Training in progress, step 15469

README.md

@@ -15,14 +15,14 @@ This student model is distilled from the teacher model [roneneldan/TinyStories-3
 The [Distily](https://github.com/lapp0/distily) library was used for this distillation.
 
 It achieves the following results on the evaluation set:
-- eval_enwikippl: 22177.1309
-- eval_frwikippl: 73852.3203
-- eval_zhwikippl: 62537.2148
-- eval_tinystoriesppl: 11654.0615
-- eval_loss: 6.9194
-- eval_runtime: 32.7141
-- eval_samples_per_second: 76.42
-- eval_steps_per_second: 9.568
+- eval_enwikippl: 12623.7412
+- eval_frwikippl: 52327.9961
+- eval_zhwikippl: 96451.4609
+- eval_tinystoriesppl: 6281.7222
+- eval_loss: 18.2212
+- eval_runtime: 32.9567
+- eval_samples_per_second: 75.857
+- eval_steps_per_second: 9.497
 
 <!-- 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.
@@ -45,9 +45,9 @@ More information needed
 ### 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=10.0, loss_fn=mse, layer_mapper=None, projector=None), attn_loss_component=LossComponent(label=attn, weight=10.0, loss_fn=raw_mse, layer_mapper=None, projector=None))
+- 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=10.0, loss_fn=raw_mse, layer_mapper=None, projector=None), attn_loss_component=LossComponent(label=attn, weight=10.0, loss_fn=raw_mse, layer_mapper=None, projector=None))
 - train_embeddings: True
-- learning_rate: 4e-05
+- learning_rate: 4e-06
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
@@ -56,24 +56,24 @@ The following hyperparameters were used during training:
 - num_epochs: 1.0
 
 ### Resource Usage
-Peak GPU Memory: 16.2515 GB
+Peak GPU Memory: 16.2498 GB
 
 ### Eval-Phase Metrics
 | step | epoch | enwikippl | frwikippl | loss | runtime | samples_per_second | steps_per_second | tinystoriesppl | zhwikippl |
 | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
 | **teacher eval** |  | 169.9865 | 47377.9414 |  |  |  |  | 3.9789 | 4998.1294 |
-| 0 | 0 | 27548.9473 | 81896.5703 | 7.1177 | 32.6791 | 76.501 | 9.578 | 15431.1592 | 64176.7344 |
-| 2000 | 0.1293 | 22177.1309 | 73852.3203 | 6.9194 | 32.645 | 76.582 | 9.588 | 11654.0615 | 62537.2148 |
-| 4000 | 0.2586 | 22177.1309 | 73852.3203 | 6.9194 | 32.649 | 76.572 | 9.587 | 11654.0615 | 62537.2148 |
-| 6000 | 0.3879 | 22177.1309 | 73852.3203 | 6.9194 | 32.8099 | 76.196 | 9.54 | 11654.0615 | 62537.2148 |
-| 8000 | 0.5172 | 22177.1309 | 73852.3203 | 6.9194 | 32.7141 | 76.42 | 9.568 | 11654.0615 | 62537.2148 |
-| 10000 | 0.6465 | 22177.1309 | 73852.3203 | 6.9194 | 32.6497 | 76.57 | 9.587 | 11654.0615 | 62537.2148 |
-| 12000 | 0.7757 | 22177.1309 | 73852.3203 | 6.9194 | 32.6408 | 76.591 | 9.589 | 11654.0615 | 62537.2148 |
-| 14000 | 0.9050 | 22177.1309 | 73852.3203 | 6.9194 | 32.6631 | 76.539 | 9.583 | 11654.0615 | 62537.2148 |
-| 15469 | 1.0 | 22177.1309 | 73852.3203 | 6.9194 | 32.6508 | 76.568 | 9.586 | 11654.0615 | 62537.2148 |
+| 0 | 0 | 12930.5508 | 52883.7109 | 18.2508 | 32.8136 | 76.188 | 9.539 | 6471.4722 | 96760.75 |
+| 2000 | 0.1293 | 12623.7412 | 52327.9961 | 18.2212 | 32.8936 | 76.003 | 9.516 | 6281.7222 | 96451.4609 |
+| 4000 | 0.2586 | 12623.7412 | 52327.9961 | 18.2212 | 32.8034 | 76.212 | 9.542 | 6281.7222 | 96451.4609 |
+| 6000 | 0.3879 | 12623.7412 | 52327.9961 | 18.2212 | 32.8868 | 76.018 | 9.517 | 6281.7222 | 96451.4609 |
+| 8000 | 0.5172 | 12623.7412 | 52327.9961 | 18.2212 | 32.9567 | 75.857 | 9.497 | 6281.7222 | 96451.4609 |
+| 10000 | 0.6465 | 12623.7412 | 52327.9961 | 18.2212 | 32.9256 | 75.929 | 9.506 | 6281.7222 | 96451.4609 |
+| 12000 | 0.7757 | 12623.7412 | 52327.9961 | 18.2212 | 32.9173 | 75.948 | 9.509 | 6281.7222 | 96451.4609 |
+| 14000 | 0.9050 | 12623.7412 | 52327.9961 | 18.2212 | 33.1691 | 75.371 | 9.437 | 6281.7222 | 96451.4609 |
+| 15469 | 1.0 | 12623.7412 | 52327.9961 | 18.2212 | 33.0829 | 75.568 | 9.461 | 6281.7222 | 96451.4609 |
 
 ### Framework versions
 - Distily 0.2.0
 - Transformers 4.44.0
 - Pytorch 2.3.0
-- Datasets 2.21.0
+- Datasets 2.20.0

logs/attn_loss_fn=raw_mse, attn_weight=10.0, hs_loss_fn=mse, hs_weight=10.0, learning_rate=4e-06/events.out.tfevents.1723762067.93d6cbb3ad53

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739b505f81064ed17b5128d7a8068336140b2bfc1eb9c0211a56b86d0e865cbf
+size 4177661

logs/attn_loss_fn=raw_mse, attn_weight=10.0, hs_loss_fn=raw_mse, hs_weight=10.0, learning_rate=4e-06/events.out.tfevents.1723761898.93d6cbb3ad53

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e29c5c31674ab017aaa74d55b1626f675e08ae2fb3ba79dedcefb5c425a6e77
-size 307
+oid sha256:75b17038955765902bca320b4d0e45edd0aafc493d10dfb0dba1568e5b5955c4
+size 578

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1125217d2452d904fbd104af46d9627774afea5c136b005dd0161d93f483f873
+oid sha256:e2f3aa452fa56b42240ee51b50d8be7acdbed06dd7363b534af5d456d9810f25
 size 137033984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26739a6af4d1470c81c2e0dd856c5102272ec50187efe372e6dcf911c045c095
+oid sha256:f55d3533da93ae93135f2e1e4741afe9f327280493c21e3a1afb6cebed627fce
 size 1017948104