Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: EleutherAI/pythia-410m
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: oop_and_text_pythia_410m
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
[<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/zhenwu/code-text-pretraining/runs/5ksxkt02)
|
| 17 |
+
# oop_and_text_pythia_410m
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [EleutherAI/pythia-410m](https://huggingface.co/EleutherAI/pythia-410m) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.6227
|
| 22 |
+
- Accuracy: 0.2170
|
| 23 |
+
- Num Input Tokens Seen: 5734400
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 2e-05
|
| 43 |
+
- train_batch_size: 4
|
| 44 |
+
- eval_batch_size: 4
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 2
|
| 48 |
+
- total_train_batch_size: 8
|
| 49 |
+
- total_eval_batch_size: 8
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: cosine
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.03
|
| 53 |
+
- num_epochs: 3.0
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Input Tokens Seen |
|
| 58 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|:-----------------:|
|
| 59 |
+
| No log | 0 | 0 | 3.0231 | 0.2075 | 0 |
|
| 60 |
+
| 1.8656 | 0.2092 | 50 | 2.0404 | 0.2358 | 409600 |
|
| 61 |
+
| 1.8788 | 0.4184 | 100 | 1.8193 | 0.2170 | 819200 |
|
| 62 |
+
| 1.7635 | 0.6276 | 150 | 1.6325 | 0.1887 | 1228800 |
|
| 63 |
+
| 1.6773 | 0.8368 | 200 | 1.6925 | 0.1887 | 1638400 |
|
| 64 |
+
| 1.6309 | 1.0460 | 250 | 1.6849 | 0.1934 | 2048000 |
|
| 65 |
+
| 1.5824 | 1.2552 | 300 | 1.8487 | 0.1840 | 2457600 |
|
| 66 |
+
| 1.8204 | 1.4644 | 350 | 1.6930 | 0.1887 | 2867200 |
|
| 67 |
+
| 1.6639 | 1.6736 | 400 | 1.6967 | 0.2123 | 3276800 |
|
| 68 |
+
| 1.5446 | 1.8828 | 450 | 1.6562 | 0.2217 | 3686400 |
|
| 69 |
+
| 1.569 | 2.0921 | 500 | 1.6151 | 0.2123 | 4096000 |
|
| 70 |
+
| 1.5797 | 2.3013 | 550 | 1.6244 | 0.2311 | 4505600 |
|
| 71 |
+
| 1.5543 | 2.5105 | 600 | 1.6461 | 0.2028 | 4915200 |
|
| 72 |
+
| 1.5691 | 2.7197 | 650 | 1.6240 | 0.2075 | 5324800 |
|
| 73 |
+
| 1.5852 | 2.9289 | 700 | 1.6227 | 0.2170 | 5734400 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- Transformers 4.43.2
|
| 79 |
+
- Pytorch 2.4.0
|
| 80 |
+
- Datasets 2.20.0
|
| 81 |
+
- Tokenizers 0.19.1
|