metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- generated_from_trainer
model-index:
- name: mistral-7B-MedText-epochs-5-lr-000002
results: []
See axolotl config
axolotl version: 0.4.0
base_model: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: utrgvseniorproject/medtext
type: completion
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./mistral-7B-MedText-epochs-5-lr-000002
sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true
adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:
wandb_project: mistral-7B-MedText
wandb_entity: utrgvmedai
wandb_watch:
wandb_name: mistral-7B-MedText-epochs-5-lr-000002
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 5
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000002
train_on_inputs: true
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: false
early_stopping_patience:
#resume_from_checkpoint: true
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
flash_attn_cross_entropy: false
flash_attn_rms_norm: true
flash_attn_fuse_qkv: false
flash_attn_fuse_mlp: true
warmup_steps: 100
evals_per_epoch: 4
eval_table_size:
eval_sample_packing: False
saves_per_epoch: 1
debug:
deepspeed: /home/josegomez15/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
mistral-7B-MedText-epochs-5-lr-000002
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.6109
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: 2e-06
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 8
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.5029 | 0.02 | 1 | 1.5677 |
| 1.5892 | 0.26 | 11 | 1.5674 |
| 1.2975 | 0.51 | 22 | 1.5646 |
| 1.6405 | 0.77 | 33 | 1.5585 |
| 1.4797 | 1.02 | 44 | 1.5535 |
| 1.4285 | 1.23 | 55 | 1.5510 |
| 1.565 | 1.49 | 66 | 1.5497 |
| 1.2469 | 1.74 | 77 | 1.5485 |
| 1.6729 | 2.0 | 88 | 1.5482 |
| 1.2883 | 2.23 | 99 | 1.5585 |
| 1.2285 | 2.49 | 110 | 1.5651 |
| 1.2074 | 2.74 | 121 | 1.5639 |
| 1.1427 | 3.0 | 132 | 1.5614 |
| 1.1015 | 3.21 | 143 | 1.5898 |
| 1.0554 | 3.47 | 154 | 1.5990 |
| 1.1675 | 3.72 | 165 | 1.5823 |
| 1.0228 | 3.98 | 176 | 1.5949 |
| 1.0462 | 4.19 | 187 | 1.6039 |
| 1.0623 | 4.44 | 198 | 1.6127 |
| 1.1305 | 4.7 | 209 | 1.6109 |
Framework versions
- Transformers 4.38.0
- Pytorch 2.0.1+cu117
- Datasets 2.17.0
- Tokenizers 0.15.0