absolute_data_files: false
adapter: lora
base_model: microsoft/phi-1_5
bf16: true
chat_template: llama3
dataset_prepared_path: /workspace/axolotl
datasets:
- chat_template: chatml
  data_files:
  - ca046136eb4a7082_train_data.json
  ds_type: json
  field_messages: conversations
  message_field_content: value
  message_field_role: from
  message_property_mappings:
    content: value
    role: from
  path: /workspace/input_data/
  roles:
    assistant:
    - gpt
    user:
    - human
  type: chat_template
debug: null
deepspeed: null
dpo:
  beta: 0.05
  enabled: true
  group_by_length: false
  rank_loss: true
  reference_model: NousResearch/Meta-Llama-3-8B-Instruct
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 1
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: sergioalves/4338f649-11bb-46ec-aeb0-bc996fb50538
hub_repo: null
hub_strategy: end
hub_token: null
learning_rate: 5.0e-07
load_in_4bit: true
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 64
lora_dropout: 0.1
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 32
lora_target_linear: true
lr_scheduler: cosine
max_steps: 200
micro_batch_size: 8
mixed_precision: bf16
mlflow_experiment_name: /tmp/ca046136eb4a7082_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
saves_per_epoch: 1
sequence_len: 1024
special_tokens:
  pad_token: <|endoftext|>
strict: false
tf32: false
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: 81fef1e3-95ff-42cf-a2cb-122451a8f81a
wandb_project: s56-7
wandb_run: your_name
wandb_runid: 81fef1e3-95ff-42cf-a2cb-122451a8f81a
warmup_steps: 25
weight_decay: 0.05
xformers_attention: false

4338f649-11bb-46ec-aeb0-bc996fb50538

This model is a fine-tuned version of microsoft/phi-1_5 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 2.1273

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: 5e-07
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: 25
training_steps: 200

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0	0	2.1888
1.9837	1.0309	100	2.1427
1.9256	2.0619	200	2.1273

Framework versions

PEFT 0.15.2
Transformers 4.52.4
Pytorch 2.5.1+cu124
Datasets 3.6.0
Tokenizers 0.21.1