Commit
•
e05c2f9
1
Parent(s):
bac2f3c
End of training
Browse files- README.md +69 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: EleutherAI/pythia-14m
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
- f1
|
| 8 |
+
- precision
|
| 9 |
+
- recall
|
| 10 |
+
model-index:
|
| 11 |
+
- name: pythia-14m-imdb-sentiment-20240729_031828
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/lklab_kaist/pythia-14m-imdb-sentiment/runs/5cdsyszv)
|
| 19 |
+
# pythia-14m-imdb-sentiment-20240729_031828
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [EleutherAI/pythia-14m](https://huggingface.co/EleutherAI/pythia-14m) on an unknown dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.2606
|
| 24 |
+
- Accuracy: 0.891
|
| 25 |
+
- F1: 0.8925
|
| 26 |
+
- Precision: 0.8805
|
| 27 |
+
- Recall: 0.9048
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 5e-05
|
| 47 |
+
- train_batch_size: 32
|
| 48 |
+
- eval_batch_size: 32
|
| 49 |
+
- seed: 42
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- lr_scheduler_warmup_steps: 500
|
| 53 |
+
- num_epochs: 3
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|
| 58 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
|
| 59 |
+
| 0.3715 | 1.0 | 782 | 0.3372 | 0.8540 | 0.8638 | 0.8095 | 0.926 |
|
| 60 |
+
| 0.234 | 2.0 | 1564 | 0.2606 | 0.891 | 0.8925 | 0.8805 | 0.9048 |
|
| 61 |
+
| 0.1667 | 3.0 | 2346 | 0.2820 | 0.8955 | 0.8951 | 0.8988 | 0.8914 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.42.4
|
| 67 |
+
- Pytorch 2.3.0+cu121
|
| 68 |
+
- Datasets 2.20.0
|
| 69 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 30511400
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88ebf9de1cd4ddb4ab3ae301420791c6fa8473d70814fbf0c78e4260d22f821d
|
| 3 |
size 30511400
|