jmeneu/Fine-tuning-Mistral
Browse files- README.md +15 -16
- adapter_config.json +3 -3
- adapter_model.safetensors +2 -2
- added_tokens.json +3 -0
- tokenizer.model +3 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
19 |
|
20 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the imdb dataset.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
-
- Loss:
|
23 |
-
- Accuracy: {'accuracy': 0.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -39,28 +39,27 @@ More information needed
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
-
- learning_rate: 0.
|
43 |
-
- train_batch_size:
|
44 |
-
- eval_batch_size:
|
45 |
- seed: 42
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
-
- lr_scheduler_type:
|
48 |
-
-
|
|
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy
|
53 |
-
|
54 |
-
|
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.6993 | 4.0 | 50000 | 0.6948 | {'accuracy': 0.5022} |
|
58 |
-
| 0.693 | 5.0 | 62500 | 0.6942 | {'accuracy': 0.50984} |
|
59 |
|
60 |
|
61 |
### Framework versions
|
62 |
|
63 |
- Transformers 4.35.2
|
64 |
-
- Pytorch 2.1.
|
65 |
-
- Datasets 2.
|
66 |
- Tokenizers 0.15.0
|
|
|
19 |
|
20 |
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the imdb dataset.
|
21 |
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 7.4068
|
23 |
+
- Accuracy: {'accuracy': 0.9338}
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 0.01
|
43 |
+
- train_batch_size: 4
|
44 |
+
- eval_batch_size: 4
|
45 |
- seed: 42
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: constant
|
48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
49 |
+
- num_epochs: 3
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------------------:|
|
55 |
+
| 57.25 | 1.0 | 5000 | 9.4656 | {'accuracy': 0.9292} |
|
56 |
+
| 0.0 | 2.0 | 10000 | 8.0567 | {'accuracy': 0.9384} |
|
57 |
+
| 0.0 | 3.0 | 15000 | 7.4068 | {'accuracy': 0.9338} |
|
|
|
|
|
58 |
|
59 |
|
60 |
### Framework versions
|
61 |
|
62 |
- Transformers 4.35.2
|
63 |
+
- Pytorch 2.1.1+cu121
|
64 |
+
- Datasets 2.4.0
|
65 |
- Tokenizers 0.15.0
|
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,
|
@@ -16,8 +16,8 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"
|
20 |
-
"
|
21 |
],
|
22 |
"task_type": "SEQ_CLS"
|
23 |
}
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": null,
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"v_proj",
|
20 |
+
"q_proj"
|
21 |
],
|
22 |
"task_type": "SEQ_CLS"
|
23 |
}
|
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 sha256:09445afa535bdc15e772b6f9c07ae2bd3acbe0e81831a622c42bb8eb8f2ae67f
|
3 |
+
size 3443360
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 32000
|
3 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
training_args.bin
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 sha256:30a1d1b03f6a1d8817ca86a84f3165ab5dd92d5b25acb127f1e184f2fd26537d
|
3 |
+
size 4600
|