Rahulholla
commited on
test101
Browse files- README.md +79 -0
- adapter_config.json +35 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
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 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 2.5e-05
|
39 |
+
- train_batch_size: 2
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 1
|
45 |
+
- training_steps: 500
|
46 |
+
|
47 |
+
### Training results
|
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
|
adapter_config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 64,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 32,
|
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,
|
34 |
+
"use_rslora": false
|
35 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f260341af3c5a3501294d86b879fd6192a4d48ec0d5890f7c1fcda0552188efc
|
3 |
+
size 864513616
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0464207dc4a228aa156dd4e77277109ec5004f3b6b6769521b8ccb6ec50733bb
|
3 |
+
size 4920
|