Sponsored by
APIMart
YoungPanda / Test1
Model's Last Updated: 2024年3月9日
text-generation
Introduction of Test1
Model Details of Test1
See axolotl config
axolotl version:
0.4.0
base_model: mistralai/Mixtral-8x7B-v0.1
model_type: AutoModelForCausalLM
tokenizer_type: LlamaTokenizer
trust_remote_code: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: Drewskidang/chatlaw
type: sharegpt
conversation: chatml
- path: Drewskidang/tool
type: sharegpt
conversation: chatml
- path: Drewskidang/pro
type: sharegpt
conversation: chatml
dataset_prepared_path: last_run_prepared
val_set_size: 0.02
output_dir: ./qlora-out
unfrozen_parameters:
# - lm_head.*
# - model.embed_tokens.*
# - model.layers.2[0-9]+.block_sparse_moe.gate.*
# - model.layers.2[0-9]+.block_sparse_moe.experts.*
# - model.layers.3[0-9]+.block_sparse_moe.gate.*
# - model.layers.3[0-9]+.block_sparse_moe.experts.*
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false
lora_r: #32
lora_alpha: #16
lora_dropout: #0.05
lora_target_linear: #true
lora_fan_in_fan_out:
wandb_project: mixtralfsdp
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 1
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
flash_attention: true
flash_attn_cross_entropy: false
flash_attn_rms_norm: true
flash_attn_fuse_qkv: false
flash_attn_fuse_mlp: true
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-4
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:
weight_decay: 0.0
#fsdp:
#- full_shard
#fsdp_config:
#fsdp_transformer_layer_cls_to_wrap: MixtralSparseMoeBlock
special_tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"
tokens: # these are delimiters
- "<|im_start|>"
- "<|im_end|>"
qlora-out
This model is a fine-tuned version of mistralai/Mixtral-8x7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8654
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
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 16
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=0.0001
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2878 | 0.02 | 1 | 1.3536 |
| 0.9516 | 0.26 | 16 | 0.9857 |
| 0.911 | 0.52 | 32 | 0.9150 |
| 0.8027 | 0.79 | 48 | 0.8654 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.0
Runs of YoungPanda Test1 on huggingface.co
4
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs
More Information About Test1 huggingface.co Model
Url of Test1
Test1 huggingface.co Url
Provider of Test1 huggingface.co
Other API from YoungPanda