Hugging Face's logo

zoohun
/
results

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
 Metrics Community
zoohun commited on
Commit
778f8e4
·
verified ·
1 Parent(s): baf51a3

Training completed!

Browse files
Files changed (8) hide show
  1. README.md +5 -4
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. runs/Apr04_12-17-29_eb8ec7d052f4/events.out.tfevents.1712233058.eb8ec7d052f4.989.0 +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer.model +3 -0
  7. tokenizer_config.json +1 -40
  8. training_args.bin +1 -1
README.md CHANGED
@@ -1,10 +1,11 @@
1
  ---
 
2
  library_name: peft
3
  tags:
4
  - trl
5
  - sft
6
  - generated_from_trainer
7
- base_model: beomi/llama-2-ko-7b
8
  model-index:
9
  - name: results
10
  results: []
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # results
17
 
18
- This model is a fine-tuned version of [beomi/llama-2-ko-7b](https://huggingface.co/beomi/llama-2-ko-7b) on an unknown dataset.
19
 
20
  ## Model description
21
 
@@ -35,13 +36,13 @@ More information needed
35
 
36
  The following hyperparameters were used during training:
37
  - learning_rate: 0.0002
38
- - train_batch_size: 4
39
  - eval_batch_size: 8
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: constant
43
  - lr_scheduler_warmup_ratio: 0.03
44
- - num_epochs: 10
45
 
46
  ### Training results
47
 
 
1
  ---
2
+ license: llama2
3
  library_name: peft
4
  tags:
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
+ base_model: malhajar/meditron-7b-chat
9
  model-index:
10
  - name: results
11
  results: []
 
16
 
17
  # results
18
 
19
+ This model is a fine-tuned version of [malhajar/meditron-7b-chat](https://huggingface.co/malhajar/meditron-7b-chat) on an unknown dataset.
20
 
21
  ## Model description
22
 
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 0.0002
39
+ - train_batch_size: 2
40
  - eval_batch_size: 8
41
  - seed: 42
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: constant
44
  - lr_scheduler_warmup_ratio: 0.03
45
+ - num_epochs: 5
46
 
47
  ### Training results
48
 
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "beomi/llama-2-ko-7b",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -19,8 +19,8 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "v_proj",
23
- "q_proj"
24
  ],
25
  "task_type": "CAUSAL_LM",
26
  "use_rslora": false
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "malhajar/meditron-7b-chat",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "q_proj",
23
+ "v_proj"
24
  ],
25
  "task_type": "CAUSAL_LM",
26
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d359b541e1677e634d8155b246fb0c35c892621c27675f217c533bd72321cff8
3
  size 134235048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f7af9f0d1c1106dc64fc0e92974b589a50f1fff25248714baec7840b761ccf0
3
  size 134235048
runs/Apr04_12-17-29_eb8ec7d052f4/events.out.tfevents.1712233058.eb8ec7d052f4.989.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee769f84103e66a9d7d4edac837972b2ab632d0c8d802ad43914dac15cf4c064
3
+ size 6204
tokenizer.json CHANGED
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -25,46 +25,6 @@
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
- },
29
- "46331": {
30
- "content": "<|sep|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "46332": {
38
- "content": "<|endoftext|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "46333": {
46
- "content": "<|acc|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": false,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "46334": {
54
- "content": "<|rrn|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": false,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "46335": {
62
- "content": "<|tel|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": false,
66
- "single_word": false,
67
- "special": true
68
  }
69
  },
70
  "bos_token": "<s>",
@@ -73,6 +33,7 @@
73
  "legacy": false,
74
  "model_max_length": 1000000000000000019884624838656,
75
  "pad_token": "</s>",
 
76
  "sp_model_kwargs": {},
77
  "tokenizer_class": "LlamaTokenizer",
78
  "unk_token": "<unk>",
 
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  }
29
  },
30
  "bos_token": "<s>",
 
33
  "legacy": false,
34
  "model_max_length": 1000000000000000019884624838656,
35
  "pad_token": "</s>",
36
+ "padding_side": "right",
37
  "sp_model_kwargs": {},
38
  "tokenizer_class": "LlamaTokenizer",
39
  "unk_token": "<unk>",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7c35c1860c0b4fd75740c170e307121aae01bd979213aee9ca737502a2f023f
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eec22afda79e639f1fff7a0e06480a865b1b46e9c2df114745f205ecc7cc356
3
  size 4664