adapter: lora
base_model: NousResearch/Yarn-Solar-10b-32k
bf16: true
chat_template: llama3
dataloader_num_workers: 24
dataset_prepared_path: null
datasets:
- data_files:
  - d725a8c1ea4d38c4_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/d725a8c1ea4d38c4_train_data.json
  type:
    field_input: input_context
    field_instruction: instruction
    field_output: errors
    format: '{instruction} {input}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 3
eval_batch_size: 2
eval_max_new_tokens: 128
eval_steps: 500
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: false
group_by_length: true
hub_model_id: abaddon182/d4ea2b35-a090-43cf-89e3-a49f58577115
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: 50
lora_alpha: 64
lora_dropout: 0.05
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_steps: 5000
micro_batch_size: 2
mlflow_experiment_name: /tmp/d725a8c1ea4d38c4_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 10
optim_args:
  adam_beta1: 0.9
  adam_beta2: 0.999
  adam_epsilon: 1e-8
optimizer: adamw_torch_fused
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 500
saves_per_epoch: null
sequence_len: 512
special_tokens:
  pad_token: </s>
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: e7fa7a03-5e90-47af-bc8b-96695b05e9fa
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: e7fa7a03-5e90-47af-bc8b-96695b05e9fa
warmup_steps: 50
weight_decay: 0.0
xformers_attention: null

d4ea2b35-a090-43cf-89e3-a49f58577115

This model is a fine-tuned version of NousResearch/Yarn-Solar-10b-32k on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.4081

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: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.999,adam_epsilon=1e-8
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 50
training_steps: 5000

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0002	1	1.6635
1.9282	0.0998	500	0.5806
2.0164	0.1996	1000	0.5739
1.812	0.2994	1500	0.5479
1.867	0.3993	2000	0.5057
1.7701	0.4991	2500	0.5104
1.7623	0.5989	3000	0.4616
1.6889	0.6987	3500	0.4322
1.7073	0.7985	4000	0.4315
1.6857	0.8983	4500	0.4095
1.6007	0.9982	5000	0.4081

Framework versions

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