|
|
--- |
|
|
library_name: transformers |
|
|
base_model: AlexHung29629/Magistral-Small-2506 |
|
|
tags: |
|
|
- axolotl |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- AlexHung29629/rr-mg-segmented |
|
|
model-index: |
|
|
- name: fix_magistral3 |
|
|
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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) |
|
|
<details><summary>See axolotl config</summary> |
|
|
|
|
|
axolotl version: `0.11.0.dev0` |
|
|
```yaml |
|
|
base_model: AlexHung29629/Magistral-Small-2506 |
|
|
tokenizer_use_mistral_common: false |
|
|
|
|
|
plugins: |
|
|
- axolotl.integrations.liger.LigerPlugin |
|
|
liger_rope: true |
|
|
liger_rms_norm: true |
|
|
liger_glu_activation: true |
|
|
liger_fused_linear_cross_entropy: true |
|
|
|
|
|
#unfrozen_parameters: |
|
|
# - ^lm_head.weight$ |
|
|
# - ^model.layers.39.*$ |
|
|
|
|
|
datasets: |
|
|
- path: AlexHung29629/rr-mg-segmented |
|
|
type: input_output |
|
|
remove_unused_columns: false |
|
|
|
|
|
sequence_len: 8192 |
|
|
sample_packing: true |
|
|
eval_sample_packing: false |
|
|
pad_to_sequence_len: true |
|
|
|
|
|
use_tensorboard: true |
|
|
|
|
|
save_only_model: true |
|
|
gradient_accumulation_steps: 1 |
|
|
micro_batch_size: 1 |
|
|
num_epochs: 2 |
|
|
optimizer: adamw_torch_fused |
|
|
#optimizer: adamw_bnb_8bit |
|
|
lr_scheduler: cosine |
|
|
learning_rate: 5e-7 |
|
|
max_grad_norm: 1.0 |
|
|
|
|
|
adam_beta1: 0.9 |
|
|
adam_beta2: 0.95 |
|
|
adam_epsilon: 1e-8 |
|
|
|
|
|
bf16: true |
|
|
tf32: false |
|
|
|
|
|
warmup_ratio: 0.05 |
|
|
saves_per_epoch: 1 |
|
|
weight_decay: 0 |
|
|
|
|
|
|
|
|
train_on_inputs: false |
|
|
|
|
|
flash_attention: true |
|
|
#deepspeed: /workspace/output/zero3.json |
|
|
|
|
|
fsdp: |
|
|
- full_shard |
|
|
- auto_wrap |
|
|
|
|
|
fsdp_config: |
|
|
fsdp_limit_all_gathers: true |
|
|
fsdp_sync_module_states: true |
|
|
fsdp_offload_params: false |
|
|
fsdp_use_orig_params: true |
|
|
fsdp_cpu_ram_efficient_loading: true |
|
|
fsdp_activation_checkpointing: true |
|
|
fsdp_transformer_layer_cls_to_wrap: MistralDecoderLayer |
|
|
fsdp_state_dict_type: FULL_STATE_DICT |
|
|
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP |
|
|
seed: 42 |
|
|
|
|
|
hub_model_id: AlexHung29629/fix_magistral3 |
|
|
output_dir: /workspace/output/output_dir3 |
|
|
dataset_processes: 0 |
|
|
dataset_prepared_path: /workspace/output/dataset_prepared |
|
|
torch_compile: false |
|
|
|
|
|
added_tokens_overrides: |
|
|
32: "[ARGS]" |
|
|
33: "[CALL_ID]" |
|
|
|
|
|
``` |
|
|
|
|
|
</details><br> |
|
|
|
|
|
# fix_magistral3 |
|
|
|
|
|
This model is a fine-tuned version of [AlexHung29629/Magistral-Small-2506](https://huggingface.co/AlexHung29629/Magistral-Small-2506) on the AlexHung29629/rr-mg-segmented dataset. |
|
|
|
|
|
## 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-07 |
|
|
- train_batch_size: 1 |
|
|
- eval_batch_size: 1 |
|
|
- seed: 42 |
|
|
- distributed_type: multi-GPU |
|
|
- num_devices: 8 |
|
|
- total_train_batch_size: 8 |
|
|
- total_eval_batch_size: 8 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 3 |
|
|
- training_steps: 70 |
|
|
|
|
|
### Training results |
|
|
|
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.52.4 |
|
|
- Pytorch 2.7.1+cu126 |
|
|
- Datasets 3.6.0 |
|
|
- Tokenizers 0.21.1 |
