Hugging Face's logo

smangrul
/
mistral-dpo

PEFT
TensorBoard
Safetensors
trl
dpo
Generated from Trainer
Model card Files Metrics Community
smangrul commited on
Commit
8779455
•
1 Parent(s): 560914e

Training in progress, epoch 1

Browse files
Files changed (20) hide show
  1. adapter_config.json +32 -0
  2. adapter_model.safetensors +3 -0
  3. added_tokens.json +7 -0
  4. runs/Jan27_13-58-30_ip-26-0-168-52/events.out.tfevents.1706363984.ip-26-0-168-52.1268816.0 +3 -0
  5. runs/Jan27_14-04-31_ip-26-0-168-52/events.out.tfevents.1706364288.ip-26-0-168-52.1269735.0 +3 -0
  6. runs/Jan27_18-42-07_ip-26-0-168-52/events.out.tfevents.1706380952.ip-26-0-168-52.1294731.0 +3 -0
  7. runs/Jan27_18-43-27_ip-26-0-168-52/events.out.tfevents.1706381025.ip-26-0-168-52.1294939.0 +3 -0
  8. runs/Jan27_18-45-50_ip-26-0-168-52/events.out.tfevents.1706381167.ip-26-0-168-52.1295238.0 +3 -0
  9. runs/Jan27_18-46-48_ip-26-0-168-52/events.out.tfevents.1706381225.ip-26-0-168-52.1295396.0 +3 -0
  10. runs/Jan27_18-52-33_ip-26-0-168-52/events.out.tfevents.1706381570.ip-26-0-168-52.1295983.0 +3 -0
  11. runs/Jan27_18-55-29_ip-26-0-168-52/events.out.tfevents.1706381747.ip-26-0-168-52.1296312.0 +3 -0
  12. runs/Jan27_18-58-14_ip-26-0-168-52/events.out.tfevents.1706381911.ip-26-0-168-52.1296640.0 +3 -0
  13. runs/Jan27_19-07-24_ip-26-0-168-52/events.out.tfevents.1706382461.ip-26-0-168-52.1297699.0 +3 -0
  14. runs/Jan27_19-30-03_ip-26-0-168-52/events.out.tfevents.1706383828.ip-26-0-168-52.1299724.0 +3 -0
  15. runs/Jan27_19-57-07_ip-26-0-175-241/events.out.tfevents.1706385493.ip-26-0-175-241.1845786.0 +3 -0
  16. special_tokens_map.json +38 -0
  17. tokenizer.json +0 -0
  18. tokenizer.model +3 -0
  19. tokenizer_config.json +90 -0
  20. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
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": 0.1,
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
+ "k_proj",
23
+ "q_proj",
24
+ "v_proj",
25
+ "up_proj",
26
+ "gate_proj",
27
+ "o_proj",
28
+ "down_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_rslora": false
32
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76453f34c2a4276adca027f8d743507cf298638f641fc356dc1a08f6cf3e7991
3
+ size 692251536
added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "<pad>": 32001,
3
+ "<|im_end|>": 32000,
4
+ "<|im_start|>assistant": 32003,
5
+ "<|im_start|>system": 32004,
6
+ "<|im_start|>user": 32002
7
+ }
runs/Jan27_13-58-30_ip-26-0-168-52/events.out.tfevents.1706363984.ip-26-0-168-52.1268816.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eaaa0b96b5abbe9e5a1060ee9d6d97749e933bd6d813f6546e8aff59b82e2b3
3
+ size 4810
runs/Jan27_14-04-31_ip-26-0-168-52/events.out.tfevents.1706364288.ip-26-0-168-52.1269735.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:352d026926ea6db24e72aababa7f489f33d3201181fe05312c761d621bdeafb8
3
+ size 83785
runs/Jan27_18-42-07_ip-26-0-168-52/events.out.tfevents.1706380952.ip-26-0-168-52.1294731.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e95792495d85da4aec1dc712601a7ae20c6d1545959730971edde346c0e06d9
3
+ size 4809
runs/Jan27_18-43-27_ip-26-0-168-52/events.out.tfevents.1706381025.ip-26-0-168-52.1294939.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db0046f8b6821315355ba0b674bfd5f852df14fcae94c7356dadae97c9ad64ba
3
+ size 4809
runs/Jan27_18-45-50_ip-26-0-168-52/events.out.tfevents.1706381167.ip-26-0-168-52.1295238.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9237086e0e0187d3070f0e6eeced658e82a4786906a2b6e742c6110c86aa7a2f
3
+ size 4809
runs/Jan27_18-46-48_ip-26-0-168-52/events.out.tfevents.1706381225.ip-26-0-168-52.1295396.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73364b1e74a70e7c4260a9c37c189914389aa80f4deb05f14881071a27d59358
3
+ size 4809
runs/Jan27_18-52-33_ip-26-0-168-52/events.out.tfevents.1706381570.ip-26-0-168-52.1295983.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:661dda00f3f5350997fe51bf33e9adfdc8c0ff5a353a7f7963035ede3aed289d
3
+ size 4809
runs/Jan27_18-55-29_ip-26-0-168-52/events.out.tfevents.1706381747.ip-26-0-168-52.1296312.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5504012f817f400f3fe1db987d33ed9eb0dda5fd4a94aa8fb2b0687f1756c901
3
+ size 4809
runs/Jan27_18-58-14_ip-26-0-168-52/events.out.tfevents.1706381911.ip-26-0-168-52.1296640.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35eec776e5db4f969c431a5bdc232380bccfb81f5b77e9b1496b9580a1cd0a3d
3
+ size 4809
runs/Jan27_19-07-24_ip-26-0-168-52/events.out.tfevents.1706382461.ip-26-0-168-52.1297699.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d03705c43e6a1bbaed094373bb566e90ac7930c03ae71c53c20e00c80b180f1
3
+ size 4809
runs/Jan27_19-30-03_ip-26-0-168-52/events.out.tfevents.1706383828.ip-26-0-168-52.1299724.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d19ec0baab5dc97faa5033a07ae383014ea3334b8746d40de5b89c85686845e
3
+ size 4810
runs/Jan27_19-57-07_ip-26-0-175-241/events.out.tfevents.1706385493.ip-26-0-175-241.1845786.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c50e742a928f5d0e5a7290851313693de261a3f63c1492433f2d4e1468974f74
3
+ size 84881
special_tokens_map.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>user",
4
+ "<|im_start|>assistant",
5
+ "<|im_start|>system",
6
+ "<|im_end|>",
7
+ "<s>",
8
+ "<pad>"
9
+ ],
10
+ "bos_token": {
11
+ "content": "<s>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<pad>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "unk_token": {
32
+ "content": "<unk>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
+ }
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32000": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<pad>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|im_start|>user",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|im_start|>assistant",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|im_start|>system",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ }
69
+ },
70
+ "additional_special_tokens": [
71
+ "<|im_start|>user",
72
+ "<|im_start|>assistant",
73
+ "<|im_start|>system",
74
+ "<|im_end|>",
75
+ "<s>",
76
+ "<pad>"
77
+ ],
78
+ "bos_token": "<s>",
79
+ "chat_template": "{% for message in messages %}\n{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% if loop.last and add_generation_prompt %}{{'<|im_start|>assistant\n' }}{% endif %}{% endfor %}",
80
+ "clean_up_tokenization_spaces": false,
81
+ "eos_token": "<|im_end|>",
82
+ "legacy": true,
83
+ "model_max_length": 1000000000000000019884624838656,
84
+ "pad_token": "<pad>",
85
+ "sp_model_kwargs": {},
86
+ "spaces_between_special_tokens": false,
87
+ "tokenizer_class": "LlamaTokenizer",
88
+ "unk_token": "<unk>",
89
+ "use_default_system_prompt": false
90
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:061cb721a9d08bf29fb96349aaf0cb35511b2e8d07630d5b57d2f90a966e39d3
3
+ size 4792