Rahulholla
commited on
Commit
•
61239f0
1
Parent(s):
fe4c1e4
llama2-stock-model
Browse files- README.md +25 -26
- adapter_config.json +7 -7
- adapter_model.safetensors +2 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,9 +1,8 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
base_model:
|
7 |
model-index:
|
8 |
- name: mistral-stock-finetune
|
9 |
results: []
|
@@ -14,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# mistral-stock-finetune
|
16 |
|
17 |
-
This model is a fine-tuned version of [
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -48,32 +47,32 @@ The following hyperparameters were used during training:
|
|
48 |
|
49 |
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
-
|
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
|
72 |
|
73 |
### Framework versions
|
74 |
|
75 |
-
- PEFT 0.
|
76 |
-
- Transformers 4.
|
77 |
- Pytorch 2.1.0+cu118
|
78 |
- Datasets 2.18.0
|
79 |
- Tokenizers 0.15.2
|
|
|
1 |
---
|
|
|
2 |
library_name: peft
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
base_model: meta-llama/Llama-2-7b-hf
|
6 |
model-index:
|
7 |
- name: mistral-stock-finetune
|
8 |
results: []
|
|
|
13 |
|
14 |
# mistral-stock-finetune
|
15 |
|
16 |
+
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.6325
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
+
| 1.2624 | 0.07 | 25 | 1.0074 |
|
51 |
+
| 0.8582 | 0.13 | 50 | 0.7799 |
|
52 |
+
| 0.7578 | 0.2 | 75 | 0.7358 |
|
53 |
+
| 0.7276 | 0.26 | 100 | 0.7133 |
|
54 |
+
| 0.7104 | 0.33 | 125 | 0.6944 |
|
55 |
+
| 0.6791 | 0.4 | 150 | 0.6819 |
|
56 |
+
| 0.6856 | 0.46 | 175 | 0.6734 |
|
57 |
+
| 0.6723 | 0.53 | 200 | 0.6658 |
|
58 |
+
| 0.6629 | 0.59 | 225 | 0.6601 |
|
59 |
+
| 0.6526 | 0.66 | 250 | 0.6553 |
|
60 |
+
| 0.6395 | 0.73 | 275 | 0.6505 |
|
61 |
+
| 0.6537 | 0.79 | 300 | 0.6471 |
|
62 |
+
| 0.6317 | 0.86 | 325 | 0.6445 |
|
63 |
+
| 0.6401 | 0.92 | 350 | 0.6405 |
|
64 |
+
| 0.6412 | 0.99 | 375 | 0.6375 |
|
65 |
+
| 0.6303 | 1.06 | 400 | 0.6367 |
|
66 |
+
| 0.6135 | 1.12 | 425 | 0.6347 |
|
67 |
+
| 0.6107 | 1.19 | 450 | 0.6336 |
|
68 |
+
| 0.605 | 1.25 | 475 | 0.6330 |
|
69 |
+
| 0.6062 | 1.32 | 500 | 0.6325 |
|
70 |
|
71 |
|
72 |
### Framework versions
|
73 |
|
74 |
+
- PEFT 0.10.1.dev0
|
75 |
+
- Transformers 4.40.0.dev0
|
76 |
- Pytorch 2.1.0+cu118
|
77 |
- Datasets 2.18.0
|
78 |
- Tokenizers 0.15.2
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
@@ -20,14 +20,14 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"gate_proj",
|
25 |
-
"o_proj",
|
26 |
-
"lm_head",
|
27 |
"v_proj",
|
|
|
28 |
"k_proj",
|
29 |
-
"
|
30 |
-
"
|
|
|
|
|
31 |
],
|
32 |
"task_type": "CAUSAL_LM",
|
33 |
"use_dora": false,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"q_proj",
|
|
|
|
|
|
|
24 |
"v_proj",
|
25 |
+
"lm_head",
|
26 |
"k_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"down_proj",
|
29 |
+
"o_proj",
|
30 |
+
"up_proj"
|
31 |
],
|
32 |
"task_type": "CAUSAL_LM",
|
33 |
"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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d02672009795a2cd99351b015eb1c026bdbd67ac8423f45150be12301ed7e2f4
|
3 |
+
size 848784976
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2053d1b83f9224c5a19a46603617d2eed3093575944f8849a1d202cf2b94090b
|
3 |
size 4920
|