postOpTranscriptAnalyzer

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 . It achieves the following results on the evaluation set:

• Loss: 0.8360

Model description

The purpose of this model is to analyze the performance of healthcare professionals in providing post-operative instructions, based on a transcript of their conversations.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-06
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 10
• num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss
0.9739	0.1739	1	0.9650
0.8749	0.3478	2	0.9442
0.896	0.6957	4	0.8696
0.8791	1.0435	6	0.8514
0.8063	1.3043	8	0.8326
0.7643	1.6522	10	0.8248
0.8239	2.0	12	0.8203
0.6914	2.2609	14	0.8261
0.6751	2.6087	16	0.8356
0.6157	2.9565	18	0.8357
0.5871	3.2174	20	0.8360

Framework versions

• Transformers 4.42.4
• Pytorch 2.1.2+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1

See axolotl config

axolotl version: 0.4.1

base_model: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: mhenrichsen/alpaca_2k_test
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./out

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: false

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000005

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: '<s>'
  eos_token: '</s>'
  unk_token: '<unk>'

hub_model_id: bmezgebu/postOpTranscriptAnalyzer
push_to_hub: True