Commit
·
3ae8ed6
1
Parent(s):
bb2ad36
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama2
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- AshtonIsNotHere/nlp_pp_code_dataset
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: codellama_CodeLlama-7b-hf_08_27_23_15_32_28
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Causal Language Modeling
|
| 14 |
+
type: text-generation
|
| 15 |
+
dataset:
|
| 16 |
+
name: AshtonIsNotHere/nlp_pp_code_dataset
|
| 17 |
+
type: AshtonIsNotHere/nlp_pp_code_dataset
|
| 18 |
+
split: test
|
| 19 |
+
metrics:
|
| 20 |
+
- name: Accuracy
|
| 21 |
+
type: accuracy
|
| 22 |
+
value: 0.8968056729128353
|
| 23 |
+
---
|
| 24 |
+
|
| 25 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 26 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 27 |
+
|
| 28 |
+
# codellama_CodeLlama-7b-hf_08_27_23_15_32_28
|
| 29 |
+
|
| 30 |
+
This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on the AshtonIsNotHere/nlp_pp_code_dataset dataset.
|
| 31 |
+
It achieves the following results on the evaluation set:
|
| 32 |
+
- Loss: 0.4129
|
| 33 |
+
- Accuracy: 0.8968
|
| 34 |
+
|
| 35 |
+
## Model description
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Intended uses & limitations
|
| 40 |
+
|
| 41 |
+
More information needed
|
| 42 |
+
|
| 43 |
+
## Training and evaluation data
|
| 44 |
+
|
| 45 |
+
More information needed
|
| 46 |
+
|
| 47 |
+
## Training procedure
|
| 48 |
+
|
| 49 |
+
### Training hyperparameters
|
| 50 |
+
|
| 51 |
+
The following hyperparameters were used during training:
|
| 52 |
+
- learning_rate: 0.00012
|
| 53 |
+
- train_batch_size: 1
|
| 54 |
+
- eval_batch_size: 1
|
| 55 |
+
- seed: 42
|
| 56 |
+
- distributed_type: multi-GPU
|
| 57 |
+
- num_devices: 4
|
| 58 |
+
- gradient_accumulation_steps: 4
|
| 59 |
+
- total_train_batch_size: 16
|
| 60 |
+
- total_eval_batch_size: 4
|
| 61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 62 |
+
- lr_scheduler_type: linear
|
| 63 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 64 |
+
- num_epochs: 7.0
|
| 65 |
+
|
| 66 |
+
### Training results
|
| 67 |
+
|
| 68 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 69 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 70 |
+
| No log | 1.0 | 61 | 0.5100 | 0.8726 |
|
| 71 |
+
| No log | 1.99 | 122 | 0.4129 | 0.8968 |
|
| 72 |
+
| No log | 2.99 | 183 | 0.4166 | 0.9072 |
|
| 73 |
+
| No log | 4.0 | 245 | 0.4595 | 0.9090 |
|
| 74 |
+
| No log | 5.0 | 306 | 0.5181 | 0.9093 |
|
| 75 |
+
| No log | 5.99 | 367 | 0.5553 | 0.9090 |
|
| 76 |
+
| No log | 6.97 | 427 | 0.5603 | 0.9089 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
### Framework versions
|
| 80 |
+
|
| 81 |
+
- Transformers 4.30.2
|
| 82 |
+
- Pytorch 2.0.1+cu117
|
| 83 |
+
- Datasets 2.13.0
|
| 84 |
+
- Tokenizers 0.13.3
|