nihal-mp/qlora-llama-ft
Browse files- README.md +11 -12
- adapter_config.json +2 -2
- adapter_model.safetensors +2 -2
- runs/Jul11_16-17-50_2b4d3b54ff86/events.out.tfevents.1720714673.2b4d3b54ff86.2432.0 +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +6 -1
- tokenizer_config.json +1 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,11 +1,10 @@
|
|
1 |
---
|
2 |
-
base_model:
|
3 |
library_name: peft
|
4 |
license: llama2
|
5 |
tags:
|
6 |
- trl
|
7 |
- sft
|
8 |
-
- unsloth
|
9 |
- generated_from_trainer
|
10 |
model-index:
|
11 |
- name: outputs
|
@@ -17,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
# outputs
|
19 |
|
20 |
-
This model is a fine-tuned version of [
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -37,15 +36,15 @@ More information needed
|
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
- learning_rate: 0.0002
|
40 |
-
- train_batch_size:
|
41 |
- eval_batch_size: 8
|
42 |
-
- seed:
|
43 |
- gradient_accumulation_steps: 4
|
44 |
-
- total_train_batch_size:
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
-
- lr_scheduler_warmup_steps:
|
48 |
-
- training_steps:
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
### Training results
|
@@ -54,8 +53,8 @@ The following hyperparameters were used during training:
|
|
54 |
|
55 |
### Framework versions
|
56 |
|
57 |
-
- PEFT 0.
|
58 |
-
- Transformers 4.
|
59 |
- Pytorch 2.3.0+cu121
|
60 |
-
- Datasets 2.
|
61 |
-
- Tokenizers 0.
|
|
|
1 |
---
|
2 |
+
base_model: meta-llama/Llama-2-7b-hf
|
3 |
library_name: peft
|
4 |
license: llama2
|
5 |
tags:
|
6 |
- trl
|
7 |
- sft
|
|
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: outputs
|
|
|
16 |
|
17 |
# outputs
|
18 |
|
19 |
+
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
- learning_rate: 0.0002
|
39 |
+
- train_batch_size: 1
|
40 |
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
- gradient_accumulation_steps: 4
|
43 |
+
- total_train_batch_size: 4
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
+
- lr_scheduler_warmup_steps: 2
|
47 |
+
- training_steps: 50
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
|
|
53 |
|
54 |
### Framework versions
|
55 |
|
56 |
+
- PEFT 0.8.2
|
57 |
+
- Transformers 4.38.0
|
58 |
- Pytorch 2.3.0+cu121
|
59 |
+
- Datasets 2.17.0
|
60 |
+
- Tokenizers 0.15.2
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path":
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
@@ -20,8 +20,8 @@
|
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
"k_proj",
|
23 |
-
"q_proj",
|
24 |
"o_proj",
|
|
|
25 |
"v_proj"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
"k_proj",
|
|
|
23 |
"o_proj",
|
24 |
+
"q_proj",
|
25 |
"v_proj"
|
26 |
],
|
27 |
"task_type": "CAUSAL_LM",
|
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 sha256:6c9a77c2291f74342b2cbe0e7d867df196cb5876e6d830d888f78dc4c09fd711
|
3 |
+
size 134252336
|
runs/Jul11_16-17-50_2b4d3b54ff86/events.out.tfevents.1720714673.2b4d3b54ff86.2432.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f54f42dc2aa7b53fab7c88b1a6f3713d037726f1280bc2e761592ec50a03d8bf
|
3 |
+
size 15717
|
special_tokens_map.json
CHANGED
@@ -13,6 +13,7 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
16 |
"unk_token": {
|
17 |
"content": "<unk>",
|
18 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "</s>",
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 1024,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
tokenizer_config.json
CHANGED
@@ -32,7 +32,7 @@
|
|
32 |
"eos_token": "</s>",
|
33 |
"legacy": false,
|
34 |
"model_max_length": 1000000000000000019884624838656,
|
35 |
-
"pad_token":
|
36 |
"padding_side": "right",
|
37 |
"sp_model_kwargs": {},
|
38 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
32 |
"eos_token": "</s>",
|
33 |
"legacy": false,
|
34 |
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": "</s>",
|
36 |
"padding_side": "right",
|
37 |
"sp_model_kwargs": {},
|
38 |
"tokenizer_class": "LlamaTokenizer",
|
training_args.bin
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:ca732ff29e2b82ba473ff3c1036118c509ff4b767a350d49c1ed3d83158ffebb
|
3 |
+
size 4856
|