Hugging Face's logo

chanchan7
/
llama-7b-dpo-qlora-relu

PEFT
TensorBoard
Safetensors
llama
alignment-handbook
Generated from Trainer
trl
dpo
Model card Files Metrics Community
chanchan7 commited on
Commit
c3da2f0
•
1 Parent(s): e629932

Training in progress, step 100

Browse files
Files changed (12) hide show
  1. adapter_config.json +31 -0
  2. adapter_model.safetensors +3 -0
  3. runs/Mar06_15-19-45_SYS-4029GP-TRT/events.out.tfevents.1709709637.SYS-4029GP-TRT.2249910.0 +3 -0
  4. runs/Mar07_13-38-01_SYS-4029GP-TRT/events.out.tfevents.1709789925.SYS-4029GP-TRT.2744823.0 +3 -0
  5. runs/Mar07_14-02-46_SYS-4029GP-TRT/events.out.tfevents.1709791413.SYS-4029GP-TRT.2753870.0 +3 -0
  6. runs/Mar07_19-37-32_SYS-4029GP-TRT/events.out.tfevents.1709811497.SYS-4029GP-TRT.2897552.0 +3 -0
  7. runs/Mar07_19-42-26_SYS-4029GP-TRT/events.out.tfevents.1709811801.SYS-4029GP-TRT.2900453.0 +3 -0
  8. special_tokens_map.json +24 -0
  9. tokenizer.json +0 -0
  10. tokenizer.model +3 -0
  11. tokenizer_config.json +42 -0
  12. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-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
+ "loftq_config": {},
12
+ "lora_alpha": 128,
13
+ "lora_dropout": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 128,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "o_proj",
23
+ "up_proj",
24
+ "k_proj",
25
+ "down_proj",
26
+ "q_proj",
27
+ "v_proj",
28
+ "gate_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM"
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c6069a2dda30449e7fd20904a16421c6c23967ef92bac5b0045cc1dee2ccee8
3
+ size 1279323952
runs/Mar06_15-19-45_SYS-4029GP-TRT/events.out.tfevents.1709709637.SYS-4029GP-TRT.2249910.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d3c8c993dbc7b69a6fbc0cda3dda46afb981b86678773dbfeb9ef40b5b5b925
3
+ size 11467
runs/Mar07_13-38-01_SYS-4029GP-TRT/events.out.tfevents.1709789925.SYS-4029GP-TRT.2744823.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7177a4eaf88d609f719dc8230f2449ad5606dd405ad996614df176c98d01901e
3
+ size 11467
runs/Mar07_14-02-46_SYS-4029GP-TRT/events.out.tfevents.1709791413.SYS-4029GP-TRT.2753870.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c3bee4aa72808c873b820b723cd14759d685fa41c182d6916c66d131fdcbdcd
3
+ size 6482
runs/Mar07_19-37-32_SYS-4029GP-TRT/events.out.tfevents.1709811497.SYS-4029GP-TRT.2897552.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:413e2beef5cf0d7b99199fd9ed9e958acff340f7fa730798deb6289e25276e2c
3
+ size 6482
runs/Mar07_19-42-26_SYS-4029GP-TRT/events.out.tfevents.1709811801.SYS-4029GP-TRT.2900453.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cca6c27b3152c22565aa7058f1f5fbe0982903f30a5299bb5dd46dd6428bec3
3
+ size 15101
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 2048,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00a882dd307fa0fb3668c54766b0ee73884d0d837febd8026216b3e5b3ae9a5a
3
+ size 4920