AndersGiovanni
commited on
Commit
•
8039447
1
Parent(s):
cc6b135
End of training
Browse files- README.md +68 -0
- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
base_model: google/gemma-7b
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
model-index:
|
12 |
+
- name: gemma-7b
|
13 |
+
results: []
|
14 |
+
library_name: peft
|
15 |
+
---
|
16 |
+
|
17 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
18 |
+
should probably proofread and complete it, then remove this comment. -->
|
19 |
+
|
20 |
+
# gemma-7b
|
21 |
+
|
22 |
+
This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the None dataset.
|
23 |
+
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 1.4939
|
25 |
+
- Accuracy: 0.0806
|
26 |
+
- Precision: 0.4535
|
27 |
+
- Recall: 0.3826
|
28 |
+
- F1: 0.4150
|
29 |
+
- Hamming Loss: 0.2312
|
30 |
+
|
31 |
+
## Model description
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Intended uses & limitations
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training and evaluation data
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training procedure
|
44 |
+
|
45 |
+
### Training hyperparameters
|
46 |
+
|
47 |
+
The following hyperparameters were used during training:
|
48 |
+
- learning_rate: 0.0001
|
49 |
+
- train_batch_size: 2
|
50 |
+
- eval_batch_size: 2
|
51 |
+
- seed: 42
|
52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
53 |
+
- lr_scheduler_type: constant
|
54 |
+
- lr_scheduler_warmup_ratio: 0.05
|
55 |
+
- num_epochs: 10
|
56 |
+
- mixed_precision_training: Native AMP
|
57 |
+
|
58 |
+
### Training results
|
59 |
+
|
60 |
+
|
61 |
+
|
62 |
+
### Framework versions
|
63 |
+
|
64 |
+
- PEFT 0.5.0
|
65 |
+
- Transformers 4.38.2
|
66 |
+
- Pytorch 2.2.1+cu121
|
67 |
+
- Datasets 2.18.0
|
68 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "google/gemma-7b",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 16,
|
11 |
+
"lora_dropout": 0.01,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 2,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_proj",
|
18 |
+
"o_proj",
|
19 |
+
"k_proj",
|
20 |
+
"v_proj",
|
21 |
+
"gate_proj",
|
22 |
+
"up_proj",
|
23 |
+
"down_proj"
|
24 |
+
],
|
25 |
+
"task_type": "SEQ_CLS"
|
26 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77685300744df86ef695a1ac0d255c572bdfe7485577f7a29c6675a49083c547
|
3 |
+
size 25176520
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5140f35b99491bb781fae4c41e7e83a4fe425f92be5d918789655e0056dda60
|
3 |
+
size 4920
|