deadcode99
commited on
Commit
•
d6140d9
1
Parent(s):
3085ce5
deadcode99/mistral-billm-token-classification-segmentwise
Browse files- README.md +14 -8
- adapter_config.json +2 -2
- adapter_model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
21 |
|
22 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
|
23 |
It achieves the following results on the evaluation set:
|
24 |
-
- Loss:
|
25 |
- Precision: 0.0
|
26 |
- Recall: 0.0
|
27 |
- F1: 0.0
|
28 |
-
- Accuracy: 0.
|
29 |
|
30 |
## Model description
|
31 |
|
@@ -44,7 +44,7 @@ More information needed
|
|
44 |
### Training hyperparameters
|
45 |
|
46 |
The following hyperparameters were used during training:
|
47 |
-
- learning_rate: 0.
|
48 |
- train_batch_size: 1
|
49 |
- eval_batch_size: 1
|
50 |
- seed: 42
|
@@ -52,16 +52,22 @@ The following hyperparameters were used during training:
|
|
52 |
- total_train_batch_size: 32
|
53 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
54 |
- lr_scheduler_type: linear
|
55 |
-
- num_epochs:
|
56 |
|
57 |
### Training results
|
58 |
|
59 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
60 |
|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
|
61 |
-
| No log | 0.9784 | 34 |
|
62 |
-
| No log | 1.9856 | 69 |
|
63 |
-
| No log | 2.9928 | 104 |
|
64 |
-
| No log |
|
|
|
|
|
|
|
|
|
|
|
|
|
65 |
|
66 |
|
67 |
### Framework versions
|
|
|
21 |
|
22 |
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
|
23 |
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 0.4998
|
25 |
- Precision: 0.0
|
26 |
- Recall: 0.0
|
27 |
- F1: 0.0
|
28 |
+
- Accuracy: 0.7829
|
29 |
|
30 |
## Model description
|
31 |
|
|
|
44 |
### Training hyperparameters
|
45 |
|
46 |
The following hyperparameters were used during training:
|
47 |
+
- learning_rate: 0.001
|
48 |
- train_batch_size: 1
|
49 |
- eval_batch_size: 1
|
50 |
- seed: 42
|
|
|
52 |
- total_train_batch_size: 32
|
53 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
54 |
- lr_scheduler_type: linear
|
55 |
+
- num_epochs: 10
|
56 |
|
57 |
### Training results
|
58 |
|
59 |
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
60 |
|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:---:|:--------:|
|
61 |
+
| No log | 0.9784 | 34 | 0.9557 | 0.0 | 0.0 | 0.0 | 0.7596 |
|
62 |
+
| No log | 1.9856 | 69 | 0.7691 | 0.0 | 0.0 | 0.0 | 0.7707 |
|
63 |
+
| No log | 2.9928 | 104 | 0.7086 | 0.0 | 0.0 | 0.0 | 0.7794 |
|
64 |
+
| No log | 4.0 | 139 | 0.5693 | 0.0 | 0.0 | 0.0 | 0.7697 |
|
65 |
+
| No log | 4.9784 | 173 | 0.5449 | 0.0 | 0.0 | 0.0 | 0.7758 |
|
66 |
+
| No log | 5.9856 | 208 | 0.5168 | 0.0 | 0.0 | 0.0 | 0.7805 |
|
67 |
+
| No log | 6.9928 | 243 | 0.5379 | 0.0 | 0.0 | 0.0 | 0.7838 |
|
68 |
+
| No log | 8.0 | 278 | 0.5301 | 0.0 | 0.0 | 0.0 | 0.7847 |
|
69 |
+
| No log | 8.9784 | 312 | 0.5007 | 0.0 | 0.0 | 0.0 | 0.7829 |
|
70 |
+
| No log | 9.7842 | 340 | 0.4998 | 0.0 | 0.0 | 0.0 | 0.7829 |
|
71 |
|
72 |
|
73 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -20,8 +20,8 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"
|
25 |
],
|
26 |
"task_type": "TOKEN_CLS",
|
27 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj"
|
25 |
],
|
26 |
"task_type": "TOKEN_CLS",
|
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 27296852
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:761c651de2687afee0d6819c465cac47ab39e50fbd77e288501079f8fc651276
|
3 |
size 27296852
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c09d3d1461ad4afa9aa8380d1ce2b1244989e1eba46cdcab4347a61033b62ac4
|
3 |
size 5176
|