End of training
Browse files
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: petals-team/falcon-rw-1b
|
9 |
+
model-index:
|
10 |
+
- name: falcon-code-generation-llm
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# falcon-code-generation-llm
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [petals-team/falcon-rw-1b](https://huggingface.co/petals-team/falcon-rw-1b) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.8328
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0002
|
41 |
+
- train_batch_size: 2
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 2
|
45 |
+
- total_train_batch_size: 4
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: cosine
|
48 |
+
- lr_scheduler_warmup_ratio: 0.03
|
49 |
+
- training_steps: 320
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
+
| 2.1898 | 0.1 | 20 | 1.9930 |
|
56 |
+
| 2.0474 | 0.2 | 40 | 1.9372 |
|
57 |
+
| 1.8768 | 0.3 | 60 | 1.9180 |
|
58 |
+
| 2.0356 | 0.4 | 80 | 1.8915 |
|
59 |
+
| 1.946 | 0.5 | 100 | 1.9185 |
|
60 |
+
| 1.9219 | 0.6 | 120 | 1.8740 |
|
61 |
+
| 1.973 | 0.7 | 140 | 1.8762 |
|
62 |
+
| 1.8046 | 0.8 | 160 | 1.8549 |
|
63 |
+
| 1.8934 | 0.9 | 180 | 1.8451 |
|
64 |
+
| 1.8365 | 1.0 | 200 | 1.8525 |
|
65 |
+
| 1.7949 | 1.1 | 220 | 1.8343 |
|
66 |
+
| 1.703 | 1.2 | 240 | 1.8443 |
|
67 |
+
| 1.6269 | 1.3 | 260 | 1.8453 |
|
68 |
+
| 1.6731 | 1.4 | 280 | 1.8330 |
|
69 |
+
| 1.6004 | 1.5 | 300 | 1.8331 |
|
70 |
+
| 1.7031 | 1.6 | 320 | 1.8328 |
|
71 |
+
|
72 |
+
|
73 |
+
### Framework versions
|
74 |
+
|
75 |
+
- PEFT 0.10.0
|
76 |
+
- Transformers 4.40.0
|
77 |
+
- Pytorch 2.2.1+cu121
|
78 |
+
- Datasets 2.19.0
|
79 |
+
- Tokenizers 0.19.1
|