End of training

README.md

@@ -1,8 +1,9 @@
 ---
 license: apache-2.0
-base_model: EleutherAI/pythia-1.4b-v0
+library_name: peft
 tags:
 - generated_from_trainer
+base_model: EleutherAI/pythia-1.4b-v0
 model-index:
 - name: pythia-1.4b-v0-finetuned-squad
   results: []
@@ -14,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # pythia-1.4b-v0-finetuned-squad
 
 This model is a fine-tuned version of [EleutherAI/pythia-1.4b-v0](https://huggingface.co/EleutherAI/pythia-1.4b-v0) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0972
 
 ## Model description
 
@@ -32,17 +35,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 0.0002
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.3333        | 1.0   | 5539 | 1.0972          |
+
 
 ### Framework versions
 
-- Transformers 4.38.2
+- PEFT 0.7.2.dev0
+- Transformers 4.36.2
 - Pytorch 2.2.1+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- Datasets 2.16.1
+- Tokenizers 0.15.2

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:670f1762965a363671c5346ce1a13709871e727ab5a9e7b499b44a710468f88f
+oid sha256:e8e6f48ee10879658c75324b94a828c209ff1376aef6b251ae4120ad8960ea8e
 size 418200864

runs/Mar29_01-14-35_5657bb8a5aae/events.out.tfevents.1711675051.5657bb8a5aae.27906.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e0df7c48ae70eb0571af3483d7439516b8dc116cf8449afda23061653317aac
-size 91175
+oid sha256:306a77371e6e6a921a292bad442441a9cd36b981f8371f99432ba259b6a963c3
+size 92271