llama_2_13b_Magiccoder_evol_10k_ortho_eye
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: 1.0987
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 |
---|---|---|---|
1.2093 | 0.0262 | 4 | 1.2192 |
1.1816 | 0.0523 | 8 | 1.1667 |
1.1073 | 0.0785 | 12 | 1.1438 |
1.0563 | 0.1047 | 16 | 1.1321 |
1.0947 | 0.1308 | 20 | 1.1265 |
1.0662 | 0.1570 | 24 | 1.1237 |
1.0636 | 0.1832 | 28 | 1.1206 |
1.1163 | 0.2093 | 32 | 1.1180 |
1.0423 | 0.2355 | 36 | 1.1149 |
1.1226 | 0.2617 | 40 | 1.1148 |
1.0991 | 0.2878 | 44 | 1.1124 |
1.1427 | 0.3140 | 48 | 1.1119 |
1.1193 | 0.3401 | 52 | 1.1081 |
1.0908 | 0.3663 | 56 | 1.1086 |
1.1406 | 0.3925 | 60 | 1.1077 |
1.1366 | 0.4186 | 64 | 1.1063 |
1.0866 | 0.4448 | 68 | 1.1051 |
1.1035 | 0.4710 | 72 | 1.1026 |
1.0523 | 0.4971 | 76 | 1.1021 |
1.1381 | 0.5233 | 80 | 1.1018 |
1.1521 | 0.5495 | 84 | 1.1016 |
1.0932 | 0.5756 | 88 | 1.1014 |
1.0467 | 0.6018 | 92 | 1.0999 |
1.0459 | 0.6280 | 96 | 1.0992 |
1.1049 | 0.6541 | 100 | 1.0996 |
1.0905 | 0.6803 | 104 | 1.0993 |
1.0828 | 0.7065 | 108 | 1.0992 |
1.1141 | 0.7326 | 112 | 1.0990 |
1.0616 | 0.7588 | 116 | 1.0989 |
1.083 | 0.7850 | 120 | 1.0984 |
1.1081 | 0.8111 | 124 | 1.0982 |
1.069 | 0.8373 | 128 | 1.0984 |
1.0085 | 0.8635 | 132 | 1.0988 |
1.1178 | 0.8896 | 136 | 1.0987 |
1.0337 | 0.9158 | 140 | 1.0988 |
1.0825 | 0.9419 | 144 | 1.0987 |
1.0976 | 0.9681 | 148 | 1.0987 |
1.0909 | 0.9943 | 152 | 1.0987 |
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
- 3
Model tree for imdatta0/llama_2_13b_Magiccoder_evol_10k_ortho_eye
Base model
meta-llama/Llama-2-13b-hf
Adapter
this model