Training in progress, step 20

README.md

@@ -1,7 +1,6 @@
 ---
-base_model: gpt2
-library_name: Distily
 license: mit
+base_model: gpt2
 tags:
 - generated_from_trainer
 model-index:
@@ -9,24 +8,14 @@ model-index:
   results: []
 ---
 
-# distily_modelcard_try
-
-This student model is distilled from the teacher model [gpt2](https://huggingface.co/gpt2) using the dataset (unspecified).
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
 
-The [Distily](https://github.com/lapp0/distily) library was used for this distillation.
+# distily_modelcard_try
 
+This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_enwikippl: 38656.0
-- eval_frwikippl: 218112.0
-- eval_zhwikippl: 54001664.0
-- eval_tinystoriesppl: 12160.0
-- eval_loss: 6.4375
-- eval_runtime: 0.0668
-- eval_samples_per_second: 29.948
-- eval_steps_per_second: 14.974
-
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment.
+- Loss: 8.125
 
 ## Model description
 
@@ -39,15 +28,12 @@ More information needed
 ## Training and evaluation data
 
 More information needed
--->
 
 ## Training procedure
 
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- distillation_objective: DistillationObjective(logits_loss_component=LossComponent(label=logits, weight=1, loss_fn=kl, layer_mapper=None, projector=None), hs_loss_component=LossComponent(label=hs, weight=0, loss_fn=mse, layer_mapper=last, projector=None), attn_loss_component=LossComponent(label=attn, weight=0, loss_fn=mse, layer_mapper=layer-2, projector=None))
-- train_embeddings: True
 - learning_rate: 0.0001
 - train_batch_size: 16
 - eval_batch_size: 8
@@ -57,18 +43,16 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.2
 - num_epochs: 1.0
 
-### Resource Usage
-Peak GPU Memory: 15.4263 GB
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 0     | 0    | 23.625          |
 
-### Eval-Phase Metrics
-| step | epoch | enwikippl | frwikippl | loss | runtime | samples_per_second | steps_per_second | tinystoriesppl | zhwikippl |
-| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
-| **teacher eval** |  | 43.75 | 61.75 |  |  |  |  | 11.8125 | 19.125 |
-| 0 | 0 | 738734374912.0 | 47828755808256.0 | 20.375 | 0.128 | 15.619 | 7.81 | 2617245696.0 | 12232066859008.0 |
-| 10 | 1.0 | 38656.0 | 218112.0 | 6.4375 | 0.0668 | 29.948 | 14.974 | 12160.0 | 54001664.0 |
 
 ### Framework versions
-- Distily 0.2.0
+
 - Transformers 4.44.0
 - Pytorch 2.3.0
 - Datasets 2.21.0
+- Tokenizers 0.19.1

logs/per_device_train_batch_size=16/events.out.tfevents.1724249431.f383272e719b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:866c45fdc821670bda6395617655199f9e372e784633b6b24cd6cf15c590da6a
+size 568

logs/per_device_train_batch_size=8/events.out.tfevents.1724249657.f383272e719b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a1ac30f91450dcdb0639684e28be61c0019fe4bd7e82be7d13cbbd745f7649
+size 11695

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef54b6c21f3e2969ec448c785ea838f4b6fb7363f1c544f03d08a0b7efdac051
+oid sha256:9bb9de2be01c242b09837c7f50e515fb69af4c10bb59ee0ed99fed4303e7ae7c
 size 248894656

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c81b96d2d153fea78d2ec64ea37216c382e12d6073cd6dd197061f03dd43be2e
+oid sha256:a74ed808eb463babbe034da6d49b7bce830f5a04b451ce3027a4bf3a88084dce
 size 1017899080