Crystalcareai
commited on
Commit
•
65a5134
1
Parent(s):
093c261
Added Training Config Files
Browse filesAdding YAML files detailing the parameters used for mergekit and training. These configurations were frequently requested.
Training-Configs/AxolotlConfig.yml
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
base_model: Crystalcareai/Qwen-1.5-8x7B
|
2 |
+
model_type: Qwen2ForCausalLM
|
3 |
+
tokenizer_type: Qwen2Tokenizer
|
4 |
+
trust_remote_code: true
|
5 |
+
|
6 |
+
|
7 |
+
load_in_8bit: false
|
8 |
+
load_in_4bit: true
|
9 |
+
strict: false
|
10 |
+
|
11 |
+
|
12 |
+
datasets:
|
13 |
+
- path: Crystalcareai/MoD
|
14 |
+
type: sharegpt
|
15 |
+
dataset_prepared_path: last_run_prepared
|
16 |
+
val_set_size: 0.0
|
17 |
+
output_dir: ./qlora-out
|
18 |
+
|
19 |
+
|
20 |
+
model_config:
|
21 |
+
output_router_logits: true
|
22 |
+
|
23 |
+
|
24 |
+
adapter: qlora
|
25 |
+
lora_model_dir:
|
26 |
+
|
27 |
+
|
28 |
+
sequence_len: 32768
|
29 |
+
sample_packing: true
|
30 |
+
pad_to_sequence_len: true
|
31 |
+
|
32 |
+
|
33 |
+
lora_r: 32
|
34 |
+
lora_alpha: 16
|
35 |
+
lora_dropout: 0.05
|
36 |
+
lora_target_linear: true
|
37 |
+
lora_fan_in_fan_out:
|
38 |
+
|
39 |
+
|
40 |
+
gradient_accumulation_steps: 2
|
41 |
+
micro_batch_size: 2
|
42 |
+
num_epochs: 4
|
43 |
+
optimizer: adamw_bnb_8bit
|
44 |
+
lr_scheduler: cosine
|
45 |
+
learning_rate: 0.0002
|
46 |
+
|
47 |
+
|
48 |
+
train_on_inputs: false
|
49 |
+
group_by_length: false
|
50 |
+
bf16: true
|
51 |
+
fp16:
|
52 |
+
tf32: false
|
53 |
+
|
54 |
+
|
55 |
+
gradient_checkpointing: true
|
56 |
+
early_stopping_patience:
|
57 |
+
resume_from_checkpoint:
|
58 |
+
local_rank:
|
59 |
+
logging_steps: 1
|
60 |
+
xformers_attention:
|
61 |
+
flash_attention: true
|
62 |
+
|
63 |
+
|
64 |
+
warmup_steps: 10
|
65 |
+
evals_per_epoch: 4
|
66 |
+
eval_table_size:
|
67 |
+
eval_max_new_tokens: 128
|
68 |
+
saves_per_epoch: 4
|
69 |
+
debug:
|
70 |
+
deepspeed: deepspeed_configs/zero2.json
|
71 |
+
weight_decay: 0.0
|
72 |
+
fsdp:
|
73 |
+
fsdp_config:
|
74 |
+
special_tokens:
|
Training-Configs/Qwen1.5-8x7b-Mergekit-Config.yml
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
gate_mode: random
|
2 |
+
dtype: bfloat16
|
3 |
+
experts_per_token: 2
|
4 |
+
experts:
|
5 |
+
- source_model: Crystalcareai/Qwen1.5-7B-MoD100k
|
6 |
+
positive_prompts:
|
7 |
+
- "You are a versatile assistant for a wide array of inquiries and daily assistance."
|
8 |
+
- source_model: Crystalcareai/Qwen1.5-7B-MoD100k
|
9 |
+
positive_prompts:
|
10 |
+
- "You are a tech and programming guide for various skill levels, from beginners to experts."
|
11 |
+
- source_model: Crystalcareai/Qwen1.5-7B-MoD100k
|
12 |
+
positive_prompts:
|
13 |
+
- "You are a world explorer - offering diverse insights on culture, and social studies."
|
14 |
+
- source_model: Crystalcareai/Qwen1.5-7B-MoD100k
|
15 |
+
positive_prompts:
|
16 |
+
- "You are a financial navigator for saving, investing, and managing money wisely."
|
17 |
+
- source_model: Crystalcareai/Qwen1.5-7B-MoD100k
|
18 |
+
positive_prompts:
|
19 |
+
- "You are an educational ally, supporting learning across a broad spectrum of subjects."
|
20 |
+
- source_model: Crystalcareai/Qwen1.5-7B-MoD100k
|
21 |
+
positive_prompts:
|
22 |
+
- "You are a well-being companion, offering advice on physical health, mental wellness, and fitness."
|
23 |
+
- source_model: Crystalcareai/Qwen1.5-7B-MoD100k
|
24 |
+
positive_prompts:
|
25 |
+
- "You are a creative muse for writing, arts, and all forms of creative expression."
|
26 |
+
- source_model: Crystalcareai/Qwen1.5-7B-MoD100k
|
27 |
+
positive_prompts:
|
28 |
+
- "You are a philosopher and interpreter and explorer of the human condition."
|