veronica-girolimetti commited on
Commit
d4dac2f
1 Parent(s): 9465d39

Training in progress, step 150

Browse files
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "BioMistral/BioMistral-7B-DARE",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -10,23 +10,23 @@
10
  "layers_pattern": null,
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
- "lora_alpha": 2048,
14
  "lora_dropout": 0,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
17
  "modules_to_save": null,
18
  "peft_type": "LORA",
19
- "r": 1024,
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "o_proj",
24
- "gate_proj",
25
  "k_proj",
26
- "down_proj",
27
  "v_proj",
 
28
  "q_proj",
29
- "up_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/mistral-7b-v0.3-bnb-4bit",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
10
  "layers_pattern": null,
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
+ "lora_alpha": 512,
14
  "lora_dropout": 0,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
17
  "modules_to_save": null,
18
  "peft_type": "LORA",
19
+ "r": 256,
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
 
23
  "k_proj",
 
24
  "v_proj",
25
+ "gate_proj",
26
  "q_proj",
27
+ "o_proj",
28
+ "up_proj",
29
+ "down_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17d13f47710f232d8ed0dab7a2ec133d902697ef9513e10bd561018040f97272
3
- size 10737480672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eaf128df6a0bac1c116102bd1295d43433ed68a83b27e69b3c2bdb81e98a62e
3
+ size 2684416208
runs/Sep18_09-26-35_4a17e5208249/events.out.tfevents.1726651607.4a17e5208249.271.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3be782142560a3436a62105604235c548ca4fb9dc8ca5768cb987ab272d92fa5
3
+ size 11459
special_tokens_map.json CHANGED
@@ -13,7 +13,13 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<unk>",
 
 
 
 
 
 
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": {
17
+ "content": "[control_768]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
  "unk_token": {
24
  "content": "<unk>",
25
  "lstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
- size 493443
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
tokenizer_config.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67b5e0816e534be7763cb62bdba0122e6978559ef83027680998287cc7f72524
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:816bbcf2b1844a16fb3cb77a96cdabf72daf51a707885c0ab7f58feaafc31b45
3
  size 5432