End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: Mistral-7B-v0.1_cola_original_cola
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# Mistral-7B-v0.1_cola_original_cola
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.9858
|
| 21 |
+
- Accuracy: 0.8692
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-05
|
| 41 |
+
- train_batch_size: 64
|
| 42 |
+
- eval_batch_size: 64
|
| 43 |
+
- seed: 2
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 6
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 768
|
| 48 |
+
- total_eval_batch_size: 384
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- training_steps: 750
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 57 |
+
| 1.0563 | 2.38 | 25 | 1.1091 | 0.6347 |
|
| 58 |
+
| 0.7148 | 4.76 | 50 | 0.7231 | 0.7210 |
|
| 59 |
+
| 0.5436 | 7.14 | 75 | 0.5349 | 0.7929 |
|
| 60 |
+
| 0.4144 | 9.52 | 100 | 0.4578 | 0.8159 |
|
| 61 |
+
| 0.3537 | 11.9 | 125 | 0.4236 | 0.8207 |
|
| 62 |
+
| 0.3208 | 14.29 | 150 | 0.3996 | 0.8274 |
|
| 63 |
+
| 0.3204 | 16.67 | 175 | 0.3874 | 0.8322 |
|
| 64 |
+
| 0.2888 | 19.05 | 200 | 0.3939 | 0.8351 |
|
| 65 |
+
| 0.2629 | 21.43 | 225 | 0.3837 | 0.8341 |
|
| 66 |
+
| 0.2288 | 23.81 | 250 | 0.3904 | 0.8437 |
|
| 67 |
+
| 0.1757 | 26.19 | 275 | 0.4016 | 0.8456 |
|
| 68 |
+
| 0.1754 | 28.57 | 300 | 0.4165 | 0.8428 |
|
| 69 |
+
| 0.1137 | 30.95 | 325 | 0.4513 | 0.8447 |
|
| 70 |
+
| 0.0611 | 33.33 | 350 | 0.5193 | 0.8399 |
|
| 71 |
+
| 0.0555 | 35.71 | 375 | 0.5863 | 0.8428 |
|
| 72 |
+
| 0.0346 | 38.1 | 400 | 0.7369 | 0.8313 |
|
| 73 |
+
| 0.0125 | 40.48 | 425 | 0.7936 | 0.8360 |
|
| 74 |
+
| 0.0041 | 42.86 | 450 | 0.8821 | 0.8351 |
|
| 75 |
+
| 0.0052 | 45.24 | 475 | 0.9493 | 0.8332 |
|
| 76 |
+
| 0.0121 | 47.62 | 500 | 1.0594 | 0.8380 |
|
| 77 |
+
| 0.0063 | 50.0 | 525 | 1.0706 | 0.8332 |
|
| 78 |
+
| 0.0025 | 52.38 | 550 | 1.0518 | 0.8303 |
|
| 79 |
+
| 0.0115 | 54.76 | 575 | 1.0344 | 0.8360 |
|
| 80 |
+
| 0.0167 | 57.14 | 600 | 1.1477 | 0.8322 |
|
| 81 |
+
| 0.0096 | 59.52 | 625 | 1.1863 | 0.8341 |
|
| 82 |
+
| 0.004 | 61.9 | 650 | 1.1809 | 0.8399 |
|
| 83 |
+
|
| 84 |
+
|
| 85 |
+
### Framework versions
|
| 86 |
+
|
| 87 |
+
- Transformers 4.35.2
|
| 88 |
+
- Pytorch 2.1.1+cu121
|
| 89 |
+
- Datasets 2.15.0
|
| 90 |
+
- Tokenizers 0.15.0
|