Built with Axolotl

See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: HuggingFaceH4/tiny-random-LlamaForCausalLM
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - c492b59df4392fc5_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/c492b59df4392fc5_train_data.json
  type:
    field_instruction: darija
    field_output: english
    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: brixeus/d7d0a622-dabb-48c2-8e5a-ce436872e92e
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/c492b59df4392fc5_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
sequence_len: 1024
special_tokens:
  pad_token: </s>
strict: false
tf32: false
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: eebf6c67-e376-496c-b631-eafc7a7c87c4
wandb_project: Gradients-On-Three
wandb_run: your_name
wandb_runid: eebf6c67-e376-496c-b631-eafc7a7c87c4
warmup_steps: 10
weight_decay: 0.0
xformers_attention: null

d7d0a622-dabb-48c2-8e5a-ce436872e92e

This model is a fine-tuned version of HuggingFaceH4/tiny-random-LlamaForCausalLM on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 10.3618

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: 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=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 0.0120 1 10.3747
10.3719 0.1081 9 10.3742
10.369 0.2162 18 10.3726
10.3703 0.3243 27 10.3708
10.3653 0.4324 36 10.3688
10.3666 0.5405 45 10.3668
10.3623 0.6486 54 10.3649
10.3606 0.7568 63 10.3635
10.3562 0.8649 72 10.3626
10.3618 0.9730 81 10.3621
10.1224 1.0811 90 10.3619
10.2493 1.1892 99 10.3618

Framework versions

  • PEFT 0.13.2
  • Transformers 4.46.0
  • Pytorch 2.5.0+cu124
  • Datasets 3.0.1
  • Tokenizers 0.20.1
Downloads last month
8
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model’s pipeline type.

Model tree for brixeus/d7d0a622-dabb-48c2-8e5a-ce436872e92e

Adapter
(262)
this model