See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: EleutherAI/gpt-neo-125m
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - af1c9fa61fc53b76_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/af1c9fa61fc53b76_train_data.json
  type:
    field_input: input
    field_instruction: instruction
    field_output: output
    format: '{instruction} {input}'
    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: false
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 8
gradient_checkpointing: true
group_by_length: false
hub_model_id: Alphatao/dd206ec7-9cef-4517-abdc-c03d9ee91679
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
lr_scheduler: cosine
max_grad_norm: 1.0
max_steps: 2520
micro_batch_size: 4
mlflow_experiment_name: /tmp/af1c9fa61fc53b76_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
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.013194596548821326
wandb_entity: null
wandb_mode: online
wandb_name: b88ca5d6-0630-4b99-b57a-7ad05d206357
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: b88ca5d6-0630-4b99-b57a-7ad05d206357
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

dd206ec7-9cef-4517-abdc-c03d9ee91679

This model is a fine-tuned version of EleutherAI/gpt-neo-125m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2057

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: 2520

Training results

Training Loss	Epoch	Step	Validation Loss
16.9762	0.0001	1	2.2205
3.6891	0.0086	100	0.4292
3.0828	0.0171	200	0.3583
2.4266	0.0257	300	0.3277
1.943	0.0342	400	0.3134
2.1649	0.0428	500	0.3031
2.2397	0.0513	600	0.2885
1.4374	0.0599	700	0.2782
2.4995	0.0685	800	0.2726
1.9345	0.0770	900	0.2634
2.1918	0.0856	1000	0.2551
1.6604	0.0941	1100	0.2485
1.9454	0.1027	1200	0.2454
2.3454	0.1112	1300	0.2371
1.9632	0.1198	1400	0.2314
1.77	0.1284	1500	0.2271
1.6156	0.1369	1600	0.2222
1.2739	0.1455	1700	0.2173
2.0335	0.1540	1800	0.2136
1.4027	0.1626	1900	0.2120
1.4062	0.1711	2000	0.2094
1.878	0.1797	2100	0.2082
1.9998	0.1883	2200	0.2068
1.4869	0.1968	2300	0.2061
1.4694	0.2054	2400	0.2058
1.3543	0.2139	2500	0.2057

Framework versions

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