base_model: IntervitensInc/Llama-3.1-Minitron-4B-Width-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: NewEden/Claude-Instruct-5k
    type: sharegpt
    conversation: chatml
  - path: Magpie-Align/Magpie-Gemma2-Pro-200K-Filtered
    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: Neo4B
wandb_entity:
wandb_watch:
wandb_name: Neo4B
wandb_log_model:

gradient_accumulation_steps: 32
micro_batch_size: 2
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: deepspeed_configs/zero3.json
fsdp:
fsdp_config:

special_tokens:
  pad_token: <|finetune_right_pad_id|>

outputs/out

This model is a fine-tuned version of IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.5576

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: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 32
total_train_batch_size: 128
total_eval_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 27
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.2446	0.0070	1	2.0325
0.8915	0.2532	36	1.6714
0.8262	0.5064	72	1.5993
0.7705	0.7596	108	1.5687
0.7547	1.0015	144	1.5541
0.6979	1.2547	180	1.5614
0.6854	1.5079	216	1.5596
0.6836	1.7611	252	1.5576

Framework versions

Transformers 4.45.0.dev0
Pytorch 2.4.0+cu121
Datasets 2.20.0
Tokenizers 0.19.1

RichardErkhov/jeiku_-_Neo-e2-8bits

Original model description:

outputs/out

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RichardErkhov/
jeiku_-_Neo-e2-8bits