Hugging Face's logo

lapp0
/
distily_bench_gpt2_activation_loss

TensorBoard
Safetensors
Distily
gpt2
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Metrics Community
lapp0 commited on
Commit
ee68f6f
•
1 Parent(s): 8757f45

Training in progress, step 24750

Browse files
Files changed (5) hide show
  1. logs/distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_kl_divergence_loss())__hs_weight_0.2__hs_loss_fn_(fn_cosine_distance_loss())__attn_weight_0__attn_loss_fn_(fn_soft_mse_loss())/events.out.tfevents.1723616077.93d6cbb3ad53 +3 -0
  2. logs/distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_kl_divergence_loss())__hs_weight_0.2__hs_loss_fn_(fn_mutual_information_loss())__attn_weight_0__attn_loss_fn_(fn_soft_mse_loss/events.out.tfevents.1723615971.93d6cbb3ad53 +3 -0
  3. logs/distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_kl_divergence_loss())__hs_weight_0.2__hs_loss_fn_(fn_reverse_kl_divergence_loss())__attn_weight_0__attn_loss_fn_(fn_soft_mse_l/events.out.tfevents.1723615796.93d6cbb3ad53 +2 -2
  4. model.safetensors +1 -1
  5. training_args.bin +1 -1
logs/distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_kl_divergence_loss())__hs_weight_0.2__hs_loss_fn_(fn_cosine_distance_loss())__attn_weight_0__attn_loss_fn_(fn_soft_mse_loss())/events.out.tfevents.1723616077.93d6cbb3ad53 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a010e22efb1b3ca34f07a2579ea623fa451393283104631a2da0182dd9e56b42
3
+ size 6729497
logs/distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_kl_divergence_loss())__hs_weight_0.2__hs_loss_fn_(fn_mutual_information_loss())__attn_weight_0__attn_loss_fn_(fn_soft_mse_loss/events.out.tfevents.1723615971.93d6cbb3ad53 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bed64cbc1a7e698eb577e680b443e56dd2138bca80871b330cd2966af7a138d7
3
+ size 6149
logs/distillation_objective=MultiObjective(logits_weight_1__logits_loss_fn_(fn_kl_divergence_loss())__hs_weight_0.2__hs_loss_fn_(fn_reverse_kl_divergence_loss())__attn_weight_0__attn_loss_fn_(fn_soft_mse_l/events.out.tfevents.1723615796.93d6cbb3ad53 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b59ef5a926b07f4be617e0d91374d9bce1391f95a64e6dff5eb1fbf5a6c67c3
3
- size 253
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f199fb620679e9758aaec40831be16014bcf85064e785003a68cf45a46f9387
3
+ size 529
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a721ddd800c6ce8e586780a8d63398040a0715159297d65a56b886763e98bfa3
3
  size 248894656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0b0e8b780774b77126560ee93d90c6756c36c085e52f55c47a4755704d2d50
3
  size 248894656
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:daae1fdcae3bd3509c03ebb89d69d60b4ba04e14b7da35c65ac5497c7a11289d
3
  size 907106756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75f2fc1365ecfa56fcff8f5f9cfb87cc90efd424689a7b7bfc87e7965be55020
3
  size 907106756