Sponsored by
APIMaster
YoungPanda / SFT_MISTRAL
Model's Last Updated: February 10 2024
text-generation
Introduction of SFT_MISTRAL
Model Details of SFT_MISTRAL
See axolotl config
axolotl version:
0.4.0
base_model: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: Drewskidang/shareinstruct
type: sharegpt
conversation: chatml
- path: Drewskidang/share
type: sharegpt
conversation: chatml
- path: Drewskidang/share
type: sharegpt
conversation: chatml
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./out
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 3
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000005
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
warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"
tokens: # these are delimiters
- "<|im_start|>"
- "<|im_end|>"
out
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1559
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: 5e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6175 | 0.22 | 1 | 1.6889 |
| 1.6196 | 0.44 | 2 | 1.6716 |
| 1.6256 | 0.67 | 3 | 1.5553 |
| 1.5162 | 0.89 | 4 | 1.3840 |
| 1.3351 | 1.06 | 5 | 1.3397 |
| 1.2556 | 1.28 | 6 | 1.2445 |
| 1.2102 | 1.5 | 7 | 1.3734 |
| 1.3125 | 1.72 | 8 | 1.2937 |
| 1.2536 | 1.94 | 9 | 1.2959 |
| 1.2171 | 2.11 | 10 | 1.1937 |
| 1.1095 | 2.33 | 11 | 1.1759 |
| 1.0971 | 2.56 | 12 | 1.1559 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.0.1
- Datasets 2.17.0
- Tokenizers 0.15.0
Runs of YoungPanda SFT_MISTRAL on huggingface.co
13
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About SFT_MISTRAL huggingface.co Model
Url of SFT_MISTRAL
SFT_MISTRAL huggingface.co Url
Provider of SFT_MISTRAL huggingface.co
Other API from YoungPanda
Total runs:
6
Run Growth:
0
Growth Rate:
0.00%
Total runs:
6
Run Growth:
0
Growth Rate:
0.00%
Total runs:
2
Run Growth:
0
Growth Rate:
0.00%
Total runs:
0
Run Growth:
0
Growth Rate:
0.00%