See axolotl config

axolotl version: 0.4.1

base_model: mistralai/Mistral-Nemo-Base-2407
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

chat_template: chatml

datasets:
  - path: PygTesting/pyg3v1
    type: sharegpt
    conversation: chatml

hub_model_id: PygTesting/pyg3v1-nemo-3ep-ckpts
hub_strategy: every_save
hf_use_auth_token: true

dataset_prepared_path: ./data/pyg3v1-data/tokenized
val_set_size: 0.0
output_dir: ./data/pyg3v1-nemo-2eps-out

sequence_len: 8192
sample_packing: true
#eval_sample_packing: false
pad_to_sequence_len: true

wandb_project: pyg3v1-nemo
wandb_entity:
wandb_watch:
wandb_name: more_eps_lower_lr
wandb_log_model:
 
 #unsloth_cross_entropy_loss: true

gradient_accumulation_steps: 4
micro_batch_size: 4
num_epochs: 3
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 0.0000075

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: 0.03
evals_per_epoch: 0
eval_table_size:
saves_per_epoch: 3
debug:
deepspeed: deepspeed_configs/zero1.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
  pad_token: <pad>

pyg3v1-nemo-3ep-ckpts

This model is a fine-tuned version of mistralai/Mistral-Nemo-Base-2407 on the None 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: 7.5e-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• total_eval_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 29
• num_epochs: 3

Training results

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.4.0+rocm6.1
• Datasets 2.21.0
• Tokenizers 0.19.1