See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: katuni4ka/tiny-random-qwen1.5-moe
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 8dd787b2d13e2b05_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/8dd787b2d13e2b05_train_data.json
  type:
    field_instruction: prompt_text
    field_output: video_text
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: false
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: ardaspear/85a121f1-a0cd-4cc1-a42f-54c3275b4007
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: 0
logging_steps: 3
lora_alpha: 128
lora_dropout: 0.1
lora_fan_in_fan_out: true
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 72GB
max_steps: 50
micro_batch_size: 8
mlflow_experiment_name: /tmp/8dd787b2d13e2b05_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: false
sample_packing: false
saves_per_epoch: 4
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: leixa-personal
wandb_mode: online
wandb_name: 85a121f1-a0cd-4cc1-a42f-54c3275b4007
wandb_project: Gradients-On-Two
wandb_run: your_name
wandb_runid: 85a121f1-a0cd-4cc1-a42f-54c3275b4007
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

85a121f1-a0cd-4cc1-a42f-54c3275b4007

This model is a fine-tuned version of katuni4ka/tiny-random-qwen1.5-moe on the None dataset. It achieves the following results on the evaluation set:

• Loss: 11.8703

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_BNB 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: 10
• training_steps: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0006	1	11.9349
11.9355	0.0029	5	11.9326
11.9286	0.0059	10	11.9237
11.9161	0.0088	15	11.9084
11.9059	0.0118	20	11.8935
11.8831	0.0147	25	11.8826
11.8796	0.0177	30	11.8763
11.8769	0.0206	35	11.8728
11.8702	0.0236	40	11.8711
11.8703	0.0265	45	11.8704
11.8696	0.0295	50	11.8703

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1