End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
base_model: NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2
|
| 7 |
+
model-index:
|
| 8 |
+
- name: mistral-sigoIAspirantes-Orca-oass-v2
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# mistral-sigoIAspirantes-Orca-oass-v2
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2](https://huggingface.co/NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.1354
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 2.5e-05
|
| 39 |
+
- train_batch_size: 2
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- lr_scheduler_warmup_steps: 1
|
| 45 |
+
- training_steps: 400
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 52 |
+
| 1.6909 | 0.35 | 25 | 1.2159 |
|
| 53 |
+
| 1.0275 | 0.7 | 50 | 0.8422 |
|
| 54 |
+
| 0.7147 | 1.06 | 75 | 0.6233 |
|
| 55 |
+
| 0.5131 | 1.41 | 100 | 0.5002 |
|
| 56 |
+
| 0.3872 | 1.76 | 125 | 0.3971 |
|
| 57 |
+
| 0.3419 | 2.11 | 150 | 0.3027 |
|
| 58 |
+
| 0.1742 | 2.46 | 175 | 0.2725 |
|
| 59 |
+
| 0.2616 | 2.82 | 200 | 0.2068 |
|
| 60 |
+
| 0.1427 | 3.17 | 225 | 0.2039 |
|
| 61 |
+
| 0.1228 | 3.52 | 250 | 0.1627 |
|
| 62 |
+
| 0.1186 | 3.87 | 275 | 0.1441 |
|
| 63 |
+
| 0.0751 | 4.23 | 300 | 0.1540 |
|
| 64 |
+
| 0.0892 | 4.58 | 325 | 0.1524 |
|
| 65 |
+
| 0.0833 | 4.93 | 350 | 0.1327 |
|
| 66 |
+
| 0.064 | 5.28 | 375 | 0.1347 |
|
| 67 |
+
| 0.06 | 5.63 | 400 | 0.1354 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- PEFT 0.10.1.dev0
|
| 73 |
+
- Transformers 4.40.0.dev0
|
| 74 |
+
- Pytorch 2.2.1+cu121
|
| 75 |
+
- Datasets 2.18.0
|
| 76 |
+
- Tokenizers 0.15.2
|