See axolotl config
axolotl version: 0.4.1
adapter: lora
base_model: microsoft/phi-1_5
bf16: auto
datasets:
- data_files:
- ba5cae4bcc0af9d8_train_data.json
ds_type: json
format: custom
path: ba5cae4bcc0af9d8_train_data.json
type:
field: null
field_input: input
field_instruction: instruction
field_output: output
field_system: null
format: null
no_input_format: null
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_sample_packing: false
eval_table_size: null
evals_per_epoch: 1
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: taopanda-4/ea8f19a6-0813-4f21-a2aa-f2ef0f269472
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: true
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
micro_batch_size: 2
model_type: AutoModelForCausalLM
num_epochs: 2
optimizer: adamw_bnb_8bit
output_dir: ./outputs/out/taopanda-4_28883253-69a6-44d4-84db-a7b6f5c25060
pad_to_sequence_len: true
resume_from_checkpoint: null
sample_packing: true
saves_per_epoch: 1
seed: 95212
sequence_len: 4096
special_tokens:
pad_token: <|endoftext|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.1
wandb_entity: fatcat87-taopanda
wandb_log_model: null
wandb_mode: online
wandb_name: taopanda-4_28883253-69a6-44d4-84db-a7b6f5c25060
wandb_project: subnet56
wandb_runid: taopanda-4_28883253-69a6-44d4-84db-a7b6f5c25060
wandb_watch: null
warmup_ratio: 0.05
weight_decay: 0.0
xformers_attention: null
ea8f19a6-0813-4f21-a2aa-f2ef0f269472
This model is a fine-tuned version of microsoft/phi-1_5 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9372
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: 2
- eval_batch_size: 2
- seed: 95212
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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: 14
- num_epochs: 2
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.1147 | 0.0069 | 1 | 2.0914 |
0.9811 | 1.0 | 144 | 0.9543 |
0.9604 | 1.9844 | 288 | 0.9372 |
Framework versions
- PEFT 0.11.1
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 9
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for taopanda-4/ea8f19a6-0813-4f21-a2aa-f2ef0f269472
Base model
microsoft/phi-1_5