You can deploy this model and start earning money today!

Alphatao/
23041908-ecec-4929-9f22-a363436ede3c

Name: 23041908-ecec-4929-9f22-a363436ede3c
Availability: InStock

generated_from_trainer

katuni4ka/tiny-random-qwen1.5-moe

adapter

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: katuni4ka/tiny-random-qwen1.5-moe
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 2a62bbed49deec50_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/2a62bbed49deec50_train_data.json
  type:
    field_instruction: en_US
    field_output: de_DE
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: 2
eval_max_new_tokens: 128
eval_steps: 100
eval_table_size: null
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/23041908-ecec-4929-9f22-a363436ede3c
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_best_model_at_end: true
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lora_target_modules:
- q_proj
- k_proj
- v_proj
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 4224
micro_batch_size: 4
mlflow_experiment_name: /tmp/2a62bbed49deec50_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 2
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 100
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: d42227aa-baf7-443b-8327-1ac31cf80adc
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: d42227aa-baf7-443b-8327-1ac31cf80adc
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

23041908-ecec-4929-9f22-a363436ede3c

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: 11.8266

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: 0.0002
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
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: 972

Training results

Training Loss	Epoch	Step	Validation Loss
11.9371	0.0021	1	11.9404
11.8796	0.2058	100	11.8676
11.8751	0.4115	200	11.8651
11.8621	0.6173	300	11.8619
11.8525	0.8230	400	11.8497
11.8365	1.0288	500	11.8395
11.8264	1.2346	600	11.8329
11.8319	1.4403	700	11.8291
11.8248	1.6461	800	11.8271
11.8352	1.8519	900	11.8266

Framework versions

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