See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: databricks/dolly-v2-3b
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 5331fe87bf00d538_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/5331fe87bf00d538_train_data.json
  type:
    field_instruction: ENName
    field_output: English
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 5
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: ardaspear/a88f8b2e-f568-4a84-88e2-a7106ee09f9c
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 10
lora_alpha: 64
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
  0: 75GB
max_steps: 600
micro_batch_size: 8
mlflow_experiment_name: /tmp/5331fe87bf00d538_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.95
  adam_epsilon: 1e-5
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: 150
saves_per_epoch: null
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: techspear-hub
wandb_mode: online
wandb_name: 2b8220c8-e099-4ec3-b5fe-01bf1bbb8399
wandb_project: Gradients-On-Five
wandb_run: your_name
wandb_runid: 2b8220c8-e099-4ec3-b5fe-01bf1bbb8399
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

a88f8b2e-f568-4a84-88e2-a7106ee09f9c

This model is a fine-tuned version of databricks/dolly-v2-3b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.8890

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: 8
• eval_batch_size: 4
• 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=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• training_steps: 600

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0010	1	5.1337
11.5191	0.0498	50	5.1384
10.9195	0.0996	100	4.2621
10.835	0.1493	150	3.6877
10.7218	0.1991	200	3.5130
10.8336	0.2489	250	3.3116
10.4789	0.2987	300	3.2133
10.8462	0.3484	350	3.1247
10.8597	0.3982	400	3.0209
10.7978	0.4480	450	2.9192
11.3832	0.4978	500	2.8906
11.3248	0.5475	550	2.8867
10.9463	0.5973	600	2.8890

Framework versions

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