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
1a31f67
·
verified ·
1 Parent(s): 5220307

Training in progress, step 24750

Browse files
Files changed (4) 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_mse_loss())__attn_weight_0__attn_loss_fn_(fn_soft_mse_loss()))/events.out.tfevents.1723607471.93d6cbb3ad53 +2 -2
  2. 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.1723607641.93d6cbb3ad53 +3 -0
  3. model.safetensors +1 -1
  4. 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_mse_loss())__attn_weight_0__attn_loss_fn_(fn_soft_mse_loss()))/events.out.tfevents.1723607471.93d6cbb3ad53 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:843ded0a5b8d59143aa666337283b611acc3158c366f3e9bcf46aed907ee6a8b
3
- size 253
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcb0e79f514e643e9f535e1a60b266720fc2e1a3414f176f9c387a171d547d86
3
+ size 529
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.1723607641.93d6cbb3ad53 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bed13105dd9d05cee431a85abdeb1fe509745c1b3aae0d72d26a9583787d041
3
+ size 6729497
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5bbd08c3dcb50ec1344b3913c2239ceaded499254761b3fa26a05a9d300a7f9
3
  size 248894656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a721ddd800c6ce8e586780a8d63398040a0715159297d65a56b886763e98bfa3
3
  size 248894656
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:983e44c17957d4070aa06a302831b03d36ff9d67798a975468fc6de12346aaa9
3
  size 907106756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daae1fdcae3bd3509c03ebb89d69d60b4ba04e14b7da35c65ac5497c7a11289d
3
  size 907106756