lvcalucioli
commited on
Commit
•
94a97ef
1
Parent(s):
6468723
llamantino7b_question_answering_finetuining
Browse files- README.md +12 -5
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- tokenizer.json +6 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [swap-uniba/LLaMAntino-2-7b-hf-ITA](https://huggingface.co/swap-uniba/LLaMAntino-2-7b-hf-ITA) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 1.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -44,15 +44,22 @@ The following hyperparameters were used during training:
|
|
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:
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
-
| 1.
|
54 |
-
| 1.
|
55 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
|
57 |
|
58 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [swap-uniba/LLaMAntino-2-7b-hf-ITA](https://huggingface.co/swap-uniba/LLaMAntino-2-7b-hf-ITA) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.9046
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
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: 10
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
+
| 1.6731 | 1.0 | 90 | 1.5039 |
|
54 |
+
| 1.2298 | 2.0 | 180 | 1.4252 |
|
55 |
+
| 0.8714 | 3.0 | 270 | 1.4593 |
|
56 |
+
| 0.5776 | 4.0 | 360 | 1.4850 |
|
57 |
+
| 0.3747 | 5.0 | 450 | 1.5199 |
|
58 |
+
| 0.2584 | 6.0 | 540 | 1.6924 |
|
59 |
+
| 0.1781 | 7.0 | 630 | 1.8130 |
|
60 |
+
| 0.1373 | 8.0 | 720 | 1.6641 |
|
61 |
+
| 0.0993 | 9.0 | 810 | 1.7835 |
|
62 |
+
| 0.0728 | 10.0 | 900 | 1.9046 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -19,8 +19,8 @@
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"
|
23 |
-
"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM",
|
26 |
"use_rslora": false
|
|
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
+
"q_proj",
|
23 |
+
"v_proj"
|
24 |
],
|
25 |
"task_type": "CAUSAL_LM",
|
26 |
"use_rslora": false
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 134235048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c2bfc2a55106a9664ae2b78b967063ba76640ded7bd529fbf1d1cfc15941e73
|
3 |
size 134235048
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 1024,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4411
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb77ff0653c5f5c2324aba636415478eb1b421b961ae164bd3772bdb21f0dc7c
|
3 |
size 4411
|