Hugging Face's logo

cognitivecomputations
/
dolphin-2.9.1-llama-3-70b

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
axolotl
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
6
dolphin-2.9.1-llama-3-70b / README.md
ehartford's picture
ehartford
Upload folder using huggingface_hub
bd035ea verified
preview code
|
raw
history blame
14 kB
metadata
license: llama3
base_model: meta-llama/Meta-Llama-3-70B
tags:
  - generated_from_trainer
model-index:
  - name: workspace/axolotl/llama-70b
    results: []

Built with Axolotl

See axolotl config

axolotl version: 0.4.0

base_model: meta-llama/Meta-Llama-3-70B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
# load_in_4bit: true
strict: false

datasets:
  - path: /workspace/datasets/dolphin-2.9/dolphin201-sharegpt2.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/dolphin-coder-translate-sharegpt2.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/dolphin-coder-codegen-sharegpt2.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/m-a-p_Code-Feedback-sharegpt-unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt-unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/not_samantha_norefusals.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/Orca-Math-resort-unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/agent_instruct_react_unfiltered.jsonl
    type: sharegpt  
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/toolbench_instruct_j1s1_3k_unfiltered.jsonl
    type: sharegpt  
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/toolbench_negative_unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/toolbench_react_10p_unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/toolbench_tflan_cot_30p_unfiltered.jsonl
    type: sharegpt
    conversation: chatml
  - path: /workspace/datasets/dolphin-2.9/openhermes200k_unfiltered.jsonl
    type: sharegpt 
    conversation: chatml

chat_template: chatml
# adapter: qlora
# lora_r: 128
# lora_alpha: 16
# lora_modules_to_save: [embed_tokens, lm_head]
# lora_dropout: 0.05
# lora_target_linear: true



unfrozen_parameters:
- ^lm_head.weight$
- ^model.embed_tokens.weight$
# mlp.down_proj layers
- model.layers.40.mlp.down_proj
- model.layers.44.mlp.down_proj
- model.layers.45.mlp.down_proj
- model.layers.46.mlp.down_proj
- model.layers.43.mlp.down_proj
- model.layers.52.mlp.down_proj
- model.layers.47.mlp.down_proj
- model.layers.48.mlp.down_proj
- model.layers.39.mlp.down_proj
- model.layers.49.mlp.down_proj
- model.layers.38.mlp.down_proj
- model.layers.53.mlp.down_proj
- model.layers.41.mlp.down_proj
- model.layers.35.mlp.down_proj
- model.layers.51.mlp.down_proj
- model.layers.42.mlp.down_proj
- model.layers.37.mlp.down_proj
- model.layers.50.mlp.down_proj
- model.layers.60.mlp.down_proj
- model.layers.76.mlp.down_proj
- model.layers.54.mlp.down_proj
- model.layers.36.mlp.down_proj
- model.layers.57.mlp.down_proj
- model.layers.56.mlp.down_proj
- model.layers.55.mlp.down_proj
- model.layers.77.mlp.down_proj
- model.layers.59.mlp.down_proj
- model.layers.61.mlp.down_proj
- model.layers.58.mlp.down_proj
- model.layers.65.mlp.down_proj
- model.layers.75.mlp.down_proj
- model.layers.64.mlp.down_proj
- model.layers.62.mlp.down_proj
- model.layers.68.mlp.down_proj
- model.layers.19.mlp.down_proj
- model.layers.66.mlp.down_proj
# mlp.gate_proj layers
- model.layers.70.mlp.gate_proj
- model.layers.71.mlp.gate_proj
- model.layers.67.mlp.gate_proj
- model.layers.58.mlp.gate_proj
- model.layers.55.mlp.gate_proj
- model.layers.57.mlp.gate_proj
- model.layers.56.mlp.gate_proj
- model.layers.66.mlp.gate_proj
- model.layers.72.mlp.gate_proj
- model.layers.69.mlp.gate_proj
- model.layers.52.mlp.gate_proj
- model.layers.54.mlp.gate_proj
- model.layers.62.mlp.gate_proj
- model.layers.60.mlp.gate_proj
- model.layers.74.mlp.gate_proj
- model.layers.59.mlp.gate_proj
- model.layers.68.mlp.gate_proj
- model.layers.61.mlp.gate_proj
- model.layers.73.mlp.gate_proj
- model.layers.53.mlp.gate_proj
- model.layers.51.mlp.gate_proj
- model.layers.63.mlp.gate_proj
- model.layers.48.mlp.gate_proj
- model.layers.49.mlp.gate_proj
- model.layers.64.mlp.gate_proj
- model.layers.50.mlp.gate_proj
- model.layers.65.mlp.gate_proj
- model.layers.47.mlp.gate_proj
- model.layers.44.mlp.gate_proj
- model.layers.45.mlp.gate_proj
- model.layers.75.mlp.gate_proj
- model.layers.46.mlp.gate_proj
- model.layers.43.mlp.gate_proj
- model.layers.77.mlp.gate_proj
- model.layers.41.mlp.gate_proj
- model.layers.42.mlp.gate_proj
# mlp.up_proj layers
- model.layers.70.mlp.up_proj
- model.layers.67.mlp.up_proj
- model.layers.66.mlp.up_proj
- model.layers.69.mlp.up_proj
- model.layers.62.mlp.up_proj
- model.layers.65.mlp.up_proj
- model.layers.63.mlp.up_proj
- model.layers.68.mlp.up_proj
- model.layers.71.mlp.up_proj
- model.layers.64.mlp.up_proj
- model.layers.61.mlp.up_proj
- model.layers.58.mlp.up_proj
- model.layers.59.mlp.up_proj
- model.layers.57.mlp.up_proj
- model.layers.55.mlp.up_proj
- model.layers.72.mlp.up_proj
- model.layers.54.mlp.up_proj
- model.layers.60.mlp.up_proj
- model.layers.56.mlp.up_proj
- model.layers.73.mlp.up_proj
- model.layers.50.mlp.up_proj
- model.layers.51.mlp.up_proj
- model.layers.53.mlp.up_proj
- model.layers.74.mlp.up_proj
- model.layers.52.mlp.up_proj
- model.layers.49.mlp.up_proj
- model.layers.30.mlp.up_proj
- model.layers.34.mlp.up_proj
- model.layers.47.mlp.up_proj
- model.layers.46.mlp.up_proj
- model.layers.48.mlp.up_proj
- model.layers.38.mlp.up_proj
- model.layers.45.mlp.up_proj
- model.layers.43.mlp.up_proj
- model.layers.29.mlp.up_proj
- model.layers.42.mlp.up_proj
# self_attn.k_proj layers
- model.layers.72.self_attn.k_proj
- model.layers.75.self_attn.k_proj
- model.layers.71.self_attn.k_proj
- model.layers.74.self_attn.k_proj
- model.layers.44.self_attn.k_proj
- model.layers.31.self_attn.k_proj
- model.layers.33.self_attn.k_proj
- model.layers.34.self_attn.k_proj
- model.layers.76.self_attn.k_proj
- model.layers.78.self_attn.k_proj
- model.layers.77.self_attn.k_proj
- model.layers.22.self_attn.k_proj
- model.layers.18.self_attn.k_proj
- model.layers.60.self_attn.k_proj
- model.layers.17.self_attn.k_proj
- model.layers.56.self_attn.k_proj
- model.layers.2.self_attn.k_proj
- model.layers.21.self_attn.k_proj
- model.layers.19.self_attn.k_proj
- model.layers.23.self_attn.k_proj
- model.layers.52.self_attn.k_proj
- model.layers.35.self_attn.k_proj
- model.layers.73.self_attn.k_proj
- model.layers.15.self_attn.k_proj
- model.layers.27.self_attn.k_proj
- model.layers.29.self_attn.k_proj
- model.layers.20.self_attn.k_proj
- model.layers.28.self_attn.k_proj
- model.layers.36.self_attn.k_proj
- model.layers.25.self_attn.k_proj
- model.layers.37.self_attn.k_proj
- model.layers.30.self_attn.k_proj
- model.layers.16.self_attn.k_proj
- model.layers.32.self_attn.k_proj
- model.layers.41.self_attn.k_proj
- model.layers.26.self_attn.k_proj
# self_attn.o_proj layers
- model.layers.50.self_attn.o_proj
- model.layers.61.self_attn.o_proj
- model.layers.46.self_attn.o_proj
- model.layers.53.self_attn.o_proj
- model.layers.54.self_attn.o_proj
- model.layers.19.self_attn.o_proj
- model.layers.42.self_attn.o_proj
- model.layers.49.self_attn.o_proj
- model.layers.41.self_attn.o_proj
- model.layers.68.self_attn.o_proj
- model.layers.18.self_attn.o_proj
- model.layers.45.self_attn.o_proj
- model.layers.11.self_attn.o_proj
- model.layers.67.self_attn.o_proj
- model.layers.48.self_attn.o_proj
- model.layers.51.self_attn.o_proj
- model.layers.64.self_attn.o_proj
- model.layers.13.self_attn.o_proj
- model.layers.14.self_attn.o_proj
- model.layers.16.self_attn.o_proj
- model.layers.17.self_attn.o_proj
- model.layers.47.self_attn.o_proj
- model.layers.0.self_attn.o_proj
- model.layers.20.self_attn.o_proj
- model.layers.63.self_attn.o_proj
- model.layers.15.self_attn.o_proj
- model.layers.5.self_attn.o_proj
- model.layers.21.self_attn.o_proj
- model.layers.52.self_attn.o_proj
- model.layers.12.self_attn.o_proj
- model.layers.10.self_attn.o_proj
- model.layers.62.self_attn.o_proj
- model.layers.56.self_attn.o_proj
- model.layers.22.self_attn.o_proj
- model.layers.6.self_attn.o_proj
- model.layers.7.self_attn.o_proj
# self_attn.q_proj layers
- model.layers.2.self_attn.q_proj
- model.layers.4.self_attn.q_proj
- model.layers.46.self_attn.q_proj
- model.layers.5.self_attn.q_proj
- model.layers.7.self_attn.q_proj
- model.layers.6.self_attn.q_proj
- model.layers.9.self_attn.q_proj
- model.layers.10.self_attn.q_proj
- model.layers.1.self_attn.q_proj
- model.layers.18.self_attn.q_proj
- model.layers.62.self_attn.q_proj
- model.layers.8.self_attn.q_proj
- model.layers.15.self_attn.q_proj
- model.layers.14.self_attn.q_proj
- model.layers.16.self_attn.q_proj
- model.layers.31.self_attn.q_proj
- model.layers.19.self_attn.q_proj
- model.layers.17.self_attn.q_proj
- model.layers.33.self_attn.q_proj
- model.layers.35.self_attn.q_proj
- model.layers.12.self_attn.q_proj
- model.layers.21.self_attn.q_proj
- model.layers.27.self_attn.q_proj
- model.layers.34.self_attn.q_proj
- model.layers.13.self_attn.q_proj
- model.layers.56.self_attn.q_proj
- model.layers.11.self_attn.q_proj
- model.layers.52.self_attn.q_proj
- model.layers.54.self_attn.q_proj
- model.layers.28.self_attn.q_proj
- model.layers.30.self_attn.q_proj
- model.layers.20.self_attn.q_proj
- model.layers.29.self_attn.q_proj
- model.layers.37.self_attn.q_proj
- model.layers.23.self_attn.q_proj
- model.layers.75.self_attn.q_proj
# self_attn.v_proj layers
- model.layers.11.self_attn.v_proj
- model.layers.17.self_attn.v_proj
- model.layers.37.self_attn.v_proj
- model.layers.40.self_attn.v_proj
- model.layers.41.self_attn.v_proj
- model.layers.42.self_attn.v_proj
- model.layers.43.self_attn.v_proj
- model.layers.44.self_attn.v_proj
- model.layers.45.self_attn.v_proj
- model.layers.46.self_attn.v_proj
- model.layers.48.self_attn.v_proj
- model.layers.49.self_attn.v_proj
- model.layers.50.self_attn.v_proj
- model.layers.51.self_attn.v_proj
- model.layers.53.self_attn.v_proj
- model.layers.54.self_attn.v_proj
- model.layers.55.self_attn.v_proj
- model.layers.57.self_attn.v_proj
- model.layers.58.self_attn.v_proj
- model.layers.59.self_attn.v_proj
- model.layers.60.self_attn.v_proj
- model.layers.61.self_attn.v_proj
- model.layers.62.self_attn.v_proj
- model.layers.63.self_attn.v_proj
- model.layers.64.self_attn.v_proj
- model.layers.65.self_attn.v_proj
- model.layers.66.self_attn.v_proj
- model.layers.67.self_attn.v_proj
- model.layers.69.self_attn.v_proj
- model.layers.75.self_attn.v_proj
- model.layers.18.self_attn.v_proj
- model.layers.78.self_attn.v_proj
- model.layers.68.self_attn.v_proj
- model.layers.47.self_attn.v_proj
- model.layers.38.self_attn.v_proj
- model.layers.71.self_attn.v_proj
# model.norm layers



dataset_prepared_path: last_run_prepared
val_set_size: 0.01
output_dir: /workspace/axolotl/llama-70b

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

wandb_project: llama-3
wandb_watch:
wandb_run_id:
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: true

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 5
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 4
save_total_limit: 2
save_steps:
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.00
fsdp:
fsdp_config:
special_tokens:
  eos_token: "<|im_end|>"
  pad_token: "<|end_of_text|>"
tokens:
  - "<|im_start|>"
  - "<|im_end|>"

workspace/axolotl/llama-70b

This model is a fine-tuned version of meta-llama/Meta-Llama-3-70B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4808

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: 5
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
0.7659 0.0004 1 0.7454
0.5006 0.2501 587 0.4817
0.4807 0.5002 1174 0.4698
0.4758 0.7503 1761 0.4627
0.4969 1.0004 2348 0.4558
0.3604 1.2346 2935 0.4635
0.3817 1.4847 3522 0.4572
0.377 1.7348 4109 0.4533
0.3695 1.9849 4696 0.4487
0.2676 2.2187 5283 0.4825
0.255 2.4688 5870 0.4814
0.2851 2.7189 6457 0.4808

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.2.2+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1