Built with Axolotl

See axolotl config

axolotl version: 0.4.0

adapter: null
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
bf16: auto
dataset_prepared_path: last_run_prepared
datasets:
- path: utrgvseniorproject/medtext
  type: completion
debug: null
deepspeed: null
early_stopping_patience: null
eval_table_size: null
evals_per_epoch: 4
flash_attention: true
flash_attn_cross_entropy: false
flash_attn_fuse_mlp: true
flash_attn_fuse_qkv: false
flash_attn_rms_norm: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 1
gradient_checkpointing: true
group_by_length: false
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: null
lora_dropout: null
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: null
lora_target_linear: null
lr_scheduler: cosine
micro_batch_size: 1
model_type: LlamaForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: ./TinyLlama-Medtext-epochs-1-lr-0002
pad_to_sequence_len: true
resume_from_checkpoint: null
sample_packing: true
saves_per_epoch: 1
sequence_len: 2048
special_tokens: null
strict: false
tf32: false
tokenizer_type: LlamaTokenizer
train_on_inputs: false
val_set_size: 0.05
wandb_entity: utrgvmedai
wandb_log_model: null
wandb_name: tinyLama_colab
wandb_project: TinyLlama-Medtext-epochs-1-lr-0002
wandb_watch: null
warmup_steps: 100
weight_decay: 0.1
xformers_attention: null

TinyLlama-Medtext-epochs-1-lr-0002

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 7.3015

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: 1
  • eval_batch_size: 1
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
1.7582 0.0 1 2.1282
9.7725 0.25 155 8.8488
7.687 0.5 310 7.3755
7.286 0.75 465 7.3066
6.8919 1.0 620 7.3015

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.2+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.0
Downloads last month
14
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for joseagmz/TinyLlama-Medtext-epochs-1-lr-0002

Finetuned
(89)
this model