base_model: microsoft/Phi-3.5-mini-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/stheno-filtered-v1.1
    type: sharegpt
    conversation: chatml
  - path: anthracite-org/nopm_claude_writing_fixed
    type: sharegpt
    conversation: chatml
  - path: Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
    type: sharegpt
    conversation: chatml
  - path: ResplendentAI/bluemoon
    type: sharegpt
    conversation: chatml
  - path: openerotica/freedom-rp
    type: sharegpt
    conversation: chatml
  - path: MinervaAI/Aesir-Preview
    type: sharegpt
    conversation: chatml
  - path: jeiku/jeikutxt
    type: completion
  - path: ResplendentAI/Sissification_Hypno_1k
    type: alpaca
  - path: ResplendentAI/theory_of_mind_fixed_output
    type: alpaca
  - path: ResplendentAI/Synthetic_Soul_1k
    type: alpaca

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: phi
wandb_entity:
wandb_watch:
wandb_name: phi
wandb_log_model:

gradient_accumulation_steps: 32
micro_batch_size: 4
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 microsoft/Phi-3.5-mini-instruct on the None dataset. It achieves the following results on the evaluation set:

Loss: 7.1048

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: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 32
total_train_batch_size: 256
total_eval_batch_size: 8
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 8
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
15.986	0.0233	1	16.8119
9.6041	0.2567	11	9.1897
7.5864	0.5135	22	7.5221
7.2575	0.7702	33	7.2532
7.1368	1.0270	44	7.1665
7.078	1.2844	55	7.1249
7.0613	1.5417	66	7.1079
7.0599	1.7990	77	7.1048

Framework versions

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

jeiku/thisisbroken

outputs/out

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jeiku/
thisisbroken