You can deploy this model and start earning money today!

Edens-Gate/
TinyMagnum-r2-exl2

Name: TinyMagnum-r2-exl2
Availability: InStock

transformers

generated_from_trainer

IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml

finetune

other

endpoints_compatible

Views

No views yet

exl2 quant (measurement.json in main branch)

check revisions for quants

See axolotl config

axolotl version: 0.4.1

yaml

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: MangoHQ/Gryphe-3.5-16k-Subset
    type: sharegpt
    conversation: chatml
  - path: Epiculous/Synthstruct-Gens-v1-Filtered-n-Cleaned
    type: sharegpt
    conversation: chatml
  - path: anthracite-org/Stheno-Data-Filtered
    type: sharegpt
    conversation: chatml
  - path: Epiculous/SynthRP-Gens-v1-Filtered-n-Cleaned
    type: sharegpt
    conversation: chatml
  - path: lodrick-the-lafted/NopmWritingStruct
    type: sharegpt
    conversation: chatml
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    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: 16384
# sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

wandb_project: tinymagnumv2
wandb_entity:
wandb_watch:
wandb_name: tinymagnumv2
wandb_log_model:

gradient_accumulation_steps: 32
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00002
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: 1

debug:
deepspeed:
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: 1.2014

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: 2e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 32
total_train_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 36
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.6733	0.0051	1	1.6590
1.4425	0.2523	49	1.3040
1.3564	0.5047	98	1.2451
1.333	0.7570	147	1.2201
1.2936	1.0093	196	1.2077
1.2235	1.2462	245	1.2041
1.2651	1.4986	294	1.2018
1.238	1.7509	343	1.2014

Framework versions

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

Edens-Gate/TinyMagnum-r2-exl2

exl2 quant (measurement.json in main branch)

check revisions for quants

outputs/out

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Edens-Gate/
TinyMagnum-r2-exl2