122 lines
2.6 KiB
Markdown
122 lines
2.6 KiB
Markdown
|
---
|
||
|
|
base_model: alpindale/Mistral-7B-v0.2-hf
|
||
|
|
tags:
|
||
|
|
- generated_from_trainer
|
||
|
|
model-index:
|
||
|
|
- name: AdamGrzesik/Samantha-PL-AG-Mistral-7B-v0.2
|
||
|
|
results: []
|
||
|
|
---
|
||
|
|
|
||
|
|
<!-- 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. -->
|
||
|
|
|
||
|
|
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
||
|
|
<details><summary>See axolotl config</summary>
|
||
|
|
|
||
|
|
axolotl version: `0.4.0`
|
||
|
|
```yaml
|
||
|
|
|
||
|
|
base_model: alpindale/Mistral-7B-v0.2-hf
|
||
|
|
model_type: MistralForCausalLM
|
||
|
|
tokenizer_type: LlamaTokenizer
|
||
|
|
is_mistral_derived_model: true
|
||
|
|
|
||
|
|
load_in_8bit: false
|
||
|
|
load_in_4bit: false
|
||
|
|
strict: false
|
||
|
|
|
||
|
|
datasets:
|
||
|
|
- path: /workspace/datasets/Samantha-PL-AG-axolotl.json
|
||
|
|
type: sharegpt
|
||
|
|
|
||
|
|
chat_template: chatml
|
||
|
|
|
||
|
|
dataset_prepared_path: last_run_prepared
|
||
|
|
val_set_size: 0.001
|
||
|
|
output_dir: /workspace/Samantha
|
||
|
|
|
||
|
|
sequence_len: 16384
|
||
|
|
sample_packing: true
|
||
|
|
pad_to_sequence_len: true
|
||
|
|
|
||
|
|
wandb_project:
|
||
|
|
wandb_entity:
|
||
|
|
wandb_watch:
|
||
|
|
wandb_run_id:
|
||
|
|
wandb_log_model:
|
||
|
|
|
||
|
|
gradient_accumulation_steps: 8
|
||
|
|
micro_batch_size: 3
|
||
|
|
num_epochs: 4
|
||
|
|
adam_beta2: 0.95
|
||
|
|
adam_epsilon: 0.00001
|
||
|
|
max_grad_norm: 1.0
|
||
|
|
lr_scheduler: cosine
|
||
|
|
learning_rate: 0.000005
|
||
|
|
optimizer: adamw_bnb_8bit
|
||
|
|
|
||
|
|
train_on_inputs: false
|
||
|
|
group_by_length: false
|
||
|
|
bf16: true
|
||
|
|
fp16: false
|
||
|
|
tf32: false
|
||
|
|
|
||
|
|
gradient_checkpointing: true
|
||
|
|
gradient_checkpointing_kwargs:
|
||
|
|
use_reentrant: true
|
||
|
|
early_stopping_patience:
|
||
|
|
resume_from_checkpoint:
|
||
|
|
local_rank:
|
||
|
|
logging_steps: 1
|
||
|
|
xformers_attention:
|
||
|
|
flash_attention: true
|
||
|
|
|
||
|
|
warmup_steps: 10
|
||
|
|
|
||
|
|
eval_steps: 73
|
||
|
|
eval_table_size:
|
||
|
|
eval_table_max_new_tokens:
|
||
|
|
eval_sample_packing: false
|
||
|
|
saves_per_epoch:
|
||
|
|
save_steps: 73
|
||
|
|
save_total_limit: 2
|
||
|
|
debug:
|
||
|
|
deepspeed: deepspeed_configs/zero3_bf16.json
|
||
|
|
weight_decay: 0.1
|
||
|
|
fsdp:
|
||
|
|
fsdp_config:
|
||
|
|
special_tokens:
|
||
|
|
eos_token: "<|im_end|>"
|
||
|
|
tokens:
|
||
|
|
- "<|im_start|>"
|
||
|
|
|
||
|
|
```
|
||
|
|
|
||
|
|
</details><br>
|
||
|
|
|
||
|
|
# AdamGrzesik/Samantha-PL-AG-Mistral-7B-v0.2
|
||
|
|
|
||
|
|
This model is a fine-tuned version of [alpindale/Mistral-7B-v0.2-hf](https://huggingface.co/alpindale/Mistral-7B-v0.2-hf) on the Samanta-PL-AG-axolotl dataset.
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
### Training hyperparameters
|
||
|
|
|
||
|
|
The following hyperparameters were used during training:
|
||
|
|
- learning_rate: 5e-06
|
||
|
|
- train_batch_size: 3
|
||
|
|
- eval_batch_size: 3
|
||
|
|
- seed: 42
|
||
|
|
- distributed_type: multi-GPU
|
||
|
|
- num_devices: 2
|
||
|
|
- gradient_accumulation_steps: 8
|
||
|
|
- total_train_batch_size: 48
|
||
|
|
- total_eval_batch_size: 6
|
||
|
|
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
|
||
|
|
- lr_scheduler_type: cosine
|
||
|
|
- lr_scheduler_warmup_steps: 10
|
||
|
|
- num_epochs: 4
|
||
|
|
|
||
|
|
|