Downloads · 30 days
7
21% of all-time downloads
Mistral-7B-Instruct-v0.2-ft
Burhan02/Mistral-7B-Instruct-v0.2-ft
Mistral-7B-Instruct-v0.2-ft is a machine learning model from Burhan02. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
33
Public
Repo size
3.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin168 MB · 50%
At a glance
- Library
- peft
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- Apr 30, 2024
- Updated
- May 2, 2024
- SHA
- 33b4a3d8
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
<details><summary>See axolotl config</summary>
axolotl version: 0.4.0
base_model: mistralai/Mistral-7B-Instruct-v0.2
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: data.jsonl
ds_type: json
type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./mistral-out
adapter: qlora
lora_model_dir:
hub_model_id: Burhan02/Mistral-7B-Instruct-v0.2-ft
hub_strategy: every_save
hf_use_auth_token: true
sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
- gate_proj
- down_proj
- up_proj
- q_proj
- v_proj
- k_proj
- o_proj
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 18
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3
warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
Mistral-7B-Instruct-v0.2-ft
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1573
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 18
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2077 | 1.0 | 1 | 0.3832 |
| 0.1985 | 2.0 | 2 | 0.3782 |
| 0.1979 | 2.0 | 3 | 0.3553 |
| 0.1901 | 3.0 | 4 | 0.3147 |
| 0.1624 | 3.0 | 5 | 0.2756 |
| 0.1489 | 4.0 | 6 | 0.2525 |
| 0.1342 | 4.0 | 7 | 0.2383 |
| 0.1137 | 5.0 | 8 | 0.2228 |
| 0.1026 | 5.0 | 9 | 0.2040 |
| 0.1001 | 6.0 | 10 | 0.1905 |
| 0.0828 | 6.0 | 11 | 0.1816 |
| 0.0746 | 7.0 | 12 | 0.1751 |
| 0.0687 | 7.0 | 13 | 0.1707 |
| 0.0544 | 8.0 | 14 | 0.1654 |
| 0.0526 | 8.0 | 15 | 0.1620 |
| 0.0469 | 9.0 | 16 | 0.1591 |
| 0.048 | 9.0 | 17 | 0.1575 |
| 0.0392 | 10.0 | 18 | 0.1573 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Library
- peft
- Type
- mistral
- License
- apache-2.0
- Created
- Apr 30, 2024
- Updated
- May 2, 2024