End of training
Browse files- README.md +69 -0
- adapter_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: bigscience-bloom-rail-1.0
|
| 3 |
+
base_model: bigscience/bloom-3b
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- squad
|
| 8 |
+
model-index:
|
| 9 |
+
- name: Bloom_3b_squad
|
| 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 |
+
# Bloom_3b_squad
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [bigscience/bloom-3b](https://huggingface.co/bigscience/bloom-3b) on the squad dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 2.8279
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 2e-05
|
| 40 |
+
- train_batch_size: 48
|
| 41 |
+
- eval_batch_size: 48
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 50
|
| 46 |
+
- num_epochs: 10
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
+
| No log | 1.0 | 313 | 2.7425 |
|
| 53 |
+
| 2.7964 | 2.0 | 626 | 2.7329 |
|
| 54 |
+
| 2.7964 | 3.0 | 939 | 2.7427 |
|
| 55 |
+
| 2.6722 | 4.0 | 1252 | 2.7565 |
|
| 56 |
+
| 2.6103 | 5.0 | 1565 | 2.7763 |
|
| 57 |
+
| 2.6103 | 6.0 | 1878 | 2.7917 |
|
| 58 |
+
| 2.5551 | 7.0 | 2191 | 2.8087 |
|
| 59 |
+
| 2.5208 | 8.0 | 2504 | 2.8161 |
|
| 60 |
+
| 2.5208 | 9.0 | 2817 | 2.8245 |
|
| 61 |
+
| 2.4993 | 10.0 | 3130 | 2.8279 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.34.0.dev0
|
| 67 |
+
- Pytorch 2.0.1+cu118
|
| 68 |
+
- Datasets 2.14.5
|
| 69 |
+
- Tokenizers 0.13.3
|
adapter_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 19683045
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:424f91a2728d933780993462f9ff6feeb5422009bfdddf4162edc1aec92e6bc1
|
| 3 |
size 19683045
|