metadata

library_name: peft
base_model: >-
  rayonlabs/merged-merged-af6dd40b-32e1-43b1-adfd-8ce14d65d738-PubMedQA-138437bf-44bd-4b03-8801-d05451a9ff28
tags:
  - axolotl
  - generated_from_trainer
model-index:
  - name: a2b745fc-6116-426b-b865-0221716d23d5
    results: []

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: rayonlabs/merged-merged-af6dd40b-32e1-43b1-adfd-8ce14d65d738-PubMedQA-138437bf-44bd-4b03-8801-d05451a9ff28
bf16: true
chat_template: llama3
datasets:
- data_files:
  - 0d8fe5cf126e320c_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/0d8fe5cf126e320c_train_data.json
  type:
    field_input: context
    field_instruction: question
    field_output: final_decision
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 2
gradient_checkpointing: true
group_by_length: false
hub_model_id: lesso09/a2b745fc-6116-426b-b865-0221716d23d5
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 1.0e-05
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 70GiB
max_steps: 30
micro_batch_size: 4
mlflow_experiment_name: /tmp/0d8fe5cf126e320c_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
optimizer: adamw_torch
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 20
save_strategy: steps
sequence_len: 1024
special_tokens:
  pad_token: <|end_of_text|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 4b810264-dad3-481e-b39e-87abe60a31a9
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: 4b810264-dad3-481e-b39e-87abe60a31a9
warmup_steps: 5
weight_decay: 0.01
xformers_attention: false

a2b745fc-6116-426b-b865-0221716d23d5

This model is a fine-tuned version of rayonlabs/merged-merged-af6dd40b-32e1-43b1-adfd-8ce14d65d738-PubMedQA-138437bf-44bd-4b03-8801-d05451a9ff28 on the None dataset. It achieves the following results on the evaluation set:

Loss: 2.1374

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
gradient_accumulation_steps: 2
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 5
training_steps: 30

Training results

Training Loss	Epoch	Step	Validation Loss
12.6573	0.0000	1	12.2763
12.3047	0.0002	4	12.1170
10.9634	0.0003	8	10.4832
8.4706	0.0005	12	7.9679
5.6449	0.0006	16	5.2114
3.9582	0.0008	20	3.3761
4.1212	0.0010	24	2.4972
3.81	0.0011	28	2.1374

Framework versions

PEFT 0.13.2
Transformers 4.46.0
Pytorch 2.5.0+cu124
Datasets 3.0.1
Tokenizers 0.20.1