See axolotl config

axolotl version: 0.4.1

adapter: lora
base_model: trl-internal-testing/tiny-random-LlamaForCausalLM
bf16: auto
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - 1a8583ea3a7a4bbf_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/1a8583ea3a7a4bbf_train_data.json
  type:
    field_input: sentence_tokens
    field_instruction: sentence
    field_output: mention_text
    format: '{instruction} {input}'
    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: false
fp16: true
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: ardaspear/5e7cb959-b615-4072-aed0-0f15e5570d38
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: 128
lora_dropout: 0.1
lora_fan_in_fan_out: true
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_memory:
  0: 72GB
max_steps: 50
micro_batch_size: 8
mlflow_experiment_name: /tmp/1a8583ea3a7a4bbf_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: false
sample_packing: false
saves_per_epoch: 4
sequence_len: 1024
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: leixa-personal
wandb_mode: online
wandb_name: 5e7cb959-b615-4072-aed0-0f15e5570d38
wandb_project: Gradients-On-Four
wandb_run: your_name
wandb_runid: 5e7cb959-b615-4072-aed0-0f15e5570d38
warmup_steps: 10
weight_decay: 0.01
xformers_attention: null

5e7cb959-b615-4072-aed0-0f15e5570d38

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

• Loss: 10.3145

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0023	1	10.3770
10.3708	0.0113	5	10.3752
10.3715	0.0226	10	10.3690
10.3518	0.0339	15	10.3594
10.3586	0.0451	20	10.3488
10.3488	0.0564	25	10.3377
10.3337	0.0677	30	10.3281
10.338	0.0790	35	10.3207
10.3198	0.0903	40	10.3165
10.3121	0.1016	45	10.3148
10.3121	0.1129	50	10.3145

Framework versions

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