turtlesama
commited on
Commit
•
38a4e4f
1
Parent(s):
43f2df8
gwurdilisk/test_codellama
Browse files- README.md +56 -0
- adapter_config.json +25 -0
- adapter_model.safetensors +3 -0
- runs/Nov05_21-38-37_f08adc52fbbf/events.out.tfevents.1699220319.f08adc52fbbf.292.0 +3 -0
- runs/Nov05_21-41-28_f08adc52fbbf/events.out.tfevents.1699220489.f08adc52fbbf.292.1 +3 -0
- runs/Nov05_21-49-19_f08adc52fbbf/events.out.tfevents.1699220960.f08adc52fbbf.292.2 +3 -0
- runs/Nov05_21-56-43_f08adc52fbbf/events.out.tfevents.1699221404.f08adc52fbbf.292.3 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
base_model: codellama/CodeLlama-7b-hf
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: outputs
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# outputs
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [codellama/CodeLlama-7b-hf](https://huggingface.co/codellama/CodeLlama-7b-hf) on an unknown dataset.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 0.0002
|
36 |
+
- train_batch_size: 10
|
37 |
+
- eval_batch_size: 8
|
38 |
+
- seed: 42
|
39 |
+
- gradient_accumulation_steps: 4
|
40 |
+
- total_train_batch_size: 40
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- lr_scheduler_warmup_steps: 2
|
44 |
+
- training_steps: 10
|
45 |
+
- mixed_precision_training: Native AMP
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
|
50 |
+
|
51 |
+
### Framework versions
|
52 |
+
|
53 |
+
- Transformers 4.36.0.dev0
|
54 |
+
- Pytorch 2.1.0+cu118
|
55 |
+
- Datasets 2.14.6
|
56 |
+
- Tokenizers 0.14.1
|
adapter_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "codellama/CodeLlama-7b-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 32,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 8,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"v_proj",
|
20 |
+
"q_proj",
|
21 |
+
"o_proj",
|
22 |
+
"k_proj"
|
23 |
+
],
|
24 |
+
"task_type": "CAUSAL_LM"
|
25 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f234816940a403b9d35c5b96c1fdbed4ce44ac1714c5fa0fed150539582a87dc
|
3 |
+
size 33588528
|
runs/Nov05_21-38-37_f08adc52fbbf/events.out.tfevents.1699220319.f08adc52fbbf.292.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9884c219954116b0e0d7fd5d44f61c5702e2f409ef3ac5c6f0e37cae1fbfb9c6
|
3 |
+
size 6481
|
runs/Nov05_21-41-28_f08adc52fbbf/events.out.tfevents.1699220489.f08adc52fbbf.292.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f95b991cf8f7ef7a9c835a89b083f3ef7eb8dd7dfcc83bca652708c6167d5044
|
3 |
+
size 6598
|
runs/Nov05_21-49-19_f08adc52fbbf/events.out.tfevents.1699220960.f08adc52fbbf.292.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1b4be6b6ba6618bd22a594111d35f5f09bd2c2843d0476798904173695f38db
|
3 |
+
size 4594
|
runs/Nov05_21-56-43_f08adc52fbbf/events.out.tfevents.1699221404.f08adc52fbbf.292.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a069d8d81883cb0fc689ed2fa61a90dbe381d278ba28d1ac3b08bdcece839b03
|
3 |
+
size 6482
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfef3f4b44871ef8e1119f229621ff4804409edea82bdbb4054d7ed138384c1c
|
3 |
+
size 4536
|