CoolFace
Modelpublic

dzanbek/cfe0545d-c311-4406-acae-9d40eac3b878

sourceHugging Facebigscience-bloom-rail-1.0updated 2y agoView on Hugging Face
0likes4downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/> <details><summary>See axolotl config</summary>

axolotl version: 0.4.1

yaml
adapter: lora
base_model: bigscience/bloomz-560m
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 437d6156515bf54f_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/437d6156515bf54f_train_data.json
  type:
    field_input: new-context
    field_instruction: new-instruction
    field_output: new-response
    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_steps: 25
eval_table_size: null
flash_attention: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: false
hub_model_id: dzanbek/cfe0545d-c311-4406-acae-9d40eac3b878
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 74GiB
max_steps: 75
micro_batch_size: 2
mlflow_experiment_name: /tmp/437d6156515bf54f_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
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: 25
save_strategy: steps
sequence_len: 2048
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: cfe0545d-c311-4406-acae-9d40eac3b878
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: cfe0545d-c311-4406-acae-9d40eac3b878
warmup_ratio: 0.05
weight_decay: 0.01
xformers_attention: true

</details><br>

cfe0545d-c311-4406-acae-9d40eac3b878

This model is a fine-tuned version of bigscience/bloomz-560m on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 1.7397

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: 0.0001
  • —trainbatchsize: 2
  • —evalbatchsize: 2
  • —seed: 42
  • —gradientaccumulationsteps: 8
  • —totaltrainbatch_size: 16
  • —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
  • —lrschedulertype: cosine
  • —lrschedulerwarmup_steps: 3
  • —training_steps: 75

Training results

Training LossEpochStepValidation Loss
17.4120.001112.1443
15.6240.0284251.7818
10.770.0568501.7447
11.56910.0853751.7397

Framework versions

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