llama_2_13b_Magiccoder_evol_10k_reverse
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: 1.0887
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 |
---|---|---|---|
1.173 | 0.0262 | 4 | 1.1853 |
1.1716 | 0.0523 | 8 | 1.1587 |
1.105 | 0.0785 | 12 | 1.1410 |
1.0534 | 0.1047 | 16 | 1.1289 |
1.0911 | 0.1308 | 20 | 1.1239 |
1.0565 | 0.1570 | 24 | 1.1172 |
1.0589 | 0.1832 | 28 | 1.1140 |
1.1027 | 0.2093 | 32 | 1.1106 |
1.0379 | 0.2355 | 36 | 1.1096 |
1.1134 | 0.2617 | 40 | 1.1087 |
1.0969 | 0.2878 | 44 | 1.1049 |
1.1361 | 0.3140 | 48 | 1.1056 |
1.1121 | 0.3401 | 52 | 1.1023 |
1.0828 | 0.3663 | 56 | 1.1047 |
1.1246 | 0.3925 | 60 | 1.1027 |
1.1285 | 0.4186 | 64 | 1.0990 |
1.0788 | 0.4448 | 68 | 1.0998 |
1.0917 | 0.4710 | 72 | 1.0950 |
1.0395 | 0.4971 | 76 | 1.0977 |
1.1267 | 0.5233 | 80 | 1.0954 |
1.1414 | 0.5495 | 84 | 1.0955 |
1.0821 | 0.5756 | 88 | 1.0930 |
1.0277 | 0.6018 | 92 | 1.0908 |
1.0303 | 0.6280 | 96 | 1.0917 |
1.0947 | 0.6541 | 100 | 1.0905 |
1.0824 | 0.6803 | 104 | 1.0903 |
1.0726 | 0.7065 | 108 | 1.0912 |
1.1064 | 0.7326 | 112 | 1.0907 |
1.0467 | 0.7588 | 116 | 1.0892 |
1.0725 | 0.7850 | 120 | 1.0885 |
1.09 | 0.8111 | 124 | 1.0893 |
1.0506 | 0.8373 | 128 | 1.0900 |
0.9951 | 0.8635 | 132 | 1.0902 |
1.1032 | 0.8896 | 136 | 1.0895 |
1.0116 | 0.9158 | 140 | 1.0891 |
1.0683 | 0.9419 | 144 | 1.0889 |
1.0902 | 0.9681 | 148 | 1.0888 |
1.0721 | 0.9943 | 152 | 1.0887 |
Framework versions
- PEFT 0.7.1
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
๐
Ask for provider support
Model tree for imdatta0/llama_2_13b_Magiccoder_evol_10k_reverse
Base model
meta-llama/Llama-2-13b-hf