CuATR-distilbert-LoRA
Browse files- README.md +6 -6
- adapter_config.json +3 -3
- adapter_model.safetensors +2 -2
- tokenizer.json +2 -14
- training_args.bin +1 -1
README.md
CHANGED
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
18 |
|
19 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
-
- Accuracy: 0.
|
23 |
-
- F1: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -54,9 +54,9 @@ The following hyperparameters were used during training:
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
|
61 |
|
62 |
### Framework versions
|
|
|
18 |
|
19 |
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.6857
|
22 |
+
- Accuracy: 0.5652
|
23 |
+
- F1: 0.7222
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
57 |
+
| 0.6809 | 0.67 | 1 | 0.6860 | 0.5652 | 0.7222 |
|
58 |
+
| 0.6938 | 2.0 | 3 | 0.6857 | 0.5652 | 0.7222 |
|
59 |
+
| 0.6844 | 2.67 | 4 | 0.6857 | 0.5652 | 0.7222 |
|
60 |
|
61 |
|
62 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -12,13 +12,13 @@
|
|
12 |
"lora_dropout": 0.05,
|
13 |
"modules_to_save": null,
|
14 |
"peft_type": "LORA",
|
15 |
-
"r":
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"q_lin",
|
20 |
-
"v_lin"
|
21 |
-
"k_lin"
|
22 |
],
|
23 |
"task_type": "TOKEN_CLS"
|
24 |
}
|
|
|
12 |
"lora_dropout": 0.05,
|
13 |
"modules_to_save": null,
|
14 |
"peft_type": "LORA",
|
15 |
+
"r": 16,
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"k_lin",
|
20 |
"q_lin",
|
21 |
+
"v_lin"
|
|
|
22 |
],
|
23 |
"task_type": "TOKEN_CLS"
|
24 |
}
|
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:a10fb40b919c270ce46691352cd62ec5656c4fbb4af0ee161e2aa1286bb5166f
|
3 |
+
size 1774720
|
tokenizer.json
CHANGED
@@ -1,19 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 512,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": "BatchLongest",
|
11 |
-
"direction": "Right",
|
12 |
-
"pad_to_multiple_of": null,
|
13 |
-
"pad_id": 0,
|
14 |
-
"pad_type_id": 0,
|
15 |
-
"pad_token": "[PAD]"
|
16 |
-
},
|
17 |
"added_tokens": [
|
18 |
{
|
19 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27caa59b4a51fd997f8759f82e5995b0c2c2b266fb9c9393b5c953d8c650c159
|
3 |
size 4600
|