axolotl version: 0.4.1
base_model: /media/kearm/Disk_2/HF_FAST_MoE_Fodder/Qwen2.5-1.5B
load_in_8bit: false
load_in_4bit: false
strict: false
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true
# plugins:
# - axolotl.integrations.spectrum.SpectrumPlugin
# spectrum_top_fraction: 0.5
# # Optional if using a pre-scanned model as your base_model. Useful if using a model mirror
# spectrum_model_name: Qwen/Qwen2.5-32B
datasets:
- path: datasets/deduped_not_samantha_norefusals.jsonl
type: sharegpt
- path: datasets/SystemChat_subset_filtered_sharegpt_utf8fix.jsonl
type: sharegpt
- path: datasets/S2.jsonl
type: sharegpt
- path: datasets/Turing.jsonl
type: sharegpt
- path: datasets/output_sharegpt.jsonl
type: sharegpt
chat_template: chatml
shuffle_merged_datasets: true
output_dir: EVA-Qwen2.5-1.5B-FRFR
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
# adapter: qlora
# lora_model_dir:
# lora_r: 64
# lora_alpha: 128
# lora_dropout: 0.05
# lora_target_linear: true
# peft_use_dora: true
wandb_project: EVA-Qwen2.5-1.5B-FRFR
wandb_entity:
wandb_watch:
wandb_name: Unit-00
wandb_log_model:
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.000006
max_grad_norm: 1.5
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: "unsloth"
gradient_checkpointing_kwargs:
use_reentrant: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 20
saves_per_epoch: 4
save_safetensors: true
save_total_limit: 8
hub_model_id:
hub_strategy:
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
# fsdp:
# - full_shard
# - auto_wrap
# fsdp_config:
# fsdp_limit_all_gathers: true
# fsdp_sync_module_states: false
# fsdp_offload_params: true
# fsdp_cpu_ram_efficient_loading: true
# fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
# fsdp_transformer_layer_cls_to_wrap: Qwen2DecoderLayer
# fsdp_activation_checkpointing: true
# fsdp_state_dict_type: SHARDED_STATE_DICT # Changed from FULL_STATE_DICT
# fsdp_sharding_strategy: FULL_SHARD
# fsdp_forward_prefetch: false # Added
# fsdp_backward_prefetch: "BACKWARD_PRE" # Added
# fsdp_backward_prefetch_limit: 1 # Added
# fsdp_mixed_precision: BF16 # Added
EVA-Qwen2.5-1.5B-FRFR
This model was trained from scratch on the None dataset.
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: 6e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- total_eval_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 3
Training results
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 2.21.0
- Tokenizers 0.20.3