Downloads · 30 days
14
32% of all-time downloads
manishiitg/open-aditi-chat-hi-1.28-llama3
open-aditi-chat-hi-1.28-llama3 is a machine learning model from manishiitg. 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 other.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
14
32% of all-time downloads
All-time downloads
44
Public
Repo size
1.2 GB
Likes
0
Public
Click a slice to open those files.
.safetensors168 MB · 95%
From the Hugging Face model README
axolotl version: 0.4.0
base_model: meta-llama/Meta-Llama-3-8B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: true
strict: false
datasets:
- path: manishiitg/aditi-syn-train-v5
type: completion
# 25 has only sythentic data, and has judge removed data
# 26 = 25 + caybara + robots
# 27 = ful capybara and robots -- this data bad
# 28 = only full capybara
hub_model_id: manishiitg/open-aditi-chat-hi-1.28-llama3
hf_use_auth_token: true
wandb_project: open-aditi-chat-hi-1.28-llama3
dataset_prepared_path: manishiitg
push_dataset_to_hub: manishiitg
val_set_size: .1
output_dir: /sky-notebook/manishiitg/open-aditi-chat-hi-1.28-llama3
adapter: qlora
lora_model_dir:
save_safetensors: true
sequence_len: 2048
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
wandb_entity:
wandb_watch:
wandb_run_id:
wandb_log_model:
gradient_accumulation_steps: 8
micro_batch_size: 6
num_epochs: 1
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
auto_resume_from_checkpoints: true ## manage check point resume from here
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 10
evals_per_epoch: 2
eval_table_size:
eval_table_max_new_tokens: 128
save_steps: 20 ## increase based on your dataset
save_strategy: steps
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
pad_token: <|end_of_text|>
</details><br>
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on an unknown dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6792 | 0.01 | 1 | 2.1170 |
| 0.9358 | 0.5 | 70 | 1.4312 |
| 0.9024 | 0.99 | 140 | 1.4011 |