Hugging Face's logo

Rahulholla
/
mistral-stock-finetune

PEFT
Safetensors
Generated from Trainer
Model card Files Community
Rahulholla commited on
Commit
61239f0
•
1 Parent(s): fe4c1e4

llama2-stock-model

Browse files
Files changed (4) hide show
  1. README.md +25 -26
  2. adapter_config.json +7 -7
  3. adapter_model.safetensors +2 -2
  4. 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: mistralai/Mistral-7B-v0.1
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 [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.6006
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
- | 0.957 | 0.07 | 25 | 0.7369 |
52
- | 0.6947 | 0.13 | 50 | 0.6830 |
53
- | 0.68 | 0.2 | 75 | 0.6631 |
54
- | 0.6596 | 0.26 | 100 | 0.6512 |
55
- | 0.655 | 0.33 | 125 | 0.6424 |
56
- | 0.6355 | 0.4 | 150 | 0.6344 |
57
- | 0.6434 | 0.46 | 175 | 0.6297 |
58
- | 0.6307 | 0.53 | 200 | 0.6252 |
59
- | 0.6224 | 0.59 | 225 | 0.6215 |
60
- | 0.6128 | 0.66 | 250 | 0.6177 |
61
- | 0.6018 | 0.73 | 275 | 0.6148 |
62
- | 0.62 | 0.79 | 300 | 0.6118 |
63
- | 0.5959 | 0.86 | 325 | 0.6093 |
64
- | 0.6046 | 0.92 | 350 | 0.6062 |
65
- | 0.6062 | 0.99 | 375 | 0.6038 |
66
- | 0.5769 | 1.06 | 400 | 0.6053 |
67
- | 0.559 | 1.12 | 425 | 0.6027 |
68
- | 0.5599 | 1.19 | 450 | 0.6021 |
69
- | 0.5522 | 1.25 | 475 | 0.6010 |
70
- | 0.5547 | 1.32 | 500 | 0.6006 |
71
 
72
 
73
  ### Framework versions
74
 
75
- - PEFT 0.9.1.dev0
76
- - Transformers 4.39.0.dev0
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": "mistralai/Mistral-7B-v0.1",
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
- "down_proj",
24
- "gate_proj",
25
- "o_proj",
26
- "lm_head",
27
  "v_proj",
 
28
  "k_proj",
29
- "up_proj",
30
- "q_proj"
 
 
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:f260341af3c5a3501294d86b879fd6192a4d48ec0d5890f7c1fcda0552188efc
3
- size 864513616
 
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 sha256:0464207dc4a228aa156dd4e77277109ec5004f3b6b6769521b8ccb6ec50733bb
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2053d1b83f9224c5a19a46603617d2eed3093575944f8849a1d202cf2b94090b
3
  size 4920