Hugging Face's logo

lapp0
/
distily_bench_gpt2_simple_objectives2

TensorBoard
Safetensors
Distily
gpt2
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Metrics Community
lapp0 commited on
Commit
6a3eb73
·
verified ·
1 Parent(s): 98a6ed3

Training in progress, step 24750

Browse files
Files changed (6) hide show
  1. logs/distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_cakld_loss())__activations_weight_0.2__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentions_loss_fn_(fn_s/events.out.tfevents.1723528003.93d6cbb3ad53 +2 -2
  2. logs/distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_jsd_loss())__activations_weight_0.2__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentions_loss_fn_(fn_sof/events.out.tfevents.1723528176.93d6cbb3ad53 +3 -0
  3. logs/distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_jsd_loss())__activations_weight_0.2__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentions_loss_fn_(fn_sof/events.out.tfevents.1723530188.93d6cbb3ad53 +3 -0
  4. logs/distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_jsd_loss())__activations_weight_0.2__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentions_loss_fn_(fn_sof/events.out.tfevents.1723530420.93d6cbb3ad53 +3 -0
  5. model.safetensors +1 -1
  6. training_args.bin +1 -1
logs/distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_cakld_loss())__activations_weight_0.2__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentions_loss_fn_(fn_s/events.out.tfevents.1723528003.93d6cbb3ad53 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5464dff160ade15d2520075da40a1ea6d40dbcc6617635026708f5e390e50abc
3
- size 253
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5eb2a759c746b71295e83ed1243e8530e1f650add1b08ade7bb1066f1ee6dae1
3
+ size 529
logs/distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_jsd_loss())__activations_weight_0.2__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentions_loss_fn_(fn_sof/events.out.tfevents.1723528176.93d6cbb3ad53 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e18f6c123c7c574d8e4d1fa45136a531390614a62a9441a1e8d2f8378150cca3
3
+ size 996197
logs/distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_jsd_loss())__activations_weight_0.2__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentions_loss_fn_(fn_sof/events.out.tfevents.1723530188.93d6cbb3ad53 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:392e1101c04889219b4b01ac21f8c4201d85f1aaec0373c985c98af212b95f7c
3
+ size 6161
logs/distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_jsd_loss())__activations_weight_0.2__activations_loss_fn_(fn_soft_mse_loss())__attentions_weight_0__attentions_loss_fn_(fn_sof/events.out.tfevents.1723530420.93d6cbb3ad53 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da211d035e3bf134831edb807ec962d309c503b6282879d25bc22efacc205b2e
3
+ size 7100759
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac36b967761a46a4f37250f26ecf19b6f549853a3edee5398faa95f95214c780
3
  size 248894656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b96b24d00accd3d6ba5c0c2c837421d7c2e86a66deab209567021a937714b59
3
  size 248894656
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1fcdd655df474200be0960829bf7a85acc9142e563137cef69fd45945303a41
3
  size 907106756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bf8f903a775989c53650cf879fc7fbbe658c33574561aef384abbb2f6fae2a7
3
  size 907106756