File size: 1,385 Bytes
bfe2093 2766622 bfe2093 2766622 bfe2093 2766622 bfe2093 2766622 bfe2093 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 |
base_model: trl-internal-testing/tiny-random-LlamaForCausalLM
batch_size: 32
bf16: true
chat_template: tokenizer_default_fallback_alpaca
datasets:
- format: custom
path: argilla/databricks-dolly-15k-curated-en
type:
field_input: original-instruction
field_instruction: original-instruction
field_output: original-response
format: '{instruction} {input}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
device_map: auto
eval_sample_packing: false
eval_steps: 200
flash_attention: true
gpu_memory_limit: 80GiB
group_by_length: true
hub_model_id: SystemAdmin123/tiny-random-LlamaForCausalLM
hub_strategy: checkpoint
learning_rate: 0.0002
logging_steps: 10
lr_scheduler: cosine
max_steps: 2500
micro_batch_size: 4
model_type: AutoModelForCausalLM
num_epochs: 100
optimizer: adamw_bnb_8bit
output_dir: /root/.sn56/axolotl/outputs/tiny-random-LlamaForCausalLM
pad_to_sequence_len: true
resize_token_embeddings_to_32x: false
sample_packing: false
save_steps: 400
save_total_limit: 1
sequence_len: 2048
tokenizer_type: LlamaTokenizerFast
torch_dtype: bf16
trust_remote_code: true
val_set_size: 0.1
wandb_entity: ''
wandb_mode: online
wandb_name: trl-internal-testing/tiny-random-LlamaForCausalLM-argilla/databricks-dolly-15k-curated-en
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: default
warmup_ratio: 0.05
|