metadata
license: mit
base_model: microsoft/Phi-3-mini-4k-instruct
tags:
- generated_from_trainer
model-index:
- name: phi3-out
results: []
See axolotl config
axolotl version: 0.4.1
base_model: microsoft/Phi-3-mini-4k-instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: dataset.json
ds_type: json
type: completion
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./phi3-out
sequence_len: 4096
sample_packing: false
#pad_to_sequence_len: true
adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_torch
# adam_beta2: 0.95
# adam_epsilon: 0.00001
# max_grad_norm: 1.0
lr_scheduler: cosine
learning_rate: 0.0002 # 0.000003 #0.0002
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:
weight_decay: 0.1
fsdp:
fsdp_config:
#resize_token_embeddings_to_32x: true
special_tokens:
pad_token: "<|endoftext|>"
eos_token: "<|end|>"
phi3-out
This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.8809
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4023 | 1.0 | 7628 | 1.4132 |
| 0.1342 | 2.0 | 15256 | 1.8809 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1