nova-sqoin
commited on
Commit
•
c7e1c5d
1
Parent(s):
a8956fe
End of training
Browse files- README.md +4 -5
- adapter_config.json +1 -1
- adapter_model.safetensors +2 -2
- added_tokens.json +3 -0
- runs/Nov21_09-00-53_Ubuntu-2204-jammy-amd64-base/events.out.tfevents.1700553653.Ubuntu-2204-jammy-amd64-base.23201.0 +3 -0
- special_tokens_map.json +3 -3
- tokenizer.json +0 -0
- tokenizer.model +2 -2
- tokenizer_config.json +18 -16
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,6 +1,5 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
base_model: 01-ai/Yi-6B
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -13,7 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# finetuned_llama
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -36,8 +35,8 @@ The following hyperparameters were used during training:
|
|
36 |
- train_batch_size: 1
|
37 |
- eval_batch_size: 8
|
38 |
- seed: 42
|
39 |
-
- gradient_accumulation_steps:
|
40 |
-
- total_train_batch_size:
|
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
|
|
|
1 |
---
|
2 |
+
base_model: NousResearch/Llama-2-7b-chat-hf
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
|
|
12 |
|
13 |
# finetuned_llama
|
14 |
|
15 |
+
This model is a fine-tuned version of [NousResearch/Llama-2-7b-chat-hf](https://huggingface.co/NousResearch/Llama-2-7b-chat-hf) on an unknown dataset.
|
16 |
|
17 |
## Model description
|
18 |
|
|
|
35 |
- train_batch_size: 1
|
36 |
- eval_batch_size: 8
|
37 |
- seed: 42
|
38 |
+
- gradient_accumulation_steps: 32
|
39 |
+
- total_train_batch_size: 32
|
40 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
- lr_scheduler_type: constant
|
42 |
- lr_scheduler_warmup_ratio: 0.03
|
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path": "
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b79962ac1dbad719913bd2a973b2e8d53ccffabdb52b6dbd0f0c821fe7ba626
|
3 |
+
size 1155352
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 32000
|
3 |
+
}
|
runs/Nov21_09-00-53_Ubuntu-2204-jammy-amd64-base/events.out.tfevents.1700553653.Ubuntu-2204-jammy-amd64-base.23201.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b5c8263b9862224a58fd17d003acc1b7d83877845ce54b817e821c40927bbd2
|
3 |
+
size 5004
|
special_tokens_map.json
CHANGED
@@ -1,19 +1,19 @@
|
|
1 |
{
|
2 |
"bos_token": {
|
3 |
-
"content": "
|
4 |
"lstrip": false,
|
5 |
"normalized": true,
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
-
"content": "
|
11 |
"lstrip": false,
|
12 |
"normalized": true,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token": "
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
|
|
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,
|
tokenizer.json
ADDED
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:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,4 @@
|
|
1 |
{
|
2 |
-
"add_bos_token": false,
|
3 |
-
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
@@ -11,7 +9,7 @@
|
|
11 |
"special": true
|
12 |
},
|
13 |
"1": {
|
14 |
-
"content": "
|
15 |
"lstrip": false,
|
16 |
"normalized": true,
|
17 |
"rstrip": false,
|
@@ -19,26 +17,30 @@
|
|
19 |
"special": true
|
20 |
},
|
21 |
"2": {
|
22 |
-
"content": "
|
23 |
"lstrip": false,
|
24 |
"normalized": true,
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
}
|
29 |
},
|
30 |
-
"
|
31 |
-
"AutoTokenizer": [
|
32 |
-
"01-ai/Yi-6B--tokenization_yi.YiTokenizer",
|
33 |
-
null
|
34 |
-
]
|
35 |
-
},
|
36 |
-
"bos_token": "<|startoftext|>",
|
37 |
"clean_up_tokenization_spaces": false,
|
38 |
-
"eos_token": "
|
39 |
-
"
|
40 |
-
"
|
|
|
41 |
"sp_model_kwargs": {},
|
42 |
-
"tokenizer_class": "
|
43 |
-
"unk_token": "<unk>"
|
|
|
44 |
}
|
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
|
|
9 |
"special": true
|
10 |
},
|
11 |
"1": {
|
12 |
+
"content": "<s>",
|
13 |
"lstrip": false,
|
14 |
"normalized": true,
|
15 |
"rstrip": false,
|
|
|
17 |
"special": true
|
18 |
},
|
19 |
"2": {
|
20 |
+
"content": "</s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": true,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
+
},
|
27 |
+
"32000": {
|
28 |
+
"content": "<pad>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": false
|
34 |
}
|
35 |
},
|
36 |
+
"bos_token": "<s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
"clean_up_tokenization_spaces": false,
|
38 |
+
"eos_token": "</s>",
|
39 |
+
"legacy": false,
|
40 |
+
"model_max_length": 1000000000000000019884624838656,
|
41 |
+
"pad_token": "</s>",
|
42 |
"sp_model_kwargs": {},
|
43 |
+
"tokenizer_class": "LlamaTokenizer",
|
44 |
+
"unk_token": "<unk>",
|
45 |
+
"use_default_system_prompt": false
|
46 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4600
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a932de1505296599656b46e27ac2c5c5ebc8f4ede3236a905b8dc9768ea8212c
|
3 |
size 4600
|