Zoyd/shisa-ai_shisa-v1-phi3-14b-4_0bpw_exl2

Exllamav2 quant (exl2 / 4.0 bpw) made with ExLlamaV2 v0.0.21

Other EXL2 quants:

Quant	Model Size	lm_head
2.2	4032 MB	6
2.5	4500 MB	6
3.0	5312 MB	6
3.5	6124 MB	6
3.75	6531 MB	6
4.0	6937 MB	6
4.25	7340 MB	6
5.0	8554 MB	6
6.0	10210 MB	8
6.5	11018 MB	8
8.0	12332 MB	8

See axolotl config

axolotl version: 0.4.0

base_model: microsoft/Phi-3-medium-128k-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true

load_in_8bit: false
load_in_4bit: false
strict: false

use_wandb: true
wandb_project: shisa-v2
wandb_entity: augmxnt
wandb_name: shisa-llama3-70b-v1.8e6

chat_template: chatml
datasets:
  - path: augmxnt/ultra-orca-boros-en-ja-v1
    type: sharegpt
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./outputs/phi3-medium-128k-14b.8e6

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
neftune_noise_alpha: 5

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 3
optimizer: paged_adamw_8bit
adam_beta2: 0.95
adam_epsilon: 0.00001
max_grad_norm: 1.0
lr_scheduler: linear
learning_rate: 0.000008

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: True
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 100
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed: axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.1
fsdp:
fsdp_config:
resize_token_embeddings_to_32x: true
special_tokens:
  pad_token: "<|endoftext|>"

outputs/phi3-medium-128k-14b.8e6

This model is a fine-tuned version of microsoft/Phi-3-medium-128k-instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3339

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: 8e-06
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
2.8309	0.0021	1	2.3406
0.7688	0.2513	121	0.4958
0.6435	0.5026	242	0.3830
0.5286	0.7539	363	0.3626
0.5559	1.0052	484	0.3549
0.4651	1.2425	605	0.3486
0.5294	1.4938	726	0.3432
0.5453	1.7451	847	0.3392
0.5258	1.9964	968	0.3376
0.4805	2.2331	1089	0.3357
0.4552	2.4844	1210	0.3352
0.5358	2.7357	1331	0.3339

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1