metadata
license: llama2
library_name: peft
tags:
- unsloth
- generated_from_trainer
base_model: meta-llama/Llama-2-13b-hf
model-index:
- name: llama_2_13b_Magiccoder_evol_10k_ortho
results: []
llama_2_13b_Magiccoder_evol_10k_ortho
This model is a fine-tuned version of meta-llama/Llama-2-13b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0888
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.02
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.1928 | 0.0262 | 4 | 1.1781 |
1.1605 | 0.0523 | 8 | 1.1408 |
1.088 | 0.0785 | 12 | 1.1262 |
1.0449 | 0.1047 | 16 | 1.1204 |
1.0849 | 0.1308 | 20 | 1.1163 |
1.0541 | 0.1570 | 24 | 1.1123 |
1.0556 | 0.1832 | 28 | 1.1095 |
1.1005 | 0.2093 | 32 | 1.1065 |
1.0338 | 0.2355 | 36 | 1.1052 |
1.1096 | 0.2617 | 40 | 1.1049 |
1.092 | 0.2878 | 44 | 1.1031 |
1.1322 | 0.3140 | 48 | 1.1033 |
1.1075 | 0.3401 | 52 | 1.0993 |
1.0792 | 0.3663 | 56 | 1.1015 |
1.1255 | 0.3925 | 60 | 1.1013 |
1.1261 | 0.4186 | 64 | 1.0988 |
1.0801 | 0.4448 | 68 | 1.0975 |
1.0908 | 0.4710 | 72 | 1.0936 |
1.0374 | 0.4971 | 76 | 1.0943 |
1.1264 | 0.5233 | 80 | 1.0945 |
1.1409 | 0.5495 | 84 | 1.0943 |
1.0822 | 0.5756 | 88 | 1.0942 |
1.0301 | 0.6018 | 92 | 1.0908 |
1.03 | 0.6280 | 96 | 1.0900 |
1.0939 | 0.6541 | 100 | 1.0902 |
1.083 | 0.6803 | 104 | 1.0902 |
1.0721 | 0.7065 | 108 | 1.0905 |
1.105 | 0.7326 | 112 | 1.0905 |
1.0472 | 0.7588 | 116 | 1.0899 |
1.0728 | 0.7850 | 120 | 1.0889 |
1.0905 | 0.8111 | 124 | 1.0885 |
1.0513 | 0.8373 | 128 | 1.0887 |
0.9946 | 0.8635 | 132 | 1.0890 |
1.1033 | 0.8896 | 136 | 1.0889 |
1.0145 | 0.9158 | 140 | 1.0890 |
1.0689 | 0.9419 | 144 | 1.0890 |
1.0904 | 0.9681 | 148 | 1.0889 |
1.0749 | 0.9943 | 152 | 1.0888 |
Framework versions
- PEFT 0.7.1
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1