Abhiijit01
commited on
Commit
·
edab5a4
1
Parent(s):
17221ef
Upload 5 files
Browse files- special_tokens_map.json +6 -0
- tokenizer.model +3 -0
- tokenizer_config.json +40 -0
- training_args.bin +3 -0
- training_params.json +41 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "</s>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
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
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"additional_special_tokens": [],
|
29 |
+
"bos_token": "<s>",
|
30 |
+
"clean_up_tokenization_spaces": false,
|
31 |
+
"eos_token": "</s>",
|
32 |
+
"legacy": false,
|
33 |
+
"model_max_length": 2048,
|
34 |
+
"pad_token": "</s>",
|
35 |
+
"padding_side": "right",
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"tokenizer_class": "LlamaTokenizer",
|
38 |
+
"unk_token": "<unk>",
|
39 |
+
"use_default_system_prompt": true
|
40 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d23b94d63217524779d106654d8f485846761dfd09ff98bdda20b5bc0b4e5ba0
|
3 |
+
size 4027
|
training_params.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "meta-llama/Llama-2-7b-chat-hf",
|
3 |
+
"data_path": "/content/sample_data",
|
4 |
+
"project_name": "llama2_Health",
|
5 |
+
"train_split": "train",
|
6 |
+
"valid_split": null,
|
7 |
+
"text_column": "ICD_and_Health",
|
8 |
+
"token": null,
|
9 |
+
"lr": 0.1,
|
10 |
+
"epochs": 2,
|
11 |
+
"batch_size": 1,
|
12 |
+
"warmup_ratio": 0.1,
|
13 |
+
"gradient_accumulation": 1,
|
14 |
+
"optimizer": "adamw_torch",
|
15 |
+
"scheduler": "linear",
|
16 |
+
"weight_decay": 0.0,
|
17 |
+
"max_grad_norm": 1.0,
|
18 |
+
"seed": 42,
|
19 |
+
"add_eos_token": false,
|
20 |
+
"block_size": -1,
|
21 |
+
"use_peft": true,
|
22 |
+
"lora_r": 16,
|
23 |
+
"lora_alpha": 32,
|
24 |
+
"lora_dropout": 0.05,
|
25 |
+
"logging_steps": -1,
|
26 |
+
"evaluation_strategy": "epoch",
|
27 |
+
"save_total_limit": 1,
|
28 |
+
"save_strategy": "epoch",
|
29 |
+
"auto_find_batch_size": false,
|
30 |
+
"fp16": false,
|
31 |
+
"push_to_hub": false,
|
32 |
+
"use_int8": false,
|
33 |
+
"model_max_length": 2048,
|
34 |
+
"repo_id": null,
|
35 |
+
"use_int4": true,
|
36 |
+
"trainer": "sft",
|
37 |
+
"target_modules": null,
|
38 |
+
"merge_adapter": false,
|
39 |
+
"username": null,
|
40 |
+
"use_flash_attention_2": false
|
41 |
+
}
|