axolotl version: 0.4.1
base_model: Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
type: sharegpt
conversation: chatml
- path: NewEden/Kalo-Opus-Instruct-22k-Refusal-Murdered
type: sharegpt
conversation: chatml
- path: Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
type: sharegpt
conversation: chatml
- path: NewEden/Gryphe-Sonnet-3.5-35k-Subset
type: sharegpt
conversation: chatml
- path: jeiku/Nitral_Medical_Dialog_Fixed
type: sharegpt
conversation: chatml
chat_template: chatml
val_set_size: 0.01
output_dir: ./outputs/out
adapter:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
sequence_len: 8192
# sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true
wandb_project: New8B
wandb_entity:
wandb_watch:
wandb_name: New8B
wandb_log_model:
gradient_accumulation_steps: 32
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00001
weight_decay: 0.05
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_ratio: 0.1
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 2
debug:
deepspeed:
fsdp:
fsdp_config:
special_tokens:
pad_token: <pad>
outputs/out
This model is a fine-tuned version of Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0138
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 32
- total_train_batch_size: 64
- total_eval_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 23
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4041 | 0.0084 | 1 | 1.5854 |
| 1.0445 | 0.2534 | 30 | 1.1313 |
| 0.9479 | 0.5069 | 60 | 1.0488 |
| 0.9697 | 0.7603 | 90 | 1.0288 |
| 0.9126 | 1.0090 | 120 | 1.0193 |
| 0.9006 | 1.2621 | 150 | 1.0156 |
| 0.9038 | 1.5153 | 180 | 1.0140 |
| 0.9095 | 1.7685 | 210 | 1.0138 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1