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/PsychiatryCaseNotes
type: completion
debug: null
deepspeed: null
early_stopping_patience: null
eval_sample_packing: false
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-Real-PsychiatryCaseNotes-epochs-1-lr-0002_Train_On_Input
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: true
val_set_size: 0.05
wandb_entity: utrgvmedai
wandb_log_model: null
wandb_name: tinyLama_PsyciatryCaseNotes_epochs_1_lr_0002
wandb_project: TinyLlama-Train-On-Input
wandb_watch: null
warmup_steps: 100
weight_decay: 0.1
xformers_attention: null
TinyLlama-Real-PsychiatryCaseNotes-epochs-1-lr-0002_Train_On_Input
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: 2.3518
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 |
|---|---|---|---|
| 5.2368 | 0.01 | 1 | 4.7826 |
| 2.2757 | 0.25 | 48 | 2.3982 |
| 2.6166 | 0.51 | 96 | 2.5288 |
| 2.6537 | 0.76 | 144 | 2.3518 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.0