You can deploy this model and start earning money today!

sn56z0/
2c2e76c8-d646-414a-ab87-2a1939c2bdc0

Name: 2c2e76c8-d646-414a-ab87-2a1939c2bdc0
Availability: InStock

generated_from_trainer

unsloth/gemma-2-2b-it

adapter

gemma

Views

No views yet

See axolotl config

axolotl version: 0.4.1

yaml

adapter: lora
base_model: unsloth/gemma-2-2b-it
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - c99f9bda443236d3_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/c99f9bda443236d3_train_data.json
  type:
    field_instruction: article
    field_output: highlights
    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: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
gradient_clipping: 1.0
group_by_length: false
hub_model_id: sn56z0/2c2e76c8-d646-414a-ab87-2a1939c2bdc0
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: 32
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 16
lora_target_linear: true
lr_scheduler: cosine
max_steps: 100
micro_batch_size: 8
mlflow_experiment_name: /tmp/c99f9bda443236d3_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: null
sample_packing: false
saves_per_epoch: 4
seed: 869809486
sequence_len: 1024
shuffle: true
strict: false
tf32: false
tokenizer_type: AutoTokenizer
torch_compile: true
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: sn56-miner
wandb_mode: disabled
wandb_name: null
wandb_project: god
wandb_run: a3ro
wandb_runid: null
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

2c2e76c8-d646-414a-ab87-2a1939c2bdc0

This model is a fine-tuned version of unsloth/gemma-2-2b-it on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.4747

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: 869809486
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 128
total_eval_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: 100

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0004	1	2.3123
1.9805	0.0039	9	1.8444
1.7135	0.0078	18	1.6604
1.6006	0.0117	27	1.5944
1.5462	0.0156	36	1.5527
1.5698	0.0194	45	1.5254
1.5211	0.0233	54	1.5040
1.5003	0.0272	63	1.4909
1.5199	0.0311	72	1.4822
1.5195	0.0350	81	1.4773
1.4748	0.0389	90	1.4752
1.4768	0.0428	99	1.4747

Framework versions

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