ranystephan
commited on
Commit
•
938a732
1
Parent(s):
852a624
NeuralFinGPT-v1-10
Browse files
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 [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 1.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -46,22 +46,28 @@ The following hyperparameters were used during training:
|
|
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 |
-
- num_epochs:
|
50 |
- mixed_precision_training: Native AMP
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss |
|
55 |
|:-------------:|:------:|:----:|:---------------:|
|
56 |
-
| No log | 0.9560 | 19 | 1.
|
57 |
-
| 1.
|
58 |
-
| 1.
|
59 |
-
| 1.
|
|
|
|
|
|
|
|
|
|
|
|
|
60 |
|
61 |
|
62 |
### Framework versions
|
63 |
|
64 |
-
- PEFT 0.
|
65 |
- Transformers 4.40.2
|
66 |
- Pytorch 2.1.0+cu121
|
67 |
- Datasets 2.19.1
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.1291
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
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 |
+
- num_epochs: 10
|
50 |
- mixed_precision_training: Native AMP
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss |
|
55 |
|:-------------:|:------:|:----:|:---------------:|
|
56 |
+
| No log | 0.9560 | 19 | 1.6214 |
|
57 |
+
| 1.8609 | 1.9623 | 39 | 1.4791 |
|
58 |
+
| 1.5247 | 2.9686 | 59 | 1.3896 |
|
59 |
+
| 1.4173 | 3.9748 | 79 | 1.3052 |
|
60 |
+
| 1.4173 | 4.9811 | 99 | 1.2385 |
|
61 |
+
| 1.3272 | 5.9874 | 119 | 1.1894 |
|
62 |
+
| 1.248 | 6.9937 | 139 | 1.1540 |
|
63 |
+
| 1.2 | 8.0 | 159 | 1.1351 |
|
64 |
+
| 1.1843 | 8.9560 | 178 | 1.1295 |
|
65 |
+
| 1.1843 | 9.5597 | 190 | 1.1291 |
|
66 |
|
67 |
|
68 |
### Framework versions
|
69 |
|
70 |
+
- PEFT 0.11.1
|
71 |
- Transformers 4.40.2
|
72 |
- Pytorch 2.1.0+cu121
|
73 |
- Datasets 2.19.1
|
adapter_config.json
CHANGED
@@ -20,8 +20,8 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
27 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"q_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
27 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 109069176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9aeb34f700a8fd7ed2cf855bd9b3d91363a9a644fa3a090b065312cf7aed7100
|
3 |
size 109069176
|
runs/May18_17-42-10_d12b2465ac42/events.out.tfevents.1716054148.d12b2465ac42.192.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f090f5b48eb431253e605b2e1b5dcb0b16f26b75ea63d0d40f93500b8251e33
|
3 |
+
size 9786
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
-
"add_eos_token":
|
|
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
@@ -35,7 +36,6 @@
|
|
35 |
"legacy": true,
|
36 |
"model_max_length": 1000000000000000019884624838656,
|
37 |
"pad_token": "</s>",
|
38 |
-
"padding_side": "left",
|
39 |
"sp_model_kwargs": {},
|
40 |
"spaces_between_special_tokens": false,
|
41 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
|
|
36 |
"legacy": true,
|
37 |
"model_max_length": 1000000000000000019884624838656,
|
38 |
"pad_token": "</s>",
|
|
|
39 |
"sp_model_kwargs": {},
|
40 |
"spaces_between_special_tokens": false,
|
41 |
"tokenizer_class": "LlamaTokenizer",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af72dd139cdb84c9e1df04e33cec371d1e84cf845137241f245555f9057f98c7
|
3 |
size 4984
|