veronica-girolimetti commited on
Commit
bc964c8
1 Parent(s): 622d063

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": "unsloth/mistral-7b-v0.3-bnb-4bit",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -10,7 +10,7 @@
10
  "layers_pattern": null,
11
  "layers_to_transform": null,
12
  "loftq_config": {},
13
- "lora_alpha": 16,
14
  "lora_dropout": 0,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "k_proj",
24
- "down_proj",
25
  "q_proj",
26
  "gate_proj",
27
- "o_proj",
28
- "up_proj",
29
- "v_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": "BioMistral/BioMistral-7B-DARE",
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": 1024,
14
  "lora_dropout": 0,
15
  "megatron_config": null,
16
  "megatron_core": "megatron.core",
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "o_proj",
 
24
  "q_proj",
25
  "gate_proj",
26
+ "v_proj",
27
+ "down_proj",
28
+ "k_proj",
29
+ "up_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:f56a296b0ce00461f05ed7bcbc224bca7882e2ddc39fbc0f1f90cff4c366c964
3
  size 5368770952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:805378084712e264a00d45521f026230ed7562e66f82d00d293a0d8d5540564d
3
  size 5368770952
runs/Sep07_22-41-51_f4a87cf37542/events.out.tfevents.1725748927.f4a87cf37542.1458.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:930290526cf8a2e463d83eb408f096536fbeae4a95580a3fb360c55092e08530
3
+ size 11461
special_tokens_map.json CHANGED
@@ -13,13 +13,7 @@
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,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "<unk>",
 
 
 
 
 
 
17
  "unk_token": {
18
  "content": "<unk>",
19
  "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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
- size 587404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
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 sha256:76e90cc15fa237b6422cb6b683ceea528432fbb0266acf485134aa12341b4da4
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f06a0a51751dbbd60eca152e8bd332bace6bc8a9fe05c18379cb4e443821032d
3
  size 5496