Model save
Browse files- README.md +134 -0
- adapter_config.json +31 -0
- adapter_model.safetensors +3 -0
- config.json +26 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +45 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
7 |
+
model-index:
|
8 |
+
- name: nohto-v0-1e
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
16 |
+
<details><summary>See axolotl config</summary>
|
17 |
+
|
18 |
+
axolotl version: `0.4.0`
|
19 |
+
```yaml
|
20 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
21 |
+
model_type: AutoModelForCausalLM
|
22 |
+
tokenizer_type: LlamaTokenizer
|
23 |
+
is_mistral_derived_model: true
|
24 |
+
load_in_8bit: false
|
25 |
+
load_in_4bit: false
|
26 |
+
strict: false
|
27 |
+
chat_template: inst
|
28 |
+
|
29 |
+
datasets:
|
30 |
+
- path: ./data/nohto/training.jsonl
|
31 |
+
type: sharegpt
|
32 |
+
|
33 |
+
dataset_prepared_path: last_run_prepared
|
34 |
+
val_set_size: 0.1
|
35 |
+
output_dir: ../nohto-v0-1e
|
36 |
+
|
37 |
+
adapter: lora
|
38 |
+
lora_model_dir:
|
39 |
+
|
40 |
+
sequence_len: 4096
|
41 |
+
sample_packing: true
|
42 |
+
pad_to_sequence_len: true
|
43 |
+
|
44 |
+
lora_r: 16
|
45 |
+
lora_alpha: 32
|
46 |
+
lora_dropout: 0.1
|
47 |
+
lora_target_linear: true
|
48 |
+
lora_fan_in_fan_out:
|
49 |
+
|
50 |
+
eval_sample_packing: false
|
51 |
+
|
52 |
+
hub_model_id: dyang415/nohto-v0-1e
|
53 |
+
|
54 |
+
wandb_project: nohto
|
55 |
+
wandb_name: nohto-v0
|
56 |
+
wandb_log_model: end
|
57 |
+
|
58 |
+
gradient_accumulation_steps: 4
|
59 |
+
micro_batch_size: 2
|
60 |
+
num_epochs: 1
|
61 |
+
optimizer: paged_adamw_8bit
|
62 |
+
lr_scheduler: cosine
|
63 |
+
learning_rate: 0.0002
|
64 |
+
|
65 |
+
train_on_inputs: false
|
66 |
+
group_by_length: false
|
67 |
+
bf16: auto
|
68 |
+
fp16:
|
69 |
+
tf32: false
|
70 |
+
|
71 |
+
gradient_checkpointing: true
|
72 |
+
early_stopping_patience:
|
73 |
+
resume_from_checkpoint:
|
74 |
+
local_rank:
|
75 |
+
logging_steps: 1
|
76 |
+
xformers_attention:
|
77 |
+
flash_attention: true
|
78 |
+
|
79 |
+
warmup_steps: 10
|
80 |
+
eval_steps: 0.2
|
81 |
+
save_steps: 0.1
|
82 |
+
eval_max_new_tokens: 128
|
83 |
+
debug:
|
84 |
+
deepspeed:
|
85 |
+
weight_decay: 0.0
|
86 |
+
fsdp:
|
87 |
+
fsdp_config:
|
88 |
+
|
89 |
+
```
|
90 |
+
|
91 |
+
</details><br>
|
92 |
+
|
93 |
+
# nohto-v0-1e
|
94 |
+
|
95 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
|
96 |
+
|
97 |
+
## Model description
|
98 |
+
|
99 |
+
More information needed
|
100 |
+
|
101 |
+
## Intended uses & limitations
|
102 |
+
|
103 |
+
More information needed
|
104 |
+
|
105 |
+
## Training and evaluation data
|
106 |
+
|
107 |
+
More information needed
|
108 |
+
|
109 |
+
## Training procedure
|
110 |
+
|
111 |
+
### Training hyperparameters
|
112 |
+
|
113 |
+
The following hyperparameters were used during training:
|
114 |
+
- learning_rate: 0.0002
|
115 |
+
- train_batch_size: 2
|
116 |
+
- eval_batch_size: 2
|
117 |
+
- seed: 42
|
118 |
+
- distributed_type: multi-GPU
|
119 |
+
- num_devices: 2
|
120 |
+
- gradient_accumulation_steps: 4
|
121 |
+
- total_train_batch_size: 16
|
122 |
+
- total_eval_batch_size: 4
|
123 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
124 |
+
- lr_scheduler_type: cosine
|
125 |
+
- lr_scheduler_warmup_steps: 10
|
126 |
+
- num_epochs: 1
|
127 |
+
|
128 |
+
### Framework versions
|
129 |
+
|
130 |
+
- PEFT 0.7.0
|
131 |
+
- Transformers 4.37.0
|
132 |
+
- Pytorch 2.0.1+cu117
|
133 |
+
- Datasets 2.17.1
|
134 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 32,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 16,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"up_proj",
|
23 |
+
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"k_proj",
|
26 |
+
"o_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"down_proj"
|
29 |
+
],
|
30 |
+
"task_type": "CAUSAL_LM"
|
31 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c5303d7e75b91849db16f8fc6a7620ee0ee08abcb643ca801b3666340083bd6
|
3 |
+
size 102820600
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 1000000.0,
|
20 |
+
"sliding_window": null,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.37.0",
|
24 |
+
"use_cache": false,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 1000000000000000019884624838656,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"trust_remote_code": false,
|
42 |
+
"unk_token": "<unk>",
|
43 |
+
"use_default_system_prompt": false,
|
44 |
+
"use_fast": true
|
45 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:facf4493f989d8066f24f726bc84f91dce52d1343027a2c3fcac9f3038b868e6
|
3 |
+
size 4795
|