base_model: Qwen/Qwen2.5-1.5B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
trust_remote_code: false

load_in_8bit: false
load_in_4bit: false
strict: false



output_dir: ./outputs_plug/out
chat_template: qwen_25
datasets:
  - path: train_plug.jsonl
    type: chat_template
    # chat_template: tokenizer_default
    field_messages: messages
    message_field_role: role
    message_field_content: content
    roles:
      system:
        - system
      user:
        - user
      assistant:
        - assistant

dataset_prepared_path: last_run_prepared
val_set_size: 0.005
output_dir: ./outputs_plug/out
eval_sample_packing: False

sequence_len: 8192
sample_packing: False
pad_to_sequence_len: False

wandb_project: hrm8k
wandb_entity:
wandb_watch: 
wandb_name: PLUG-1.5B-50k
hub_model_id: Cartinoe5930/PLUG-1.5B-50k

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

gradient_accumulation_steps: 8
micro_batch_size: 8
eval_batch_size: 4
num_epochs: 1
optimizer: paged_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
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_ratio: 0.05
evals_per_epoch: 1
eval_max_new_tokens: 128
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: deepspeed_configs/zero1.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:

PLUG-1.5B-50k

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the train_plug.jsonl dataset. It achieves the following results on the evaluation set:

Loss: 0.4009

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: 8
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 8
total_train_batch_size: 128
total_eval_batch_size: 8
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 19
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.3579	0.9981	388	0.4009

Framework versions

Transformers 4.49.0
Pytorch 2.5.1+cu121
Datasets 3.2.0
Tokenizers 0.21.1

Cartinoe5930/PLUG-1.5B-50k-depr

PLUG-1.5B-50k

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Cartinoe5930/
PLUG-1.5B-50k-depr