vasugupta0607/llama2_instruct_generation

1---2library_name: peft3tags:4- trl5- sft6- generated_from_trainer7datasets:8- generator9base_model: NousResearch/Llama-2-7b-hf10model-index:11- name: llama2_instruct_generation12  results: []13---14 15<!-- This model card has been generated automatically according to the information the Trainer had access to. You16should probably proofread and complete it, then remove this comment. -->17 18# llama2_instruct_generation19 20This model is a fine-tuned version of [NousResearch/Llama-2-7b-hf](https://huggingface.co/NousResearch/Llama-2-7b-hf) on the generator dataset.21It achieves the following results on the evaluation set:22- Loss: 1.673423 24## Model description25 26More information needed27 28## Intended uses & limitations29 30More information needed31 32## Training and evaluation data33 34More information needed35 36## Training procedure37 38### Training hyperparameters39 40The following hyperparameters were used during training:41- learning_rate: 0.000242- train_batch_size: 443- eval_batch_size: 844- seed: 4245- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-0846- lr_scheduler_type: constant47- lr_scheduler_warmup_steps: 0.0348- training_steps: 50049 50### Training results51 52| Training Loss | Epoch | Step | Validation Loss |53|:-------------:|:-----:|:----:|:---------------:|54| 1.9364        | 0.0   | 20   | 1.8092          |55| 1.9198        | 0.01  | 40   | 1.7826          |56| 1.8451        | 0.01  | 60   | 1.7675          |57| 1.8487        | 0.01  | 80   | 1.7573          |58| 1.8667        | 0.01  | 100  | 1.7435          |59| 1.7463        | 0.02  | 120  | 1.7132          |60| 1.7789        | 0.02  | 140  | 1.7038          |61| 1.8167        | 0.02  | 160  | 1.7008          |62| 1.8654        | 0.02  | 180  | 1.6944          |63| 1.9158        | 0.03  | 200  | 1.6939          |64| 1.6581        | 0.03  | 220  | 1.6909          |65| 1.793         | 0.03  | 240  | 1.6896          |66| 1.7878        | 0.04  | 260  | 1.6872          |67| 1.7542        | 0.04  | 280  | 1.6862          |68| 1.7723        | 0.04  | 300  | 1.6863          |69| 1.7606        | 0.04  | 320  | 1.6832          |70| 1.8054        | 0.05  | 340  | 1.6802          |71| 1.7307        | 0.05  | 360  | 1.6803          |72| 1.8278        | 0.05  | 380  | 1.6790          |73| 1.7912        | 0.05  | 400  | 1.6768          |74| 1.7826        | 0.06  | 420  | 1.6749          |75| 1.8975        | 0.06  | 440  | 1.6756          |76| 1.8395        | 0.06  | 460  | 1.6763          |77| 1.8319        | 0.07  | 480  | 1.6749          |78| 1.7879        | 0.07  | 500  | 1.6734          |79 80 81### Framework versions82 83- PEFT 0.7.184- Transformers 4.37.285- Pytorch 2.1.0+cu12186- Datasets 2.16.187- Tokenizers 0.15.1