Downloads · 30 days
4
8% of all-time downloads
shisa-ai/ablation-31-rafathenev2.reasoning-shisa-v2-llama3.1-8b
ablation-31-rafathenev2.reasoning-shisa-v2-llama3.1-8b is a text generation model from shisa-ai. Use it when you need the model to write or continue text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
4
8% of all-time downloads
All-time downloads
52
Public
Parameters
8B
16.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.1 GB · 100%
From the Hugging Face model README
axolotl version: 0.6.0
# train w/ shisa-ai/shisa-v1-athenev2-reannotated-filtered
base_model: /fsx2/outputs/ablation-26-reasoning.inputs-shisa-v2-llama-3.1-8b-lr8e6
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
# User Liger
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true
chat_template: llama3
datasets:
- path: shisa-ai/shisa-v1-athenev2-reannotated-filtered
# type: sharegpt deprecated
type: chat_template
field_messages: conversations
message_field_role: from
message_field_content: value
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./outputs/ablation-31-rafathenev2.reasoning-shisa-v2-llama3.1-8b
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
# marginal difference
neftune_noise_alpha: 5
use_wandb: true
wandb_project: shisa-v2
wandb_entity: augmxnt
wandb_name: ablation-31-rafathenev2.reasoning-shisa-v2-llama3.1-8b
gradient_accumulation_steps: 2
micro_batch_size: 4
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: linear
learning_rate: 8e-6
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_ratio: 0.05
evals_per_epoch: 2
eval_table_size:
saves_per_epoch: 0
save_total_limit: 1 # Only store a single checkpoint
debug:
deepspeed: zero3_bf16.json
weight_decay: 1e-4
fsdp:
fsdp_config:
special_tokens:
pad_token: <|end_of_text|>
</details><br>
This model was trained from scratch on the shisa-ai/shisa-v1-athenev2-reannotated-filtered 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 |
|---|---|---|---|
| 1.1097 | 0.0059 | 1 | 0.7727 |
| 0.6367 | 0.5 | 85 | 0.4654 |
| 0.616 | 1.0 | 170 | 0.4435 |
| 0.4771 | 1.5 | 255 | 0.4420 |
| 0.4612 | 2.0 | 340 | 0.4351 |
| 0.4139 | 2.5 | 425 | 0.4498 |
| 0.4211 | 3.0 | 510 | 0.4482 |