Hugging Face's logo

floleuerer
/
zephyr-7b-dpo-qlora

TensorBoard
Safetensors
Model card Files Metrics Community
floleuerer commited on
Commit
94d32df
•
1 Parent(s): 8ef1024

Training in progress, step 100

Browse files
Files changed (11) hide show
  1. adapter_config.json +31 -0
  2. adapter_model.safetensors +3 -0
  3. runs/Jan13_18-22-16_bronxx/events.out.tfevents.1705166795.bronxx.24762.0 +3 -0
  4. runs/Jan13_19-34-47_bronxx/events.out.tfevents.1705171126.bronxx.28129.0 +3 -0
  5. runs/Jan13_19-41-47_bronxx/events.out.tfevents.1705171344.bronxx.29207.0 +3 -0
  6. runs/Jan13_19-43-26_bronxx/events.out.tfevents.1705171439.bronxx.29662.0 +3 -0
  7. runs/Jan13_19-44-38_bronxx/events.out.tfevents.1705171510.bronxx.30076.0 +3 -0
  8. special_tokens_map.json +24 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +43 -0
  11. 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": "mistralai/Mistral-7B-Instruct-v0.2",
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": 16,
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": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "q_proj",
24
+ "o_proj",
25
+ "up_proj",
26
+ "gate_proj",
27
+ "k_proj",
28
+ "down_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 sha256:4d010c2c27021502cf6df2913a0e30703bb1fbfb6c25bb97f0dda53888038bac
3
+ size 167832240
runs/Jan13_18-22-16_bronxx/events.out.tfevents.1705166795.bronxx.24762.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd0244892f755b773afa5dfa25335f0a19da4797bb4c32ff7a9852123cc4b51d
3
+ size 4928
runs/Jan13_19-34-47_bronxx/events.out.tfevents.1705171126.bronxx.28129.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ed1f08228d9c0a37317efde2a8301ff087bdeb1c81807c92c61d0c716c11719
3
+ size 6797
runs/Jan13_19-41-47_bronxx/events.out.tfevents.1705171344.bronxx.29207.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e85f14ef5dfff09b04a5a790b4ea2fa823317d774c6578fdbb54967ff627566
3
+ size 5551
runs/Jan13_19-43-26_bronxx/events.out.tfevents.1705171439.bronxx.29662.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:583eaf8f8f34f036b7de2acef641c2b7a98aa97fb9fbb42aff13239ffe5d6f37
3
+ size 4928
runs/Jan13_19-44-38_bronxx/events.out.tfevents.1705171510.bronxx.30076.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0e2a73c70df5cf9ebd4b8ecc395c16ab91e94afdbfc4d3de596b6d03adba8d
3
+ size 12508
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_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{{ bos_token }}{% for message in messages if message['role'] != 'system' %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 2048,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c5ba1518b11ab2f80c224e84884e9b180a2118029730e4dac0921ab8e5d9af9
3
+ size 4856