013180208863e-06,
1105
+ "loss": 2.3907,
1106
+ "step": 90000
1107
+ },
1108
+ {
1109
+ "epoch": 2.69,
1110
+ "learning_rate": 2.0495274364543354e-06,
1111
+ "loss": 2.3999,
1112
+ "step": 90500
1113
+ },
1114
+ {
1115
+ "epoch": 2.71,
1116
+ "learning_rate": 1.950353554887785e-06,
1117
+ "loss": 2.4117,
1118
+ "step": 91000
1119
+ },
1120
+ {
1121
+ "epoch": 2.72,
1122
+ "learning_rate": 1.8511796733212343e-06,
1123
+ "loss": 2.4146,
1124
+ "step": 91500
1125
+ },
1126
+ {
1127
+ "epoch": 2.74,
1128
+ "learning_rate": 1.7520057917546838e-06,
1129
+ "loss": 2.3863,
1130
+ "step": 92000
1131
+ },
1132
+ {
1133
+ "epoch": 2.75,
1134
+ "learning_rate": 1.652831910188133e-06,
1135
+ "loss": 2.3857,
1136
+ "step": 92500
1137
+ },
1138
+ {
1139
+ "epoch": 2.77,
1140
+ "learning_rate": 1.5536580286215825e-06,
1141
+ "loss": 2.4035,
1142
+ "step": 93000
1143
+ },
1144
+ {
1145
+ "epoch": 2.78,
1146
+ "learning_rate": 1.4544841470550317e-06,
1147
+ "loss": 2.39,
1148
+ "step": 93500
1149
+ },
1150
+ {
1151
+ "epoch": 2.8,
1152
+ "learning_rate": 1.3553102654884812e-06,
1153
+ "loss": 2.3929,
1154
+ "step": 94000
1155
+ },
1156
+ {
1157
+ "epoch": 2.81,
1158
+ "learning_rate": 1.2561363839219304e-06,
1159
+ "loss": 2.3998,
1160
+ "step": 94500
1161
+ },
1162
+ {
1163
+ "epoch": 2.83,
1164
+ "learning_rate": 1.1569625023553797e-06,
1165
+ "loss": 2.3968,
1166
+ "step": 95000
1167
+ },
1168
+ {
1169
+ "epoch": 2.84,
1170
+ "learning_rate": 1.0577886207888292e-06,
1171
+ "loss": 2.3752,
1172
+ "step": 95500
1173
+ },
1174
+ {
1175
+ "epoch": 2.86,
1176
+ "learning_rate": 9.586147392222784e-07,
1177
+ "loss": 2.3943,
1178
+ "step": 96000
1179
+ },
1180
+ {
1181
+ "epoch": 2.87,
1182
+ "learning_rate": 8.594408576557279e-07,
1183
+ "loss": 2.3826,
1184
+ "step": 96500
1185
+ },
1186
+ {
1187
+ "epoch": 2.89,
1188
+ "learning_rate": 7.602669760891772e-07,
1189
+ "loss": 2.395,
1190
+ "step": 97000
1191
+ },
1192
+ {
1193
+ "epoch": 2.9,
1194
+ "learning_rate": 6.610930945226266e-07,
1195
+ "loss": 2.403,
1196
+ "step": 97500
1197
+ },
1198
+ {
1199
+ "epoch": 2.92,
1200
+ "learning_rate": 5.619192129560759e-07,
1201
+ "loss": 2.4108,
1202
+ "step": 98000
1203
+ },
1204
+ {
1205
+ "epoch": 2.93,
1206
+ "learning_rate": 4.6274533138952524e-07,
1207
+ "loss": 2.3714,
1208
+ "step": 98500
1209
+ },
1210
+ {
1211
+ "epoch": 2.95,
1212
+ "learning_rate": 3.6357144982297465e-07,
1213
+ "loss": 2.4135,
1214
+ "step": 99000
1215
  }
1216
  ],
1217
  "max_steps": 100833,
1218
  "num_train_epochs": 3,
1219
+ "total_flos": 2.677110317041582e+17,
1220
  "trial_name": null,
1221
  "trial_params": null
1222
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41ea2dbc0e7a213968965fd9cad858083c988e3c6021026300ebbce433d9cb8e
3
  size 1200739717
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95a868f38e06c1d0679daaf4d5510e7ff02a3e67b90ee3a4b468a09643d77131
3
  size 1200739717
runs/Feb14_18-29-07_39730b194efc/events.out.tfevents.1676399391.39730b194efc.3664.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72896d4de38208d32d9fc0cb01472292451c3e8480b2eb567f3b3a007fcf4fea
3
- size 33077
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30c1c47592e796d4ffdc458b36558eef785bbf2aa92130eff24c37516d6638f2
3
+ size 36597