Hemanth-thunder
commited on
Commit
•
1f8e404
1
Parent(s):
f1d7e63
Hemanth-thunder/aimo-lora-deepseek-math
Browse files- README.md +20 -25
- adapter_config.json +7 -7
- adapter_model.safetensors +2 -2
- special_tokens_map.json +6 -7
- tokenizer.json +0 -0
- tokenizer_config.json +14 -104
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
-
base_model:
|
3 |
library_name: peft
|
4 |
-
license:
|
5 |
tags:
|
6 |
- trl
|
7 |
- sft
|
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# phi-3-mini-LoRA
|
18 |
|
19 |
-
This model is a fine-tuned version of [
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -39,36 +39,31 @@ More information needed
|
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 0.0001
|
41 |
- train_batch_size: 1
|
42 |
-
- eval_batch_size:
|
43 |
- seed: 42
|
44 |
-
- gradient_accumulation_steps: 2
|
45 |
-
- total_train_batch_size: 2
|
46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
- lr_scheduler_type: linear
|
48 |
- lr_scheduler_warmup_ratio: 0.1
|
49 |
-
- num_epochs:
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
| 0.
|
69 |
-
| 0.2968 | 2.55 | 7500 | 0.3525 |
|
70 |
-
| 0.2968 | 2.72 | 8000 | 0.3526 |
|
71 |
-
| 0.3094 | 2.89 | 8500 | 0.3525 |
|
72 |
|
73 |
|
74 |
### Framework versions
|
|
|
1 |
---
|
2 |
+
base_model: deepseek-ai/deepseek-math-7b-base
|
3 |
library_name: peft
|
4 |
+
license: other
|
5 |
tags:
|
6 |
- trl
|
7 |
- sft
|
|
|
16 |
|
17 |
# phi-3-mini-LoRA
|
18 |
|
19 |
+
This model is a fine-tuned version of [deepseek-ai/deepseek-math-7b-base](https://huggingface.co/deepseek-ai/deepseek-math-7b-base) on the None dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.4014
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 0.0001
|
41 |
- train_batch_size: 1
|
42 |
+
- eval_batch_size: 1
|
43 |
- seed: 42
|
|
|
|
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_ratio: 0.1
|
47 |
+
- num_epochs: 1
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
+
| 0.4522 | 0.07 | 500 | 0.4533 |
|
54 |
+
| 0.4512 | 0.14 | 1000 | 0.4301 |
|
55 |
+
| 0.4386 | 0.21 | 1500 | 0.4199 |
|
56 |
+
| 0.4268 | 0.28 | 2000 | 0.4144 |
|
57 |
+
| 0.4167 | 0.35 | 2500 | 0.4104 |
|
58 |
+
| 0.3955 | 0.42 | 3000 | 0.4092 |
|
59 |
+
| 0.436 | 0.49 | 3500 | 0.4062 |
|
60 |
+
| 0.3912 | 0.55 | 4000 | 0.4057 |
|
61 |
+
| 0.425 | 0.62 | 4500 | 0.4036 |
|
62 |
+
| 0.4066 | 0.69 | 5000 | 0.4026 |
|
63 |
+
| 0.3963 | 0.76 | 5500 | 0.4016 |
|
64 |
+
| 0.3862 | 0.83 | 6000 | 0.4019 |
|
65 |
+
| 0.3902 | 0.9 | 6500 | 0.4015 |
|
66 |
+
| 0.4364 | 0.97 | 7000 | 0.4014 |
|
|
|
|
|
|
|
67 |
|
68 |
|
69 |
### Framework versions
|
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,
|
@@ -9,23 +9,23 @@
|
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
"loftq_config": {},
|
12 |
-
"lora_alpha":
|
13 |
"lora_dropout": 0.05,
|
14 |
"megatron_config": null,
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
-
"r":
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
"v_proj",
|
23 |
"o_proj",
|
24 |
-
"down_proj",
|
25 |
-
"k_proj",
|
26 |
-
"up_proj",
|
27 |
"gate_proj",
|
28 |
-
"
|
|
|
|
|
|
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_rslora": false
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-math-7b-base",
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
"loftq_config": {},
|
12 |
+
"lora_alpha": 32,
|
13 |
"lora_dropout": 0.05,
|
14 |
"megatron_config": null,
|
15 |
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
+
"r": 64,
|
19 |
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
"v_proj",
|
23 |
"o_proj",
|
|
|
|
|
|
|
24 |
"gate_proj",
|
25 |
+
"k_proj",
|
26 |
+
"down_proj",
|
27 |
+
"q_proj",
|
28 |
+
"up_proj"
|
29 |
],
|
30 |
"task_type": "CAUSAL_LM",
|
31 |
"use_rslora": false
|
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 sha256:55d4dd2d8f5dca57eb6f2d585953032833e9fb028643fdf5c2a12c0c661b190e
|
3 |
+
size 299884176
|
special_tokens_map.json
CHANGED
@@ -1,21 +1,20 @@
|
|
1 |
{
|
2 |
"bos_token": {
|
3 |
-
"content": "
|
4 |
"lstrip": false,
|
5 |
-
"normalized":
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
-
"content": "
|
11 |
"lstrip": false,
|
12 |
-
"normalized":
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token":
|
17 |
-
|
18 |
-
"content": "<unk>",
|
19 |
"lstrip": false,
|
20 |
"normalized": false,
|
21 |
"rstrip": false,
|
|
|
1 |
{
|
2 |
"bos_token": {
|
3 |
+
"content": "<|begin▁of▁sentence|>",
|
4 |
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
+
"content": "<|end▁of▁sentence|>",
|
11 |
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
|
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
"rstrip": false,
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -2,129 +2,39 @@
|
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": true,
|
4 |
"added_tokens_decoder": {
|
5 |
-
"
|
6 |
-
"content": "
|
7 |
"lstrip": false,
|
8 |
-
"normalized":
|
9 |
"rstrip": false,
|
10 |
"single_word": false,
|
11 |
"special": true
|
12 |
},
|
13 |
-
"
|
14 |
-
"content": "
|
15 |
"lstrip": false,
|
16 |
-
"normalized":
|
17 |
"rstrip": false,
|
18 |
"single_word": false,
|
19 |
"special": true
|
20 |
},
|
21 |
-
"
|
22 |
-
"content": "
|
23 |
-
"lstrip": false,
|
24 |
-
"normalized": false,
|
25 |
-
"rstrip": true,
|
26 |
-
"single_word": false,
|
27 |
-
"special": false
|
28 |
-
},
|
29 |
-
"32000": {
|
30 |
-
"content": "<|endoftext|>",
|
31 |
"lstrip": false,
|
32 |
"normalized": false,
|
33 |
"rstrip": false,
|
34 |
"single_word": false,
|
35 |
"special": true
|
36 |
-
},
|
37 |
-
"32001": {
|
38 |
-
"content": "<|assistant|>",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": false,
|
41 |
-
"rstrip": true,
|
42 |
-
"single_word": false,
|
43 |
-
"special": true
|
44 |
-
},
|
45 |
-
"32002": {
|
46 |
-
"content": "<|placeholder1|>",
|
47 |
-
"lstrip": false,
|
48 |
-
"normalized": false,
|
49 |
-
"rstrip": true,
|
50 |
-
"single_word": false,
|
51 |
-
"special": true
|
52 |
-
},
|
53 |
-
"32003": {
|
54 |
-
"content": "<|placeholder2|>",
|
55 |
-
"lstrip": false,
|
56 |
-
"normalized": false,
|
57 |
-
"rstrip": true,
|
58 |
-
"single_word": false,
|
59 |
-
"special": true
|
60 |
-
},
|
61 |
-
"32004": {
|
62 |
-
"content": "<|placeholder3|>",
|
63 |
-
"lstrip": false,
|
64 |
-
"normalized": false,
|
65 |
-
"rstrip": true,
|
66 |
-
"single_word": false,
|
67 |
-
"special": true
|
68 |
-
},
|
69 |
-
"32005": {
|
70 |
-
"content": "<|placeholder4|>",
|
71 |
-
"lstrip": false,
|
72 |
-
"normalized": false,
|
73 |
-
"rstrip": true,
|
74 |
-
"single_word": false,
|
75 |
-
"special": true
|
76 |
-
},
|
77 |
-
"32006": {
|
78 |
-
"content": "<|system|>",
|
79 |
-
"lstrip": false,
|
80 |
-
"normalized": false,
|
81 |
-
"rstrip": true,
|
82 |
-
"single_word": false,
|
83 |
-
"special": true
|
84 |
-
},
|
85 |
-
"32007": {
|
86 |
-
"content": "<|end|>",
|
87 |
-
"lstrip": false,
|
88 |
-
"normalized": false,
|
89 |
-
"rstrip": true,
|
90 |
-
"single_word": false,
|
91 |
-
"special": true
|
92 |
-
},
|
93 |
-
"32008": {
|
94 |
-
"content": "<|placeholder5|>",
|
95 |
-
"lstrip": false,
|
96 |
-
"normalized": false,
|
97 |
-
"rstrip": true,
|
98 |
-
"single_word": false,
|
99 |
-
"special": true
|
100 |
-
},
|
101 |
-
"32009": {
|
102 |
-
"content": "<|placeholder6|>",
|
103 |
-
"lstrip": false,
|
104 |
-
"normalized": false,
|
105 |
-
"rstrip": true,
|
106 |
-
"single_word": false,
|
107 |
-
"special": true
|
108 |
-
},
|
109 |
-
"32010": {
|
110 |
-
"content": "<|user|>",
|
111 |
-
"lstrip": false,
|
112 |
-
"normalized": false,
|
113 |
-
"rstrip": true,
|
114 |
-
"single_word": false,
|
115 |
-
"special": true
|
116 |
}
|
117 |
},
|
118 |
-
"bos_token": "
|
119 |
-
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
|
120 |
"clean_up_tokenization_spaces": false,
|
121 |
-
"eos_token": "
|
122 |
-
"legacy":
|
123 |
-
"model_max_length":
|
124 |
-
"pad_token": "
|
125 |
-
"padding_side": "left",
|
126 |
"sp_model_kwargs": {},
|
127 |
"tokenizer_class": "LlamaTokenizer",
|
128 |
-
"unk_token":
|
129 |
"use_default_system_prompt": false
|
130 |
}
|
|
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": true,
|
4 |
"added_tokens_decoder": {
|
5 |
+
"100000": {
|
6 |
+
"content": "<|begin▁of▁sentence|>",
|
7 |
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
"rstrip": false,
|
10 |
"single_word": false,
|
11 |
"special": true
|
12 |
},
|
13 |
+
"100001": {
|
14 |
+
"content": "<|end▁of▁sentence|>",
|
15 |
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
"rstrip": false,
|
18 |
"single_word": false,
|
19 |
"special": true
|
20 |
},
|
21 |
+
"100002": {
|
22 |
+
"content": "[PAD]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
"lstrip": false,
|
24 |
"normalized": false,
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
}
|
29 |
},
|
30 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
|
|
31 |
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "<|end▁of▁sentence|>",
|
33 |
+
"legacy": true,
|
34 |
+
"model_max_length": 4096,
|
35 |
+
"pad_token": "[PAD]",
|
|
|
36 |
"sp_model_kwargs": {},
|
37 |
"tokenizer_class": "LlamaTokenizer",
|
38 |
+
"unk_token": null,
|
39 |
"use_default_system_prompt": false
|
40 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4856
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07499305a79f43d712f931d36cda48241ab9bcdb9e62eca12ee76486978e406f
|
3 |
size 4856
|