Hugging Face's logo

cognitivecomputations
/
dolphin-2.9.2-qwen2-7b

Text Generation
Transformers
Safetensors
8 datasets
qwen2
Generated from Trainer
axolotl
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
6
dolphin-2.9.2-qwen2-7b / README.md
Crystalcareai's picture
Crystalcareai
Upload folder using huggingface_hub
52f354c verified
preview code
|
raw
history blame
No virus
5.05 kB
metadata
license: other
base_model: Qwen/Qwen2-7B
tags:
  - generated_from_trainer
model-index:
  - name: qwen2-7b
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: Qwen/Qwen2-7B
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
tokenizer_use_fast: true

# load_in_8bit: true
# load_in_4bit: false
# strict: false

datasets:
  - path: /workspace/datasets/dolphin-2.9.2/dolphin201-sharegpt2.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9.2/dolphin-coder-codegen-sharegpt2.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9.2/dolphin-coder-translate-sharegpt2.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9.2/m-a-p_Code-Feedback-sharegpt-unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9.2/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt-unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9.2/not_samantha_norefusals.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9.2/openhermes200k_unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9.2/Orca-Math-resort-unfiltered.jsonl
    type: sharegpt  
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9.2/SystemChat_sharegpt.jsonl
    type: sharegpt  
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9.2/toolbench_instruct_j1s1_3k_unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9.2/toolbench_negative_unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9.2/toolbench_react_10p_unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9.2/toolbench_tflan_cot_30p_unfiltered.jsonl
    type: sharegpt 
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9.2/agent_instruct_react_unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  
chat_template: chatml
dataset_prepared_path: qwen2-7b-data
val_set_size: 0.01
output_dir: qwen2-7b

sequence_len: 16384  
sample_packing: true
pad_to_sequence_len: true

# adapter: lora
# lora_model_dir:
# lora_r: 32
# lora_alpha: 16
# lora_dropout: 0.05
# lora_target_linear: true
# lora_fan_in_fan_out:

wandb_project: qwen2-72b
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_8bit
lr_scheduler: cosine
learning_rate: 1e-5

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 2
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 4
save_total_limit: 2
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
weight_decay: 0.05
fsdp:
fsdp_config:
special_tokens:
  pad_token: "<|endoftext|>"
  eos_token: "<|im_end|>"

qwen2-7b

This model is a fine-tuned version of Qwen/Qwen2-7B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5746

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: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 64
  • 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: 10
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
0.7835 0.0014 1 0.7811
0.597 0.4998 355 0.6048
0.5885 0.9996 710 0.5834
0.5216 1.4805 1065 0.5770
0.5407 1.9803 1420 0.5697
0.4955 2.4611 1775 0.5752
0.487 2.9609 2130 0.5746

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1