Hugging Face's logo

kkaung66
/
meta-chat

Text Generation
Transformers
llama
Generated from Trainer
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
kkaung66 commited on
Commit
241d7d2
•
1 Parent(s): 0a93402

Model save

Browse files
Files changed (5) hide show
  1. README.md +4 -4
  2. adapter_config.json +4 -4
  3. special_tokens_map.json +3 -3
  4. tokenizer_config.json +3 -3
  5. training_args.bin +1 -1
README.md CHANGED
@@ -33,15 +33,15 @@ More information needed
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 0.0002
36
- - train_batch_size: 12
37
- - eval_batch_size: 12
38
  - seed: 42
39
  - gradient_accumulation_steps: 8
40
- - total_train_batch_size: 96
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
  - lr_scheduler_warmup_steps: 10
44
- - num_epochs: 2
45
 
46
  ### Framework versions
47
 
 
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 0.0002
36
+ - train_batch_size: 14
37
+ - eval_batch_size: 14
38
  - seed: 42
39
  - gradient_accumulation_steps: 8
40
+ - total_train_batch_size: 112
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
  - lr_scheduler_warmup_steps: 10
44
+ - num_epochs: 0.5
45
 
46
  ### Framework versions
47
 
adapter_config.json CHANGED
@@ -16,13 +16,13 @@
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
19
  "v_proj",
20
- "gate_proj",
21
  "o_proj",
22
- "q_proj",
 
23
  "k_proj",
24
- "down_proj",
25
- "up_proj"
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
+ "down_proj",
20
  "v_proj",
 
21
  "o_proj",
22
+ "gate_proj",
23
+ "up_proj",
24
  "k_proj",
25
+ "q_proj"
 
26
  ],
27
  "task_type": "CAUSAL_LM"
28
  }
special_tokens_map.json CHANGED
@@ -2,14 +2,14 @@
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
5
- "normalized": true,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
  "content": "</s>",
11
  "lstrip": false,
12
- "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
@@ -23,7 +23,7 @@
23
  "unk_token": {
24
  "content": "<unk>",
25
  "lstrip": false,
26
- "normalized": true,
27
  "rstrip": false,
28
  "single_word": false
29
  }
 
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
  },
 
23
  "unk_token": {
24
  "content": "<unk>",
25
  "lstrip": false,
26
+ "normalized": false,
27
  "rstrip": false,
28
  "single_word": false
29
  }
tokenizer_config.json CHANGED
@@ -5,7 +5,7 @@
5
  "0": {
6
  "content": "<unk>",
7
  "lstrip": false,
8
- "normalized": true,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
@@ -13,7 +13,7 @@
13
  "1": {
14
  "content": "<s>",
15
  "lstrip": false,
16
- "normalized": true,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
@@ -21,7 +21,7 @@
21
  "2": {
22
  "content": "</s>",
23
  "lstrip": false,
24
- "normalized": true,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
 
5
  "0": {
6
  "content": "<unk>",
7
  "lstrip": false,
8
+ "normalized": false,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
 
13
  "1": {
14
  "content": "<s>",
15
  "lstrip": false,
16
+ "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
 
21
  "2": {
22
  "content": "</s>",
23
  "lstrip": false,
24
+ "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f18a66285138510e8e7ff5faa1f80798a6ce5bd366be8ff88a79e9b1190b708b
3
  size 4475
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5f95d56bdfdc02c2bd7817384ede3db60ec8f478d307ded07f14894833e731
3
  size 4475