Model save
Browse files- README.md +4 -12
- adapter_config.json +32 -0
- adapter_model.safetensors +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,8 +1,9 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
-
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
model-index:
|
7 |
- name: Codet5
|
8 |
results: []
|
@@ -14,8 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
# Codet5
|
15 |
|
16 |
This model is a fine-tuned version of [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small) on an unknown dataset.
|
17 |
-
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.4498
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -41,21 +40,14 @@ The following hyperparameters were used during training:
|
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
- num_epochs: 5
|
44 |
-
- mixed_precision_training: Native AMP
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
-
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
| 2.0468 | 1.0 | 9 | 1.2151 |
|
51 |
-
| 1.7107 | 2.0 | 18 | 0.9257 |
|
52 |
-
| 0.5894 | 3.0 | 27 | 0.6283 |
|
53 |
-
| 0.3785 | 4.0 | 36 | 0.5134 |
|
54 |
-
| 0.2473 | 5.0 | 45 | 0.4498 |
|
55 |
|
56 |
|
57 |
### Framework versions
|
58 |
|
|
|
59 |
- Transformers 4.40.0
|
60 |
- Pytorch 2.2.1+cu121
|
61 |
-
- Tokenizers 0.19.1
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
base_model: Salesforce/codet5-small
|
7 |
model-index:
|
8 |
- name: Codet5
|
9 |
results: []
|
|
|
15 |
# Codet5
|
16 |
|
17 |
This model is a fine-tuned version of [Salesforce/codet5-small](https://huggingface.co/Salesforce/codet5-small) on an unknown dataset.
|
|
|
|
|
18 |
|
19 |
## Model description
|
20 |
|
|
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: linear
|
42 |
- num_epochs: 5
|
|
|
43 |
|
44 |
### Training results
|
45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
|
47 |
|
48 |
### Framework versions
|
49 |
|
50 |
+
- PEFT 0.10.0
|
51 |
- Transformers 4.40.0
|
52 |
- Pytorch 2.2.1+cu121
|
53 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "T5ForConditionalGeneration",
|
5 |
+
"parent_library": "transformers.models.t5.modeling_t5"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "Salesforce/codet5-small",
|
8 |
+
"bias": "none",
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 8,
|
17 |
+
"lora_dropout": 0.0,
|
18 |
+
"megatron_config": null,
|
19 |
+
"megatron_core": "megatron.core",
|
20 |
+
"modules_to_save": null,
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 8,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"v",
|
27 |
+
"q"
|
28 |
+
],
|
29 |
+
"task_type": null,
|
30 |
+
"use_dora": false,
|
31 |
+
"use_rslora": false
|
32 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5eac198845b3fa6712954c560fa38f870f26f7565df28c8da657d575a4c00df5
|
3 |
+
size 1189536
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79ba529c90fdd470db586fcec07c53e7c086ef12514addb53000ab3c923c8b2a
|
3 |
size 4984
|