See axolotl config

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