update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,23 +1,18 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
-
|
| 4 |
-
-
|
| 5 |
-
|
| 6 |
-
-
|
| 7 |
-
|
| 8 |
-
- accuracy
|
| 9 |
-
library_name: transformers
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
-
#
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [EleutherAI/pythia-1b-deduped](https://huggingface.co/EleutherAI/pythia-1b-deduped) on
|
| 18 |
-
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 2.8991
|
| 20 |
-
- Accuracy: 0.4548
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -38,31 +33,21 @@ More information needed
|
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
- learning_rate: 0.0001
|
| 40 |
- train_batch_size: 1
|
| 41 |
-
- eval_batch_size:
|
| 42 |
- seed: 42
|
| 43 |
-
- distributed_type: multi-GPU
|
| 44 |
-
- num_devices: 8
|
| 45 |
- gradient_accumulation_steps: 8
|
| 46 |
-
- total_train_batch_size:
|
| 47 |
-
- total_eval_batch_size: 8
|
| 48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
- lr_scheduler_type: linear
|
| 50 |
- training_steps: 1000
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
| 54 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 55 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 56 |
-
| 2.6694 | 0.14 | 200 | 2.9416 | 0.4486 |
|
| 57 |
-
| 2.6174 | 0.29 | 400 | 2.9312 | 0.4502 |
|
| 58 |
-
| 2.611 | 0.43 | 600 | 2.9167 | 0.4519 |
|
| 59 |
-
| 2.576 | 0.57 | 800 | 2.9057 | 0.4537 |
|
| 60 |
-
| 2.5796 | 0.72 | 1000 | 2.8991 | 0.4548 |
|
| 61 |
|
| 62 |
|
| 63 |
### Framework versions
|
| 64 |
|
| 65 |
- Transformers 4.28.1
|
| 66 |
-
- Pytorch 2.0.
|
| 67 |
- Datasets 2.11.0
|
| 68 |
-
- Tokenizers 0.13.3
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: expert-philpapers
|
| 7 |
+
results: []
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
|
| 13 |
+
# expert-philpapers
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [EleutherAI/pythia-1b-deduped](https://huggingface.co/EleutherAI/pythia-1b-deduped) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
|
|
| 33 |
The following hyperparameters were used during training:
|
| 34 |
- learning_rate: 0.0001
|
| 35 |
- train_batch_size: 1
|
| 36 |
+
- eval_batch_size: 8
|
| 37 |
- seed: 42
|
|
|
|
|
|
|
| 38 |
- gradient_accumulation_steps: 8
|
| 39 |
+
- total_train_batch_size: 8
|
|
|
|
| 40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
- lr_scheduler_type: linear
|
| 42 |
- training_steps: 1000
|
| 43 |
|
| 44 |
### Training results
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
|
| 48 |
### Framework versions
|
| 49 |
|
| 50 |
- Transformers 4.28.1
|
| 51 |
+
- Pytorch 2.0.1+cu117
|
| 52 |
- Datasets 2.11.0
|
| 53 |
+
- Tokenizers 0.13.3
|