Hugging Face's logo

gang21
/
llama2-icd10-finetuned-qlora

PEFT
Model card Files Community
1
gang21 commited on
Commit
1501772
·
1 Parent(s): e8ae1fe

results -> checkpoint commit

Browse files
Files changed (9) hide show
  1. README.md +12 -0
  2. optimizer.pt +3 -0
  3. rng_state.pth +3 -0
  4. scheduler.pt +3 -0
  5. special_tokens_map.json +24 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +31 -0
  8. trainer_state.json +76 -0
  9. training_args.bin +3 -0
README.md CHANGED
@@ -4,6 +4,17 @@ library_name: peft
4
  ## Training procedure
5
 
6
 
 
 
 
 
 
 
 
 
 
 
 
7
  The following `bitsandbytes` quantization config was used during training:
8
  - load_in_8bit: False
9
  - load_in_4bit: True
@@ -16,5 +27,6 @@ The following `bitsandbytes` quantization config was used during training:
16
  - bnb_4bit_compute_dtype: float16
17
  ### Framework versions
18
 
 
19
 
20
  - PEFT 0.5.0.dev0
 
4
  ## Training procedure
5
 
6
 
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+
18
  The following `bitsandbytes` quantization config was used during training:
19
  - load_in_8bit: False
20
  - load_in_4bit: True
 
27
  - bnb_4bit_compute_dtype: float16
28
  ### Framework versions
29
 
30
+ - PEFT 0.5.0.dev0
31
 
32
  - PEFT 0.5.0.dev0
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed70e50e1db841cd1450cb7fa0739d3422af2d75243acccc970ef5d10bdf314b
3
+ size 268514437
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc89b1f8f721b2bf3b6e518c76d075243048472651896040e2293c6f231e167d
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a013cd39c0d2f465c83eacee4ec5985af67e895f7cb30488d865bba6bcfd47c
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
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
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "model_max_length": 1000000000000000019884624838656,
20
+ "pad_token": null,
21
+ "sp_model_kwargs": {},
22
+ "tokenizer_class": "LlamaTokenizer",
23
+ "unk_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<unk>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.02196715909714976,
5
+ "global_step": 100,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.0,
12
+ "learning_rate": 0.0002,
13
+ "loss": 4.7118,
14
+ "step": 10
15
+ },
16
+ {
17
+ "epoch": 0.0,
18
+ "learning_rate": 0.0002,
19
+ "loss": 1.4998,
20
+ "step": 20
21
+ },
22
+ {
23
+ "epoch": 0.01,
24
+ "learning_rate": 0.0002,
25
+ "loss": 0.9322,
26
+ "step": 30
27
+ },
28
+ {
29
+ "epoch": 0.01,
30
+ "learning_rate": 0.0002,
31
+ "loss": 0.8296,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 0.01,
36
+ "learning_rate": 0.0002,
37
+ "loss": 1.2456,
38
+ "step": 50
39
+ },
40
+ {
41
+ "epoch": 0.01,
42
+ "learning_rate": 0.0002,
43
+ "loss": 2.6588,
44
+ "step": 60
45
+ },
46
+ {
47
+ "epoch": 0.02,
48
+ "learning_rate": 0.0002,
49
+ "loss": 1.121,
50
+ "step": 70
51
+ },
52
+ {
53
+ "epoch": 0.02,
54
+ "learning_rate": 0.0002,
55
+ "loss": 1.0009,
56
+ "step": 80
57
+ },
58
+ {
59
+ "epoch": 0.02,
60
+ "learning_rate": 0.0002,
61
+ "loss": 1.147,
62
+ "step": 90
63
+ },
64
+ {
65
+ "epoch": 0.02,
66
+ "learning_rate": 0.0002,
67
+ "loss": 3.7583,
68
+ "step": 100
69
+ }
70
+ ],
71
+ "max_steps": 100,
72
+ "num_train_epochs": 1,
73
+ "total_flos": 2270248445214720.0,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ef290c4aea912e9c020831561dbf680df1583bdc74bd10cdd31c2c9c69941af
3
+ size 3963