TopperThijs
commited on
Commit
•
1c6a3f3
1
Parent(s):
313c4f7
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: tiiuae/falcon-7b
|
9 |
+
model-index:
|
10 |
+
- name: Falcon-Complete-8-15
|
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-Complete-8-15
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [tiiuae/falcon-7b](https://huggingface.co/tiiuae/falcon-7b) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 2.6751
|
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 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: constant
|
46 |
+
- lr_scheduler_warmup_ratio: 0.03
|
47 |
+
- num_epochs: 8
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
|
52 |
+
|
53 |
+
### Framework versions
|
54 |
+
|
55 |
+
- PEFT 0.12.0
|
56 |
+
- Transformers 4.39.3
|
57 |
+
- Pytorch 2.1.2
|
58 |
+
- Datasets 2.18.0
|
59 |
+
- Tokenizers 0.15.2
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2439332736
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c316219ea85fba0e542c52ca39d27f10ddd1ea4d9db2333d039cd563a2aa4fe
|
3 |
size 2439332736
|
runs/Aug04_13-27-34_77fa68f1731e/events.out.tfevents.1722778241.77fa68f1731e.25.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:437a89880c0b5518a16f95ca6a55d64027393772a188477760c65bd41a12384c
|
3 |
+
size 57798
|
runs/Aug04_13-27-34_77fa68f1731e/events.out.tfevents.1722814011.77fa68f1731e.25.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f788f1842720925a34c4f3e7414f6add74d45a15725fda0ed597bab1beb13bc
|
3 |
+
size 364
|
tokenizer.json
CHANGED
@@ -173,7 +173,6 @@
|
|
173 |
"end_of_word_suffix": null,
|
174 |
"fuse_unk": false,
|
175 |
"byte_fallback": false,
|
176 |
-
"ignore_merges": false,
|
177 |
"vocab": {
|
178 |
">>TITLE<<": 0,
|
179 |
">>ABSTRACT<<": 1,
|
|
|
173 |
"end_of_word_suffix": null,
|
174 |
"fuse_unk": false,
|
175 |
"byte_fallback": false,
|
|
|
176 |
"vocab": {
|
177 |
">>TITLE<<": 0,
|
178 |
">>ABSTRACT<<": 1,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:319388fd69780bbc4c99ab327b8f1d2706728a955e3cc2e6c1fc1f2fb2c54b0c
|
3 |
+
size 5176
|