trashpanda-org/Qwen2.5-32B-31-clush-stage2

See axolotl config

axolotl version: 0.8.0.dev0

base_model: ./marigold-exp-pretrain
model_type: AutoModelForCausalLM

load_in_8bit: false
load_in_4bit: false
strict: false

chat_template: chatml
datasets:
  # Instruct datasets (local)
  - path: datasets/competition-math-sharegpt.jsonl
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/systemchat-1k-sharegpt.jsonl
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/opencai_rp_sharegpt.json
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/floyd-instruct-8k.jsonl
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/woke-identity.jsonl
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/Claude-Sonnet35-Charcard-Unslop-v2.json
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/gryphe-4o-WP-sharegpt.json
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/amoral-r1.json
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/kalo-opus-22k-unslop.json
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/gryphe-4o-WP-sharegpt.json
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/discord-logs-cleaned-sharegpt.json
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/creative-writing-multiturn-16k.json
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/limo-sharegpt.jsonl
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/tot-bio-2k-subset-sharegpt.json
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/UBW_Tapestries.json
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/gpqa-benchmaxxing.jsonl
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/medical-o1-reasoning-default-sys.jsonl
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
  - path: datasets/c2-logs-cleaned.json
    type: chat_template
    field_messages: conversations
    message_field_role: from
    message_field_content: value
shuffle_merged_datasets: true

special_tokens:
  eos_token: "<|im_end|>"

dataset_prepared_path: instruct_run_prepared
val_set_size: 0.02
output_dir: ./marigold-exp-instruct

sequence_len: 10240
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

micro_batch_size: 2
gradient_accumulation_steps: 2
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: rex
learning_rate: 2e-5
warmup_ratio: 0.05
cosine_min_lr_ratio: 0.1

weight_decay: 0.01
max_grad_norm: 2

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

evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 256

saves_per_epoch: 4
save_total_limit: 12

debug:

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

deepspeed: deepspeed_configs/zero3_bf16.json

wandb_project: Qwen2.5-32B-Marigold-v2-exp
wandb_entity:
wandb_name: Marigold-v2-exp-instruct

marigold-exp-instruct

This model is a fine-tuned version of ./marigold-exp-pretrain on the datasets/competition-math-sharegpt.jsonl, the datasets/systemchat-1k-sharegpt.jsonl, the datasets/opencai_rp_sharegpt.json, the datasets/floyd-instruct-8k.jsonl, the datasets/woke-identity.jsonl, the datasets/Claude-Sonnet35-Charcard-Unslop-v2.json, the datasets/gryphe-4o-WP-sharegpt.json, the datasets/amoral-r1.json, the datasets/kalo-opus-22k-unslop.json, the datasets/gryphe-4o-WP-sharegpt.json, the datasets/discord-logs-cleaned-sharegpt.json, the datasets/creative-writing-multiturn-16k.json, the datasets/limo-sharegpt.jsonl, the datasets/tot-bio-2k-subset-sharegpt.json, the datasets/UBW_Tapestries.json, the datasets/gpqa-benchmaxxing.jsonl, the datasets/medical-o1-reasoning-default-sys.jsonl and the datasets/c2-logs-cleaned.json datasets. It achieves the following results on the evaluation set:

• Loss: 1.2771

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• total_eval_batch_size: 16
• optimizer: Use 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: 24
• num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss
1.597	0.0041	1	1.5916
1.4889	0.2515	62	1.4007
1.3936	0.5030	124	1.3699
1.4116	0.7546	186	1.3446
1.2267	1.0041	248	1.3268
1.1274	1.2556	310	1.3302
1.0862	1.5071	372	1.3105
1.1317	1.7586	434	1.2771

Framework versions

• Transformers 4.50.0
• Pytorch 2.5.1+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1