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:
  - f1bfae7be46056e8_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/f1bfae7be46056e8_train_data.json
  type:
    field_input: intent
    field_instruction: instruction
    field_output: response_8b_instruct
    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/a3a3ad81-b4a1-4f93-93ae-295283c65877
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: 4140
micro_batch_size: 4
mlflow_experiment_name: /tmp/f1bfae7be46056e8_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: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: ff228523-b38e-4081-8a47-fba2a3a7734a
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: ff228523-b38e-4081-8a47-fba2a3a7734a
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

a3a3ad81-b4a1-4f93-93ae-295283c65877

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: 1.4956

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: 4140

Training results

Training Loss	Epoch	Step	Validation Loss
14.944	0.0004	1	1.8463
13.2896	0.0410	100	1.6569
12.6626	0.0819	200	1.6212
12.1594	0.1229	300	1.6025
13.1368	0.1638	400	1.5895
11.7641	0.2048	500	1.5792
12.2521	0.2458	600	1.5706
12.7007	0.2867	700	1.5628
12.4073	0.3277	800	1.5566
11.8441	0.3686	900	1.5502
12.0474	0.4096	1000	1.5450
12.2819	0.4506	1100	1.5404
12.1005	0.4915	1200	1.5361
12.0294	0.5325	1300	1.5318
10.9226	0.5734	1400	1.5287
12.699	0.6144	1500	1.5249
11.1465	0.6554	1600	1.5220
12.7089	0.6963	1700	1.5190
11.913	0.7373	1800	1.5169
12.6178	0.7782	1900	1.5142
12.4096	0.8192	2000	1.5120
12.1816	0.8602	2100	1.5102
11.997	0.9011	2200	1.5080
11.2863	0.9421	2300	1.5063
12.8136	0.9831	2400	1.5051
11.1348	1.0240	2500	1.5036
10.9168	1.0650	2600	1.5024
12.2777	1.1059	2700	1.5012
11.5514	1.1469	2800	1.5004
11.6384	1.1879	2900	1.4996
12.1427	1.2288	3000	1.4987
11.562	1.2698	3100	1.4981
12.3934	1.3107	3200	1.4976
11.4483	1.3517	3300	1.4971
12.2488	1.3927	3400	1.4965
12.2295	1.4336	3500	1.4963
12.5171	1.4746	3600	1.4961
11.0663	1.5155	3700	1.4959
12.0324	1.5565	3800	1.4957
11.9398	1.5975	3900	1.4957
12.7317	1.6384	4000	1.4957
12.2614	1.6794	4100	1.4956

Framework versions

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